Release v0.3.13

* feat: Add Japanaese JIS layout

* feat: Add KanaSelector and KanaSizeSelector

* test: Try out new selectors

* fix: Add new selectors to polymorphic key data list

This should help make florisboard recognize the new selectors
when used in layouts.

* fix: Implement `evaluteKana` for ComputingEvaluator

This should fix the crashes, hopefully

* feat: Rework the JIS layout

* fix: Implement basic logic for kana state

* feat: Add popups for JIS

* chore: Rename JIS specific layouts

For some reason this change broke the pop-ups

* feat: Add Kana Unicode compositor

* feat: Implement flipping small state and refactor

This should allow small kana characters to be switched over to their
normal counterparts. Also clean up and refactor `KanaUnicode` and make
the filename more appropriate

* Merge `master` to `japanese`

* chore: Add internal codes for Kana switching

This should be the starting point for getting actual keys
to switch between the kana types

* feat: Add initial modifer layout for JIS

* chore: Add keycode for ideographic CJK space

* feat: Add logic for kana switching

* chore: Update layout modifer to use kana switch

* feat: Add icon for kana switcher button

* fix: Scale the icon and update relevant entries

* feat: Begin work on kana selector popup

* Add kana attributes to keyboard state

* Add workaround for Japanese popups

* chore: Remove URL popups for JIS layout

* chore: Add codes and groups for kana switching

This commit adds the "~kana" group with groupId 4.

* feat: Use "~kana" in JIS layout.

* feat: Remove `KanaSizeSelector`.

It will be redundant when compositor handles it instead.

* feat: Add alpha code for making kana small.

This code currently uses a sentinel character to trigger
the transformation. This is not ideal as that means that users
won't be able to use that character in the keyboard. This won't
be a problem if the sentinel character is a Unicode codepoint
that cannot or would not be used normally. As such, this is just
a demonstration of the how the feature should function not it's
final implementation.

* test: Add kana small key in JIS for testing.

This is to preview changes to the kana small algorithm,
This commit should be removed from history later on.

* fix: Add `KANA_SWITCHER` to exceptionsForKeyCodes

* chore: Change "~kana" groupId to avoid conflicts

* fix: Change Kana small behaviour

* chore: Change internal kana small key code

* test: Remove kana small button from JIS layout

* feat: Add iteration marks to daku list

* feat: Allow swtiching between kana modifiers

This allows users to add/remove dakuten/handakuten/small
from kana and swtiching between the three. This is helpful
as it allows users to quickly rectify mistakes. It also lays
the groundwork for the future 12 flick layout

* feat: Change Kana swticher behaviour on katakana

Makes katakana switch over to hiragana immediately. As half-width
katakana is not usually used. The kana-switcher pop-up suffices
switching over to it when needed.

A potential downside to doing it like this making the half-width
katakana more hidden and less likely to be used.

* Add CJK_SPACE special behavior to input logic

* feat: Add CJK punctuation to popups and JIS layout

* feat: Add CJK punctuation symbols

* feat: Add CJK row numbers

* feat: Add postal mark symbol in CJK symbols

And change kana small internal code. Used to be set to
postal mark with face. Now set to geta mark.

* chore: Set default numeric row to CJK for JIS

* feat: Add modifiers layouts for CJK punctuation

* chore: Add latin half-width braces to CJK layout

* fix: Change composer behaviour on empty string

* chore: Add non-composing (han)daku to JIS popups

* fix: Change composer behaviour to be consistent

Also clean up the code a little.

* fix: Change composer empty string behaviour

* feat: Add WidthSelector and migrate half_kata Kana

This adds width selector for all languages instead of tying it down
to only `KanaSelector`. As such `KanaSelector`'s `half_kata`' field
is obsolete.

* fix: Fix bug in composing logic

* fix: Implement width properly and remove half_kata

* refactor: Clean up JIS layout JSON

* fix: Change JIS punctuation to use width_selector

* Improve half width implementation / Clean-up code base

* fix: Remove Half-kata from kana switcher cycle.

* feat: Add char width keycodes and implementation

* feat: Add half-width forms to symbols/cjk layouts

* feat: Add char width switcher to CJK mod layouts

Icons are yet to be added, so the labels will be strings for now

* feat: Add half-width forms for symbols2/cjk layout

* chore: Add more appropriate CJK chars to symbols2

* feat: Add icons for character width switching.

Note that `ic_keyboard_char_width_full` and `ic_keyboard_char_width_half`
are just copies of `ic_keyboard_char_width_switcher` for now.

* feat: Add relevant entries to show char width icons

* chore: Update the character width pop up icons.

And rename the internal names so that they match up with kana_switcher.

* fix: Make char width swticher icon toggle instead

* fix: Make character width icons more consistent.

* chore: Remove reference to char_width_switcher icon

* test: Iest code for why the composer is not working

* test: Remove test code for KanaUnicode

This reverts commit f6ae545183.

* fix: Correct small kana association for E and U

* test: Remove test code for KanaUnicode

This reverts commit f6ae545183.

* fix: Don't add small sentinel on non small char.

* fix: Correct small ya entry in KanaUnicode

* feat: Make kana switcher icon toggle between modes

* fix: Update svg colors to fit with other vectors

* Update app/src/main/java/dev/patrickgold/florisboard/ime/text/TextInputManager.kt

Co-authored-by: Patrick Goldinger <patrick.goldinger@pm.me>

* chore: Fix author name

* chore: Fix author name in CJK numbers

* chore: Fix indentation on author field

Co-authored-by: Waelwindows <waelwindows@hotmail.com>
Co-authored-by: Patrick Goldinger <patrick@patrickgold.dev>

.github/ISSUE_TEMPLATE/config.yml

@@ -1,5 +1,8 @@
 blank_issues_enabled: false
 contact_links:
+  - name: Ask a question
+    url: https://github.com/florisboard/florisboard/discussions/new?category=q-a
+    about: Ask here if you have a question about FlorisBoard or need assistance
   - name: General feedback
-    url: https://github.com/florisboard/florisboard/blob/master/CONTRIBUTING.md
+    url: https://github.com/florisboard/florisboard/discussions/new?category=feedback
     about: Give general feedback about this project

.github/ISSUE_TEMPLATE/feature_request.md

@@ -8,12 +8,11 @@ assignees: ''
 ---
 
 <!--
-- Describe your idea in a short but concise way.
-- If you have multiple ideas which are not directly connected to each
-  other, file an issue per idea. This makes it easy to implement one
-  feature proposal at a time.
-- If you have any examples, e.g. screenshots or other keyboards which
-  have the proposed feature implemented, link them here.
-- Please search existing proposals to avoid creating duplicates.
-- Thank you for your help in making FlorisBoard better!
+Thank you for your help in making FlorisBoard better!
+
+Guide to a good feature-request:
+• Please search existing proposals to avoid creating duplicates.
+• If you have multiple ideas which are not directly connected to other, file a new issue for each idea. This makes it easier to implement your proposals.
+• Describe your idea in a short but concise way.
+• If you have any examples, e.g. screenshots or other keyboards have the proposed feature implemented, feel free to post them after your description.
 -->

.github/ISSUE_TEMPLATE/question.md

@@ -1,16 +0,0 @@
----
-name: Question
-about: Ask here if you have a question about FlorisBoard
-title: ''
-labels: question
-assignees: ''
-
----
-
-<!--
-- If you need assistance in using FlorisBoard, ask it here!
-- If you want to suggest an idea for this project, please use the
-  Feature request template instead.
-- Please search existing questions to avoid creating duplicates.
-- Thank you for your help in making FlorisBoard better!
--->

.github/workflows/android.yml

@@ -11,11 +11,13 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v1
-      - name: set up JDK 1.8
+      - uses: actions/checkout@v2
+      - name: Checkout submodules
+        run: git submodule update --init --recursive
+      - name: set up JDK 11
         uses: actions/setup-java@v1
         with:
-          java-version: 1.8
+          java-version: 11
       - name: Setup CMake and Ninja
         uses: lukka/get-cmake@v3.20.1
       - uses: actions/cache@v2

.gitmodules

@@ -1,3 +1,3 @@
-[submodule "app/src/main/cpp/icu4c/android"]
-	path = app/src/main/cpp/icu4c/android
-	url = https://github.com/patrickgold/icu4c-android
+[submodule "app/src/main/icu4c"]
+	path = app/src/main/icu4c
+	url = https://github.com/florisboard/icu4c

CONTRIBUTING.md

@@ -7,8 +7,13 @@ provides some general guidelines for each type of contribution.
 
 ## Giving general feedback
 
-Either use the review function within Google Play or email me at
-[florisboard@patrickgold.dev](mailto:florisboard@patrickgold.dev). I
+NEW! You can now [give general feedback](https://github.com/florisboard/florisboard/discussions/new?category=feedback)
+directly here on GitHub. This is the preferred way to give feedback, as
+it allows not only for me to read and respond to feedback, but for everyone
+in this community.
+
+Optionally you can also use the review function within Google Play or email me
+at [florisboard@patrickgold.dev](mailto:florisboard@patrickgold.dev). I
 love to hear from you! Note, that the amount of feedback emails I get
 is overwhelmingly high - so if I don't answer or answer really late, I
 apologize - I guarantee though that I read through every email and that

README.md

@@ -64,7 +64,7 @@ alt="Preview image">
 ## Implemented features
 This list contains all implemented and fully functional features
 FlorisBoard currently has to offer. For planned features and its
-milestones, please refer to the [Feature roadmap](#feature-roadmap).
+milestones, please refer to the [Feature roadmap](ROADMAP.md).
 
 ### Basics
 * [x] Implementation of the keyboard core (InputMethodService)
@@ -72,14 +72,14 @@ milestones, please refer to the [Feature roadmap](#feature-roadmap).
 * [x] Caps + Caps Lock
 * [x] Key popups
 * [x] Extended key popups (e.g. a -> á, à, ä, ...)
-* [x] Key press sound/vibration
+* [x] Audio/haptic feedback for keyboard touch interaction
 * [x] Portrait orientation support
 * [x] Landscape orientation support (needs tweaks)
 
 ### Layouts
 * [x] Latin character layouts (QWERTY, QWERTZ, AZERTY, Swiss, Spanish, Norwegian, Swedish/Finnish, Icelandic, Danish,
       Hungarian, Croatian, Polish, Romanian, Colemak, Dvorak, Turkish-Q, Turkish-F, and more...)
-* [x] Non-latin character layouts (Arabic, Persian, Kurdish, Greek, Russian (JCUKEN), and more...)
+* [x] Non-latin character layouts (Arabic, Persian, Kurdish, Greek, Russian (JCUKEN), Japanese JIS, and more...)
 * [x] Adapt to situation in app (password, url, text, etc. )
 * [x] Special character layout(s)
 * [x] Numeric layout
@@ -106,79 +106,17 @@ milestones, please refer to the [Feature roadmap](#feature-roadmap).
 * [x] Clipboard manager/history
 * [x] Integrated number row / symbols in character layouts
 * [x] Gesture support
+* [x] System-wide spell checker with spell results from FlorisBoard
 * [x] Full support for the system user dictionary (shared dictionary
       between all keyboards) and a private, internal user dictionary
 * [x] Full integration in IME service list of Android (xml/method)
       (integration is internal-only, because Android's default subtype
       implementation not really allows for dynamic language/layout
       pairs, only compile-time defined ones)
-* [ ] Description and settings reference in System Language & Input
+* [x] Description and settings reference in System Language & Input
 * [ ] (dev only) Generate well-structured documentation of code
 * [ ] ...
 
-## Feature roadmap
-This section describes the features which are planned to be implemented
-in FlorisBoard for the next major versions, modularized into sections.
-Please note that the milestone due dates are only raw estimates and will
-most likely be delayed back, even though I'm eager to stick to these as
-close as possible.
-
-### [v0.4.0](https://github.com/florisboard/florisboard/milestone/4)
-- Module A: Smartbar rework (Implemented with [#91])
-  - Ability to enable/disable Smartbar (features below thus only work if
-    Smartbar is enabled)
-  - Dynamic switching between clipboard tools and word suggestions
-  - Ability to show both the number row and word suggestions at once
-  - Better icons in quick actions
-  - Complete rework of the Smartbar code base and the Smartbar layout
-    definition in XML
-
-- Module B: Composing suggestions (Phase 1: [#329])
-  - Auto-suggestion of words based of precompiled dictionaries
-  - Management of custom dictionary entries
-  - Next-word suggestions by training language models. Data collected here is stored locally and never leaves
-    the user's device.
-
-- Module C: Extension packs (Implemented with [#162], reworked several times and still not stable)
-  - Ability to load dictionaries (and later potentially other cool
-    features too) only if needed to keep the core APK size small
-  - Currently unclear how exactly this will work, but this is definitely
-    a must-have feature
-  - A full implementation may come only in v0.5.0
-
-- Module D: Glide typing (Implemented with [#544])
-  - Swiping over the characters will automatically convert this to a word
-  - Possibly also add improvements based on the Flow keyboard
-
-- Module E: Theme rework (Implemented with [#162])
-  - Themes are now based on the Asset schema
-  - Dynamic theme creation
-  - Different theme modes (`Always day`, `Always night`, `Follow system`
-    and `Follow time`)
-  - Define a separate theme both for day and night theme
-  - Adapt to app theme if possible
-  - Theme import/export
-
-### [v0.5.0](https://github.com/florisboard/florisboard/milestone/5)
-There's no exact roadmap yet, but these are the most important points:
-- Full layout customization in runtime
-- Extensive rework and customization of the media input (emojis, emoticons, kaomoji)
-- Better Smartbar customization
-- As an extension GIF support
-
-### > v0.5.0
-This is completely open as of now and will gather planned features as time
-passes...
-
-Backlog (currently not assigned to any milestone):
-
-- Floating keyboard
-
-[#91]: https://github.com/florisboard/florisboard/pull/91
-[#162]: https://github.com/florisboard/florisboard/pull/162
-[#329]: https://github.com/florisboard/florisboard/pull/329
-[#544]: https://github.com/florisboard/florisboard/pull/544
-
 ## Contributing
 Wanna contribute to FlorisBoard? That's great to hear! There are lots of
 different ways to help out. Bug reporting, making pull requests,
@@ -207,8 +145,6 @@ to get more information on this topic.
   [The Unicode Consortium](https://github.com/unicode-org)
 * [Nuspell](https://github.com/nuspell/nuspell) by
   [Nuspell](https://github.com/nuspell)
-* [TokyoCabinet (only used glob.h and glob.c)](https://github.com/white-gecko/TokyoCabinet) by
-  [Natanael Arndt](https://github.com/white-gecko)
 
 ## License
 ```

ROADMAP.md

@@ -0,0 +1,106 @@
+# FlorisBoard's feature roadmap & milestones
+
+This feature roadmap intents to provide transparency to what I want to add
+to FlorisBoard in the foreseeable future. Note that there are no ETAs for any
+version milestones down below, experience says these won't hold anyways.
+
+I try my best to release regularly, though some features take a lot longer
+than others and thus releases can be spaced out a bit on the stable track.
+If you are interested in following the development more closely, make sure to
+follow along the beta track releases! These are generally more unstable but
+you get new stuff faster and can provide early feedback, which helps a lot!
+
+## 0.3.x and 0.4.0
+Releases in this section still follow the old versioning scheme, meaning the
+patch number is a feature upgrade. As this naming convention is more confusing
+than useful, after the v0.4.0 release a new release/development cycle will be
+introduced.
+
+### 0.3.13 (currently in development and soon done)
+- Spell checking (mainly completed and relatively well working, Smartbar integration still missing)
+- Performance improvements in keyboard rendering
+- Audio/haptic feedback rework
+- Lots and lots of bug fixing in all areas, really fix some annoying bugs
+- New layouts added by contributors
+
+### 0.3.14
+- Re-write of the Preference core
+  - Reduce redundancy in key/default value definitions
+  - Avoid having to manually add redundant code for adding a new pref
+  - Goes hand-in-hand with the Settings UI re-write
+- Re-write of the Settings UI with Jetpack Compose
+  - Also re-structure UI into a more list-like panel
+  - Adjust theme colors of Settings a bit to make it more modern
+  - Preview the keyboard at any time from within the Settings
+  - Settings language different than device language
+- Re-write the Setup UI in Jetpack Compose
+  - Simplify screen based on previously discussed ideas and mock-ups
+  - Improve backend setup logic
+- Implement base-UI for extensions and further continue development
+  of existing Flex (FlorisBoard extension) format
+  - Allows for a continuous experience of customizing FlorisBoard in different areas
+  - Planned in the future (not in this version though) what will use Flex:
+    - Themes
+    - Layouts (Characters, symbols, numeric, ...)
+    - Composers for non-Latin script languages
+    - Word suggestion dictionaries
+    - Spell check dictionaries
+    - User dictionaries
+    - Other features that require only data and no logic
+- Maybe full backup of preferences? Not 100% confirmed though and may be pushed back
+
+### 0.3.15
+- Re-adding word suggestions (at least for Latin-based languages at first)
+  - Importing the dictionaries as well as management relies on the Flex extension core and UI in Kotlin
+  - Actually parsing and generating suggestions happens in C++ to avoid another OOM catastrophe like in 0.3.9/10
+  - The actual format of the dictionary and word list source is not decided yet
+- Improvement of the candidate view in Smartbar (for word suggestions)
+- Theme rework part I:
+  - Custom key corner radius
+  - Custom key border color (not shadow!!)
+  - Re-work theme internals so they use Flex format
+  - Community repository on GitHub for theme sharing across users (when Theme Flex format is ready)
+
+### 0.4.0
+- Prepare FlorisBoard repository and app store presence for public beta release
+  on Google Play
+- Rework branding images and texts of FlorisBoard for the app stores
+- Focus on polishing the app and fixing bugs/crashes
+
+With this release the versioning scheme changes: the second number now indicates new features,
+changes in the third "patch" number now indicates bug fixes for the stable track. The development
+cycle for each 0.x release will have -betaXX and -rcXX (release candidate) releases on the beta
+track for interested people to follow along the development.
+
+## 0.5.0
+- Complete rework of the Emoji panel
+  - Recently used / Emoji history
+  - Emoji search
+  - Emoji suggestions when using :emoji_name: syntax
+  - Kaomoji panel implementation (the third tab which currently has "not yet implemented")
+- Full Smartbar customization
+  - Includes internal rework how Smartbar is build and assembled
+  - Allow for more than one Smartbar / Stackable and Collapsible Smartbars
+  - Customizable quick actions, clipboard row
+
+## 0.6.0
+- Full on-board layout editor which allows users to create their own layouts
+  without writing a JSON file
+- Import/Export of custom layout files packed in Flex extensions
+
+## Backlog / Features that MAY be added
+- Theme rework part II
+- Adaptive themes v2
+- Voice-to-text with Mozilla's open-source voice service
+- Text translation
+- Glide typing better word detection
+- Proximity-based key typo detection
+- Floating keyboard
+- Tablet mode / Optimizations for landscape input
+- Stickers/GIFs
+- FlorisBoard landing web page for presentation
+- Implementing additional layouts
+- Support for Tasker/Automate/MacroDroid plugins
+- Support for WearOS/Smartwatches
+- Handwriting
+- ...

app/build.gradle.kts

@@ -1,14 +1,13 @@
-
 plugins {
-    id("com.android.application") version "4.2.1"
+    id("com.android.application") version "7.0.1"
     kotlin("android") version "1.5.20"
     kotlin("kapt") version "1.5.20"
     kotlin("plugin.serialization") version "1.5.20"
 }
 
 android {
-    compileSdkVersion(30)
-    buildToolsVersion("30.0.3")
+    compileSdk = 30
+    buildToolsVersion = "30.0.3"
     ndkVersion = "22.1.7171670"
 
     compileOptions {
@@ -23,10 +22,10 @@ android {
 
     defaultConfig {
         applicationId = "dev.patrickgold.florisboard"
-        minSdkVersion(23)
-        targetSdkVersion(30)
-        versionCode(49)
-        versionName("0.3.13")
+        minSdk = 23
+        targetSdk = 30
+        versionCode = 56
+        versionName = "0.3.13"
 
         testInstrumentationRunner = "androidx.test.runner.AndroidJUnitRunner"
 
@@ -55,8 +54,11 @@ android {
 
         sourceSets {
             maybeCreate("main").apply {
-                jni {
-                    srcDirs("src/main/jniLibs")
+                assets {
+                    srcDirs("src/main/assets", "src/main/icu4c/prebuilt/assets")
+                }
+                jniLibs {
+                    srcDirs("src/main/icu4c/prebuilt/jniLibs")
                 }
             }
         }
@@ -88,7 +90,7 @@ android {
         create("beta") // Needed because by default the "beta" BuildType does not exist
         named("beta").configure {
             applicationIdSuffix = ".beta"
-            versionNameSuffix = "-beta06"
+            versionNameSuffix = "-beta12"
             proguardFiles.add(getDefaultProguardFile("proguard-android-optimize.txt"))
 
             resValue("mipmap", "floris_app_icon", "@mipmap/ic_app_icon_beta")
@@ -111,12 +113,11 @@ android {
         }
     }
 
-    lintOptions {
+    lint {
         isAbortOnError = false
     }
 }
 
-
 dependencies {
     implementation("androidx.activity", "activity-ktx", "1.2.1")
     implementation("androidx.appcompat", "appcompat", "1.2.0")
@@ -126,7 +127,7 @@ dependencies {
     implementation("androidx.preference", "preference-ktx", "1.1.1")
     implementation("androidx.constraintlayout", "constraintlayout", "2.0.4")
     implementation("androidx.lifecycle", "lifecycle-service", "2.2.0")
-    implementation("com.google.android", "flexbox", "2.0.1")
+    implementation("com.google.android.flexbox", "flexbox", "3.0.0")
     implementation("com.google.android.material", "material", "1.3.0")
     implementation("org.jetbrains.kotlinx", "kotlinx-coroutines-android", "1.4.2")
     implementation("org.jetbrains.kotlinx", "kotlinx-serialization-json", "1.1.0")

app/src/main/AndroidManifest.xml

@@ -34,7 +34,8 @@
             android:name="dev.patrickgold.florisboard.FlorisImeService"
             android:label="@string/floris_app_name"
             android:permission="android.permission.BIND_INPUT_METHOD"
-            android:directBootAware="true">
+            android:directBootAware="true"
+            android:exported="true">
             <intent-filter>
                 <action android:name="android.view.InputMethod"/>
             </intent-filter>
@@ -45,7 +46,8 @@
         <service
             android:name="dev.patrickgold.florisboard.FlorisSpellCheckerService"
             android:label="@string/floris_app_name"
-            android:permission="android.permission.BIND_TEXT_SERVICE">
+            android:permission="android.permission.BIND_TEXT_SERVICE"
+            android:exported="true">
             <intent-filter>
                 <action android:name="android.service.textservice.SpellCheckerService"/>
             </intent-filter>
@@ -68,7 +70,8 @@
             android:label="@string/floris_app_name"
             android:launchMode="singleTask"
             android:roundIcon="@mipmap/floris_app_icon_round"
-            android:targetActivity="dev.patrickgold.florisboard.setup.SetupActivity">
+            android:targetActivity="dev.patrickgold.florisboard.setup.SetupActivity"
+            android:exported="true">
             <intent-filter>
                 <action android:name="android.intent.action.MAIN"/>
                 <category android:name="android.intent.category.LAUNCHER"/>

app/src/main/assets/ime/config.json

@@ -2,7 +2,8 @@
   "package": "dev.patrickgold.florisboard",
   "composers": [
     { "$": "appender" },
-    { "$": "hangul-unicode" }
+    { "$": "hangul-unicode" },
+    { "$": "kana-unicode" }
   ],
   "currencySets": [
     {
@@ -682,6 +683,27 @@
       "preferred": {
         "characters": "korean"
       }
+    },
+    {
+      "id": 3000,
+      "languageTag": "lt-LT",
+      "composer": "appender",
+      "currencySet": "euro",
+      "preferred": {
+        "characters": "qwerty"
+      }
+    },
+    {
+      "id": 3100,
+      "languageTag": "ja-JP-jis",
+      "composer": "kana-unicode",
+      "currencySet": "yen",
+      "preferred": {
+        "characters": "jis",
+        "symbols": "cjk",
+        "symbols2": "cjk",
+        "numericRow": "cjk"
+      }
     }
   ]
 }

app/src/main/assets/ime/text/characters/extended_popups/ar.json

@@ -4,59 +4,21 @@
   "authors": [ "HeiWiper" ],
   "mapping": {
     "all": {
-      "ض": {
-        "relevant": [
-          { "code": 1633, "label": "١" }
-        ]
-      },
-      "ص": {
-        "relevant": [
-          { "code": 1634, "label": "٢" }
-        ]
-      },
-      "ث": {
-        "relevant": [
-          { "code": 1635, "label": "٣" }
-        ]
-      },
       "ق": {
         "relevant": [
-          { "code": 1704, "label": "ڨ" },
-          { "code": 1636, "label": "٤" }
+          { "code": 1704, "label": "ڨ" }
         ]
       },
       "ف": {
         "relevant": [
           { "code": 1701, "label": "ڥ" },
           { "code": 1700, "label": "ڤ" },
-          { "code": 1698, "label": "ڢ" },
-          { "code": 1637, "label": "٥" }
-        ]
-      },
-      "غ": {
-        "relevant": [
-          { "code": 1638, "label": "٦" }
-        ]
-      },
-      "ع": {
-        "relevant": [
-          { "code": 1639, "label": "٧" }
+          { "code": 1698, "label": "ڢ" }
         ]
       },
       "ه": {
         "relevant": [
-          { "code": 1726, "label": "ھ" },
-          { "code": 1640, "label": "٨" }
-        ]
-      },
-      "خ": {
-        "relevant": [
-          { "code": 1641, "label": "٩" }
-        ]
-      },
-      "ح": {
-        "relevant": [
-          { "code": 1632, "label": "٠" }
+          { "code": 1726, "label": "ھ" }
         ]
       },
       "ج": {
@@ -70,8 +32,8 @@
         ]
       },
       "ي": {
+        "main": { "code": 1574, "label": "ئ" },
         "relevant": [
-          { "code": 1574, "label": "ئ" },
           { "code": 1609, "label": "ى" }
         ]
       },
@@ -89,10 +51,10 @@
         ]
       },
       "ا": {
+        "main": { "code": 1571, "label": "أ" },
         "relevant": [
           { "code": 1570, "label": "آ" },
           { "code": 1569, "label": "ء" },
-          { "code": 1571, "label": "أ" },
           { "code": 1573, "label": "إ" },
           { "code": 1649, "label": "ٱ" }
         ]
@@ -104,9 +66,7 @@
         ]
       },
       "ى": {
-        "relevant": [
-          { "code": 1574, "label": "ئ" }
-        ]
+        "main": { "code": 1574, "label": "ئ" }
       },
       "ز": {
         "relevant": [

app/src/main/assets/ime/text/characters/extended_popups/ja-JP-jis.json

@@ -0,0 +1,292 @@
+{
+  "type": "characters/extended_popups",
+  "name": "ja-JP-jis",
+  "authors": [ "waelwindows" ],
+  "mapping": {
+    "all": {
+      "あ": {
+        "main": { "code": 12353, "label": "ぁ" }
+      },
+      "ア": {
+        "main": { "code": 12449, "label": "ァ" }
+      },
+      "ｱ": {
+        "main": { "code": 65383, "label": "ｧ" }
+      },
+      "い": {
+        "main": { "code": 12355, "label": "ぃ" },
+        "relevant": [
+          { "code":  12432, "label": "ゐ" },
+          { "code": 110928, "label": "𛅐" }
+        ]
+      },
+      "イ": {
+        "main": { "code": 12451, "label": "ィ" },
+        "relevant": [
+          { "code":  12528, "label": "ヰ" },
+          { "code": 110948, "label": "𛅤" }
+        ]
+      },
+      "ｲ": {
+        "main": { "code": 65384, "label": "ｨ" }
+      },
+      "う": {
+        "main": { "code": 12357, "label": "ぅ" }
+      },
+      "ウ": {
+        "main": { "code": 12453, "label": "ゥ" }
+      },
+      "ｳ": {
+        "main": { "code": 65385, "label": "ｩ" }
+      },
+      "え": {
+        "main": { "code": 12359, "label": "ぇ" },
+        "relevant": [
+          { "code":  12433, "label": "ゑ" },
+          { "code": 110929, "label": "𛅑" }
+        ]
+      },
+      "エ": {
+        "main": { "code": 12455, "label": "ェ" },
+        "relevant": [
+          { "code":  12529, "label": "ヱ" },
+          { "code": 110949, "label": "𛅥" }
+        ]
+      },
+      "ｴ": {
+        "main": { "code": 65386, "label": "ｪ" }
+      },
+      "お": {
+        "main": { "code": 12361, "label": "ぉ" }
+      },
+      "オ": {
+        "main": { "code": 12457, "label": "ォ" }
+      },
+      "ｵ": {
+        "main": { "code": 65387, "label": "ｫ" }
+      },
+      "や": {
+        "main": { "code": 12419, "label": "ゃ" }
+      },
+      "ヤ": {
+        "main": { "code": 12515, "label": "ャ" }
+      },
+      "ﾔ": {
+        "main": { "code": 65388, "label": "ｬ" }
+      },
+      "ゆ": {
+        "main": { "code": 12421, "label": "ゅ" }
+      },
+      "ユ": {
+        "main": { "code": 12517, "label": "ュ" }
+      },
+      "ﾕ": {
+        "main": { "code": 65389, "label": "ｭ" }
+      },
+      "よ": {
+        "main": { "code": 12423, "label": "ょ" }
+      },
+      "ヨ": {
+        "main": { "code": 12519, "label": "ョ" }
+      },
+      "ﾖ": {
+        "main": { "code": 65390, "label": "ｮ" }
+      },
+      "わ": {
+        "main": { "code": 12434, "label": "を" },
+        "relevant": [
+          { "code":  12430, "label": "ゎ" },
+          { "code": 110930, "label": "𛅒" }
+        ]
+      },
+      "ワ": {
+        "main": { "code": 12530, "label": "ヲ" },
+        "relevant": [
+          { "code":  12526, "label": "ヮ" },
+          { "code": 110950, "label": "𛅦" }
+        ]
+      },
+      "ﾜ": {
+        "main": { "code": 65382, "label": "ｦ" }
+      },
+      "つ": {
+        "main": { "code": 12387, "label": "っ" }
+      },
+      "ツ": {
+        "main": { "code": 12483, "label": "ッ" }
+      },
+      "ﾂ": {
+        "main": { "code": 65391, "label": "ｯ" }
+      },
+      "ト": {
+        "relevant": [
+          { "code": 12787, "label": "ㇳ" }
+        ]
+      },
+      "シ": {
+        "relevant": [
+          { "code": 12785, "label": "ㇱ" }
+        ]
+      },
+      "ス": {
+        "main": { "code": 12786, "label": "ㇲ" }
+      },
+      "か": {
+        "main": { "code": 12437, "label": "ゕ" }
+      },
+      "カ": {
+        "main": { "code": 12533, "label": "ヵ" }
+      },
+      "ク": {
+        "main": { "code": 12784, "label": "ㇰ" }
+      },
+      "け": {
+        "main": { "code": 12438, "label": "ゖ" }
+      },
+      "ケ": {
+        "main": { "code": 12534, "label": "ヶ" }
+      },
+      "ヌ": {
+        "relevant": [
+          { "code": 12788, "label": "ㇴ" }
+        ]
+      },
+      "ハ": {
+        "relevant": [
+          { "code": 12789, "label": "ㇵ" }
+        ]
+      },
+      "ヒ": {
+        "relevant": [
+          { "code": 12790, "label": "ㇶ" }
+        ]
+      },
+      "フ": {
+        "relevant": [
+          { "code": 12791, "label": "ㇷ" }
+        ]
+      },
+      "ヘ": {
+        "relevant": [
+          { "code": 12792, "label": "ㇸ" }
+        ]
+      },
+      "ホ": {
+        "relevant": [
+          { "code": 12793, "label": "ㇹ" }
+        ]
+      },
+      "ム": {
+        "relevant": [
+          { "code": 12794, "label": "ㇺ" }
+        ]
+      },
+      "ラ": {
+        "relevant": [
+          { "code": 12795, "label": "ㇻ" }
+        ]
+      },
+      "リ": {
+        "relevant": [
+          { "code": 12796, "label": "ㇼ" }
+        ]
+      },
+      "ル": {
+        "relevant": [
+          { "code": 12797, "label": "ㇽ" }
+        ]
+      },
+      "レ": {
+        "relevant": [
+          { "code": 12798, "label": "ㇾ" }
+        ]
+      },
+      "ロ": {
+        "relevant": [
+          { "code": 12799, "label": "ㇿ" }
+        ]
+      },
+      "゛": {
+        "main": { "code": 12443, "label": "゛" }
+      },
+      "゜": {
+        "main": { "code": 12444, "label": "゜" }
+      },
+      "~kana": {
+        "relevant": [
+          { "code": -9711, "label": "あ" },
+          { "code": -9712, "label": "ア" },
+          { "code": -9713, "label": "ｱ" }
+        ]
+      },
+      "~right": {
+        "main": { "$": "char_width_selector",
+          "full": { "code": 12539, "label": "・" },
+          "half": { "code": 9834, "label": "♪" }
+        },
+        "relevant": [
+          { "$": "char_width_selector",
+            "full": { "code": 65286, "label": "＆" },
+            "half": { "code":    38, "label": "&" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65285, "label": "％" },
+            "half": { "code":    37, "label": "%" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65291, "label": "＋" },
+            "half": { "code":    43, "label": "+" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65340, "label": "＼" },
+            "half": { "code":    92, "label": "\\" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65293, "label": "－" },
+            "half": { "code":    45, "label": "-" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65306, "label": "：" },
+            "half": { "code":    58, "label": ":" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65287, "label": "＇" },
+            "half": { "code":    39, "label": "'" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65312, "label": "＠" },
+            "half": { "code":    64, "label": "@" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65307, "label": "；" },
+            "half": { "code":    59, "label": ";" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65295, "label": "／" },
+            "half": { "code":    47, "label": "/" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65288, "label": "（" },
+            "half": { "code":    40, "label": "(" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65289, "label": "）" },
+            "half": { "code":    41, "label": ")" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65283, "label": "＃" },
+            "half": { "code":    35, "label": "#" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65281, "label": "！" },
+            "half": { "code":    33, "label": "!" }
+          },
+          { "$": "char_width_selector",
+            "full": { "code": 65311, "label": "？" },
+            "half": { "code":    63, "label": "?" }
+          }
+        ]
+      }
+    }
+  }
+}

app/src/main/assets/ime/text/characters/extended_popups/lt.json

@@ -0,0 +1,167 @@
+{
+  "type": "characters/extended_popups",
+  "name": "lv",
+  "authors": [ "patrickgold" ],
+  "mapping": {
+    "all": {
+      "a": {
+        "main": { "$": "auto_text_key", "code":  261, "label": "ą" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  226, "label": "â" },
+          { "$": "auto_text_key", "code":  227, "label": "ã" },
+          { "$": "auto_text_key", "code":  229, "label": "å" },
+          { "$": "auto_text_key", "code":  230, "label": "æ" },
+          { "$": "auto_text_key", "code":  228, "label": "ä" },
+          { "$": "auto_text_key", "code":  257, "label": "ā" },
+          { "$": "auto_text_key", "code":  224, "label": "à" },
+          { "$": "auto_text_key", "code":  225, "label": "á" }
+        ]
+      },
+      "c": {
+        "main": { "$": "auto_text_key", "code":  269, "label": "č" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  263, "label": "ć" },
+          { "$": "auto_text_key", "code":  231, "label": "ç" }
+        ]
+      },
+      "d": {
+        "main": { "$": "auto_text_key", "code":  271, "label": "ď" }
+      },
+      "e": {
+        "main": { "$": "auto_text_key", "code":  279, "label": "ė" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  235, "label": "ë" },
+          { "$": "auto_text_key", "code":  233, "label": "é" },
+          { "$": "auto_text_key", "code":  234, "label": "ê" },
+          { "$": "auto_text_key", "code":  283, "label": "ě" },
+          { "$": "auto_text_key", "code":  275, "label": "ē" },
+          { "$": "auto_text_key", "code":  281, "label": "ę" },
+          { "$": "auto_text_key", "code":  232, "label": "è" }
+        ]
+      },
+      "g": {
+        "main": { "$": "auto_text_key", "code":  291, "label": "ģ" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  287, "label": "ğ" }
+        ]
+      },
+      "i": {
+        "main": { "$": "auto_text_key", "code":  303, "label": "į" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  238, "label": "î" },
+          { "$": "auto_text_key", "code":  239, "label": "ï" },
+          { "$": "auto_text_key", "code":  236, "label": "ì" },
+          { "$": "auto_text_key", "code":  299, "label": "ī" },
+          { "$": "auto_text_key", "code":  237, "label": "í" }
+        ]
+      },
+      "k": {
+        "main": { "$": "auto_text_key", "code":  311, "label": "ķ" }
+      },
+      "l": {
+        "main": { "$": "auto_text_key", "code":  316, "label": "ļ" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  318, "label": "ľ" },
+          { "$": "auto_text_key", "code":  314, "label": "ĺ" },
+          { "$": "auto_text_key", "code":  322, "label": "ł" }
+        ]
+      },
+      "n": {
+        "main": { "$": "auto_text_key", "code":  326, "label": "ņ" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  324, "label": "ń" },
+          { "$": "auto_text_key", "code":  241, "label": "ñ" }
+        ]
+      },
+      "o": {
+        "main": { "$": "auto_text_key", "code":  246, "label": "ö" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  248, "label": "ø" },
+          { "$": "auto_text_key", "code":  337, "label": "ő" },
+          { "$": "auto_text_key", "code":  244, "label": "ô" },
+          { "$": "auto_text_key", "code":  339, "label": "œ" },
+          { "$": "auto_text_key", "code":  243, "label": "ó" },
+          { "$": "auto_text_key", "code":  242, "label": "ò" },
+          { "$": "auto_text_key", "code":  245, "label": "õ" }
+        ]
+      },
+      "r": {
+        "main": { "$": "auto_text_key", "code":  343, "label": "ŗ" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  341, "label": "ŕ" },
+          { "$": "auto_text_key", "code":  345, "label": "ř" }
+        ]
+      },
+      "s": {
+        "main": { "$": "auto_text_key", "code":  353, "label": "š" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  347, "label": "ś" },
+          { "$": "auto_text_key", "code":  223, "label": "ß" },
+          { "$": "auto_text_key", "code":  351, "label": "ş" }
+        ]
+      },
+      "t": {
+        "main": { "$": "auto_text_key", "code":  355, "label": "ţ" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  357, "label": "ť" }
+        ]
+      },
+      "u": {
+        "main": { "$": "auto_text_key", "code":  363, "label": "ū" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  367, "label": "ů" },
+          { "$": "auto_text_key", "code":  250, "label": "ú" },
+          { "$": "auto_text_key", "code":  251, "label": "û" },
+          { "$": "auto_text_key", "code":  369, "label": "ű" },
+          { "$": "auto_text_key", "code":  249, "label": "ù" },
+          { "$": "auto_text_key", "code":  252, "label": "ü" },
+          { "$": "auto_text_key", "code":  371, "label": "ų" }
+        ]
+      },
+      "y": {
+        "main": { "$": "auto_text_key", "code":  253, "label": "ý" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  255, "label": "ÿ" }
+        ]
+      },
+      "z": {
+        "main": { "$": "auto_text_key", "code":  382, "label": "ž" },
+        "relevant": [
+          { "$": "auto_text_key", "code":  378, "label": "ź" },
+          { "$": "auto_text_key", "code":  380, "label": "ż" }
+        ]
+      },
+      "~right": {
+        "main": { "code":   44, "label": "," },
+        "relevant": [
+          { "code":   38, "label": "&" },
+          { "code":   37, "label": "%" },
+          { "code":   43, "label": "+" },
+          { "code":   34, "label": "\"" },
+          { "code":   45, "label": "-" },
+          { "code":   58, "label": ":" },
+          { "code":   39, "label": "'" },
+          { "code":   64, "label": "@" },
+          { "code":   59, "label": ";" },
+          { "code":   47, "label": "/" },
+          { "code":   40, "label": "(" },
+          { "code":   41, "label": ")" },
+          { "code":   35, "label": "#" },
+          { "code":   33, "label": "!" },
+          { "code":   63, "label": "?" }
+        ]
+      }
+    },
+    "uri": {
+      "~right": {
+        "main": { "code": -255, "label": ".lv" },
+        "relevant": [
+          { "code": -255, "label": ".gov" },
+          { "code": -255, "label": ".edu" },
+          { "code": -255, "label": ".com" },
+          { "code": -255, "label": ".net" }
+        ]
+      }
+    }
+  }
+}

app/src/main/assets/ime/text/characters/extended_popups/tr.json

@@ -1,99 +1,35 @@
 {
   "type": "characters/extended_popups",
   "name": "tr",
-  "authors": [ "kisekinopureya", "patrickgold" ],
+  "authors": [ "kisekinopureya", "patrickgold", "dvrnynr" ],
   "mapping": {
     "all": {
-      "a": {
-        "relevant": [
-          { "$": "auto_text_key", "code":  226, "label": "â" },
-          { "$": "auto_text_key", "code":  228, "label": "ä" },
-          { "$": "auto_text_key", "code":  225, "label": "á" }
-        ]
-      },
       "c": {
-        "main": { "$": "auto_text_key", "code":  231, "label": "ç" },
-        "relevant": [
-          { "$": "auto_text_key", "code":  269, "label": "č" },
-          { "$": "auto_text_key", "code":  263, "label": "ć" }
-        ]
-      },
-      "e": {
-        "relevant": [
-          { "$": "auto_text_key", "code":  233, "label": "é" },
-          { "$": "auto_text_key", "code":  601, "label": "ə" },
-          { "$": "auto_text_key", "code":  234, "label": "ê" }
-        ]
+        "main": { "$": "auto_text_key", "code":  231, "label": "ç" }
       },
       "g": {
         "main": { "$": "auto_text_key", "code":  287, "label": "ğ" }
       },
       "i": {
-        "main": { "$": "auto_text_key", "code":  305, "label": "ı" },
-        "relevant": [
-          { "$": "auto_text_key", "code":  303, "label": "į" },
-          { "$": "auto_text_key", "code":  236, "label": "ì" },
-          { "$": "auto_text_key", "code":  237, "label": "í" },
-          { "$": "auto_text_key", "code":  299, "label": "ī" },
-          { "$": "auto_text_key", "code":  238, "label": "î" },
-          { "$": "auto_text_key", "code":  239, "label": "ï" }
-        ]
+        "main": { "$": "case_selector",
+          "lower": { "code":  305, "label": "ı" },
+          "upper": { "code":   73, "label": "I" }
+        }
       },
       "ı": {
-        "main": { "$": "auto_text_key", "code":  105, "label": "i" },
-        "relevant": [
-          { "$": "auto_text_key", "code":  303, "label": "į" },
-          { "$": "auto_text_key", "code":  236, "label": "ì" },
-          { "$": "auto_text_key", "code":  237, "label": "í" },
-          { "$": "auto_text_key", "code":  299, "label": "ī" },
-          { "$": "auto_text_key", "code":  238, "label": "î" },
-          { "$": "auto_text_key", "code":  239, "label": "ï" }
-        ]
-      },
-      "n": {
-        "relevant": [
-          { "$": "auto_text_key", "code":  328, "label": "ň" },
-          { "$": "auto_text_key", "code":  241, "label": "ñ" }
-        ]
+        "main": { "$": "case_selector",
+          "lower": { "code":  105, "label": "i" },
+          "upper": { "code":  304, "label": "İ" }
+        }
       },
       "o": {
-        "main": { "$": "auto_text_key", "code":  246, "label": "ö" },
-        "relevant": [
-          { "$": "auto_text_key", "code":  333, "label": "ō" },
-          { "$": "auto_text_key", "code":  248, "label": "ø" },
-          { "$": "auto_text_key", "code":  243, "label": "ó" },
-          { "$": "auto_text_key", "code":  245, "label": "õ" },
-          { "$": "auto_text_key", "code":  242, "label": "ò" },
-          { "$": "auto_text_key", "code":  339, "label": "œ" },
-          { "$": "auto_text_key", "code":  244, "label": "ô" }
-        ]
+        "main": { "$": "auto_text_key", "code":  246, "label": "ö" }
       },
       "s": {
-        "main": { "$": "auto_text_key", "code":  351, "label": "ş" },
-        "relevant": [
-          { "$": "auto_text_key", "code":  347, "label": "ś" },
-          { "$": "auto_text_key", "code":  223, "label": "ß" },
-          { "$": "auto_text_key", "code":  353, "label": "š" }
-        ]
+        "main": { "$": "auto_text_key", "code":  351, "label": "ş" }
       },
       "u": {
-        "main": { "$": "auto_text_key", "code":  252, "label": "ü" },
-        "relevant": [
-          { "$": "auto_text_key", "code":  363, "label": "ū" },
-          { "$": "auto_text_key", "code":  249, "label": "ù" },
-          { "$": "auto_text_key", "code":  250, "label": "ú" },
-          { "$": "auto_text_key", "code":  251, "label": "û" }
-        ]
-      },
-      "y": {
-        "relevant": [
-          { "$": "auto_text_key", "code":  253, "label": "ý" }
-        ]
-      },
-      "z": {
-        "relevant": [
-          { "$": "auto_text_key", "code":  382, "label": "ž" }
-        ]
+        "main": { "$": "auto_text_key", "code":  252, "label": "ü" }
       },
       "~right": {
         "main": { "code":   44, "label": "," },
@@ -120,10 +56,10 @@
       "~right": {
         "main": { "code": -255, "label": ".com" },
         "relevant": [
-          { "code": -255, "label": ".gov" },
+          { "code": -255, "label": ".gov.tr" },
           { "code": -255, "label": ".org" },
-          { "code": -255, "label": ".edu" },
-          { "code": -255, "label": ".tr" },
+          { "code": -255, "label": ".edu.tr" },
+          { "code": -255, "label": ".com.tr" },
           { "code": -255, "label": ".net" }
         ]
       }

app/src/main/assets/ime/text/characters/jis.json

@@ -0,0 +1,354 @@
+{
+  "type": "characters",
+  "name": "jis",
+  "label": "JIS",
+  "authors": [ "waelwindows" ],
+  "direction": "ltr",
+  "modifier": "jis",
+  "arrangement": [
+    [
+      { "$": "kana_selector",
+        "hira": { "code": 12396, "label": "ぬ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12492, "label": "ヌ" },
+          "half": { "code": 65415, "label": "ﾇ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12405, "label": "ふ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12501, "label": "フ" },
+          "half": { "code": 65420, "label": "ﾌ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12354, "label": "あ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12450, "label": "ア" },
+          "half": { "code": 65393, "label": "ｱ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12358, "label": "う" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12454, "label": "ウ" },
+          "half": { "code": 65395, "label": "ｳ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12360, "label": "え" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12456, "label": "エ" },
+          "half": { "code": 65396, "label": "ｴ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12362, "label": "お" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12458, "label": "オ" },
+          "half": { "code": 65397, "label": "ｵ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12420, "label": "や" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12516, "label": "ヤ" },
+          "half": { "code": 65428, "label": "ﾔ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12422, "label": "ゆ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12518, "label": "ユ" },
+          "half": { "code": 65429, "label": "ﾕ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12424, "label": "よ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12520, "label": "ヨ" },
+          "half": { "code": 65430, "label": "ﾖ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12431, "label": "わ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12527, "label": "ワ" },
+          "half": { "code": 65436, "label": "ﾜ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12411, "label": "ほ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12507, "label": "ホ" },
+          "half": { "code": 65422, "label": "ﾎ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12408, "label": "へ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12504, "label": "ヘ" },
+          "half": { "code": 65421, "label": "ﾍ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12540, "label": "ー" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12540, "label": "ー" },
+          "half": { "code": 65392, "label": "ｰ" }
+        }
+      }
+    ],
+    [
+      { "$": "kana_selector",
+        "hira": { "code": 12383, "label": "た" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12479, "label": "タ" },
+          "half": { "code": 65408, "label": "ﾀ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12390, "label": "て" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12486, "label": "テ" },
+          "half": { "code": 65411, "label": "ﾃ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12356, "label": "い" },
+        "kata": { "$": "char_width_selector",
+             "full": { "code": 12452, "label": "イ" },
+             "half": { "code": 65394, "label": "ｲ" }
+         }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12377, "label": "す" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12473, "label": "ス" },
+          "half": { "code": 65405, "label": "ｽ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12363, "label": "か" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12459, "label": "カ" },
+          "half": { "code": 65398, "label": "ｶ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12435, "label": "ん" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12531, "label": "ン" },
+          "half": { "code": 65437, "label": "ﾝ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12394, "label": "な" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12490, "label": "ナ" },
+          "half": { "code": 65413, "label": "ﾅ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12395, "label": "に" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12491, "label": "ニ" },
+          "half": { "code": 65414, "label": "ﾆ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12425, "label": "ら" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12521, "label": "ラ" },
+          "half": { "code": 65431, "label": "ﾗ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12379, "label": "せ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12475, "label": "セ" },
+          "half": { "code": 65406, "label": "ｾ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12441, "label": "゛" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12441, "label": "゛" },
+          "half": { "code": 65438, "label": "ﾞ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12442, "label": "゜" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12442, "label": "゜" },
+          "half": { "code": 65439, "label": "ﾟ" }
+        }
+      }
+    ],
+    [
+      { "$": "kana_selector",
+        "hira": { "code": 12385, "label": "ち" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12481, "label": "チ" },
+          "half": { "code": 65409, "label": "ﾁ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12392, "label": "と" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12488, "label": "ト" },
+          "half": { "code": 65412, "label": "ﾄ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12375, "label": "し" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12471, "label": "シ" },
+          "half": { "code": 65410, "label": "ｼ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12399, "label": "は" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12495, "label": "ハ" },
+          "half": { "code": 65418, "label": "ﾊ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12365, "label": "き" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12461, "label": "キ" },
+          "half": { "code": 65399, "label": "ｷ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12367, "label": "く" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12463, "label": "ク" },
+          "half": { "code": 65400, "label": "ｸ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12414, "label": "ま" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12510, "label": "マ" },
+          "half": { "code": 65423, "label": "ﾏ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12398, "label": "の" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12494, "label": "ノ" },
+          "half": { "code": 65417, "label": "ﾉ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12426, "label": "り" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12522, "label": "リ" },
+          "half": { "code": 65432, "label": "ﾘ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12428, "label": "れ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12524, "label": "レ" },
+          "half": { "code": 65434, "label": "ﾚ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12369, "label": "け" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12465, "label": "ケ" },
+          "half": { "code": 65401, "label": "ｹ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12416, "label": "む" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12512, "label": "ム" },
+          "half": { "code": 65425, "label": "ﾑ" }
+        }
+      }
+    ],
+    [
+      { "$": "kana_selector",
+        "hira": { "code": 12388, "label": "つ" },
+        "kata": { "$": "char_width_selector",
+             "full": { "code": 12484, "label": "ツ" },
+             "half": { "code": 65410, "label": "ﾂ" }
+         }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12373, "label": "さ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12469, "label": "サ" },
+          "half": { "code": 65403, "label": "ｻ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12381, "label": "そ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12477, "label": "ソ" },
+          "half": { "code": 65407, "label": "ｿ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12402, "label": "ひ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12498, "label": "ヒ" },
+          "half": { "code": 65419, "label": "ﾋ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12371, "label": "こ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12467, "label": "コ" },
+          "half": { "code": 65402, "label": "ｺ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12415, "label": "み" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12511, "label": "ミ" },
+          "half": { "code": 65424, "label": "ﾐ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12418, "label": "も" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12514, "label": "モ" },
+          "half": { "code": 65427, "label": "ﾓ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12397, "label": "ね" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12493, "label": "ネ" },
+          "half": { "code": 65416, "label": "ﾈ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12427, "label": "る" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12523, "label": "ル" },
+          "half": { "code": 65433, "label": "ﾙ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12417, "label": "め" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12513, "label": "メ" },
+          "half": { "code": 65426, "label": "ﾒ" }
+        }
+      },
+      { "$": "kana_selector",
+        "hira": { "code": 12429, "label": "ろ" },
+        "kata": { "$": "char_width_selector",
+          "full": { "code": 12525, "label": "ロ" },
+          "half": { "code": 65435, "label": "ﾛ" }
+        }
+      }
+    ]
+  ]
+}

app/src/main/assets/ime/text/characters/mod/jis.json

@@ -0,0 +1,29 @@
+{
+  "type": "characters/mod",
+  "name": "jis",
+  "label": "JIS",
+  "authors": [ "waelwindows" ],
+  "direction": "ltr",
+  "arrangement": [
+    [
+      { "code":     0, "type": "placeholder" },
+      { "code":    -5, "label": "delete", "type": "enter_editing" }
+    ],
+    [
+      { "code":  -202, "label": "view_symbols", "type": "system_gui" },
+      { "$": "char_width_selector",
+        "full": { "code": 12289, "label": "、", "groupId": 1 },
+        "half": { "code": 65380, "label": "､", "groupId": 1 }
+      },
+      { "code":  -210, "label": "language_switch", "type": "system_gui" },
+      { "code":  -213, "label": "switch_to_media_context", "type": "system_gui" },
+      { "code": 12288, "label": "空白" },
+      { "code": -9710, "label": "かな", "groupId": 97, "type": "system_gui" },
+      { "$": "char_width_selector",
+        "full": { "code": 12290, "label": "。", "groupId": 2 },
+        "half": { "code": 65377, "label": "｡", "groupId": 2 }
+      },
+      { "code":    10, "label": "enter", "groupId": 3, "type": "enter_editing" }
+    ]
+  ]
+}

app/src/main/assets/ime/text/characters/turkish_f.json

@@ -9,7 +9,10 @@
       { "$": "auto_text_key", "code":  102, "label": "f" },
       { "$": "auto_text_key", "code":  103, "label": "g" },
       { "$": "auto_text_key", "code":  287, "label": "ğ" },
-      { "$": "auto_text_key", "code":  305, "label": "ı" },
+      { "$": "case_selector",
+        "lower": { "code":  305, "label": "ı" },
+        "upper": { "code":   73, "label": "I" }
+      },
       { "$": "auto_text_key", "code":  111, "label": "o" },
       { "$": "auto_text_key", "code":  100, "label": "d" },
       { "$": "auto_text_key", "code":  114, "label": "r" },
@@ -21,7 +24,10 @@
     ],
     [
       { "$": "auto_text_key", "code":  117, "label": "u" },
-      { "$": "auto_text_key", "code":  105, "label": "i" },
+      { "$": "case_selector",
+        "lower": { "code":  105, "label": "i" },
+        "upper": { "code":  304, "label": "İ" }
+      },
       { "$": "auto_text_key", "code":  101, "label": "e" },
       { "$": "auto_text_key", "code":   97, "label": "a" },
       { "$": "auto_text_key", "code":  252, "label": "ü" },

app/src/main/assets/ime/text/characters/turkish_q.json

@@ -13,7 +13,10 @@
       { "$": "auto_text_key", "code":  116, "label": "t" },
       { "$": "auto_text_key", "code":  121, "label": "y" },
       { "$": "auto_text_key", "code":  117, "label": "u" },
-      { "$": "auto_text_key", "code":  305, "label": "ı" },
+      { "$": "case_selector",
+        "lower": { "code":  305, "label": "ı" },
+        "upper": { "code":   73, "label": "I" }
+      },
       { "$": "auto_text_key", "code":  111, "label": "o" },
       { "$": "auto_text_key", "code":  112, "label": "p" },
       { "$": "auto_text_key", "code":  287, "label": "ğ" },
@@ -30,7 +33,10 @@
       { "$": "auto_text_key", "code":  107, "label": "k" },
       { "$": "auto_text_key", "code":  108, "label": "l" },
       { "$": "auto_text_key", "code":  351, "label": "ş" },
-      { "$": "auto_text_key", "code":  105, "label": "i" }
+      { "$": "case_selector",
+        "lower": { "code":  105, "label": "i" },
+        "upper": { "code":  304, "label": "İ" }
+      }
     ],
     [
       { "$": "auto_text_key", "code":  122, "label": "z" },

app/src/main/assets/ime/text/numeric/advanced/western_arabic_pc.json

@@ -0,0 +1,55 @@
+{
+  "type": "numeric_advanced",
+  "name": "western_arabic_pc",
+  "label": "Western Arabic (PC)",
+  "authors": [ "patrickgold" ],
+  "direction": "ltr",
+  "arrangement": [
+    [
+      { "code":   43, "label": "+", "popup": {
+        "relevant": [
+          { "code":   45, "label": "-" },
+          { "code":   42, "label": "*" },
+          { "code":   47, "label": "/" }
+        ]
+      } },
+      { "code":   55, "label": "7", "type": "numeric" },
+      { "code":   56, "label": "8", "type": "numeric" },
+      { "code":   57, "label": "9", "type": "numeric" },
+      { "code":   37, "label": "%" }
+    ],
+    [
+      { "code":   40, "label": "(", "popup": {
+        "relevant": [
+          { "code":   91, "label": "[" },
+          { "code":  123, "label": "{" }
+        ]
+      } },
+      { "code":   52, "label": "4", "type": "numeric" },
+      { "code":   53, "label": "5", "type": "numeric" },
+      { "code":   54, "label": "6", "type": "numeric" },
+      { "code":   32, "label": "space" }
+    ],
+    [
+      { "code":   41, "label": ")", "popup": {
+        "relevant": [
+          { "code":   93, "label": "]" },
+          { "code":  125, "label": "}" }
+        ]
+      } },
+      { "code":   49, "label": "1", "type": "numeric" },
+      { "code":   50, "label": "2", "type": "numeric" },
+      { "code":   51, "label": "3", "type": "numeric" },
+      { "code":   -5, "label": "delete", "type": "enter_editing" }
+    ],
+    [
+      { "code": -201, "label": "view_characters", "type": "system_gui" },
+      { "code":   44, "label": "," },
+      { "code": -202, "label": "view_symbols", "type": "system_gui" },
+      { "code":   48, "label": "0", "type": "numeric" },
+      { "code":   61, "label": "=" },
+      { "code":   46, "label": "." },
+      { "code":   10, "label": "enter", "groupId": 3, "type": "enter_editing" }
+    ]
+  ]
+}

app/src/main/assets/ime/text/numeric/row/cjk.json

@@ -0,0 +1,108 @@
+{
+  "type": "numeric_row",
+  "name": "cjk",
+  "label": "CJK",
+  "authors": [ "waelwindows" ],
+  "direction": "ltr",
+  "arrangement": [
+    [
+      { "code": 19968, "label": "一", "type": "numeric", "popup": {
+        "main": { "code":   49, "label": "1" },
+        "relevant": [
+          { "code": 22769, "label": "壱" },
+          { "code": 22777, "label": "壹" },
+          { "code": 24332, "label": "弌" },
+          { "code": 65297, "label": "１" }
+        ]
+      } },
+      { "code": 20108, "label": "二", "type": "numeric", "popup": {
+        "main": { "code":   50, "label": "2" },
+        "relevant": [
+          { "code": 24336, "label": "弐" },
+          { "code": 36019, "label": "貳" },
+          { "code": 36014, "label": "貮" },
+          { "code": 65298, "label": "２" }
+        ]
+      } },
+      { "code": 19977, "label": "三", "type": "numeric", "popup": {
+        "main": { "code":   51, "label": "3" },
+        "relevant": [
+          { "code": 21442, "label": "参" },
+          { "code": 21443, "label": "參" },
+          { "code": 24334, "label": "弎" },
+          { "code": 65299, "label": "３" }
+        ]
+      } },
+      { "code": 22235, "label": "四", "type": "numeric", "popup": {
+        "main": { "code":   52, "label": "4" },
+        "relevant": [
+          { "code": 32902, "label": "肆" },
+          { "code": 18825, "label": "䦉" },
+          { "code": 20118, "label": "亖" },
+          { "code": 65300, "label": "３" }
+        ]
+      } },
+      { "code": 20116, "label": "五", "type": "numeric", "popup": {
+        "main": { "code":   53, "label": "5" },
+        "relevant": [
+          { "code": 20237, "label": "伍" },
+          { "code": 65301, "label": "５" }
+        ]
+      } },
+      { "code": 20845, "label": "六", "type": "numeric", "popup": {
+        "main": { "code":   54, "label": "6" },
+        "relevant": [
+          { "code": 38520, "label": "陸" },
+          { "code": 65302, "label": "６" }
+        ]
+      } },
+      { "code": 19971, "label": "七", "type": "numeric", "popup": {
+        "main": { "code":   55, "label": "7" },
+        "relevant": [
+          { "code": 28422, "label": "漆" },
+          { "code": 26578, "label": "柒" },
+          { "code": 65303, "label": "７" }
+        ]
+      } },
+      { "code": 20843, "label": "八", "type": "numeric", "popup": {
+        "main": { "code":   56, "label": "8" },
+        "relevant": [
+          { "code": 25420, "label": "捌" },
+          { "code": 65304, "label": "８" }
+        ]
+      } },
+      { "code": 20061, "label": "九", "type": "numeric", "popup": {
+        "main": {"code":   57, "label": "9" },
+        "relevant": [
+          { "code": 29590, "label": "玖" },
+          { "code": 65305, "label": "９" }
+        ]
+      } },
+      { "code": 38646, "label": "零", "type": "numeric", "popup": {
+        "main": { "code":   48, "label": "0" },
+        "relevant": [
+          { "code": 12295, "label": "〇" },
+          { "code": 65296, "label": "０" }
+        ]
+      } },
+      { "code": 21313, "label": "十", "type": "numeric", "popup": {
+        "main": { "code": 25342, "label": "拾" },
+        "relevant": [
+          { "code": 20160, "label": "什" }
+        ]
+      } },
+      { "code": 30334, "label": "百", "type": "numeric", "popup": {
+        "main": { "code": 20336, "label": "佰" },
+        "relevant": [
+          { "code": 38476, "label": "陌" }
+        ]
+      } },
+      { "code": 21315, "label": "千", "type": "numeric", "popup": {
+        "main": { "code": 20191, "label": "仟" },
+        "relevant": [
+          { "code": 38433, "label": "阡" }
+        ]
+      } }
+    ]
+  ]
+}

app/src/main/assets/ime/text/numeric/western_arabic_pc.json

@@ -0,0 +1,35 @@
+{
+  "type": "numeric",
+  "name": "western_arabic_pc",
+  "label": "Western Arabic (PC)",
+  "authors": [ "patrickgold" ],
+  "direction": "ltr",
+  "arrangement": [
+    [
+      { "code":   55, "label": "7", "type": "numeric" },
+      { "code":   56, "label": "8", "type": "numeric" },
+      { "code":   57, "label": "9", "type": "numeric" },
+      { "code":   45, "label": "-" }
+    ],
+    [
+      { "code":   52, "label": "4", "type": "numeric" },
+      { "code":   53, "label": "5", "type": "numeric" },
+      { "code":   54, "label": "6", "type": "numeric" },
+      { "code":   32, "label": "space" }
+    ],
+    [
+      { "code":   49, "label": "1", "type": "numeric" },
+      { "code":   50, "label": "2", "type": "numeric" },
+      { "code":   51, "label": "3", "type": "numeric" },
+      { "code":   -5, "label": "delete", "type": "enter_editing" }
+    ],
+    [
+      { "code":   44, "label": "," },
+      { "code":   48, "label": "0", "type": "numeric", "popup": {
+        "main": { "code":   43, "label": "+" }
+      } },
+      { "code":   46, "label": "." },
+      { "code":   10, "label": "enter", "type": "enter_editing" }
+    ]
+  ]
+}

app/src/main/assets/ime/text/symbols/cjk.json

@@ -0,0 +1,283 @@
+{
+  "type": "symbols",
+  "name": "cjk",
+  "label": "CJK",
+  "authors": [ "waelwindows" ],
+  "direction": "ltr",
+  "modifier": "cjk",
+  "arrangement": [
+    [
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65312, "label": "＠", "popup": {
+            "main": { "code": 64, "label": "@" }
+          }
+        },
+        "half": { "code": 64, "label": "@" }
+      },
+      { "code": 12306, "label": "〒", "popup": {
+          "main": { "code": 12320, "label": "〠" }
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65283, "label": "＃", "popup": {
+            "main": { "code": 35, "label": "#" },
+            "relevant": [
+              { "code": 8470, "label": "№" }
+            ]
+          }
+        },
+        "half": { "code": 35, "label": "#", "popup": {
+            "main": { "code": 65283, "label": "＃" },
+            "relevant": [
+              { "code": 8470, "label": "№" }
+            ]
+          }
+        }
+      },
+      { "code": -801, "label": "currency_slot_1", "popup": {
+          "main": { "code": -802, "label": "currency_slot_2" },
+          "relevant": [
+            { "code": -806, "label": "currency_slot_6" },
+            { "code": -803, "label": "currency_slot_3" },
+            { "code": -804, "label": "currency_slot_4" },
+            { "code": -805, "label": "currency_slot_5" }
+          ]
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65285, "label": "％", "popup": {
+            "main": { "code": 37, "label": "%" },
+            "relevant": [
+              { "code": 8240, "label": "‰" },
+              { "code": 8453, "label": "℅" }
+            ]
+          }
+        },
+        "half": { "code": 37, "label": "%", "popup": {
+            "main": { "code": 65285, "label": "％" },
+            "relevant": [
+              { "code": 8240, "label": "‰" },
+              { "code": 8453, "label": "℅" }
+            ]
+          }
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65286, "label": "＆", "popup": {
+            "main": { "code": 38, "label": "&" }
+          }
+        },
+        "half": { "code": 38, "label": "&", "popup": {
+            "main": { "code": 65286, "label": "＆" }
+          }
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65293, "label": "－", "popup": {
+            "main": { "code": 65343, "label": "＿" },
+            "relevant": [
+              { "code": 45, "label": "-" },
+              { "code": 95, "label": "_" },
+              { "code": 8212, "label": "—" },
+              { "code": 8211, "label": "–" },
+              { "code": 183, "label": "·" }
+            ]
+          }
+        },
+        "half": { "code": 45, "label": "-", "popup": {
+            "main": { "code": 95, "label": "_" },
+            "relevant": [
+              { "code": 65293, "label": "－" },
+              { "code": 65343, "label": "＿" },
+              { "code": 8212, "label": "—" },
+              { "code": 8211, "label": "–" },
+              { "code": 183, "label": "·" }
+            ]
+          }
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65291, "label": "＋", "popup": {
+            "main": { "code": 43, "label": "+" },
+            "relevant": [
+              { "code": 177, "label": "±" }
+            ]
+          }
+        },
+        "half": { "code": 43, "label": "+", "popup": {
+            "main": { "code": 65291, "label": "＋" },
+            "relevant": [
+              { "code": 177, "label": "±" }
+            ]
+          }
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 12300, "label": "「", "popup": {
+            "main": { "code": 12302, "label": "『" },
+            "relevant": [
+              { "code": 12304, "label": "【" },
+              { "code": 12310, "label": "〖" }
+            ]
+          }
+        },
+        "half": { "code": 65378, "label": "｢", "popup": {
+            "main": { "code": 12301, "label": "」" },
+            "relevant": [
+              { "code": 12303, "label": "』" },
+              { "code": 12304, "label": "【" },
+              { "code": 12310, "label": "〖" }
+            ]
+          }
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 12301, "label": "」", "popup": {
+            "main": { "code": 12303, "label": "』" },
+            "relevant": [
+              { "code": 12305, "label": "】" },
+              { "code": 12311, "label": "〗" }
+            ]
+          }
+        },
+        "half": { "code": 65379, "label": "｣", "popup": {
+            "main": { "code": 12301, "label": "」" },
+            "relevant": [
+              { "code": 12303, "label": "』" },
+              { "code": 12305, "label": "】" },
+              { "code": 12311, "label": "〗" }
+            ]
+          }
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65295, "label": "／", "popup": {
+            "main": { "code": 47, "label": "/" }
+          }
+        },
+        "half": { "code": 47, "label": "/", "popup": {
+            "main": { "code": 65295, "label": "／" }
+          }
+        }
+      }
+    ],
+    [
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65290, "label": "＊", "popup": {
+            "main": { "code": 8251, "label": "※" },
+            "relevant": [
+              { "code": 42, "label": "*" },
+              { "code": 8224, "label": "†" },
+              { "code": 9733, "label": "★" },
+              { "code": 8225, "label": "‡" }
+            ]
+          }
+        },
+        "half": {  "code": 42, "label": "*", "popup": {
+            "main": { "code": 65290, "label": "＊" },
+            "relevant": [
+              { "code": 8251, "label": "※" },
+              { "code": 8224, "label": "†" },
+              { "code": 9733, "label": "★" },
+              { "code": 8225, "label": "‡" }
+            ]
+          }
+        }
+      },
+      { "code": 34, "label": "\"", "popup": {
+          "main": { "code": 8221, "label": "”" },
+          "relevant": [
+            { "code": 8222, "label": "„" },
+            { "code": 8220, "label": "“" },
+            { "code": 171, "label": "«" },
+            { "code": 187, "label": "»" }
+          ]
+        }
+      },
+      { "code": 39, "label": "'", "popup": {
+          "main": { "code": 8217, "label": "’" },
+          "relevant": [
+            { "code": 8218, "label": "‚" },
+            { "code": 8216, "label": "‘" },
+            { "code": 8249, "label": "‹" },
+            { "code": 8250, "label": "›" }
+          ]
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65306, "label": "：", "popup": {
+            "main": { "code": 58, "label": ":" },
+            "relevant": [
+              { "code": 8942, "label": "⋮" }
+            ]
+          }
+        },
+        "half": { "code": 58, "label": ":", "popup": {
+            "main": { "code": 65306, "label": "：" },
+            "relevant": [
+              { "code": 8942, "label": "⋮" }
+            ]
+          }
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65307, "label": "；", "popup": {
+            "main": { "code": 59, "label": ";" }
+          }
+        },
+        "half": { "code": 59, "label": ";", "popup": {
+            "main": { "code": 65307, "label": "；" }
+          }
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65281, "label": "！", "popup": {
+            "main": { "code": 33, "label": "!" },
+            "relevant": [
+              { "code": 161, "label": "¡" }
+            ]
+          }
+        },
+        "half": { "code": 33, "label": "!", "popup": {
+            "main": { "code": 65281, "label": "！" },
+            "relevant": [
+              { "code": 161, "label": "¡" }
+            ]
+          }
+        }
+      },
+      {
+        "$": "char_width_selector",
+        "full": { "code": 65311, "label": "？", "popup": {
+            "main": { "code": 63, "label": "?" },
+            "relevant": [
+              { "code": 191, "label": "¿" },
+              { "code": 8253, "label": "‽" }
+            ]
+          }
+        },
+        "half": {  "code": 63, "label": "?", "popup": {
+            "main": { "code": 65311, "label": "？" },
+            "relevant": [
+              { "code": 191, "label": "¿" },
+              { "code": 8253, "label": "‽" }
+            ]
+          }
+        }
+      }
+    ]
+  ]
+}

app/src/main/assets/ime/text/symbols/mod/cjk.json

@@ -0,0 +1,55 @@
+{
+  "type": "symbols/mod",
+  "name": "cjk",
+  "label": "CJK",
+  "authors": [ "waelwindows" ],
+  "direction": "ltr",
+  "arrangement": [
+    [
+      { "code": -203, "label": "view_symbols2", "type": "system_gui" },
+      { "code":    0, "type": "placeholder" },
+      { "code":   -5, "label": "delete", "type": "enter_editing" }
+    ],
+    [
+      { "code": -201, "label": "view_characters", "type": "system_gui" },
+      { "$": "char_width_selector",
+        "full": { "code": 12289, "label": "、", "popup": {
+            "main": { "code":   44, "label": "," }
+          }
+        },
+        "half": { "code": 65380, "label": "､", "popup": {
+            "main": { "code":   44, "label": "," }
+          }
+        }
+      },
+      { "code": -205, "label": "view_numeric_advanced", "type": "system_gui" },
+      { "code": 12288, "label": "空白" },
+      { "code": -9701, "label": "char_width_switcher", "type": "system_gui", "popup": {
+          "relevant": [
+            { "code": -9702, "label": "char_width_full", "type": "system_gui" },
+            { "code": -9703, "label": "char_width_half", "type": "system_gui" }
+          ]
+        }
+      },
+      { "$": "char_width_selector",
+        "full": { "code": 12290, "label": "。", "popup": {
+            "main": { "code": 8230, "label": "…" },
+            "relevant": [
+              { "code": 12539, "label": "・" },
+              { "code":    46, "label": "." }
+            ]
+          }
+        },
+        "half": { "code": 65377, "label": "｡", "popup": {
+            "main": { "code": 8230, "label": "…" },
+            "relevant": [
+              { "code": 65381, "label": "･" },
+              { "code":    46, "label": "." }
+            ]
+          }
+        }
+      },
+      { "code":   10, "label": "enter", "groupId": 3, "type": "enter_editing" }
+    ]
+  ]
+}

app/src/main/assets/ime/text/symbols2/cjk.json

@@ -0,0 +1,225 @@
+{
+  "type": "symbols2",
+  "name": "cjk",
+  "label": "CJK",
+  "authors": [ "waelwindows" ],
+  "direction": "ltr",
+  "modifier": "cjk",
+  "arrangement": [
+    [
+      { "$": "char_width_selector",
+        "full": { "code": 12316, "label": "〜", "popup": {
+          "main": { "code":  126, "label": "~" }
+          }
+        },
+        "half": { "code":  126, "label": "~", "popup": {
+          "main": { "code": 12316, "label": "〜" }
+          }
+        }
+      },
+      { "$": "char_width_selector",
+        "full": { "code": 65344, "label": "｀", "popup": {
+          "main": { "code":   96, "label": "`" }
+          }
+        },
+        "half": { "code":   96, "label": "`", "popup": {
+          "main": { "code": 65344, "label": "｀" }
+          }
+        }
+      },
+      { "$": "char_width_selector",
+        "full": { "code": 65372, "label": "｜", "popup": {
+          "main": { "code":  124, "label": "|" }
+          }
+        },
+        "half": { "code":  124, "label": "|", "popup": {
+          "main": { "code": 65372, "label": "｜" }
+          }
+        }
+      },
+      { "$": "char_width_selector",
+        "full":
+          { "code": 12539, "label": "・", "popup": {
+            "main": { "code": 9834, "label": "♪" },
+            "relevant": [
+              { "code": 8226, "label": "•" },
+              { "code": 9827, "label": "♣" },
+              { "code": 9824, "label": "♠" },
+              { "code": 9829, "label": "♥" },
+              { "code": 9830, "label": "♦" }
+            ]
+          } },
+        "half":
+          { "code": 8226, "label": "•", "popup": {
+            "main": { "code": 9834, "label": "♪" },
+            "relevant": [
+              { "code": 12539, "label": "・" },
+              { "code": 9827, "label": "♣" },
+              { "code": 9824, "label": "♠" },
+              { "code": 9829, "label": "♥" },
+              { "code": 9830, "label": "♦" }
+            ]
+          } }
+      },
+      { "code": 8730, "label": "√" },
+      { "code":  960, "label": "π", "popup": {
+        "main": { "code":  928, "label": "Π" },
+        "relevant": [
+          { "code":  969, "label": "ω" },
+          { "code":  945, "label": "α" },
+          { "code":  946, "label": "β" },
+          { "code":  937, "label": "Ω" },
+          { "code":  956, "label": "μ" }
+        ]
+      } },
+      { "code":  247, "label": "÷" },
+      { "code":  215, "label": "×" },
+      { "code":  182, "label": "¶" },
+      { "code": 8710, "label": "∆" }
+    ],
+    [
+      { "code": -805, "label": "currency_slot_5" },
+      { "code": -804, "label": "currency_slot_4" },
+      { "code": -803, "label": "currency_slot_3" },
+      { "code": -802, "label": "currency_slot_2" },
+      { "code":   94, "label": "^", "popup": {
+        "main": { "code": 8593, "label": "↑" },
+        "relevant": [
+          { "code": 8592, "label": "←" },
+          { "code": 8595, "label": "↓" },
+          { "code": 8594, "label": "→" }
+        ]
+      } },
+      { "code":  176, "label": "°", "popup": {
+        "main": { "code": 8242, "label": "′" },
+        "relevant": [
+          { "code": 8243, "label": "″" }
+        ]
+      } },
+      { "$": "char_width_selector",
+        "full":
+          { "code": 65309, "label": "＝", "popup": {
+            "main": { "code": 8800, "label": "≠" },
+            "relevant": [
+              { "code":   61, "label": "=" },
+              { "code": 8734, "label": "∞" },
+              { "code": 8776, "label": "≈" }
+            ]
+          }
+        },
+        "half":
+          { "code":   61, "label": "=", "popup": {
+            "main": { "code": 8800, "label": "≠" },
+            "relevant": [
+              { "code":   61, "label": "=" },
+              { "code": 8734, "label": "∞" },
+              { "code": 8776, "label": "≈" }
+            ]
+          }
+        }
+      },
+      { "$": "char_width_selector",
+        "full": { "code": 65371, "label": "｛", "popup": {
+            "main": { "code": 65288, "label": "（" },
+            "relevant": [
+              { "code":   123, "label": "{" },
+              { "code": 12308, "label": "〔" },
+              { "code": 12312, "label": "〘" },
+              { "code": 65375, "label": "｟" }
+            ]
+          }
+        },
+        "half": { "code":   123, "label": "{", "popup": {
+            "main": { "code": 40, "label": "(" },
+            "relevant": [
+              { "code": 65371, "label": "｛" }
+            ]
+          }
+        }
+      },
+      { "$": "char_width_selector",
+        "full": { "code": 65373, "label": "｝", "popup": {
+            "main": { "code": 65289, "label": "）" },
+            "relevant": [
+              { "code":   125, "label": "}" },
+              { "code": 12309, "label": "〕" },
+              { "code": 12313, "label": "〙" },
+              { "code": 65376, "label": "｠" }
+            ]
+          }
+        },
+        "half": { "code":   125, "label": "}", "popup": {
+            "main": { "code": 41, "label": ")" },
+            "relevant": [
+              { "code": 65373, "label": "｝" }
+            ]
+          }
+        }
+      },
+      { "$": "char_width_selector",
+        "full": { "code": 65340, "label": "＼", "popup": {
+            "main": { "code":   92, "label": "\\" }
+          }
+        },
+        "half": { "code":   92, "label": "\\", "popup": {
+            "main": { "code": 65340, "label": "＼" }
+          }
+        }
+      }
+    ],
+    [
+      { "code": 12292, "label": "〄" },
+      { "code": 12293, "label": "々" },
+      { "code": 12294, "label": "〆" },
+      { "code": 12295, "label": "〇" },
+      { "$": "kana_selector",
+        "hira": { "code": 12445, "label": "ゝ", "popup": {
+              "main": { "code": 12446, "label": "ゞ" },
+              "relevant": [
+                { "code": 12541, "label": "ヽ" },
+                { "code": 12542, "label": "ヾ" }
+              ]
+          }
+        },
+        "kata": { "code": 12541, "label": "ヽ", "popup": {
+              "main": { "code": 12542, "label": "ヾ" },
+              "relevant": [
+                { "code": 12445, "label": "ゝ" },
+                { "code": 12446, "label": "ゞ" }
+              ]
+          }
+        }
+      },
+      { "$": "char_width_selector",
+        "full": { "code": 65339, "label": "［", "popup": {
+            "main": { "code":   91, "label": "[" },
+            "relevant": [
+              { "code": 12314, "label": "〚" },
+              { "code": 12304, "label": "【" },
+              { "code": 12310, "label": "〖" }
+            ]
+          }
+        },
+        "half": { "code":   91, "label": "[", "popup": {
+            "main": { "code": 65339, "label": "［" }
+          }
+        }
+      },
+      { "$": "char_width_selector",
+        "full": { "code": 65341, "label": "］", "popup": {
+            "main": { "code":   93, "label": "]" },
+            "relevant": [
+              { "code": 12315, "label": "〛" },
+              { "code": 12305, "label": "】" },
+              { "code": 12311, "label": "〗" }
+            ]
+          }
+        },
+        "half": { "code":   93, "label": "]", "popup": {
+            "main": { "code": 65341, "label": "］" }
+          }
+        }
+      }
+    ]
+  ]
+}

app/src/main/assets/ime/text/symbols2/mod/cjk.json

@@ -0,0 +1,45 @@
+{
+  "type": "symbols2/mod",
+  "name": "cjk",
+  "label": "CJK",
+  "authors": [ "waelwindows" ],
+  "direction": "ltr",
+  "arrangement": [
+    [
+      { "code": -202, "label": "view_symbols", "type": "system_gui" },
+      { "code":    0, "type": "placeholder" },
+      { "code":   -5, "label": "delete", "type": "enter_editing" }
+    ],
+    [
+      { "code": -201, "label": "view_characters", "type": "system_gui" },
+      { "code": 12296, "label": "〈", "popup": {
+        "main": { "code": 12298, "label": "《" },
+        "relevant": [
+          { "code":  8804, "label": "≤" },
+          { "code":  8249, "label": "‹" },
+          { "code": 10216, "label": "⟨" },
+          { "code": 65308, "label": "＜" }
+        ]
+      } },
+      { "code": -205, "label": "view_numeric_advanced", "type": "system_gui" },
+      { "code": 12288, "label": "空白" },
+      { "code": -9701, "label": "char_width_switcher", "type": "system_gui", "popup": {
+          "relevant": [
+            { "code": -9702, "label": "char_width_full", "type": "system_gui" },
+            { "code": -9703, "label": "char_width_half", "type": "system_gui" }
+          ]
+        }
+      },
+      { "code": 12297, "label": "〉", "popup": {
+        "main": { "code": 12299, "label": "》" },
+        "relevant": [
+          { "code":    62, "label": ">" },
+          { "code":  8805, "label": "≥" },
+          { "code": 10217, "label": "⟩" },
+          { "code": 65310, "label": "＞" }
+        ]
+      } },
+      { "code":   10, "label": "enter", "groupId": 3, "type": "enter_editing" }
+    ]
+  ]
+}

app/src/main/assets/license/open_source_licenses.html

@@ -1130,680 +1130,171 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
     <h3>Nuspell</h3>
     <span>Copyright (c) 2021 Nuspell</span>
     <pre>
-                    GNU GENERAL PUBLIC LICENSE
+                   GNU LESSER GENERAL PUBLIC LICENSE
                        Version 3, 29 June 2007
 
- Copyright (C) 2007 Free Software Foundation, Inc. http://fsf.org/
+ Copyright (C) 2007 Free Software Foundation, Inc. &lt;http://fsf.org/&gt;
  Everyone is permitted to copy and distribute verbatim copies
  of this license document, but changing it is not allowed.
 
-                            Preamble
-
-  The GNU General Public License is a free, copyleft license for
-software and other kinds of works.
-
-  The licenses for most software and other practical works are designed
-to take away your freedom to share and change the works.  By contrast,
-the GNU General Public License is intended to guarantee your freedom to
-share and change all versions of a program--to make sure it remains free
-software for all its users.  We, the Free Software Foundation, use the
-GNU General Public License for most of our software; it applies also to
-any other work released this way by its authors.  You can apply it to
-your programs, too.
-
-  When we speak of free software, we are referring to freedom, not
-price.  Our General Public Licenses are designed to make sure that you
-have the freedom to distribute copies of free software (and charge for
-them if you wish), that you receive source code or can get it if you
-want it, that you can change the software or use pieces of it in new
-free programs, and that you know you can do these things.
-
-  To protect your rights, we need to prevent others from denying you
-these rights or asking you to surrender the rights.  Therefore, you have
-certain responsibilities if you distribute copies of the software, or if
-you modify it: responsibilities to respect the freedom of others.
-
-  For example, if you distribute copies of such a program, whether
-gratis or for a fee, you must pass on to the recipients the same
-freedoms that you received.  You must make sure that they, too, receive
-or can get the source code.  And you must show them these terms so they
-know their rights.
-
-  Developers that use the GNU GPL protect your rights with two steps:
-(1) assert copyright on the software, and (2) offer you this License
-giving you legal permission to copy, distribute and/or modify it.
-
-  For the developers' and authors' protection, the GPL clearly explains
-that there is no warranty for this free software.  For both users' and
-authors' sake, the GPL requires that modified versions be marked as
-changed, so that their problems will not be attributed erroneously to
-authors of previous versions.
-
-  Some devices are designed to deny users access to install or run
-modified versions of the software inside them, although the manufacturer
-can do so.  This is fundamentally incompatible with the aim of
-protecting users' freedom to change the software.  The systematic
-pattern of such abuse occurs in the area of products for individuals to
-use, which is precisely where it is most unacceptable.  Therefore, we
-have designed this version of the GPL to prohibit the practice for those
-products.  If such problems arise substantially in other domains, we
-stand ready to extend this provision to those domains in future versions
-of the GPL, as needed to protect the freedom of users.
-
-  Finally, every program is threatened constantly by software patents.
-States should not allow patents to restrict development and use of
-software on general-purpose computers, but in those that do, we wish to
-avoid the special danger that patents applied to a free program could
-make it effectively proprietary.  To prevent this, the GPL assures that
-patents cannot be used to render the program non-free.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.
-
-                       TERMS AND CONDITIONS
-
-  0. Definitions.
-
-  "This License" refers to version 3 of the GNU General Public License.
-
-  "Copyright" also means copyright-like laws that apply to other kinds of
-works, such as semiconductor masks.
-
-  "The Program" refers to any copyrightable work licensed under this
-License.  Each licensee is addressed as "you".  "Licensees" and
-"recipients" may be individuals or organizations.
-
-  To "modify" a work means to copy from or adapt all or part of the work
-in a fashion requiring copyright permission, other than the making of an
-exact copy.  The resulting work is called a "modified version" of the
-earlier work or a work "based on" the earlier work.
-
-  A "covered work" means either the unmodified Program or a work based
-on the Program.
-
-  To "propagate" a work means to do anything with it that, without
-permission, would make you directly or secondarily liable for
-infringement under applicable copyright law, except executing it on a
-computer or modifying a private copy.  Propagation includes copying,
-distribution (with or without modification), making available to the
-public, and in some countries other activities as well.
-
-  To "convey" a work means any kind of propagation that enables other
-parties to make or receive copies.  Mere interaction with a user through
-a computer network, with no transfer of a copy, is not conveying.
-
-  An interactive user interface displays "Appropriate Legal Notices"
-to the extent that it includes a convenient and prominently visible
-feature that (1) displays an appropriate copyright notice, and (2)
-tells the user that there is no warranty for the work (except to the
-extent that warranties are provided), that licensees may convey the
-work under this License, and how to view a copy of this License.  If
-the interface presents a list of user commands or options, such as a
-menu, a prominent item in the list meets this criterion.
-
-  1. Source Code.
-
-  The "source code" for a work means the preferred form of the work
-for making modifications to it.  "Object code" means any non-source
-form of a work.
-
-  A "Standard Interface" means an interface that either is an official
-standard defined by a recognized standards body, or, in the case of
-interfaces specified for a particular programming language, one that
-is widely used among developers working in that language.
-
-  The "System Libraries" of an executable work include anything, other
-than the work as a whole, that (a) is included in the normal form of
-packaging a Major Component, but which is not part of that Major
-Component, and (b) serves only to enable use of the work with that
-Major Component, or to implement a Standard Interface for which an
-implementation is available to the public in source code form.  A
-"Major Component", in this context, means a major essential component
-(kernel, window system, and so on) of the specific operating system
-(if any) on which the executable work runs, or a compiler used to
-produce the work, or an object code interpreter used to run it.
-
-  The "Corresponding Source" for a work in object code form means all
-the source code needed to generate, install, and (for an executable
-work) run the object code and to modify the work, including scripts to
-control those activities.  However, it does not include the work's
-System Libraries, or general-purpose tools or generally available free
-programs which are used unmodified in performing those activities but
-which are not part of the work.  For example, Corresponding Source
-includes interface definition files associated with source files for
-the work, and the source code for shared libraries and dynamically
-linked subprograms that the work is specifically designed to require,
-such as by intimate data communication or control flow between those
-subprograms and other parts of the work.
-
-  The Corresponding Source need not include anything that users
-can regenerate automatically from other parts of the Corresponding
-Source.
-
-  The Corresponding Source for a work in source code form is that
-same work.
-
-  2. Basic Permissions.
-
-  All rights granted under this License are granted for the term of
-copyright on the Program, and are irrevocable provided the stated
-conditions are met.  This License explicitly affirms your unlimited
-permission to run the unmodified Program.  The output from running a
-covered work is covered by this License only if the output, given its
-content, constitutes a covered work.  This License acknowledges your
-rights of fair use or other equivalent, as provided by copyright law.
-
-  You may make, run and propagate covered works that you do not
-convey, without conditions so long as your license otherwise remains
-in force.  You may convey covered works to others for the sole purpose
-of having them make modifications exclusively for you, or provide you
-with facilities for running those works, provided that you comply with
-the terms of this License in conveying all material for which you do
-not control copyright.  Those thus making or running the covered works
-for you must do so exclusively on your behalf, under your direction
-and control, on terms that prohibit them from making any copies of
-your copyrighted material outside their relationship with you.
-
-  Conveying under any other circumstances is permitted solely under
-the conditions stated below.  Sublicensing is not allowed; section 10
-makes it unnecessary.
-
-  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
-
-  No covered work shall be deemed part of an effective technological
-measure under any applicable law fulfilling obligations under article
-11 of the WIPO copyright treaty adopted on 20 December 1996, or
-similar laws prohibiting or restricting circumvention of such
-measures.
-
-  When you convey a covered work, you waive any legal power to forbid
-circumvention of technological measures to the extent such circumvention
-is effected by exercising rights under this License with respect to
-the covered work, and you disclaim any intention to limit operation or
-modification of the work as a means of enforcing, against the work's
-users, your or third parties' legal rights to forbid circumvention of
-technological measures.
-
-  4. Conveying Verbatim Copies.
-
-  You may convey verbatim copies of the Program's source code as you
-receive it, in any medium, provided that you conspicuously and
-appropriately publish on each copy an appropriate copyright notice;
-keep intact all notices stating that this License and any
-non-permissive terms added in accord with section 7 apply to the code;
-keep intact all notices of the absence of any warranty; and give all
-recipients a copy of this License along with the Program.
-
-  You may charge any price or no price for each copy that you convey,
-and you may offer support or warranty protection for a fee.
-
-  5. Conveying Modified Source Versions.
-
-  You may convey a work based on the Program, or the modifications to
-produce it from the Program, in the form of source code under the
-terms of section 4, provided that you also meet all of these conditions:
-
-    a) The work must carry prominent notices stating that you modified
-    it, and giving a relevant date.
-
-    b) The work must carry prominent notices stating that it is
-    released under this License and any conditions added under section
-    7.  This requirement modifies the requirement in section 4 to
-    "keep intact all notices".
-
-    c) You must license the entire work, as a whole, under this
-    License to anyone who comes into possession of a copy.  This
-    License will therefore apply, along with any applicable section 7
-    additional terms, to the whole of the work, and all its parts,
-    regardless of how they are packaged.  This License gives no
-    permission to license the work in any other way, but it does not
-    invalidate such permission if you have separately received it.
-
-    d) If the work has interactive user interfaces, each must display
-    Appropriate Legal Notices; however, if the Program has interactive
-    interfaces that do not display Appropriate Legal Notices, your
-    work need not make them do so.
-
-  A compilation of a covered work with other separate and independent
-works, which are not by their nature extensions of the covered work,
-and which are not combined with it such as to form a larger program,
-in or on a volume of a storage or distribution medium, is called an
-"aggregate" if the compilation and its resulting copyright are not
-used to limit the access or legal rights of the compilation's users
-beyond what the individual works permit.  Inclusion of a covered work
-in an aggregate does not cause this License to apply to the other
-parts of the aggregate.
-
-  6. Conveying Non-Source Forms.
-
-  You may convey a covered work in object code form under the terms
-of sections 4 and 5, provided that you also convey the
-machine-readable Corresponding Source under the terms of this License,
-in one of these ways:
-
-    a) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by the
-    Corresponding Source fixed on a durable physical medium
-    customarily used for software interchange.
-
-    b) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by a
-    written offer, valid for at least three years and valid for as
-    long as you offer spare parts or customer support for that product
-    model, to give anyone who possesses the object code either (1) a
-    copy of the Corresponding Source for all the software in the
-    product that is covered by this License, on a durable physical
-    medium customarily used for software interchange, for a price no
-    more than your reasonable cost of physically performing this
-    conveying of source, or (2) access to copy the
-    Corresponding Source from a network server at no charge.
-
-    c) Convey individual copies of the object code with a copy of the
-    written offer to provide the Corresponding Source.  This
-    alternative is allowed only occasionally and noncommercially, and
-    only if you received the object code with such an offer, in accord
-    with subsection 6b.
-
-    d) Convey the object code by offering access from a designated
-    place (gratis or for a charge), and offer equivalent access to the
-    Corresponding Source in the same way through the same place at no
-    further charge.  You need not require recipients to copy the
-    Corresponding Source along with the object code.  If the place to
-    copy the object code is a network server, the Corresponding Source
-    may be on a different server (operated by you or a third party)
-    that supports equivalent copying facilities, provided you maintain
-    clear directions next to the object code saying where to find the
-    Corresponding Source.  Regardless of what server hosts the
-    Corresponding Source, you remain obligated to ensure that it is
-    available for as long as needed to satisfy these requirements.
-
-    e) Convey the object code using peer-to-peer transmission, provided
-    you inform other peers where the object code and Corresponding
-    Source of the work are being offered to the general public at no
-    charge under subsection 6d.
-
-  A separable portion of the object code, whose source code is excluded
-from the Corresponding Source as a System Library, need not be
-included in conveying the object code work.
-
-  A "User Product" is either (1) a "consumer product", which means any
-tangible personal property which is normally used for personal, family,
-or household purposes, or (2) anything designed or sold for incorporation
-into a dwelling.  In determining whether a product is a consumer product,
-doubtful cases shall be resolved in favor of coverage.  For a particular
-product received by a particular user, "normally used" refers to a
-typical or common use of that class of product, regardless of the status
-of the particular user or of the way in which the particular user
-actually uses, or expects or is expected to use, the product.  A product
-is a consumer product regardless of whether the product has substantial
-commercial, industrial or non-consumer uses, unless such uses represent
-the only significant mode of use of the product.
-
-  "Installation Information" for a User Product means any methods,
-procedures, authorization keys, or other information required to install
-and execute modified versions of a covered work in that User Product from
-a modified version of its Corresponding Source.  The information must
-suffice to ensure that the continued functioning of the modified object
-code is in no case prevented or interfered with solely because
-modification has been made.
-
-  If you convey an object code work under this section in, or with, or
-specifically for use in, a User Product, and the conveying occurs as
-part of a transaction in which the right of possession and use of the
-User Product is transferred to the recipient in perpetuity or for a
-fixed term (regardless of how the transaction is characterized), the
-Corresponding Source conveyed under this section must be accompanied
-by the Installation Information.  But this requirement does not apply
-if neither you nor any third party retains the ability to install
-modified object code on the User Product (for example, the work has
-been installed in ROM).
-
-  The requirement to provide Installation Information does not include a
-requirement to continue to provide support service, warranty, or updates
-for a work that has been modified or installed by the recipient, or for
-the User Product in which it has been modified or installed.  Access to a
-network may be denied when the modification itself materially and
-adversely affects the operation of the network or violates the rules and
-protocols for communication across the network.
-
-  Corresponding Source conveyed, and Installation Information provided,
-in accord with this section must be in a format that is publicly
-documented (and with an implementation available to the public in
-source code form), and must require no special password or key for
-unpacking, reading or copying.
-
-  7. Additional Terms.
-
-  "Additional permissions" are terms that supplement the terms of this
-License by making exceptions from one or more of its conditions.
-Additional permissions that are applicable to the entire Program shall
-be treated as though they were included in this License, to the extent
-that they are valid under applicable law.  If additional permissions
-apply only to part of the Program, that part may be used separately
-under those permissions, but the entire Program remains governed by
-this License without regard to the additional permissions.
-
-  When you convey a copy of a covered work, you may at your option
-remove any additional permissions from that copy, or from any part of
-it.  (Additional permissions may be written to require their own
-removal in certain cases when you modify the work.)  You may place
-additional permissions on material, added by you to a covered work,
-for which you have or can give appropriate copyright permission.
-
-  Notwithstanding any other provision of this License, for material you
-add to a covered work, you may (if authorized by the copyright holders of
-that material) supplement the terms of this License with terms:
-
-    a) Disclaiming warranty or limiting liability differently from the
-    terms of sections 15 and 16 of this License; or
-
-    b) Requiring preservation of specified reasonable legal notices or
-    author attributions in that material or in the Appropriate Legal
-    Notices displayed by works containing it; or
-
-    c) Prohibiting misrepresentation of the origin of that material, or
-    requiring that modified versions of such material be marked in
-    reasonable ways as different from the original version; or
-
-    d) Limiting the use for publicity purposes of names of licensors or
-    authors of the material; or
-
-    e) Declining to grant rights under trademark law for use of some
-    trade names, trademarks, or service marks; or
-
-    f) Requiring indemnification of licensors and authors of that
-    material by anyone who conveys the material (or modified versions of
-    it) with contractual assumptions of liability to the recipient, for
-    any liability that these contractual assumptions directly impose on
-    those licensors and authors.
-
-  All other non-permissive additional terms are considered "further
-restrictions" within the meaning of section 10.  If the Program as you
-received it, or any part of it, contains a notice stating that it is
-governed by this License along with a term that is a further
-restriction, you may remove that term.  If a license document contains
-a further restriction but permits relicensing or conveying under this
-License, you may add to a covered work material governed by the terms
-of that license document, provided that the further restriction does
-not survive such relicensing or conveying.
-
-  If you add terms to a covered work in accord with this section, you
-must place, in the relevant source files, a statement of the
-additional terms that apply to those files, or a notice indicating
-where to find the applicable terms.
-
-  Additional terms, permissive or non-permissive, may be stated in the
-form of a separately written license, or stated as exceptions;
-the above requirements apply either way.
-
-  8. Termination.
-
-  You may not propagate or modify a covered work except as expressly
-provided under this License.  Any attempt otherwise to propagate or
-modify it is void, and will automatically terminate your rights under
-this License (including any patent licenses granted under the third
-paragraph of section 11).
-
-  However, if you cease all violation of this License, then your
-license from a particular copyright holder is reinstated (a)
-provisionally, unless and until the copyright holder explicitly and
-finally terminates your license, and (b) permanently, if the copyright
-holder fails to notify you of the violation by some reasonable means
-prior to 60 days after the cessation.
-
-  Moreover, your license from a particular copyright holder is
-reinstated permanently if the copyright holder notifies you of the
-violation by some reasonable means, this is the first time you have
-received notice of violation of this License (for any work) from that
-copyright holder, and you cure the violation prior to 30 days after
-your receipt of the notice.
-
-  Termination of your rights under this section does not terminate the
-licenses of parties who have received copies or rights from you under
-this License.  If your rights have been terminated and not permanently
-reinstated, you do not qualify to receive new licenses for the same
-material under section 10.
-
-  9. Acceptance Not Required for Having Copies.
-
-  You are not required to accept this License in order to receive or
-run a copy of the Program.  Ancillary propagation of a covered work
-occurring solely as a consequence of using peer-to-peer transmission
-to receive a copy likewise does not require acceptance.  However,
-nothing other than this License grants you permission to propagate or
-modify any covered work.  These actions infringe copyright if you do
-not accept this License.  Therefore, by modifying or propagating a
-covered work, you indicate your acceptance of this License to do so.
-
-  10. Automatic Licensing of Downstream Recipients.
-
-  Each time you convey a covered work, the recipient automatically
-receives a license from the original licensors, to run, modify and
-propagate that work, subject to this License.  You are not responsible
-for enforcing compliance by third parties with this License.
-
-  An "entity transaction" is a transaction transferring control of an
-organization, or substantially all assets of one, or subdividing an
-organization, or merging organizations.  If propagation of a covered
-work results from an entity transaction, each party to that
-transaction who receives a copy of the work also receives whatever
-licenses to the work the party's predecessor in interest had or could
-give under the previous paragraph, plus a right to possession of the
-Corresponding Source of the work from the predecessor in interest, if
-the predecessor has it or can get it with reasonable efforts.
-
-  You may not impose any further restrictions on the exercise of the
-rights granted or affirmed under this License.  For example, you may
-not impose a license fee, royalty, or other charge for exercise of
-rights granted under this License, and you may not initiate litigation
-(including a cross-claim or counterclaim in a lawsuit) alleging that
-any patent claim is infringed by making, using, selling, offering for
-sale, or importing the Program or any portion of it.
-
-  11. Patents.
-
-  A "contributor" is a copyright holder who authorizes use under this
-License of the Program or a work on which the Program is based.  The
-work thus licensed is called the contributor's "contributor version".
-
-  A contributor's "essential patent claims" are all patent claims
-owned or controlled by the contributor, whether already acquired or
-hereafter acquired, that would be infringed by some manner, permitted
-by this License, of making, using, or selling its contributor version,
-but do not include claims that would be infringed only as a
-consequence of further modification of the contributor version.  For
-purposes of this definition, "control" includes the right to grant
-patent sublicenses in a manner consistent with the requirements of
-this License.
-
-  Each contributor grants you a non-exclusive, worldwide, royalty-free
-patent license under the contributor's essential patent claims, to
-make, use, sell, offer for sale, import and otherwise run, modify and
-propagate the contents of its contributor version.
-
-  In the following three paragraphs, a "patent license" is any express
-agreement or commitment, however denominated, not to enforce a patent
-(such as an express permission to practice a patent or covenant not to
-sue for patent infringement).  To "grant" such a patent license to a
-party means to make such an agreement or commitment not to enforce a
-patent against the party.
-
-  If you convey a covered work, knowingly relying on a patent license,
-and the Corresponding Source of the work is not available for anyone
-to copy, free of charge and under the terms of this License, through a
-publicly available network server or other readily accessible means,
-then you must either (1) cause the Corresponding Source to be so
-available, or (2) arrange to deprive yourself of the benefit of the
-patent license for this particular work, or (3) arrange, in a manner
-consistent with the requirements of this License, to extend the patent
-license to downstream recipients.  "Knowingly relying" means you have
-actual knowledge that, but for the patent license, your conveying the
-covered work in a country, or your recipient's use of the covered work
-in a country, would infringe one or more identifiable patents in that
-country that you have reason to believe are valid.
-
-  If, pursuant to or in connection with a single transaction or
-arrangement, you convey, or propagate by procuring conveyance of, a
-covered work, and grant a patent license to some of the parties
-receiving the covered work authorizing them to use, propagate, modify
-or convey a specific copy of the covered work, then the patent license
-you grant is automatically extended to all recipients of the covered
-work and works based on it.
-
-  A patent license is "discriminatory" if it does not include within
-the scope of its coverage, prohibits the exercise of, or is
-conditioned on the non-exercise of one or more of the rights that are
-specifically granted under this License.  You may not convey a covered
-work if you are a party to an arrangement with a third party that is
-in the business of distributing software, under which you make payment
-to the third party based on the extent of your activity of conveying
-the work, and under which the third party grants, to any of the
-parties who would receive the covered work from you, a discriminatory
-patent license (a) in connection with copies of the covered work
-conveyed by you (or copies made from those copies), or (b) primarily
-for and in connection with specific products or compilations that
-contain the covered work, unless you entered into that arrangement,
-or that patent license was granted, prior to 28 March 2007.
-
-  Nothing in this License shall be construed as excluding or limiting
-any implied license or other defenses to infringement that may
-otherwise be available to you under applicable patent law.
-
-  12. No Surrender of Others' Freedom.
-
-  If conditions are imposed on you (whether by court order, agreement or
-otherwise) that contradict the conditions of this License, they do not
-excuse you from the conditions of this License.  If you cannot convey a
-covered work so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you may
-not convey it at all.  For example, if you agree to terms that obligate you
-to collect a royalty for further conveying from those to whom you convey
-the Program, the only way you could satisfy both those terms and this
-License would be to refrain entirely from conveying the Program.
-
-  13. Use with the GNU Affero General Public License.
-
-  Notwithstanding any other provision of this License, you have
-permission to link or combine any covered work with a work licensed
-under version 3 of the GNU Affero General Public License into a single
-combined work, and to convey the resulting work.  The terms of this
-License will continue to apply to the part which is the covered work,
-but the special requirements of the GNU Affero General Public License,
-section 13, concerning interaction through a network will apply to the
-combination as such.
-
-  14. Revised Versions of this License.
-
-  The Free Software Foundation may publish revised and/or new versions of
-the GNU General Public License from time to time.  Such new versions will
-be similar in spirit to the present version, but may differ in detail to
-address new problems or concerns.
-
-  Each version is given a distinguishing version number.  If the
-Program specifies that a certain numbered version of the GNU General
-Public License "or any later version" applies to it, you have the
-option of following the terms and conditions either of that numbered
-version or of any later version published by the Free Software
-Foundation.  If the Program does not specify a version number of the
-GNU General Public License, you may choose any version ever published
-by the Free Software Foundation.
-
-  If the Program specifies that a proxy can decide which future
-versions of the GNU General Public License can be used, that proxy's
-public statement of acceptance of a version permanently authorizes you
-to choose that version for the Program.
-
-  Later license versions may give you additional or different
-permissions.  However, no additional obligations are imposed on any
-author or copyright holder as a result of your choosing to follow a
-later version.
-
-  15. Disclaimer of Warranty.
-
-  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
-APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
-HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
-OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
-THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
-IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
-ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
-
-  16. Limitation of Liability.
-
-  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
-WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
-THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
-GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
-USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
-DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
-PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
-EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
-SUCH DAMAGES.
-
-  17. Interpretation of Sections 15 and 16.
-
-  If the disclaimer of warranty and limitation of liability provided
-above cannot be given local legal effect according to their terms,
-reviewing courts shall apply local law that most closely approximates
-an absolute waiver of all civil liability in connection with the
-Program, unless a warranty or assumption of liability accompanies a
-copy of the Program in return for a fee.
-
-                     END OF TERMS AND CONDITIONS
-
-            How to Apply These Terms to Your New Programs
-
-  If you develop a new program, and you want it to be of the greatest
-possible use to the public, the best way to achieve this is to make it
-free software which everyone can redistribute and change under these terms.
-
-  To do so, attach the following notices to the program.  It is safest
-to attach them to the start of each source file to most effectively
-state the exclusion of warranty; and each file should have at least
-the "copyright" line and a pointer to where the full notice is found.
-
-    one line to give the program's name and a brief idea of what it does.
-    Copyright (C) year  name of author
-
-    This program is free software: you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation, either version 3 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License
-    along with this program.  If not, see http://www.gnu.org/licenses/.
-
-Also add information on how to contact you by electronic and paper mail.
-
-  If the program does terminal interaction, make it output a short
-notice like this when it starts in an interactive mode:
-
-    p  Copyright (C) year  name of author
-    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
-    This is free software, and you are welcome to redistribute it
-    under certain conditions; type `show c' for details.
-
-The hypothetical commands `show w' and `show c' should show the appropriate
-parts of the General Public License.  Of course, your program's commands
-might be different; for a GUI interface, you would use an "about box".
-
-  You should also get your employer (if you work as a programmer) or school,
-if any, to sign a "copyright disclaimer" for the program, if necessary.
-For more information on this, and how to apply and follow the GNU GPL, see
-http://www.gnu.org/licenses/.
-
-  The GNU General Public License does not permit incorporating your program
-into proprietary programs.  If your program is a subroutine library, you
-may consider it more useful to permit linking proprietary applications with
-the library.  If this is what you want to do, use the GNU Lesser General
-Public License instead of this License.  But first, please read
-http://www.gnu.org/philosophy/why-not-lgpl.html.
+
+  This version of the GNU Lesser General Public License incorporates
+the terms and conditions of version 3 of the GNU General Public
+License, supplemented by the additional permissions listed below.
+
+  0. Additional Definitions.
+
+  As used herein, "this License" refers to version 3 of the GNU Lesser
+General Public License, and the "GNU GPL" refers to version 3 of the GNU
+General Public License.
+
+  "The Library" refers to a covered work governed by this License,
+other than an Application or a Combined Work as defined below.
+
+  An "Application" is any work that makes use of an interface provided
+by the Library, but which is not otherwise based on the Library.
+Defining a subclass of a class defined by the Library is deemed a mode
+of using an interface provided by the Library.
+
+  A "Combined Work" is a work produced by combining or linking an
+Application with the Library.  The particular version of the Library
+with which the Combined Work was made is also called the "Linked
+Version".
+
+  The "Minimal Corresponding Source" for a Combined Work means the
+Corresponding Source for the Combined Work, excluding any source code
+for portions of the Combined Work that, considered in isolation, are
+based on the Application, and not on the Linked Version.
+
+  The "Corresponding Application Code" for a Combined Work means the
+object code and/or source code for the Application, including any data
+and utility programs needed for reproducing the Combined Work from the
+Application, but excluding the System Libraries of the Combined Work.
+
+  1. Exception to Section 3 of the GNU GPL.
+
+  You may convey a covered work under sections 3 and 4 of this License
+without being bound by section 3 of the GNU GPL.
+
+  2. Conveying Modified Versions.
+
+  If you modify a copy of the Library, and, in your modifications, a
+facility refers to a function or data to be supplied by an Application
+that uses the facility (other than as an argument passed when the
+facility is invoked), then you may convey a copy of the modified
+version:
+
+   a) under this License, provided that you make a good faith effort to
+   ensure that, in the event an Application does not supply the
+   function or data, the facility still operates, and performs
+   whatever part of its purpose remains meaningful, or
+
+   b) under the GNU GPL, with none of the additional permissions of
+   this License applicable to that copy.
+
+  3. Object Code Incorporating Material from Library Header Files.
+
+  The object code form of an Application may incorporate material from
+a header file that is part of the Library.  You may convey such object
+code under terms of your choice, provided that, if the incorporated
+material is not limited to numerical parameters, data structure
+layouts and accessors, or small macros, inline functions and templates
+(ten or fewer lines in length), you do both of the following:
+
+   a) Give prominent notice with each copy of the object code that the
+   Library is used in it and that the Library and its use are
+   covered by this License.
+
+   b) Accompany the object code with a copy of the GNU GPL and this license
+   document.
+
+  4. Combined Works.
+
+  You may convey a Combined Work under terms of your choice that,
+taken together, effectively do not restrict modification of the
+portions of the Library contained in the Combined Work and reverse
+engineering for debugging such modifications, if you also do each of
+the following:
+
+   a) Give prominent notice with each copy of the Combined Work that
+   the Library is used in it and that the Library and its use are
+   covered by this License.
+
+   b) Accompany the Combined Work with a copy of the GNU GPL and this license
+   document.
+
+   c) For a Combined Work that displays copyright notices during
+   execution, include the copyright notice for the Library among
+   these notices, as well as a reference directing the user to the
+   copies of the GNU GPL and this license document.
+
+   d) Do one of the following:
+
+       0) Convey the Minimal Corresponding Source under the terms of this
+       License, and the Corresponding Application Code in a form
+       suitable for, and under terms that permit, the user to
+       recombine or relink the Application with a modified version of
+       the Linked Version to produce a modified Combined Work, in the
+       manner specified by section 6 of the GNU GPL for conveying
+       Corresponding Source.
+
+       1) Use a suitable shared library mechanism for linking with the
+       Library.  A suitable mechanism is one that (a) uses at run time
+       a copy of the Library already present on the user's computer
+       system, and (b) will operate properly with a modified version
+       of the Library that is interface-compatible with the Linked
+       Version.
+
+   e) Provide Installation Information, but only if you would otherwise
+   be required to provide such information under section 6 of the
+   GNU GPL, and only to the extent that such information is
+   necessary to install and execute a modified version of the
+   Combined Work produced by recombining or relinking the
+   Application with a modified version of the Linked Version. (If
+   you use option 4d0, the Installation Information must accompany
+   the Minimal Corresponding Source and Corresponding Application
+   Code. If you use option 4d1, you must provide the Installation
+   Information in the manner specified by section 6 of the GNU GPL
+   for conveying Corresponding Source.)
+
+  5. Combined Libraries.
+
+  You may place library facilities that are a work based on the
+Library side by side in a single library together with other library
+facilities that are not Applications and are not covered by this
+License, and convey such a combined library under terms of your
+choice, if you do both of the following:
+
+   a) Accompany the combined library with a copy of the same work based
+   on the Library, uncombined with any other library facilities,
+   conveyed under the terms of this License.
+
+   b) Give prominent notice with the combined library that part of it
+   is a work based on the Library, and explaining where to find the
+   accompanying uncombined form of the same work.
+
+  6. Revised Versions of the GNU Lesser General Public License.
+
+  The Free Software Foundation may publish revised and/or new versions
+of the GNU Lesser General Public License from time to time. Such new
+versions will be similar in spirit to the present version, but may
+differ in detail to address new problems or concerns.
+
+  Each version is given a distinguishing version number. If the
+Library as you received it specifies that a certain numbered version
+of the GNU Lesser General Public License "or any later version"
+applies to it, you have the option of following the terms and
+conditions either of that published version or of any later version
+published by the Free Software Foundation. If the Library as you
+received it does not specify a version number of the GNU Lesser
+General Public License, you may choose any version of the GNU Lesser
+General Public License ever published by the Free Software Foundation.
+
+  If the Library as you received it specifies that a proxy can decide
+whether future versions of the GNU Lesser General Public License shall
+apply, that proxy's public statement of acceptance of any version is
+permanent authorization for you to choose that version for the
+Library.
     </pre>
 
     <h3>Timber</h3>

app/src/main/cpp/CMakeLists.txt

@@ -10,21 +10,15 @@ set(CMAKE_CXX_STANDARD 17)
 include_directories(.)
 
 ### ICU4C ###
-include_directories(icu4c/include)
-#link_directories(${CMAKE_SOURCE_DIR}/../${ANDROID_ABI})
-set(JNI_LIBS ${CMAKE_SOURCE_DIR}/../jniLibs/${ANDROID_ABI})
+include_directories(../icu4c/prebuilt/include)
+set(JNI_LIBS ${CMAKE_SOURCE_DIR}/../icu4c/prebuilt/jniLibs/${ANDROID_ABI})
 add_library(ICU::data STATIC IMPORTED)
 set_property(TARGET ICU::data PROPERTY IMPORTED_LOCATION "${JNI_LIBS}/libicudata.a")
-#add_library(ICU::i18n STATIC IMPORTED)
-#set_property(TARGET ICU::i18n PROPERTY IMPORTED_LOCATION "${JNI_LIBS}/libicui18n.a")
-#add_library(ICU::tu STATIC IMPORTED)
-#set_property(TARGET ICU::tu PROPERTY IMPORTED_LOCATION "${JNI_LIBS}/libicutu.a")
 add_library(ICU::uc STATIC IMPORTED)
 set_property(TARGET ICU::uc PROPERTY IMPORTED_LOCATION "${JNI_LIBS}/libicuuc.a")
 
 ### FlorisBoard ###
 add_subdirectory(nuspell)
-add_subdirectory(glob_ndk)
 add_subdirectory(utils)
 add_subdirectory(ime/nlp)
 add_subdirectory(ime/spelling)
@@ -32,6 +26,7 @@ add_subdirectory(ime/spelling)
 add_library(
         florisboard-native
         SHARED
+        dev_patrickgold_florisboard_FlorisApplication.cpp
         dev_patrickgold_florisboard_ime_nlp_SuggestionList.cpp
         dev_patrickgold_florisboard_ime_spelling_SpellingDict.cpp
 )
@@ -44,7 +39,6 @@ target_link_libraries(
         # Sources
         android
         log
-        glob_ndk
         ICU::uc
         ICU::data
         Nuspell::nuspell

app/src/main/cpp/dev_patrickgold_florisboard_FlorisApplication.cpp

@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2021 Patrick Goldinger
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include <fstream>
+#include <vector>
+#include <jni.h>
+#include <unicode/udata.h>
+#include "utils/jni_utils.h"
+
+#pragma ide diagnostic ignored "UnusedLocalVariable"
+
+extern "C"
+JNIEXPORT jint JNICALL
+Java_dev_patrickgold_florisboard_FlorisApplication_00024Companion_nativeInitICUData(
+        JNIEnv *env,
+        jobject thiz,
+        jobject path) {
+    auto path_str = utils::j2std_string(env, path);
+    std::ifstream in_file(path_str, std::ios::in | std::ios::binary);
+    if (!in_file) {
+        return U_FILE_ACCESS_ERROR;
+    }
+    in_file.seekg(0, std::ios::end);
+    size_t size = in_file.tellg();
+    if (size <= 0) {
+        return U_FILE_ACCESS_ERROR;
+    }
+    in_file.seekg(0, std::ios::beg);
+    char *icu_data = new char[size + 1];
+    in_file.read(icu_data, size);
+    if (!in_file) {
+        in_file.close();
+        return U_FILE_ACCESS_ERROR;
+    }
+    icu_data[size] = 0;
+    in_file.close();
+    UErrorCode status = U_ZERO_ERROR;
+    udata_setCommonData(reinterpret_cast<void *>(icu_data), &status);
+    return status;
+}

app/src/main/cpp/glob_ndk/CMakeLists.txt

@@ -1,2 +0,0 @@
-add_library(glob_ndk
-        glob_ndk.c glob_ndk.h)

app/src/main/cpp/glob_ndk/glob_ndk.c

@@ -1,906 +0,0 @@
-/*
- * Natanael Arndt, 2011: removed collate.h dependencies
- *  (my changes are trivial)
- *
- * Copyright (c) 1989, 1993
- *	The Regents of the University of California.  All rights reserved.
- *
- * This code is derived from software contributed to Berkeley by
- * Guido van Rossum.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 4. Neither the name of the University nor the names of its contributors
- *    may be used to endorse or promote products derived from this software
- *    without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- */
-
-#if defined(LIBC_SCCS) && !defined(lint)
-static char sccsid[] = "@(#)glob.c	8.3 (Berkeley) 10/13/93";
-#endif /* LIBC_SCCS and not lint */
-#include <sys/cdefs.h>
-__FBSDID("$FreeBSD$");
-
-/*
- * glob(3) -- a superset of the one defined in POSIX 1003.2.
- *
- * The [!...] convention to negate a range is supported (SysV, Posix, ksh).
- *
- * Optional extra services, controlled by flags not defined by POSIX:
- *
- * GLOB_QUOTE:
- *	Escaping convention: \ inhibits any special meaning the following
- *	character might have (except \ at end of string is retained).
- * GLOB_MAGCHAR:
- *	Set in gl_flags if pattern contained a globbing character.
- * GLOB_NOMAGIC:
- *	Same as GLOB_NOCHECK, but it will only append pattern if it did
- *	not contain any magic characters.  [Used in csh style globbing]
- * GLOB_ALTDIRFUNC:
- *	Use alternately specified directory access functions.
- * GLOB_TILDE:
- *	expand ~user/foo to the /home/dir/of/user/foo
- * GLOB_BRACE:
- *	expand {1,2}{a,b} to 1a 1b 2a 2b
- * gl_matchc:
- *	Number of matches in the current invocation of glob.
- */
-
-/*
- * Some notes on multibyte character support:
- * 1. Patterns with illegal byte sequences match nothing - even if
- *    GLOB_NOCHECK is specified.
- * 2. Illegal byte sequences in filenames are handled by treating them as
- *    single-byte characters with a value of the first byte of the sequence
- *    cast to wchar_t.
- * 3. State-dependent encodings are not currently supported.
- */
-
-#include <sys/param.h>
-#include <sys/stat.h>
-
-#include <ctype.h>
-#include <dirent.h>
-#include <errno.h>
-#include "glob_ndk.h"
-#include <limits.h>
-#include <pwd.h>
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-#include <wchar.h>
-
-#define	DOLLAR		'$'
-#define	DOT		'.'
-#define	EOS		'\0'
-#define	LBRACKET	'['
-#define	NOT		'!'
-#define	QUESTION	'?'
-#define	QUOTE		'\\'
-#define	RANGE		'-'
-#define	RBRACKET	']'
-#define	SEP		'/'
-#define	STAR		'*'
-#define	TILDE		'~'
-#define	UNDERSCORE	'_'
-#define	LBRACE		'{'
-#define	RBRACE		'}'
-#define	SLASH		'/'
-#define	COMMA		','
-
-#ifndef DEBUG
-
-#define	M_QUOTE		0x8000000000ULL
-#define	M_PROTECT	0x4000000000ULL
-#define	M_MASK		0xffffffffffULL
-#define	M_CHAR		0x00ffffffffULL
-
-typedef uint_fast64_t Char;
-
-#else
-
-#define	M_QUOTE		0x80
-#define	M_PROTECT	0x40
-#define	M_MASK		0xff
-#define	M_CHAR		0x7f
-
-typedef char Char;
-
-#endif
-
-
-#define	CHAR(c)		((Char)((c)&M_CHAR))
-#define	META(c)		((Char)((c)|M_QUOTE))
-#define	M_ALL		META('*')
-#define	M_END		META(']')
-#define	M_NOT		META('!')
-#define	M_ONE		META('?')
-#define	M_RNG		META('-')
-#define	M_SET		META('[')
-#define	ismeta(c)	(((c)&M_QUOTE) != 0)
-
-
-static int	 compare(const void *, const void *);
-static int	 g_Ctoc(const Char *, char *, size_t);
-static int	 g_lstat(Char *, struct stat *, glob_t *);
-static DIR	*g_opendir(Char *, glob_t *);
-static const Char *g_strchr(const Char *, wchar_t);
-#ifdef notdef
-static Char	*g_strcat(Char *, const Char *);
-#endif
-static int	 g_stat(Char *, struct stat *, glob_t *);
-static int	 glob0(const Char *, glob_t *, size_t *);
-static int	 glob1(Char *, glob_t *, size_t *);
-static int	 glob2(Char *, Char *, Char *, Char *, glob_t *, size_t *);
-static int	 glob3(Char *, Char *, Char *, Char *, Char *, glob_t *, size_t *);
-static int	 globextend(const Char *, glob_t *, size_t *);
-static const Char *
-globtilde(const Char *, Char *, size_t, glob_t *);
-static int	 globexp1(const Char *, glob_t *, size_t *);
-static int	 globexp2(const Char *, const Char *, glob_t *, int *, size_t *);
-static int	 match(Char *, Char *, Char *);
-#ifdef DEBUG
-static void	 qprintf(const char *, Char *);
-#endif
-
-int
-glob(const char *pattern, int flags, int (*errfunc)(const char *, int), glob_t *pglob)
-{
-    const char *patnext;
-    size_t limit;
-    Char *bufnext, *bufend, patbuf[MAXPATHLEN], prot;
-    mbstate_t mbs;
-    wchar_t wc;
-    size_t clen;
-
-    patnext = pattern;
-    if (!(flags & GLOB_APPEND)) {
-        pglob->gl_pathc = 0;
-        pglob->gl_pathv = NULL;
-        if (!(flags & GLOB_DOOFFS))
-            pglob->gl_offs = 0;
-    }
-    if (flags & GLOB_LIMIT) {
-        limit = pglob->gl_matchc;
-        if (limit == 0)
-            limit = ARG_MAX;
-    } else
-        limit = 0;
-    pglob->gl_flags = flags & ~GLOB_MAGCHAR;
-    pglob->gl_errfunc = errfunc;
-    pglob->gl_matchc = 0;
-
-    bufnext = patbuf;
-    bufend = bufnext + MAXPATHLEN - 1;
-    if (flags & GLOB_NOESCAPE) {
-        memset(&mbs, 0, sizeof(mbs));
-        while (bufend - bufnext >= MB_CUR_MAX) {
-            clen = mbrtowc(&wc, patnext, MB_LEN_MAX, &mbs);
-            if (clen == (size_t)-1 || clen == (size_t)-2)
-                return (GLOB_NOMATCH);
-            else if (clen == 0)
-                break;
-            *bufnext++ = wc;
-            patnext += clen;
-        }
-    } else {
-        /* Protect the quoted characters. */
-        memset(&mbs, 0, sizeof(mbs));
-        while (bufend - bufnext >= MB_CUR_MAX) {
-            if (*patnext == QUOTE) {
-                if (*++patnext == EOS) {
-                    *bufnext++ = QUOTE | M_PROTECT;
-                    continue;
-                }
-                prot = M_PROTECT;
-            } else
-                prot = 0;
-            clen = mbrtowc(&wc, patnext, MB_LEN_MAX, &mbs);
-            if (clen == (size_t)-1 || clen == (size_t)-2)
-                return (GLOB_NOMATCH);
-            else if (clen == 0)
-                break;
-            *bufnext++ = wc | prot;
-            patnext += clen;
-        }
-    }
-    *bufnext = EOS;
-
-    if (flags & GLOB_BRACE)
-        return globexp1(patbuf, pglob, &limit);
-    else
-        return glob0(patbuf, pglob, &limit);
-}
-
-/*
- * Expand recursively a glob {} pattern. When there is no more expansion
- * invoke the standard globbing routine to glob the rest of the magic
- * characters
- */
-static int
-globexp1(const Char *pattern, glob_t *pglob, size_t *limit)
-{
-    const Char* ptr = pattern;
-    int rv;
-
-    /* Protect a single {}, for find(1), like csh */
-    if (pattern[0] == LBRACE && pattern[1] == RBRACE && pattern[2] == EOS)
-        return glob0(pattern, pglob, limit);
-
-    while ((ptr = g_strchr(ptr, LBRACE)) != NULL)
-        if (!globexp2(ptr, pattern, pglob, &rv, limit))
-            return rv;
-
-    return glob0(pattern, pglob, limit);
-}
-
-
-/*
- * Recursive brace globbing helper. Tries to expand a single brace.
- * If it succeeds then it invokes globexp1 with the new pattern.
- * If it fails then it tries to glob the rest of the pattern and returns.
- */
-static int
-globexp2(const Char *ptr, const Char *pattern, glob_t *pglob, int *rv, size_t *limit)
-{
-    int     i;
-    Char   *lm, *ls;
-    const Char *pe, *pm, *pm1, *pl;
-    Char    patbuf[MAXPATHLEN];
-
-    /* copy part up to the brace */
-    for (lm = patbuf, pm = pattern; pm != ptr; *lm++ = *pm++)
-        continue;
-    *lm = EOS;
-    ls = lm;
-
-    /* Find the balanced brace */
-    for (i = 0, pe = ++ptr; *pe; pe++)
-        if (*pe == LBRACKET) {
-            /* Ignore everything between [] */
-            for (pm = pe++; *pe != RBRACKET && *pe != EOS; pe++)
-                continue;
-            if (*pe == EOS) {
-                /*
-                 * We could not find a matching RBRACKET.
-                 * Ignore and just look for RBRACE
-                 */
-                pe = pm;
-            }
-        }
-        else if (*pe == LBRACE)
-            i++;
-        else if (*pe == RBRACE) {
-            if (i == 0)
-                break;
-            i--;
-        }
-
-    /* Non matching braces; just glob the pattern */
-    if (i != 0 || *pe == EOS) {
-        *rv = glob0(patbuf, pglob, limit);
-        return 0;
-    }
-
-    for (i = 0, pl = pm = ptr; pm <= pe; pm++)
-        switch (*pm) {
-            case LBRACKET:
-                /* Ignore everything between [] */
-                for (pm1 = pm++; *pm != RBRACKET && *pm != EOS; pm++)
-                    continue;
-                if (*pm == EOS) {
-                    /*
-                     * We could not find a matching RBRACKET.
-                     * Ignore and just look for RBRACE
-                     */
-                    pm = pm1;
-                }
-                break;
-
-            case LBRACE:
-                i++;
-                break;
-
-            case RBRACE:
-                if (i) {
-                    i--;
-                    break;
-                }
-                /* FALLTHROUGH */
-            case COMMA:
-                if (i && *pm == COMMA)
-                    break;
-                else {
-                    /* Append the current string */
-                    for (lm = ls; (pl < pm); *lm++ = *pl++)
-                        continue;
-                    /*
-                     * Append the rest of the pattern after the
-                     * closing brace
-                     */
-                    for (pl = pe + 1; (*lm++ = *pl++) != EOS;)
-                        continue;
-
-                    /* Expand the current pattern */
-#ifdef DEBUG
-                    qprintf("globexp2:", patbuf);
-#endif
-                    *rv = globexp1(patbuf, pglob, limit);
-
-                    /* move after the comma, to the next string */
-                    pl = pm + 1;
-                }
-                break;
-
-            default:
-                break;
-        }
-    *rv = 0;
-    return 0;
-}
-
-
-
-/*
- * expand tilde from the passwd file.
- */
-static const Char *
-globtilde(const Char *pattern, Char *patbuf, size_t patbuf_len, glob_t *pglob)
-{
-    struct passwd *pwd;
-    char *h;
-    const Char *p;
-    Char *b, *eb;
-
-    if (*pattern != TILDE || !(pglob->gl_flags & GLOB_TILDE))
-        return pattern;
-
-    /*
-     * Copy up to the end of the string or /
-     */
-    eb = &patbuf[patbuf_len - 1];
-    for (p = pattern + 1, h = (char *) patbuf;
-         h < (char *)eb && *p && *p != SLASH; *h++ = *p++)
-        continue;
-
-    *h = EOS;
-
-    if (((char *) patbuf)[0] == EOS) {
-        /*
-         * handle a plain ~ or ~/ by expanding $HOME first (iff
-         * we're not running setuid or setgid) and then trying
-         * the password file
-         */
-        if (issetugid() != 0 ||
-            (h = getenv("HOME")) == NULL) {
-            if (((h = getlogin()) != NULL &&
-                 (pwd = getpwnam(h)) != NULL) ||
-                (pwd = getpwuid(getuid())) != NULL)
-                h = pwd->pw_dir;
-            else
-                return pattern;
-        }
-    }
-    else {
-        /*
-         * Expand a ~user
-         */
-        if ((pwd = getpwnam((char*) patbuf)) == NULL)
-            return pattern;
-        else
-            h = pwd->pw_dir;
-    }
-
-    /* Copy the home directory */
-    for (b = patbuf; b < eb && *h; *b++ = *h++)
-        continue;
-
-    /* Append the rest of the pattern */
-    while (b < eb && (*b++ = *p++) != EOS)
-        continue;
-    *b = EOS;
-
-    return patbuf;
-}
-
-
-/*
- * The main glob() routine: compiles the pattern (optionally processing
- * quotes), calls glob1() to do the real pattern matching, and finally
- * sorts the list (unless unsorted operation is requested).  Returns 0
- * if things went well, nonzero if errors occurred.
- */
-static int
-glob0(const Char *pattern, glob_t *pglob, size_t *limit)
-{
-    const Char *qpatnext;
-    int err;
-    size_t oldpathc;
-    Char *bufnext, c, patbuf[MAXPATHLEN];
-
-    qpatnext = globtilde(pattern, patbuf, MAXPATHLEN, pglob);
-    oldpathc = pglob->gl_pathc;
-    bufnext = patbuf;
-
-    /* We don't need to check for buffer overflow any more. */
-    while ((c = *qpatnext++) != EOS) {
-        switch (c) {
-            case LBRACKET:
-                c = *qpatnext;
-                if (c == NOT)
-                    ++qpatnext;
-                if (*qpatnext == EOS ||
-                    g_strchr(qpatnext+1, RBRACKET) == NULL) {
-                    *bufnext++ = LBRACKET;
-                    if (c == NOT)
-                        --qpatnext;
-                    break;
-                }
-                *bufnext++ = M_SET;
-                if (c == NOT)
-                    *bufnext++ = M_NOT;
-                c = *qpatnext++;
-                do {
-                    *bufnext++ = CHAR(c);
-                    if (*qpatnext == RANGE &&
-                        (c = qpatnext[1]) != RBRACKET) {
-                        *bufnext++ = M_RNG;
-                        *bufnext++ = CHAR(c);
-                        qpatnext += 2;
-                    }
-                } while ((c = *qpatnext++) != RBRACKET);
-                pglob->gl_flags |= GLOB_MAGCHAR;
-                *bufnext++ = M_END;
-                break;
-            case QUESTION:
-                pglob->gl_flags |= GLOB_MAGCHAR;
-                *bufnext++ = M_ONE;
-                break;
-            case STAR:
-                pglob->gl_flags |= GLOB_MAGCHAR;
-                /* collapse adjacent stars to one,
-                 * to avoid exponential behavior
-                 */
-                if (bufnext == patbuf || bufnext[-1] != M_ALL)
-                    *bufnext++ = M_ALL;
-                break;
-            default:
-                *bufnext++ = CHAR(c);
-                break;
-        }
-    }
-    *bufnext = EOS;
-#ifdef DEBUG
-    qprintf("glob0:", patbuf);
-#endif
-
-    if ((err = glob1(patbuf, pglob, limit)) != 0)
-        return(err);
-
-    /*
-     * If there was no match we are going to append the pattern
-     * if GLOB_NOCHECK was specified or if GLOB_NOMAGIC was specified
-     * and the pattern did not contain any magic characters
-     * GLOB_NOMAGIC is there just for compatibility with csh.
-     */
-    if (pglob->gl_pathc == oldpathc) {
-        if (((pglob->gl_flags & GLOB_NOCHECK) ||
-             ((pglob->gl_flags & GLOB_NOMAGIC) &&
-              !(pglob->gl_flags & GLOB_MAGCHAR))))
-            return(globextend(pattern, pglob, limit));
-        else
-            return(GLOB_NOMATCH);
-    }
-    if (!(pglob->gl_flags & GLOB_NOSORT))
-        qsort(pglob->gl_pathv + pglob->gl_offs + oldpathc,
-              pglob->gl_pathc - oldpathc, sizeof(char *), compare);
-    return(0);
-}
-
-static int
-compare(const void *p, const void *q)
-{
-    return(strcmp(*(char **)p, *(char **)q));
-}
-
-static int
-glob1(Char *pattern, glob_t *pglob, size_t *limit)
-{
-    Char pathbuf[MAXPATHLEN];
-
-    /* A null pathname is invalid -- POSIX 1003.1 sect. 2.4. */
-    if (*pattern == EOS)
-        return(0);
-    return(glob2(pathbuf, pathbuf, pathbuf + MAXPATHLEN - 1,
-                 pattern, pglob, limit));
-}
-
-/*
- * The functions glob2 and glob3 are mutually recursive; there is one level
- * of recursion for each segment in the pattern that contains one or more
- * meta characters.
- */
-static int
-glob2(Char *pathbuf, Char *pathend, Char *pathend_last, Char *pattern,
-      glob_t *pglob, size_t *limit)
-{
-    struct stat sb;
-    Char *p, *q;
-    int anymeta;
-
-    /*
-     * Loop over pattern segments until end of pattern or until
-     * segment with meta character found.
-     */
-    for (anymeta = 0;;) {
-        if (*pattern == EOS) {		/* End of pattern? */
-            *pathend = EOS;
-            if (g_lstat(pathbuf, &sb, pglob))
-                return(0);
-
-            if (((pglob->gl_flags & GLOB_MARK) &&
-                 pathend[-1] != SEP) && (S_ISDIR(sb.st_mode)
-                                         || (S_ISLNK(sb.st_mode) &&
-                                             (g_stat(pathbuf, &sb, pglob) == 0) &&
-                                             S_ISDIR(sb.st_mode)))) {
-                if (pathend + 1 > pathend_last)
-                    return (GLOB_ABORTED);
-                *pathend++ = SEP;
-                *pathend = EOS;
-            }
-            ++pglob->gl_matchc;
-            return(globextend(pathbuf, pglob, limit));
-        }
-
-        /* Find end of next segment, copy tentatively to pathend. */
-        q = pathend;
-        p = pattern;
-        while (*p != EOS && *p != SEP) {
-            if (ismeta(*p))
-                anymeta = 1;
-            if (q + 1 > pathend_last)
-                return (GLOB_ABORTED);
-            *q++ = *p++;
-        }
-
-        if (!anymeta) {		/* No expansion, do next segment. */
-            pathend = q;
-            pattern = p;
-            while (*pattern == SEP) {
-                if (pathend + 1 > pathend_last)
-                    return (GLOB_ABORTED);
-                *pathend++ = *pattern++;
-            }
-        } else			/* Need expansion, recurse. */
-            return(glob3(pathbuf, pathend, pathend_last, pattern, p,
-                         pglob, limit));
-    }
-    /* NOTREACHED */
-}
-
-static int
-glob3(Char *pathbuf, Char *pathend, Char *pathend_last,
-      Char *pattern, Char *restpattern,
-      glob_t *pglob, size_t *limit)
-{
-    struct dirent *dp;
-    DIR *dirp;
-    int err;
-    char buf[MAXPATHLEN];
-
-    /*
-     * The readdirfunc declaration can't be prototyped, because it is
-     * assigned, below, to two functions which are prototyped in glob.h
-     * and dirent.h as taking pointers to differently typed opaque
-     * structures.
-     */
-    struct dirent *(*readdirfunc)();
-
-    if (pathend > pathend_last)
-        return (GLOB_ABORTED);
-    *pathend = EOS;
-    errno = 0;
-
-    if ((dirp = g_opendir(pathbuf, pglob)) == NULL) {
-        /* TODO: don't call for ENOENT or ENOTDIR? */
-        if (pglob->gl_errfunc) {
-            if (g_Ctoc(pathbuf, buf, sizeof(buf)))
-                return (GLOB_ABORTED);
-            if (pglob->gl_errfunc(buf, errno) ||
-                pglob->gl_flags & GLOB_ERR)
-                return (GLOB_ABORTED);
-        }
-        return(0);
-    }
-
-    err = 0;
-
-    /* Search directory for matching names. */
-    if (pglob->gl_flags & GLOB_ALTDIRFUNC)
-        readdirfunc = pglob->gl_readdir;
-    else
-        readdirfunc = readdir;
-    while ((dp = (*readdirfunc)(dirp))) {
-        char *sc;
-        Char *dc;
-        wchar_t wc;
-        size_t clen;
-        mbstate_t mbs;
-
-        /* Initial DOT must be matched literally. */
-        if (dp->d_name[0] == DOT && *pattern != DOT)
-            continue;
-        memset(&mbs, 0, sizeof(mbs));
-        dc = pathend;
-        sc = dp->d_name;
-        while (dc < pathend_last) {
-            clen = mbrtowc(&wc, sc, MB_LEN_MAX, &mbs);
-            if (clen == (size_t)-1 || clen == (size_t)-2) {
-                wc = *sc;
-                clen = 1;
-                memset(&mbs, 0, sizeof(mbs));
-            }
-            if ((*dc++ = wc) == EOS)
-                break;
-            sc += clen;
-        }
-        if (!match(pathend, pattern, restpattern)) {
-            *pathend = EOS;
-            continue;
-        }
-        err = glob2(pathbuf, --dc, pathend_last, restpattern,
-                    pglob, limit);
-        if (err)
-            break;
-    }
-
-    if (pglob->gl_flags & GLOB_ALTDIRFUNC)
-        (*pglob->gl_closedir)(dirp);
-    else
-        closedir(dirp);
-    return(err);
-}
-
-
-/*
- * Extend the gl_pathv member of a glob_t structure to accomodate a new item,
- * add the new item, and update gl_pathc.
- *
- * This assumes the BSD realloc, which only copies the block when its size
- * crosses a power-of-two boundary; for v7 realloc, this would cause quadratic
- * behavior.
- *
- * Return 0 if new item added, error code if memory couldn't be allocated.
- *
- * Invariant of the glob_t structure:
- *	Either gl_pathc is zero and gl_pathv is NULL; or gl_pathc > 0 and
- *	gl_pathv points to (gl_offs + gl_pathc + 1) items.
- */
-static int
-globextend(const Char *path, glob_t *pglob, size_t *limit)
-{
-    char **pathv;
-    size_t i, newsize, len;
-    char *copy;
-    const Char *p;
-
-    if (*limit && pglob->gl_pathc > *limit) {
-        errno = 0;
-        return (GLOB_NOSPACE);
-    }
-
-    newsize = sizeof(*pathv) * (2 + pglob->gl_pathc + pglob->gl_offs);
-    pathv = pglob->gl_pathv ?
-            realloc((char *)pglob->gl_pathv, newsize) :
-            malloc(newsize);
-    if (pathv == NULL) {
-        if (pglob->gl_pathv) {
-            free(pglob->gl_pathv);
-            pglob->gl_pathv = NULL;
-        }
-        return(GLOB_NOSPACE);
-    }
-
-    if (pglob->gl_pathv == NULL && pglob->gl_offs > 0) {
-        /* first time around -- clear initial gl_offs items */
-        pathv += pglob->gl_offs;
-        for (i = pglob->gl_offs + 1; --i > 0; )
-            *--pathv = NULL;
-    }
-    pglob->gl_pathv = pathv;
-
-    for (p = path; *p++;)
-        continue;
-    len = MB_CUR_MAX * (size_t)(p - path);	/* XXX overallocation */
-    if ((copy = malloc(len)) != NULL) {
-        if (g_Ctoc(path, copy, len)) {
-            free(copy);
-            return (GLOB_NOSPACE);
-        }
-        pathv[pglob->gl_offs + pglob->gl_pathc++] = copy;
-    }
-    pathv[pglob->gl_offs + pglob->gl_pathc] = NULL;
-    return(copy == NULL ? GLOB_NOSPACE : 0);
-}
-
-/*
- * pattern matching function for filenames.  Each occurrence of the *
- * pattern causes a recursion level.
- */
-static int
-match(Char *name, Char *pat, Char *patend)
-{
-    int ok, negate_range;
-    Char c, k;
-
-    while (pat < patend) {
-        c = *pat++;
-        switch (c & M_MASK) {
-            case M_ALL:
-                if (pat == patend)
-                    return(1);
-                do
-                    if (match(name, pat, patend))
-                        return(1);
-                while (*name++ != EOS);
-                return(0);
-            case M_ONE:
-                if (*name++ == EOS)
-                    return(0);
-                break;
-            case M_SET:
-                ok = 0;
-                if ((k = *name++) == EOS)
-                    return(0);
-                if ((negate_range = ((*pat & M_MASK) == M_NOT)) != EOS)
-                    ++pat;
-                while (((c = *pat++) & M_MASK) != M_END)
-                    if ((*pat & M_MASK) == M_RNG) {
-                        if (CHAR(c) <= CHAR(k) && CHAR(k) <= CHAR(pat[1])) ok = 1;
-                        pat += 2;
-                    } else if (c == k)
-                        ok = 1;
-                if (ok == negate_range)
-                    return(0);
-                break;
-            default:
-                if (*name++ != c)
-                    return(0);
-                break;
-        }
-    }
-    return(*name == EOS);
-}
-
-/* Free allocated data belonging to a glob_t structure. */
-void
-globfree(glob_t *pglob)
-{
-    size_t i;
-    char **pp;
-
-    if (pglob->gl_pathv != NULL) {
-        pp = pglob->gl_pathv + pglob->gl_offs;
-        for (i = pglob->gl_pathc; i--; ++pp)
-            if (*pp)
-                free(*pp);
-        free(pglob->gl_pathv);
-        pglob->gl_pathv = NULL;
-    }
-}
-
-static DIR *
-g_opendir(Char *str, glob_t *pglob)
-{
-    char buf[MAXPATHLEN];
-
-    if (!*str)
-        strcpy(buf, ".");
-    else {
-        if (g_Ctoc(str, buf, sizeof(buf)))
-            return (NULL);
-    }
-
-    if (pglob->gl_flags & GLOB_ALTDIRFUNC)
-        return((*pglob->gl_opendir)(buf));
-
-    return(opendir(buf));
-}
-
-static int
-g_lstat(Char *fn, struct stat *sb, glob_t *pglob)
-{
-    char buf[MAXPATHLEN];
-
-    if (g_Ctoc(fn, buf, sizeof(buf))) {
-        errno = ENAMETOOLONG;
-        return (-1);
-    }
-    if (pglob->gl_flags & GLOB_ALTDIRFUNC)
-        return((*pglob->gl_lstat)(buf, sb));
-    return(lstat(buf, sb));
-}
-
-static int
-g_stat(Char *fn, struct stat *sb, glob_t *pglob)
-{
-    char buf[MAXPATHLEN];
-
-    if (g_Ctoc(fn, buf, sizeof(buf))) {
-        errno = ENAMETOOLONG;
-        return (-1);
-    }
-    if (pglob->gl_flags & GLOB_ALTDIRFUNC)
-        return((*pglob->gl_stat)(buf, sb));
-    return(stat(buf, sb));
-}
-
-static const Char *
-g_strchr(const Char *str, wchar_t ch)
-{
-
-    do {
-        if (*str == ch)
-            return (str);
-    } while (*str++);
-    return (NULL);
-}
-
-static int
-g_Ctoc(const Char *str, char *buf, size_t len)
-{
-    mbstate_t mbs;
-    size_t clen;
-
-    memset(&mbs, 0, sizeof(mbs));
-    while (len >= MB_CUR_MAX) {
-        clen = wcrtomb(buf, *str, &mbs);
-        if (clen == (size_t)-1)
-            return (1);
-        if (*str == L'\0')
-            return (0);
-        str++;
-        buf += clen;
-        len -= clen;
-    }
-    return (1);
-}
-
-#ifdef DEBUG
-static void
-qprintf(const char *str, Char *s)
-{
-	Char *p;
-
-	(void)printf("%s:\n", str);
-	for (p = s; *p; p++)
-		(void)printf("%c", CHAR(*p));
-	(void)printf("\n");
-	for (p = s; *p; p++)
-		(void)printf("%c", *p & M_PROTECT ? '"' : ' ');
-	(void)printf("\n");
-	for (p = s; *p; p++)
-		(void)printf("%c", ismeta(*p) ? '_' : ' ');
-	(void)printf("\n");
-}
-#endif

app/src/main/cpp/glob_ndk/glob_ndk.h

@@ -1,98 +0,0 @@
-/*
- * Copyright (c) 1989, 1993
- *	The Regents of the University of California.  All rights reserved.
- *
- * This code is derived from software contributed to Berkeley by
- * Guido van Rossum.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the University nor the names of its contributors
- *    may be used to endorse or promote products derived from this software
- *    without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- *
- *	@(#)glob.h	8.1 (Berkeley) 6/2/93
- * $FreeBSD$
- */
-
-#ifndef _GLOB_H_
-#define	_GLOB_H_
-
-#include <sys/cdefs.h>
-#include <sys/types.h>
-
-#include <glob.h>
-
-/*#ifndef	_SIZE_T_DECLARED
-typedef	__size_t	size_t;
-#define	_SIZE_T_DECLARED
-#endif*/
-
-struct stat;
-typedef struct {
-    size_t gl_pathc;	/* Count of total paths so far. */
-    size_t gl_matchc;	/* Count of paths matching pattern. */
-    size_t gl_offs;		/* Reserved at beginning of gl_pathv. */
-    int gl_flags;		/* Copy of flags parameter to glob. */
-    char **gl_pathv;	/* List of paths matching pattern. */
-    /* Copy of errfunc parameter to glob. */
-    int (*gl_errfunc)(const char *, int);
-
-    /*
-     * Alternate filesystem access methods for glob; replacement
-     * versions of closedir(3), readdir(3), opendir(3), stat(2)
-     * and lstat(2).
-     */
-    void (*gl_closedir)(void *);
-    struct dirent *(*gl_readdir)(void *);
-    void *(*gl_opendir)(const char *);
-    int (*gl_lstat)(const char *, struct stat *);
-    int (*gl_stat)(const char *, struct stat *);
-} glob_t;
-
-/* Believed to have been introduced in 1003.2-1992 */
-#define GLOB_APPEND	0x0001	/* Append to output from previous call. */
-#define GLOB_DOOFFS	0x0002	/* Prepend `gl_offs` null pointers (leaving space for exec, say). */
-#define GLOB_ERR	0x0004	/* Return on error. */
-#define GLOB_MARK	0x0008	/* Append "/" to the names of returned directories. */
-#define GLOB_NOCHECK	0x0010	/* Return pattern itself if nothing matches. */
-#define GLOB_NOSORT	0x0020	/* Don't sort. */
-#define GLOB_NOESCAPE	0x2000	/* Disable backslash escaping. */
-
-/* Error values returned by glob(3) */
-#define GLOB_NOSPACE	(-1)	/* Malloc call failed. */
-#define GLOB_ABORTED	(-2)	/* Unignored error. */
-#define GLOB_NOMATCH	(-3)	/* No match and GLOB_NOCHECK was not set. */
-
-#define GLOB_ALTDIRFUNC	0x0040	/* Use alternately specified directory funcs. */
-#define GLOB_BRACE	0x0080	/* Expand braces like csh. */
-#define GLOB_MAGCHAR	0x0100	/* Set in `gl_flags` if the pattern had globbing characters. */
-#define GLOB_NOMAGIC	0x0200	/* GLOB_NOCHECK without magic chars (csh). */
-#define GLOB_QUOTE	0x0400	/* Quote special chars with \. */
-#define GLOB_TILDE	0x0800	/* Expand tilde names from the passwd file. */
-#define GLOB_LIMIT	0x1000	/* limit number of returned paths */
-
-__BEGIN_DECLS
-int	glob(const char *, int, int (*)(const char *, int), glob_t *);
-void	globfree(glob_t *);
-__END_DECLS
-
-#endif /* !_GLOB_H_ */

app/src/main/cpp/icu4c/data-feature-filter.json

@@ -1,55 +0,0 @@
-{
-  "strategy": "subtractive",
-  "featureFilters": {
-    "coll_ucadata": {
-      "filterType": "exclude"
-    },
-    "coll_tree": {
-      "filterType": "exclude"
-    },
-    "confusables": {
-      "filterType": "exclude"
-    },
-    "curr_supplemental": {
-      "filterType": "exclude"
-    },
-    "curr_tree": {
-      "filterType": "exclude"
-    },
-    "locales_tree": {
-      "excludelist": [
-        "en_US_POSIX"
-      ]
-    },
-    "misc": {
-      "excludelist": [
-        "currencyNumericCodes",
-        "genderList"
-      ]
-    },
-    "region_tree": {
-      "filterType": "exclude"
-    },
-    "rbnf_tree": {
-      "filterType": "exclude"
-    },
-    "stringprep": {
-      "filterType": "exclude"
-    },
-    "translit": {
-      "filterType": "exclude"
-    },
-    "unames": {
-      "filterType": "exclude"
-    },
-    "unit_tree": {
-      "filterType": "exclude"
-    },
-    "zone_supplemental": {
-      "filterType": "exclude"
-    },
-    "zone_tree": {
-      "filterType": "exclude"
-    }
-  }
-}

app/src/main/cpp/icu4c/floris-cc-icu4c.sh

@@ -1,106 +0,0 @@
-#!/bin/bash
-
-# Copyright 2021 Patrick Goldinger
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# Build script for ICU4C, tailored exactly for FlorisBoard's needs.
-
-# Before executing this script to manually rebuild the ICU libraries, make sure to execute
-#  git submodule update --init --recursive
-# else the script won't find the ICU source files!
-
-###### Build ICU4C ######
-
-./android/cc-icu4c.sh build \
-    --arch=arm,arm64 \
-    --api=23 \
-    --library-type=static \
-    --build-dir=./build \
-    --icu-src-dir=./android/icu/icu4c \
-    --install-include-dir=./include \
-    --install-libs-dir=./../../jniLibs \
-    --data-filter-file=./data-feature-filter.json \
-    --enable-collation=no \
-    --enable-formatting=no \
-    --enable-legacy-converters=yes \
-    --enable-regex=no \
-    --enable-transliteration=no
-
-###### Clean up unused header files in include/unicode header dir ######
-
-readonly SEP=":"
-readonly NUSPELL_DIR=$(realpath ../nuspell)
-readonly UNICODE_DIR=$(realpath include/unicode)
-
-scan_file() {
-    file=$1
-    local -n var=$2
-    #echo "Scanning '$file'..."
-    while IFS= read -r line; do
-        case $line in
-        *"#include <unicode/"*)
-            # shellcheck disable=SC2001
-            header=$(sed -e 's/.*<unicode\/\(.*\)>.*/\1/' <<< "$line")
-            ;;
-        *"#include \"unicode/"*)
-            # shellcheck disable=SC2001
-            header=$(sed -e 's/.*\"unicode\/\(.*\)\".*/\1/' <<< "$line")
-            ;;
-        *)
-            header=""
-            ;;
-        esac
-        if [ -z "$header" ]; then
-            continue
-        fi
-        # shellcheck disable=SC2091
-        # shellcheck disable=SC2086
-        if [[ ! "$var" == *"$header"* ]]; then
-            # shellcheck disable=SC2140
-            var+="$SEP$header"
-        fi
-    done < "$file"
-}
-
-req_headers=""
-
-for nsrcfile in "$NUSPELL_DIR"/*; do
-    scan_file "$nsrcfile" "req_headers"
-done
-
-if [ -n "$req_headers" ]; then
-    req_headers=${req_headers:1}
-fi
-
-while true; do
-    old_req_headers=$req_headers
-    IFS="$SEP" read -ra req_header_splitted <<< "$req_headers"
-    for req_header in "${req_header_splitted[@]}"; do
-        scan_file "$UNICODE_DIR/$req_header" "req_headers"
-    done
-    [ ! $req_headers = $old_req_headers ] || break
-done
-
-#echo "$req_headers"
-
-for headerfile in "$UNICODE_DIR"/*; do
-    header=$(basename "$headerfile")
-    if [[ "$req_headers" == *"$header"* ]]; then
-        echo "KEEP      '$headerfile'"
-    else
-        echo "DELETE    '$headerfile'"
-        rm "$headerfile"
-    fi
-done
-

app/src/main/cpp/icu4c/include/unicode/brkiter.h

@@ -1,670 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-********************************************************************************
-*   Copyright (C) 1997-2016, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-********************************************************************************
-*
-* File brkiter.h
-*
-* Modification History:
-*
-*   Date        Name        Description
-*   02/18/97    aliu        Added typedef for TextCount.  Made DONE const.
-*   05/07/97    aliu        Fixed DLL declaration.
-*   07/09/97    jfitz       Renamed BreakIterator and interface synced with JDK
-*   08/11/98    helena      Sync-up JDK1.2.
-*   01/13/2000  helena      Added UErrorCode parameter to createXXXInstance methods.
-********************************************************************************
-*/
-
-#ifndef BRKITER_H
-#define BRKITER_H
-
-#include "unicode/utypes.h"
-
-/**
- * \file
- * \brief C++ API: Break Iterator.
- */
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-
-#if UCONFIG_NO_BREAK_ITERATION
-
-U_NAMESPACE_BEGIN
-
-/*
- * Allow the declaration of APIs with pointers to BreakIterator
- * even when break iteration is removed from the build.
- */
-class BreakIterator;
-
-U_NAMESPACE_END
-
-#else
-
-#include "unicode/uobject.h"
-#include "unicode/unistr.h"
-#include "unicode/chariter.h"
-#include "unicode/locid.h"
-#include "unicode/ubrk.h"
-#include "unicode/strenum.h"
-#include "unicode/utext.h"
-#include "unicode/umisc.h"
-
-U_NAMESPACE_BEGIN
-
-/**
- * The BreakIterator class implements methods for finding the location
- * of boundaries in text. BreakIterator is an abstract base class.
- * Instances of BreakIterator maintain a current position and scan over
- * text returning the index of characters where boundaries occur.
- * <p>
- * Line boundary analysis determines where a text string can be broken
- * when line-wrapping. The mechanism correctly handles punctuation and
- * hyphenated words.
- * <p>
- * Sentence boundary analysis allows selection with correct
- * interpretation of periods within numbers and abbreviations, and
- * trailing punctuation marks such as quotation marks and parentheses.
- * <p>
- * Word boundary analysis is used by search and replace functions, as
- * well as within text editing applications that allow the user to
- * select words with a double click. Word selection provides correct
- * interpretation of punctuation marks within and following
- * words. Characters that are not part of a word, such as symbols or
- * punctuation marks, have word-breaks on both sides.
- * <p>
- * Character boundary analysis allows users to interact with
- * characters as they expect to, for example, when moving the cursor
- * through a text string. Character boundary analysis provides correct
- * navigation of through character strings, regardless of how the
- * character is stored.  For example, an accented character might be
- * stored as a base character and a diacritical mark. What users
- * consider to be a character can differ between languages.
- * <p>
- * The text boundary positions are found according to the rules
- * described in Unicode Standard Annex #29, Text Boundaries, and
- * Unicode Standard Annex #14, Line Breaking Properties.  These
- * are available at http://www.unicode.org/reports/tr14/ and
- * http://www.unicode.org/reports/tr29/.
- * <p>
- * In addition to the C++ API defined in this header file, a
- * plain C API with equivalent functionality is defined in the
- * file ubrk.h
- * <p>
- * Code snippets illustrating the use of the Break Iterator APIs
- * are available in the ICU User Guide,
- * http://icu-project.org/userguide/boundaryAnalysis.html
- * and in the sample program icu/source/samples/break/break.cpp
- *
- */
-class U_COMMON_API BreakIterator : public UObject {
-public:
-    /**
-     *  destructor
-     *  @stable ICU 2.0
-     */
-    virtual ~BreakIterator();
-
-    /**
-     * Return true if another object is semantically equal to this
-     * one. The other object should be an instance of the same subclass of
-     * BreakIterator. Objects of different subclasses are considered
-     * unequal.
-     * <P>
-     * Return true if this BreakIterator is at the same position in the
-     * same text, and is the same class and type (word, line, etc.) of
-     * BreakIterator, as the argument.  Text is considered the same if
-     * it contains the same characters, it need not be the same
-     * object, and styles are not considered.
-     * @stable ICU 2.0
-     */
-    virtual UBool operator==(const BreakIterator&) const = 0;
-
-    /**
-     * Returns the complement of the result of operator==
-     * @param rhs The BreakIterator to be compared for inequality
-     * @return the complement of the result of operator==
-     * @stable ICU 2.0
-     */
-    UBool operator!=(const BreakIterator& rhs) const { return !operator==(rhs); }
-
-    /**
-     * Return a polymorphic copy of this object.  This is an abstract
-     * method which subclasses implement.
-     * @stable ICU 2.0
-     */
-    virtual BreakIterator* clone() const = 0;
-
-    /**
-     * Return a polymorphic class ID for this object. Different subclasses
-     * will return distinct unequal values.
-     * @stable ICU 2.0
-     */
-    virtual UClassID getDynamicClassID(void) const = 0;
-
-    /**
-     * Return a CharacterIterator over the text being analyzed.
-     * @stable ICU 2.0
-     */
-    virtual CharacterIterator& getText(void) const = 0;
-
-
-    /**
-      *  Get a UText for the text being analyzed.
-      *  The returned UText is a shallow clone of the UText used internally
-      *  by the break iterator implementation.  It can safely be used to
-      *  access the text without impacting any break iterator operations,
-      *  but the underlying text itself must not be altered.
-      *
-      * @param fillIn A UText to be filled in.  If NULL, a new UText will be
-      *           allocated to hold the result.
-      * @param status receives any error codes.
-      * @return   The current UText for this break iterator.  If an input
-      *           UText was provided, it will always be returned.
-      * @stable ICU 3.4
-      */
-     virtual UText *getUText(UText *fillIn, UErrorCode &status) const = 0;
-
-    /**
-     * Change the text over which this operates. The text boundary is
-     * reset to the start.
-     *
-     * The BreakIterator will retain a reference to the supplied string.
-     * The caller must not modify or delete the text while the BreakIterator
-     * retains the reference.
-     *
-     * @param text The UnicodeString used to change the text.
-     * @stable ICU 2.0
-     */
-    virtual void  setText(const UnicodeString &text) = 0;
-
-    /**
-     * Reset the break iterator to operate over the text represented by
-     * the UText.  The iterator position is reset to the start.
-     *
-     * This function makes a shallow clone of the supplied UText.  This means
-     * that the caller is free to immediately close or otherwise reuse the
-     * Utext that was passed as a parameter, but that the underlying text itself
-     * must not be altered while being referenced by the break iterator.
-     *
-     * All index positions returned by break iterator functions are
-     * native indices from the UText. For example, when breaking UTF-8
-     * encoded text, the break positions returned by next(), previous(), etc.
-     * will be UTF-8 string indices, not UTF-16 positions.
-     *
-     * @param text The UText used to change the text.
-     * @param status receives any error codes.
-     * @stable ICU 3.4
-     */
-    virtual void  setText(UText *text, UErrorCode &status) = 0;
-
-    /**
-     * Change the text over which this operates. The text boundary is
-     * reset to the start.
-     * Note that setText(UText *) provides similar functionality to this function,
-     * and is more efficient.
-     * @param it The CharacterIterator used to change the text.
-     * @stable ICU 2.0
-     */
-    virtual void  adoptText(CharacterIterator* it) = 0;
-
-    enum {
-        /**
-         * DONE is returned by previous() and next() after all valid
-         * boundaries have been returned.
-         * @stable ICU 2.0
-         */
-        DONE = (int32_t)-1
-    };
-
-    /**
-     * Sets the current iteration position to the beginning of the text, position zero.
-     * @return The offset of the beginning of the text, zero.
-     * @stable ICU 2.0
-     */
-    virtual int32_t first(void) = 0;
-
-    /**
-     * Set the iterator position to the index immediately BEYOND the last character in the text being scanned.
-     * @return The index immediately BEYOND the last character in the text being scanned.
-     * @stable ICU 2.0
-     */
-    virtual int32_t last(void) = 0;
-
-    /**
-     * Set the iterator position to the boundary preceding the current boundary.
-     * @return The character index of the previous text boundary or DONE if all
-     * boundaries have been returned.
-     * @stable ICU 2.0
-     */
-    virtual int32_t previous(void) = 0;
-
-    /**
-     * Advance the iterator to the boundary following the current boundary.
-     * @return The character index of the next text boundary or DONE if all
-     * boundaries have been returned.
-     * @stable ICU 2.0
-     */
-    virtual int32_t next(void) = 0;
-
-    /**
-     * Return character index of the current iterator position within the text.
-     * @return The boundary most recently returned.
-     * @stable ICU 2.0
-     */
-    virtual int32_t current(void) const = 0;
-
-    /**
-     * Advance the iterator to the first boundary following the specified offset.
-     * The value returned is always greater than the offset or
-     * the value BreakIterator.DONE
-     * @param offset the offset to begin scanning.
-     * @return The first boundary after the specified offset.
-     * @stable ICU 2.0
-     */
-    virtual int32_t following(int32_t offset) = 0;
-
-    /**
-     * Set the iterator position to the first boundary preceding the specified offset.
-     * The value returned is always smaller than the offset or
-     * the value BreakIterator.DONE
-     * @param offset the offset to begin scanning.
-     * @return The first boundary before the specified offset.
-     * @stable ICU 2.0
-     */
-    virtual int32_t preceding(int32_t offset) = 0;
-
-    /**
-     * Return true if the specified position is a boundary position.
-     * As a side effect, the current position of the iterator is set
-     * to the first boundary position at or following the specified offset.
-     * @param offset the offset to check.
-     * @return True if "offset" is a boundary position.
-     * @stable ICU 2.0
-     */
-    virtual UBool isBoundary(int32_t offset) = 0;
-
-    /**
-     * Set the iterator position to the nth boundary from the current boundary
-     * @param n the number of boundaries to move by.  A value of 0
-     * does nothing.  Negative values move to previous boundaries
-     * and positive values move to later boundaries.
-     * @return The new iterator position, or
-     * DONE if there are fewer than |n| boundaries in the specified direction.
-     * @stable ICU 2.0
-     */
-    virtual int32_t next(int32_t n) = 0;
-
-   /**
-     * For RuleBasedBreakIterators, return the status tag from the break rule
-     * that determined the boundary at the current iteration position.
-     * <p>
-     * For break iterator types that do not support a rule status,
-     * a default value of 0 is returned.
-     * <p>
-     * @return the status from the break rule that determined the boundary at
-     *         the current iteration position.
-     * @see RuleBaseBreakIterator::getRuleStatus()
-     * @see UWordBreak
-     * @stable ICU 52
-     */
-    virtual int32_t getRuleStatus() const;
-
-   /**
-    * For RuleBasedBreakIterators, get the status (tag) values from the break rule(s)
-    * that determined the boundary at the current iteration position.
-    * <p>
-    * For break iterator types that do not support rule status,
-    * no values are returned.
-    * <p>
-    * The returned status value(s) are stored into an array provided by the caller.
-    * The values are stored in sorted (ascending) order.
-    * If the capacity of the output array is insufficient to hold the data,
-    *  the output will be truncated to the available length, and a
-    *  U_BUFFER_OVERFLOW_ERROR will be signaled.
-    * <p>
-    * @see RuleBaseBreakIterator::getRuleStatusVec
-    *
-    * @param fillInVec an array to be filled in with the status values.
-    * @param capacity  the length of the supplied vector.  A length of zero causes
-    *                  the function to return the number of status values, in the
-    *                  normal way, without attempting to store any values.
-    * @param status    receives error codes.
-    * @return          The number of rule status values from rules that determined
-    *                  the boundary at the current iteration position.
-    *                  In the event of a U_BUFFER_OVERFLOW_ERROR, the return value
-    *                  is the total number of status values that were available,
-    *                  not the reduced number that were actually returned.
-    * @see getRuleStatus
-    * @stable ICU 52
-    */
-    virtual int32_t getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UErrorCode &status);
-
-    /**
-     * Create BreakIterator for word-breaks using the given locale.
-     * Returns an instance of a BreakIterator implementing word breaks.
-     * WordBreak is useful for word selection (ex. double click)
-     * @param where the locale.
-     * @param status the error code
-     * @return A BreakIterator for word-breaks.  The UErrorCode& status
-     * parameter is used to return status information to the user.
-     * To check whether the construction succeeded or not, you should check
-     * the value of U_SUCCESS(err).  If you wish more detailed information, you
-     * can check for informational error results which still indicate success.
-     * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
-     * example, 'de_CH' was requested, but nothing was found there, so 'de' was
-     * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
-     * used; neither the requested locale nor any of its fall back locales
-     * could be found.
-     * The caller owns the returned object and is responsible for deleting it.
-     * @stable ICU 2.0
-     */
-    static BreakIterator* U_EXPORT2
-    createWordInstance(const Locale& where, UErrorCode& status);
-
-    /**
-     * Create BreakIterator for line-breaks using specified locale.
-     * Returns an instance of a BreakIterator implementing line breaks. Line
-     * breaks are logically possible line breaks, actual line breaks are
-     * usually determined based on display width.
-     * LineBreak is useful for word wrapping text.
-     * @param where the locale.
-     * @param status The error code.
-     * @return A BreakIterator for line-breaks.  The UErrorCode& status
-     * parameter is used to return status information to the user.
-     * To check whether the construction succeeded or not, you should check
-     * the value of U_SUCCESS(err).  If you wish more detailed information, you
-     * can check for informational error results which still indicate success.
-     * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
-     * example, 'de_CH' was requested, but nothing was found there, so 'de' was
-     * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
-     * used; neither the requested locale nor any of its fall back locales
-     * could be found.
-     * The caller owns the returned object and is responsible for deleting it.
-     * @stable ICU 2.0
-     */
-    static BreakIterator* U_EXPORT2
-    createLineInstance(const Locale& where, UErrorCode& status);
-
-    /**
-     * Create BreakIterator for character-breaks using specified locale
-     * Returns an instance of a BreakIterator implementing character breaks.
-     * Character breaks are boundaries of combining character sequences.
-     * @param where the locale.
-     * @param status The error code.
-     * @return A BreakIterator for character-breaks.  The UErrorCode& status
-     * parameter is used to return status information to the user.
-     * To check whether the construction succeeded or not, you should check
-     * the value of U_SUCCESS(err).  If you wish more detailed information, you
-     * can check for informational error results which still indicate success.
-     * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
-     * example, 'de_CH' was requested, but nothing was found there, so 'de' was
-     * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
-     * used; neither the requested locale nor any of its fall back locales
-     * could be found.
-     * The caller owns the returned object and is responsible for deleting it.
-     * @stable ICU 2.0
-     */
-    static BreakIterator* U_EXPORT2
-    createCharacterInstance(const Locale& where, UErrorCode& status);
-
-    /**
-     * Create BreakIterator for sentence-breaks using specified locale
-     * Returns an instance of a BreakIterator implementing sentence breaks.
-     * @param where the locale.
-     * @param status The error code.
-     * @return A BreakIterator for sentence-breaks.  The UErrorCode& status
-     * parameter is used to return status information to the user.
-     * To check whether the construction succeeded or not, you should check
-     * the value of U_SUCCESS(err).  If you wish more detailed information, you
-     * can check for informational error results which still indicate success.
-     * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
-     * example, 'de_CH' was requested, but nothing was found there, so 'de' was
-     * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
-     * used; neither the requested locale nor any of its fall back locales
-     * could be found.
-     * The caller owns the returned object and is responsible for deleting it.
-     * @stable ICU 2.0
-     */
-    static BreakIterator* U_EXPORT2
-    createSentenceInstance(const Locale& where, UErrorCode& status);
-
-#ifndef U_HIDE_DEPRECATED_API
-    /**
-     * Create BreakIterator for title-casing breaks using the specified locale
-     * Returns an instance of a BreakIterator implementing title breaks.
-     * The iterator returned locates title boundaries as described for
-     * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration,
-     * please use a word boundary iterator. See {@link #createWordInstance }.
-     *
-     * @param where the locale.
-     * @param status The error code.
-     * @return A BreakIterator for title-breaks.  The UErrorCode& status
-     * parameter is used to return status information to the user.
-     * To check whether the construction succeeded or not, you should check
-     * the value of U_SUCCESS(err).  If you wish more detailed information, you
-     * can check for informational error results which still indicate success.
-     * U_USING_FALLBACK_WARNING indicates that a fall back locale was used.  For
-     * example, 'de_CH' was requested, but nothing was found there, so 'de' was
-     * used.  U_USING_DEFAULT_WARNING indicates that the default locale data was
-     * used; neither the requested locale nor any of its fall back locales
-     * could be found.
-     * The caller owns the returned object and is responsible for deleting it.
-     * @deprecated ICU 64 Use createWordInstance instead.
-     */
-    static BreakIterator* U_EXPORT2
-    createTitleInstance(const Locale& where, UErrorCode& status);
-#endif /* U_HIDE_DEPRECATED_API */
-
-    /**
-     * Get the set of Locales for which TextBoundaries are installed.
-     * <p><b>Note:</b> this will not return locales added through the register
-     * call. To see the registered locales too, use the getAvailableLocales
-     * function that returns a StringEnumeration object </p>
-     * @param count the output parameter of number of elements in the locale list
-     * @return available locales
-     * @stable ICU 2.0
-     */
-    static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count);
-
-    /**
-     * Get name of the object for the desired Locale, in the desired language.
-     * @param objectLocale must be from getAvailableLocales.
-     * @param displayLocale specifies the desired locale for output.
-     * @param name the fill-in parameter of the return value
-     * Uses best match.
-     * @return user-displayable name
-     * @stable ICU 2.0
-     */
-    static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale,
-                                         const Locale& displayLocale,
-                                         UnicodeString& name);
-
-    /**
-     * Get name of the object for the desired Locale, in the language of the
-     * default locale.
-     * @param objectLocale must be from getMatchingLocales
-     * @param name the fill-in parameter of the return value
-     * @return user-displayable name
-     * @stable ICU 2.0
-     */
-    static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale,
-                                         UnicodeString& name);
-
-#ifndef U_FORCE_HIDE_DEPRECATED_API
-    /**
-     * Deprecated functionality. Use clone() instead.
-     *
-     * Thread safe client-buffer-based cloning operation
-     *    Do NOT call delete on a safeclone, since 'new' is not used to create it.
-     * @param stackBuffer user allocated space for the new clone. If NULL new memory will be allocated.
-     * If buffer is not large enough, new memory will be allocated.
-     * @param BufferSize reference to size of allocated space.
-     * If BufferSize == 0, a sufficient size for use in cloning will
-     * be returned ('pre-flighting')
-     * If BufferSize is not enough for a stack-based safe clone,
-     * new memory will be allocated.
-     * @param status to indicate whether the operation went on smoothly or there were errors
-     *  An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were
-     *  necessary.
-     * @return pointer to the new clone
-     *
-     * @deprecated ICU 52. Use clone() instead.
-     */
-    virtual BreakIterator *  createBufferClone(void *stackBuffer,
-                                               int32_t &BufferSize,
-                                               UErrorCode &status) = 0;
-#endif  // U_FORCE_HIDE_DEPRECATED_API
-
-#ifndef U_HIDE_DEPRECATED_API
-
-    /**
-     *   Determine whether the BreakIterator was created in user memory by
-     *   createBufferClone(), and thus should not be deleted.  Such objects
-     *   must be closed by an explicit call to the destructor (not delete).
-     * @deprecated ICU 52. Always delete the BreakIterator.
-     */
-    inline UBool isBufferClone(void);
-
-#endif /* U_HIDE_DEPRECATED_API */
-
-#if !UCONFIG_NO_SERVICE
-    /**
-     * Register a new break iterator of the indicated kind, to use in the given locale.
-     * The break iterator will be adopted.  Clones of the iterator will be returned
-     * if a request for a break iterator of the given kind matches or falls back to
-     * this locale.
-     * Because ICU may choose to cache BreakIterators internally, this must
-     * be called at application startup, prior to any calls to
-     * BreakIterator::createXXXInstance to avoid undefined behavior.
-     * @param toAdopt the BreakIterator instance to be adopted
-     * @param locale the Locale for which this instance is to be registered
-     * @param kind the type of iterator for which this instance is to be registered
-     * @param status the in/out status code, no special meanings are assigned
-     * @return a registry key that can be used to unregister this instance
-     * @stable ICU 2.4
-     */
-    static URegistryKey U_EXPORT2 registerInstance(BreakIterator* toAdopt,
-                                        const Locale& locale,
-                                        UBreakIteratorType kind,
-                                        UErrorCode& status);
-
-    /**
-     * Unregister a previously-registered BreakIterator using the key returned from the
-     * register call.  Key becomes invalid after a successful call and should not be used again.
-     * The BreakIterator corresponding to the key will be deleted.
-     * Because ICU may choose to cache BreakIterators internally, this should
-     * be called during application shutdown, after all calls to
-     * BreakIterator::createXXXInstance to avoid undefined behavior.
-     * @param key the registry key returned by a previous call to registerInstance
-     * @param status the in/out status code, no special meanings are assigned
-     * @return true if the iterator for the key was successfully unregistered
-     * @stable ICU 2.4
-     */
-    static UBool U_EXPORT2 unregister(URegistryKey key, UErrorCode& status);
-
-    /**
-     * Return a StringEnumeration over the locales available at the time of the call,
-     * including registered locales.
-     * @return a StringEnumeration over the locales available at the time of the call
-     * @stable ICU 2.4
-     */
-    static StringEnumeration* U_EXPORT2 getAvailableLocales(void);
-#endif
-
-    /**
-     * Returns the locale for this break iterator. Two flavors are available: valid and
-     * actual locale.
-     * @stable ICU 2.8
-     */
-    Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const;
-
-#ifndef U_HIDE_INTERNAL_API
-    /** Get the locale for this break iterator object. You can choose between valid and actual locale.
-     *  @param type type of the locale we're looking for (valid or actual)
-     *  @param status error code for the operation
-     *  @return the locale
-     *  @internal
-     */
-    const char *getLocaleID(ULocDataLocaleType type, UErrorCode& status) const;
-#endif  /* U_HIDE_INTERNAL_API */
-
-    /**
-     *  Set the subject text string upon which the break iterator is operating
-     *  without changing any other aspect of the matching state.
-     *  The new and previous text strings must have the same content.
-     *
-     *  This function is intended for use in environments where ICU is operating on
-     *  strings that may move around in memory.  It provides a mechanism for notifying
-     *  ICU that the string has been relocated, and providing a new UText to access the
-     *  string in its new position.
-     *
-     *  Note that the break iterator implementation never copies the underlying text
-     *  of a string being processed, but always operates directly on the original text
-     *  provided by the user. Refreshing simply drops the references to the old text
-     *  and replaces them with references to the new.
-     *
-     *  Caution:  this function is normally used only by very specialized,
-     *  system-level code.  One example use case is with garbage collection that moves
-     *  the text in memory.
-     *
-     * @param input      The new (moved) text string.
-     * @param status     Receives errors detected by this function.
-     * @return           *this
-     *
-     * @stable ICU 49
-     */
-    virtual BreakIterator &refreshInputText(UText *input, UErrorCode &status) = 0;
-
- private:
-    static BreakIterator* buildInstance(const Locale& loc, const char *type, UErrorCode& status);
-    static BreakIterator* createInstance(const Locale& loc, int32_t kind, UErrorCode& status);
-    static BreakIterator* makeInstance(const Locale& loc, int32_t kind, UErrorCode& status);
-
-    friend class ICUBreakIteratorFactory;
-    friend class ICUBreakIteratorService;
-
-protected:
-    // Do not enclose protected default/copy constructors with #ifndef U_HIDE_INTERNAL_API
-    // or else the compiler will create a public ones.
-    /** @internal */
-    BreakIterator();
-    /** @internal */
-    BreakIterator (const BreakIterator &other);
-#ifndef U_HIDE_INTERNAL_API
-    /** @internal */
-    BreakIterator (const Locale& valid, const Locale &actual);
-    /** @internal. Assignment Operator, used by RuleBasedBreakIterator. */
-    BreakIterator &operator = (const BreakIterator &other);
-#endif  /* U_HIDE_INTERNAL_API */
-
-private:
-
-    /** @internal (private) */
-    char actualLocale[ULOC_FULLNAME_CAPACITY];
-    char validLocale[ULOC_FULLNAME_CAPACITY];
-};
-
-#ifndef U_HIDE_DEPRECATED_API
-
-inline UBool BreakIterator::isBufferClone()
-{
-    return false;
-}
-
-#endif /* U_HIDE_DEPRECATED_API */
-
-U_NAMESPACE_END
-
-#endif /* #if !UCONFIG_NO_BREAK_ITERATION */
-
-#endif /* U_SHOW_CPLUSPLUS_API */
-
-#endif // BRKITER_H
-//eof

app/src/main/cpp/icu4c/include/unicode/bytestream.h

@@ -1,307 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-// Copyright (C) 2009-2012, International Business Machines
-// Corporation and others. All Rights Reserved.
-//
-// Copyright 2007 Google Inc. All Rights Reserved.
-// Author: sanjay@google.com (Sanjay Ghemawat)
-//
-// Abstract interface that consumes a sequence of bytes (ByteSink).
-//
-// Used so that we can write a single piece of code that can operate
-// on a variety of output string types.
-//
-// Various implementations of this interface are provided:
-//   ByteSink:
-//      CheckedArrayByteSink    Write to a flat array, with bounds checking
-//      StringByteSink          Write to an STL string
-
-// This code is a contribution of Google code, and the style used here is
-// a compromise between the original Google code and the ICU coding guidelines.
-// For example, data types are ICU-ified (size_t,int->int32_t),
-// and API comments doxygen-ified, but function names and behavior are
-// as in the original, if possible.
-// Assertion-style error handling, not available in ICU, was changed to
-// parameter "pinning" similar to UnicodeString.
-//
-// In addition, this is only a partial port of the original Google code,
-// limited to what was needed so far. The (nearly) complete original code
-// is in the ICU svn repository at icuhtml/trunk/design/strings/contrib
-// (see ICU ticket 6765, r25517).
-
-#ifndef __BYTESTREAM_H__
-#define __BYTESTREAM_H__
-
-/**
- * \file
- * \brief C++ API: Interface for writing bytes, and implementation classes.
- */
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-
-#include "unicode/uobject.h"
-#include "unicode/std_string.h"
-
-U_NAMESPACE_BEGIN
-
-/**
- * A ByteSink can be filled with bytes.
- * @stable ICU 4.2
- */
-class U_COMMON_API ByteSink : public UMemory {
-public:
-  /**
-   * Default constructor.
-   * @stable ICU 4.2
-   */
-  ByteSink() { }
-  /**
-   * Virtual destructor.
-   * @stable ICU 4.2
-   */
-  virtual ~ByteSink();
-
-  /**
-   * Append "bytes[0,n-1]" to this.
-   * @param bytes the pointer to the bytes
-   * @param n the number of bytes; must be non-negative
-   * @stable ICU 4.2
-   */
-  virtual void Append(const char* bytes, int32_t n) = 0;
-
-  /**
-   * Appends n bytes to this. Same as Append().
-   * Call AppendU8() with u8"string literals" which are const char * in C++11
-   * but const char8_t * in C++20.
-   * If the compiler does support char8_t as a distinct type,
-   * then an AppendU8() overload for that is defined and will be chosen.
-   *
-   * @param bytes the pointer to the bytes
-   * @param n the number of bytes; must be non-negative
-   * @stable ICU 67
-   */
-  inline void AppendU8(const char* bytes, int32_t n) {
-    Append(bytes, n);
-  }
-
-#if defined(__cpp_char8_t) || defined(U_IN_DOXYGEN)
-  /**
-   * Appends n bytes to this. Same as Append() but for a const char8_t * pointer.
-   * Call AppendU8() with u8"string literals" which are const char * in C++11
-   * but const char8_t * in C++20.
-   * If the compiler does support char8_t as a distinct type,
-   * then this AppendU8() overload for that is defined and will be chosen.
-   *
-   * @param bytes the pointer to the bytes
-   * @param n the number of bytes; must be non-negative
-   * @stable ICU 67
-   */
-  inline void AppendU8(const char8_t* bytes, int32_t n) {
-    Append(reinterpret_cast<const char*>(bytes), n);
-  }
-#endif
-
-  /**
-   * Returns a writable buffer for appending and writes the buffer's capacity to
-   * *result_capacity. Guarantees *result_capacity>=min_capacity.
-   * May return a pointer to the caller-owned scratch buffer which must have
-   * scratch_capacity>=min_capacity.
-   * The returned buffer is only valid until the next operation
-   * on this ByteSink.
-   *
-   * After writing at most *result_capacity bytes, call Append() with the
-   * pointer returned from this function and the number of bytes written.
-   * Many Append() implementations will avoid copying bytes if this function
-   * returned an internal buffer.
-   *
-   * Partial usage example:
-   *  int32_t capacity;
-   *  char* buffer = sink->GetAppendBuffer(..., &capacity);
-   *  ... Write n bytes into buffer, with n <= capacity.
-   *  sink->Append(buffer, n);
-   * In many implementations, that call to Append will avoid copying bytes.
-   *
-   * If the ByteSink allocates or reallocates an internal buffer, it should use
-   * the desired_capacity_hint if appropriate.
-   * If a caller cannot provide a reasonable guess at the desired capacity,
-   * it should pass desired_capacity_hint=0.
-   *
-   * If a non-scratch buffer is returned, the caller may only pass
-   * a prefix to it to Append().
-   * That is, it is not correct to pass an interior pointer to Append().
-   *
-   * The default implementation always returns the scratch buffer.
-   *
-   * @param min_capacity required minimum capacity of the returned buffer;
-   *                     must be non-negative
-   * @param desired_capacity_hint desired capacity of the returned buffer;
-   *                              must be non-negative
-   * @param scratch default caller-owned buffer
-   * @param scratch_capacity capacity of the scratch buffer
-   * @param result_capacity pointer to an integer which will be set to the
-   *                        capacity of the returned buffer
-   * @return a buffer with *result_capacity>=min_capacity
-   * @stable ICU 4.2
-   */
-  virtual char* GetAppendBuffer(int32_t min_capacity,
-                                int32_t desired_capacity_hint,
-                                char* scratch, int32_t scratch_capacity,
-                                int32_t* result_capacity);
-
-  /**
-   * Flush internal buffers.
-   * Some byte sinks use internal buffers or provide buffering
-   * and require calling Flush() at the end of the stream.
-   * The ByteSink should be ready for further Append() calls after Flush().
-   * The default implementation of Flush() does nothing.
-   * @stable ICU 4.2
-   */
-  virtual void Flush();
-
-private:
-  ByteSink(const ByteSink &) = delete;
-  ByteSink &operator=(const ByteSink &) = delete;
-};
-
-// -------------------------------------------------------------
-// Some standard implementations
-
-/** 
- * Implementation of ByteSink that writes to a flat byte array,
- * with bounds-checking:
- * This sink will not write more than capacity bytes to outbuf.
- * If more than capacity bytes are Append()ed, then excess bytes are ignored,
- * and Overflowed() will return true.
- * Overflow does not cause a runtime error.
- * @stable ICU 4.2
- */
-class U_COMMON_API CheckedArrayByteSink : public ByteSink {
-public:
-  /**
-   * Constructs a ByteSink that will write to outbuf[0..capacity-1].
-   * @param outbuf buffer to write to
-   * @param capacity size of the buffer
-   * @stable ICU 4.2
-   */
-  CheckedArrayByteSink(char* outbuf, int32_t capacity);
-  /**
-   * Destructor.
-   * @stable ICU 4.2
-   */
-  virtual ~CheckedArrayByteSink();
-  /**
-   * Returns the sink to its original state, without modifying the buffer.
-   * Useful for reusing both the buffer and the sink for multiple streams.
-   * Resets the state to NumberOfBytesWritten()=NumberOfBytesAppended()=0
-   * and Overflowed()=false.
-   * @return *this
-   * @stable ICU 4.6
-   */
-  virtual CheckedArrayByteSink& Reset();
-  /**
-   * Append "bytes[0,n-1]" to this.
-   * @param bytes the pointer to the bytes
-   * @param n the number of bytes; must be non-negative
-   * @stable ICU 4.2
-   */
-  virtual void Append(const char* bytes, int32_t n);
-  /**
-   * Returns a writable buffer for appending and writes the buffer's capacity to
-   * *result_capacity. For details see the base class documentation.
-   * @param min_capacity required minimum capacity of the returned buffer;
-   *                     must be non-negative
-   * @param desired_capacity_hint desired capacity of the returned buffer;
-   *                              must be non-negative
-   * @param scratch default caller-owned buffer
-   * @param scratch_capacity capacity of the scratch buffer
-   * @param result_capacity pointer to an integer which will be set to the
-   *                        capacity of the returned buffer
-   * @return a buffer with *result_capacity>=min_capacity
-   * @stable ICU 4.2
-   */
-  virtual char* GetAppendBuffer(int32_t min_capacity,
-                                int32_t desired_capacity_hint,
-                                char* scratch, int32_t scratch_capacity,
-                                int32_t* result_capacity);
-  /**
-   * Returns the number of bytes actually written to the sink.
-   * @return number of bytes written to the buffer
-   * @stable ICU 4.2
-   */
-  int32_t NumberOfBytesWritten() const { return size_; }
-  /**
-   * Returns true if any bytes were discarded, i.e., if there was an
-   * attempt to write more than 'capacity' bytes.
-   * @return true if more than 'capacity' bytes were Append()ed
-   * @stable ICU 4.2
-   */
-  UBool Overflowed() const { return overflowed_; }
-  /**
-   * Returns the number of bytes appended to the sink.
-   * If Overflowed() then NumberOfBytesAppended()>NumberOfBytesWritten()
-   * else they return the same number.
-   * @return number of bytes written to the buffer
-   * @stable ICU 4.6
-   */
-  int32_t NumberOfBytesAppended() const { return appended_; }
-private:
-  char* outbuf_;
-  const int32_t capacity_;
-  int32_t size_;
-  int32_t appended_;
-  UBool overflowed_;
-
-  CheckedArrayByteSink() = delete;
-  CheckedArrayByteSink(const CheckedArrayByteSink &) = delete;
-  CheckedArrayByteSink &operator=(const CheckedArrayByteSink &) = delete;
-};
-
-/** 
- * Implementation of ByteSink that writes to a "string".
- * The StringClass is usually instantiated with a std::string.
- * @stable ICU 4.2
- */
-template<typename StringClass>
-class StringByteSink : public ByteSink {
- public:
-  /**
-   * Constructs a ByteSink that will append bytes to the dest string.
-   * @param dest pointer to string object to append to
-   * @stable ICU 4.2
-   */
-  StringByteSink(StringClass* dest) : dest_(dest) { }
-  /**
-   * Constructs a ByteSink that reserves append capacity and will append bytes to the dest string.
-   * 
-   * @param dest pointer to string object to append to
-   * @param initialAppendCapacity capacity beyond dest->length() to be reserve()d
-   * @stable ICU 60
-   */
-  StringByteSink(StringClass* dest, int32_t initialAppendCapacity) : dest_(dest) {
-    if (initialAppendCapacity > 0 &&
-        (uint32_t)initialAppendCapacity > (dest->capacity() - dest->length())) {
-      dest->reserve(dest->length() + initialAppendCapacity);
-    }
-  }
-  /**
-   * Append "bytes[0,n-1]" to this.
-   * @param data the pointer to the bytes
-   * @param n the number of bytes; must be non-negative
-   * @stable ICU 4.2
-   */
-  virtual void Append(const char* data, int32_t n) { dest_->append(data, n); }
- private:
-  StringClass* dest_;
-
-  StringByteSink() = delete;
-  StringByteSink(const StringByteSink &) = delete;
-  StringByteSink &operator=(const StringByteSink &) = delete;
-};
-
-U_NAMESPACE_END
-
-#endif /* U_SHOW_CPLUSPLUS_API */
-
-#endif  // __BYTESTREAM_H__

app/src/main/cpp/icu4c/include/unicode/char16ptr.h

@@ -1,313 +0,0 @@
-// © 2017 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-
-// char16ptr.h
-// created: 2017feb28 Markus W. Scherer
-
-#ifndef __CHAR16PTR_H__
-#define __CHAR16PTR_H__
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-
-#include <cstddef>
-
-/**
- * \file
- * \brief C++ API: char16_t pointer wrappers with
- *        implicit conversion from bit-compatible raw pointer types.
- *        Also conversion functions from char16_t * to UChar * and OldUChar *.
- */
-
-U_NAMESPACE_BEGIN
-
-/**
- * \def U_ALIASING_BARRIER
- * Barrier for pointer anti-aliasing optimizations even across function boundaries.
- * @internal
- */
-#ifdef U_ALIASING_BARRIER
-    // Use the predefined value.
-#elif (defined(__clang__) || defined(__GNUC__)) && U_PLATFORM != U_PF_BROWSER_NATIVE_CLIENT
-#   define U_ALIASING_BARRIER(ptr) asm volatile("" : : "rm"(ptr) : "memory")
-#elif defined(U_IN_DOXYGEN)
-#   define U_ALIASING_BARRIER(ptr)
-#endif
-
-/**
- * char16_t * wrapper with implicit conversion from distinct but bit-compatible pointer types.
- * @stable ICU 59
- */
-class U_COMMON_API Char16Ptr U_FINAL {
-public:
-    /**
-     * Copies the pointer.
-     * @param p pointer
-     * @stable ICU 59
-     */
-    inline Char16Ptr(char16_t *p);
-#if !U_CHAR16_IS_TYPEDEF
-    /**
-     * Converts the pointer to char16_t *.
-     * @param p pointer to be converted
-     * @stable ICU 59
-     */
-    inline Char16Ptr(uint16_t *p);
-#endif
-#if U_SIZEOF_WCHAR_T==2 || defined(U_IN_DOXYGEN)
-    /**
-     * Converts the pointer to char16_t *.
-     * (Only defined if U_SIZEOF_WCHAR_T==2.)
-     * @param p pointer to be converted
-     * @stable ICU 59
-     */
-    inline Char16Ptr(wchar_t *p);
-#endif
-    /**
-     * nullptr constructor.
-     * @param p nullptr
-     * @stable ICU 59
-     */
-    inline Char16Ptr(std::nullptr_t p);
-    /**
-     * Destructor.
-     * @stable ICU 59
-     */
-    inline ~Char16Ptr();
-
-    /**
-     * Pointer access.
-     * @return the wrapped pointer
-     * @stable ICU 59
-     */
-    inline char16_t *get() const;
-    /**
-     * char16_t pointer access via type conversion (e.g., static_cast).
-     * @return the wrapped pointer
-     * @stable ICU 59
-     */
-    inline operator char16_t *() const { return get(); }
-
-private:
-    Char16Ptr() = delete;
-
-#ifdef U_ALIASING_BARRIER
-    template<typename T> static char16_t *cast(T *t) {
-        U_ALIASING_BARRIER(t);
-        return reinterpret_cast<char16_t *>(t);
-    }
-
-    char16_t *p_;
-#else
-    union {
-        char16_t *cp;
-        uint16_t *up;
-        wchar_t *wp;
-    } u_;
-#endif
-};
-
-/// \cond
-#ifdef U_ALIASING_BARRIER
-
-Char16Ptr::Char16Ptr(char16_t *p) : p_(p) {}
-#if !U_CHAR16_IS_TYPEDEF
-Char16Ptr::Char16Ptr(uint16_t *p) : p_(cast(p)) {}
-#endif
-#if U_SIZEOF_WCHAR_T==2
-Char16Ptr::Char16Ptr(wchar_t *p) : p_(cast(p)) {}
-#endif
-Char16Ptr::Char16Ptr(std::nullptr_t p) : p_(p) {}
-Char16Ptr::~Char16Ptr() {
-    U_ALIASING_BARRIER(p_);
-}
-
-char16_t *Char16Ptr::get() const { return p_; }
-
-#else
-
-Char16Ptr::Char16Ptr(char16_t *p) { u_.cp = p; }
-#if !U_CHAR16_IS_TYPEDEF
-Char16Ptr::Char16Ptr(uint16_t *p) { u_.up = p; }
-#endif
-#if U_SIZEOF_WCHAR_T==2
-Char16Ptr::Char16Ptr(wchar_t *p) { u_.wp = p; }
-#endif
-Char16Ptr::Char16Ptr(std::nullptr_t p) { u_.cp = p; }
-Char16Ptr::~Char16Ptr() {}
-
-char16_t *Char16Ptr::get() const { return u_.cp; }
-
-#endif
-/// \endcond
-
-/**
- * const char16_t * wrapper with implicit conversion from distinct but bit-compatible pointer types.
- * @stable ICU 59
- */
-class U_COMMON_API ConstChar16Ptr U_FINAL {
-public:
-    /**
-     * Copies the pointer.
-     * @param p pointer
-     * @stable ICU 59
-     */
-    inline ConstChar16Ptr(const char16_t *p);
-#if !U_CHAR16_IS_TYPEDEF
-    /**
-     * Converts the pointer to char16_t *.
-     * @param p pointer to be converted
-     * @stable ICU 59
-     */
-    inline ConstChar16Ptr(const uint16_t *p);
-#endif
-#if U_SIZEOF_WCHAR_T==2 || defined(U_IN_DOXYGEN)
-    /**
-     * Converts the pointer to char16_t *.
-     * (Only defined if U_SIZEOF_WCHAR_T==2.)
-     * @param p pointer to be converted
-     * @stable ICU 59
-     */
-    inline ConstChar16Ptr(const wchar_t *p);
-#endif
-    /**
-     * nullptr constructor.
-     * @param p nullptr
-     * @stable ICU 59
-     */
-    inline ConstChar16Ptr(const std::nullptr_t p);
-
-    /**
-     * Destructor.
-     * @stable ICU 59
-     */
-    inline ~ConstChar16Ptr();
-
-    /**
-     * Pointer access.
-     * @return the wrapped pointer
-     * @stable ICU 59
-     */
-    inline const char16_t *get() const;
-    /**
-     * char16_t pointer access via type conversion (e.g., static_cast).
-     * @return the wrapped pointer
-     * @stable ICU 59
-     */
-    inline operator const char16_t *() const { return get(); }
-
-private:
-    ConstChar16Ptr() = delete;
-
-#ifdef U_ALIASING_BARRIER
-    template<typename T> static const char16_t *cast(const T *t) {
-        U_ALIASING_BARRIER(t);
-        return reinterpret_cast<const char16_t *>(t);
-    }
-
-    const char16_t *p_;
-#else
-    union {
-        const char16_t *cp;
-        const uint16_t *up;
-        const wchar_t *wp;
-    } u_;
-#endif
-};
-
-/// \cond
-#ifdef U_ALIASING_BARRIER
-
-ConstChar16Ptr::ConstChar16Ptr(const char16_t *p) : p_(p) {}
-#if !U_CHAR16_IS_TYPEDEF
-ConstChar16Ptr::ConstChar16Ptr(const uint16_t *p) : p_(cast(p)) {}
-#endif
-#if U_SIZEOF_WCHAR_T==2
-ConstChar16Ptr::ConstChar16Ptr(const wchar_t *p) : p_(cast(p)) {}
-#endif
-ConstChar16Ptr::ConstChar16Ptr(const std::nullptr_t p) : p_(p) {}
-ConstChar16Ptr::~ConstChar16Ptr() {
-    U_ALIASING_BARRIER(p_);
-}
-
-const char16_t *ConstChar16Ptr::get() const { return p_; }
-
-#else
-
-ConstChar16Ptr::ConstChar16Ptr(const char16_t *p) { u_.cp = p; }
-#if !U_CHAR16_IS_TYPEDEF
-ConstChar16Ptr::ConstChar16Ptr(const uint16_t *p) { u_.up = p; }
-#endif
-#if U_SIZEOF_WCHAR_T==2
-ConstChar16Ptr::ConstChar16Ptr(const wchar_t *p) { u_.wp = p; }
-#endif
-ConstChar16Ptr::ConstChar16Ptr(const std::nullptr_t p) { u_.cp = p; }
-ConstChar16Ptr::~ConstChar16Ptr() {}
-
-const char16_t *ConstChar16Ptr::get() const { return u_.cp; }
-
-#endif
-/// \endcond
-
-/**
- * Converts from const char16_t * to const UChar *.
- * Includes an aliasing barrier if available.
- * @param p pointer
- * @return p as const UChar *
- * @stable ICU 59
- */
-inline const UChar *toUCharPtr(const char16_t *p) {
-#ifdef U_ALIASING_BARRIER
-    U_ALIASING_BARRIER(p);
-#endif
-    return reinterpret_cast<const UChar *>(p);
-}
-
-/**
- * Converts from char16_t * to UChar *.
- * Includes an aliasing barrier if available.
- * @param p pointer
- * @return p as UChar *
- * @stable ICU 59
- */
-inline UChar *toUCharPtr(char16_t *p) {
-#ifdef U_ALIASING_BARRIER
-    U_ALIASING_BARRIER(p);
-#endif
-    return reinterpret_cast<UChar *>(p);
-}
-
-/**
- * Converts from const char16_t * to const OldUChar *.
- * Includes an aliasing barrier if available.
- * @param p pointer
- * @return p as const OldUChar *
- * @stable ICU 59
- */
-inline const OldUChar *toOldUCharPtr(const char16_t *p) {
-#ifdef U_ALIASING_BARRIER
-    U_ALIASING_BARRIER(p);
-#endif
-    return reinterpret_cast<const OldUChar *>(p);
-}
-
-/**
- * Converts from char16_t * to OldUChar *.
- * Includes an aliasing barrier if available.
- * @param p pointer
- * @return p as OldUChar *
- * @stable ICU 59
- */
-inline OldUChar *toOldUCharPtr(char16_t *p) {
-#ifdef U_ALIASING_BARRIER
-    U_ALIASING_BARRIER(p);
-#endif
-    return reinterpret_cast<OldUChar *>(p);
-}
-
-U_NAMESPACE_END
-
-#endif /* U_SHOW_CPLUSPLUS_API */
-
-#endif  // __CHAR16PTR_H__

app/src/main/cpp/icu4c/include/unicode/chariter.h

@@ -1,734 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-********************************************************************
-*
-*   Copyright (C) 1997-2011, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-********************************************************************
-*/
-
-#ifndef CHARITER_H
-#define CHARITER_H
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-
-#include "unicode/uobject.h"
-#include "unicode/unistr.h"
-/**
- * \file
- * \brief C++ API: Character Iterator
- */
- 
-U_NAMESPACE_BEGIN
-/**
- * Abstract class that defines an API for forward-only iteration
- * on text objects.
- * This is a minimal interface for iteration without random access
- * or backwards iteration. It is especially useful for wrapping
- * streams with converters into an object for collation or
- * normalization.
- *
- * <p>Characters can be accessed in two ways: as code units or as
- * code points.
- * Unicode code points are 21-bit integers and are the scalar values
- * of Unicode characters. ICU uses the type UChar32 for them.
- * Unicode code units are the storage units of a given
- * Unicode/UCS Transformation Format (a character encoding scheme).
- * With UTF-16, all code points can be represented with either one
- * or two code units ("surrogates").
- * String storage is typically based on code units, while properties
- * of characters are typically determined using code point values.
- * Some processes may be designed to work with sequences of code units,
- * or it may be known that all characters that are important to an
- * algorithm can be represented with single code units.
- * Other processes will need to use the code point access functions.</p>
- *
- * <p>ForwardCharacterIterator provides nextPostInc() to access
- * a code unit and advance an internal position into the text object,
- * similar to a <code>return text[position++]</code>.<br>
- * It provides next32PostInc() to access a code point and advance an internal
- * position.</p>
- *
- * <p>next32PostInc() assumes that the current position is that of
- * the beginning of a code point, i.e., of its first code unit.
- * After next32PostInc(), this will be true again.
- * In general, access to code units and code points in the same
- * iteration loop should not be mixed. In UTF-16, if the current position
- * is on a second code unit (Low Surrogate), then only that code unit
- * is returned even by next32PostInc().</p>
- *
- * <p>For iteration with either function, there are two ways to
- * check for the end of the iteration. When there are no more
- * characters in the text object:
- * <ul>
- * <li>The hasNext() function returns false.</li>
- * <li>nextPostInc() and next32PostInc() return DONE
- *     when one attempts to read beyond the end of the text object.</li>
- * </ul>
- *
- * Example:
- * \code 
- * void function1(ForwardCharacterIterator &it) {
- *     UChar32 c;
- *     while(it.hasNext()) {
- *         c=it.next32PostInc();
- *         // use c
- *     }
- * }
- *
- * void function1(ForwardCharacterIterator &it) {
- *     char16_t c;
- *     while((c=it.nextPostInc())!=ForwardCharacterIterator::DONE) {
- *         // use c
- *      }
- *  }
- * \endcode
- * </p>
- *
- * @stable ICU 2.0
- */
-class U_COMMON_API ForwardCharacterIterator : public UObject {
-public:
-    /**
-     * Value returned by most of ForwardCharacterIterator's functions
-     * when the iterator has reached the limits of its iteration.
-     * @stable ICU 2.0
-     */
-    enum { DONE = 0xffff };
-    
-    /**
-     * Destructor.  
-     * @stable ICU 2.0
-     */
-    virtual ~ForwardCharacterIterator();
-    
-    /**
-     * Returns true when both iterators refer to the same
-     * character in the same character-storage object.  
-     * @param that The ForwardCharacterIterator to be compared for equality
-     * @return true when both iterators refer to the same
-     * character in the same character-storage object
-     * @stable ICU 2.0
-     */
-    virtual UBool operator==(const ForwardCharacterIterator& that) const = 0;
-    
-    /**
-     * Returns true when the iterators refer to different
-     * text-storage objects, or to different characters in the
-     * same text-storage object.  
-     * @param that The ForwardCharacterIterator to be compared for inequality
-     * @return true when the iterators refer to different
-     * text-storage objects, or to different characters in the
-     * same text-storage object
-     * @stable ICU 2.0
-     */
-    inline UBool operator!=(const ForwardCharacterIterator& that) const;
-    
-    /**
-     * Generates a hash code for this iterator.  
-     * @return the hash code.
-     * @stable ICU 2.0
-     */
-    virtual int32_t hashCode(void) const = 0;
-    
-    /**
-     * Returns a UClassID for this ForwardCharacterIterator ("poor man's
-     * RTTI").<P> Despite the fact that this function is public,
-     * DO NOT CONSIDER IT PART OF CHARACTERITERATOR'S API! 
-     * @return a UClassID for this ForwardCharacterIterator 
-     * @stable ICU 2.0
-     */
-    virtual UClassID getDynamicClassID(void) const = 0;
-    
-    /**
-     * Gets the current code unit for returning and advances to the next code unit
-     * in the iteration range
-     * (toward endIndex()).  If there are
-     * no more code units to return, returns DONE.
-     * @return the current code unit.
-     * @stable ICU 2.0
-     */
-    virtual char16_t         nextPostInc(void) = 0;
-    
-    /**
-     * Gets the current code point for returning and advances to the next code point
-     * in the iteration range
-     * (toward endIndex()).  If there are
-     * no more code points to return, returns DONE.
-     * @return the current code point.
-     * @stable ICU 2.0
-     */
-    virtual UChar32       next32PostInc(void) = 0;
-    
-    /**
-     * Returns false if there are no more code units or code points
-     * at or after the current position in the iteration range.
-     * This is used with nextPostInc() or next32PostInc() in forward
-     * iteration.
-     * @returns false if there are no more code units or code points
-     * at or after the current position in the iteration range.
-     * @stable ICU 2.0
-     */
-    virtual UBool        hasNext() = 0;
-    
-protected:
-    /** Default constructor to be overridden in the implementing class. @stable ICU 2.0*/
-    ForwardCharacterIterator();
-    
-    /** Copy constructor to be overridden in the implementing class. @stable ICU 2.0*/
-    ForwardCharacterIterator(const ForwardCharacterIterator &other);
-    
-    /**
-     * Assignment operator to be overridden in the implementing class.
-     * @stable ICU 2.0
-     */
-    ForwardCharacterIterator &operator=(const ForwardCharacterIterator&) { return *this; }
-};
-
-/**
- * Abstract class that defines an API for iteration
- * on text objects.
- * This is an interface for forward and backward iteration
- * and random access into a text object.
- *
- * <p>The API provides backward compatibility to the Java and older ICU
- * CharacterIterator classes but extends them significantly:
- * <ol>
- * <li>CharacterIterator is now a subclass of ForwardCharacterIterator.</li>
- * <li>While the old API functions provided forward iteration with
- *     "pre-increment" semantics, the new one also provides functions
- *     with "post-increment" semantics. They are more efficient and should
- *     be the preferred iterator functions for new implementations.
- *     The backward iteration always had "pre-decrement" semantics, which
- *     are efficient.</li>
- * <li>Just like ForwardCharacterIterator, it provides access to
- *     both code units and code points. Code point access versions are available
- *     for the old and the new iteration semantics.</li>
- * <li>There are new functions for setting and moving the current position
- *     without returning a character, for efficiency.</li>
- * </ol>
- *
- * See ForwardCharacterIterator for examples for using the new forward iteration
- * functions. For backward iteration, there is also a hasPrevious() function
- * that can be used analogously to hasNext().
- * The old functions work as before and are shown below.</p>
- *
- * <p>Examples for some of the new functions:</p>
- *
- * Forward iteration with hasNext():
- * \code
- * void forward1(CharacterIterator &it) {
- *     UChar32 c;
- *     for(it.setToStart(); it.hasNext();) {
- *         c=it.next32PostInc();
- *         // use c
- *     }
- *  }
- * \endcode
- * Forward iteration more similar to loops with the old forward iteration,
- * showing a way to convert simple for() loops:
- * \code
- * void forward2(CharacterIterator &it) {
- *     char16_t c;
- *     for(c=it.firstPostInc(); c!=CharacterIterator::DONE; c=it.nextPostInc()) {
- *          // use c
- *      }
- * }
- * \endcode
- * Backward iteration with setToEnd() and hasPrevious():
- * \code
- *  void backward1(CharacterIterator &it) {
- *      UChar32 c;
- *      for(it.setToEnd(); it.hasPrevious();) {
- *         c=it.previous32();
- *          // use c
- *      }
- *  }
- * \endcode
- * Backward iteration with a more traditional for() loop:
- * \code
- * void backward2(CharacterIterator &it) {
- *     char16_t c;
- *     for(c=it.last(); c!=CharacterIterator::DONE; c=it.previous()) {
- *         // use c
- *      }
- *  }
- * \endcode
- *
- * Example for random access:
- * \code
- *  void random(CharacterIterator &it) {
- *      // set to the third code point from the beginning
- *      it.move32(3, CharacterIterator::kStart);
- *      // get a code point from here without moving the position
- *      UChar32 c=it.current32();
- *      // get the position
- *      int32_t pos=it.getIndex();
- *      // get the previous code unit
- *      char16_t u=it.previous();
- *      // move back one more code unit
- *      it.move(-1, CharacterIterator::kCurrent);
- *      // set the position back to where it was
- *      // and read the same code point c and move beyond it
- *      it.setIndex(pos);
- *      if(c!=it.next32PostInc()) {
- *          exit(1); // CharacterIterator inconsistent
- *      }
- *  }
- * \endcode
- *
- * <p>Examples, especially for the old API:</p>
- *
- * Function processing characters, in this example simple output
- * <pre>
- * \code
- *  void processChar( char16_t c )
- *  {
- *      cout << " " << c;
- *  }
- * \endcode
- * </pre>
- * Traverse the text from start to finish
- * <pre> 
- * \code
- *  void traverseForward(CharacterIterator& iter)
- *  {
- *      for(char16_t c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) {
- *          processChar(c);
- *      }
- *  }
- * \endcode
- * </pre>
- * Traverse the text backwards, from end to start
- * <pre>
- * \code
- *  void traverseBackward(CharacterIterator& iter)
- *  {
- *      for(char16_t c = iter.last(); c != CharacterIterator.DONE; c = iter.previous()) {
- *          processChar(c);
- *      }
- *  }
- * \endcode
- * </pre>
- * Traverse both forward and backward from a given position in the text. 
- * Calls to notBoundary() in this example represents some additional stopping criteria.
- * <pre>
- * \code
- * void traverseOut(CharacterIterator& iter, int32_t pos)
- * {
- *      char16_t c;
- *      for (c = iter.setIndex(pos);
- *      c != CharacterIterator.DONE && (Unicode::isLetter(c) || Unicode::isDigit(c));
- *          c = iter.next()) {}
- *      int32_t end = iter.getIndex();
- *      for (c = iter.setIndex(pos);
- *          c != CharacterIterator.DONE && (Unicode::isLetter(c) || Unicode::isDigit(c));
- *          c = iter.previous()) {}
- *      int32_t start = iter.getIndex() + 1;
- *  
- *      cout << "start: " << start << " end: " << end << endl;
- *      for (c = iter.setIndex(start); iter.getIndex() < end; c = iter.next() ) {
- *          processChar(c);
- *     }
- *  }
- * \endcode
- * </pre>
- * Creating a StringCharacterIterator and calling the test functions
- * <pre>
- * \code
- *  void CharacterIterator_Example( void )
- *   {
- *       cout << endl << "===== CharacterIterator_Example: =====" << endl;
- *       UnicodeString text("Ein kleiner Satz.");
- *       StringCharacterIterator iterator(text);
- *       cout << "----- traverseForward: -----------" << endl;
- *       traverseForward( iterator );
- *       cout << endl << endl << "----- traverseBackward: ----------" << endl;
- *       traverseBackward( iterator );
- *       cout << endl << endl << "----- traverseOut: ---------------" << endl;
- *       traverseOut( iterator, 7 );
- *       cout << endl << endl << "-----" << endl;
- *   }
- * \endcode
- * </pre>
- *
- * @stable ICU 2.0
- */
-class U_COMMON_API CharacterIterator : public ForwardCharacterIterator {
-public:
-    /**
-     * Origin enumeration for the move() and move32() functions.
-     * @stable ICU 2.0
-     */
-    enum EOrigin { kStart, kCurrent, kEnd };
-
-    /**
-     * Destructor.
-     * @stable ICU 2.0
-     */
-    virtual ~CharacterIterator();
-
-    /**
-     * Returns a pointer to a new CharacterIterator of the same
-     * concrete class as this one, and referring to the same
-     * character in the same text-storage object as this one.  The
-     * caller is responsible for deleting the new clone.  
-     * @return a pointer to a new CharacterIterator
-     * @stable ICU 2.0
-     */
-    virtual CharacterIterator* clone() const = 0;
-
-    /**
-     * Sets the iterator to refer to the first code unit in its
-     * iteration range, and returns that code unit.
-     * This can be used to begin an iteration with next().
-     * @return the first code unit in its iteration range.
-     * @stable ICU 2.0
-     */
-    virtual char16_t         first(void) = 0;
-
-    /**
-     * Sets the iterator to refer to the first code unit in its
-     * iteration range, returns that code unit, and moves the position
-     * to the second code unit. This is an alternative to setToStart()
-     * for forward iteration with nextPostInc().
-     * @return the first code unit in its iteration range.
-     * @stable ICU 2.0
-     */
-    virtual char16_t         firstPostInc(void);
-
-    /**
-     * Sets the iterator to refer to the first code point in its
-     * iteration range, and returns that code unit,
-     * This can be used to begin an iteration with next32().
-     * Note that an iteration with next32PostInc(), beginning with,
-     * e.g., setToStart() or firstPostInc(), is more efficient.
-     * @return the first code point in its iteration range.
-     * @stable ICU 2.0
-     */
-    virtual UChar32       first32(void) = 0;
-
-    /**
-     * Sets the iterator to refer to the first code point in its
-     * iteration range, returns that code point, and moves the position
-     * to the second code point. This is an alternative to setToStart()
-     * for forward iteration with next32PostInc().
-     * @return the first code point in its iteration range.
-     * @stable ICU 2.0
-     */
-    virtual UChar32       first32PostInc(void);
-
-    /**
-     * Sets the iterator to refer to the first code unit or code point in its
-     * iteration range. This can be used to begin a forward
-     * iteration with nextPostInc() or next32PostInc().
-     * @return the start position of the iteration range
-     * @stable ICU 2.0
-     */
-    inline int32_t    setToStart();
-
-    /**
-     * Sets the iterator to refer to the last code unit in its
-     * iteration range, and returns that code unit.
-     * This can be used to begin an iteration with previous().
-     * @return the last code unit.
-     * @stable ICU 2.0
-     */
-    virtual char16_t         last(void) = 0;
-        
-    /**
-     * Sets the iterator to refer to the last code point in its
-     * iteration range, and returns that code unit.
-     * This can be used to begin an iteration with previous32().
-     * @return the last code point.
-     * @stable ICU 2.0
-     */
-    virtual UChar32       last32(void) = 0;
-
-    /**
-     * Sets the iterator to the end of its iteration range, just behind
-     * the last code unit or code point. This can be used to begin a backward
-     * iteration with previous() or previous32().
-     * @return the end position of the iteration range
-     * @stable ICU 2.0
-     */
-    inline int32_t    setToEnd();
-
-    /**
-     * Sets the iterator to refer to the "position"-th code unit
-     * in the text-storage object the iterator refers to, and
-     * returns that code unit.  
-     * @param position the "position"-th code unit in the text-storage object
-     * @return the "position"-th code unit.
-     * @stable ICU 2.0
-     */
-    virtual char16_t         setIndex(int32_t position) = 0;
-
-    /**
-     * Sets the iterator to refer to the beginning of the code point
-     * that contains the "position"-th code unit
-     * in the text-storage object the iterator refers to, and
-     * returns that code point.
-     * The current position is adjusted to the beginning of the code point
-     * (its first code unit).
-     * @param position the "position"-th code unit in the text-storage object
-     * @return the "position"-th code point.
-     * @stable ICU 2.0
-     */
-    virtual UChar32       setIndex32(int32_t position) = 0;
-
-    /**
-     * Returns the code unit the iterator currently refers to. 
-     * @return the current code unit. 
-     * @stable ICU 2.0
-     */
-    virtual char16_t         current(void) const = 0;
-        
-    /**
-     * Returns the code point the iterator currently refers to.  
-     * @return the current code point.
-     * @stable ICU 2.0
-     */
-    virtual UChar32       current32(void) const = 0;
-        
-    /**
-     * Advances to the next code unit in the iteration range
-     * (toward endIndex()), and returns that code unit.  If there are
-     * no more code units to return, returns DONE.
-     * @return the next code unit.
-     * @stable ICU 2.0
-     */
-    virtual char16_t         next(void) = 0;
-        
-    /**
-     * Advances to the next code point in the iteration range
-     * (toward endIndex()), and returns that code point.  If there are
-     * no more code points to return, returns DONE.
-     * Note that iteration with "pre-increment" semantics is less
-     * efficient than iteration with "post-increment" semantics
-     * that is provided by next32PostInc().
-     * @return the next code point.
-     * @stable ICU 2.0
-     */
-    virtual UChar32       next32(void) = 0;
-        
-    /**
-     * Advances to the previous code unit in the iteration range
-     * (toward startIndex()), and returns that code unit.  If there are
-     * no more code units to return, returns DONE.  
-     * @return the previous code unit.
-     * @stable ICU 2.0
-     */
-    virtual char16_t         previous(void) = 0;
-
-    /**
-     * Advances to the previous code point in the iteration range
-     * (toward startIndex()), and returns that code point.  If there are
-     * no more code points to return, returns DONE. 
-     * @return the previous code point. 
-     * @stable ICU 2.0
-     */
-    virtual UChar32       previous32(void) = 0;
-
-    /**
-     * Returns false if there are no more code units or code points
-     * before the current position in the iteration range.
-     * This is used with previous() or previous32() in backward
-     * iteration.
-     * @return false if there are no more code units or code points
-     * before the current position in the iteration range, return true otherwise.
-     * @stable ICU 2.0
-     */
-    virtual UBool        hasPrevious() = 0;
-
-    /**
-     * Returns the numeric index in the underlying text-storage
-     * object of the character returned by first().  Since it's
-     * possible to create an iterator that iterates across only
-     * part of a text-storage object, this number isn't
-     * necessarily 0.  
-     * @returns the numeric index in the underlying text-storage
-     * object of the character returned by first().
-     * @stable ICU 2.0
-     */
-    inline int32_t       startIndex(void) const;
-        
-    /**
-     * Returns the numeric index in the underlying text-storage
-     * object of the position immediately BEYOND the character
-     * returned by last().  
-     * @return the numeric index in the underlying text-storage
-     * object of the position immediately BEYOND the character
-     * returned by last().
-     * @stable ICU 2.0
-     */
-    inline int32_t       endIndex(void) const;
-        
-    /**
-     * Returns the numeric index in the underlying text-storage
-     * object of the character the iterator currently refers to
-     * (i.e., the character returned by current()).  
-     * @return the numeric index in the text-storage object of 
-     * the character the iterator currently refers to
-     * @stable ICU 2.0
-     */
-    inline int32_t       getIndex(void) const;
-
-    /**
-     * Returns the length of the entire text in the underlying
-     * text-storage object.
-     * @return the length of the entire text in the text-storage object
-     * @stable ICU 2.0
-     */
-    inline int32_t           getLength() const;
-
-    /**
-     * Moves the current position relative to the start or end of the
-     * iteration range, or relative to the current position itself.
-     * The movement is expressed in numbers of code units forward
-     * or backward by specifying a positive or negative delta.
-     * @param delta the position relative to origin. A positive delta means forward;
-     * a negative delta means backward.
-     * @param origin Origin enumeration {kStart, kCurrent, kEnd}
-     * @return the new position
-     * @stable ICU 2.0
-     */
-    virtual int32_t      move(int32_t delta, EOrigin origin) = 0;
-
-    /**
-     * Moves the current position relative to the start or end of the
-     * iteration range, or relative to the current position itself.
-     * The movement is expressed in numbers of code points forward
-     * or backward by specifying a positive or negative delta.
-     * @param delta the position relative to origin. A positive delta means forward;
-     * a negative delta means backward.
-     * @param origin Origin enumeration {kStart, kCurrent, kEnd}
-     * @return the new position
-     * @stable ICU 2.0
-     */
-#ifdef move32
-     // One of the system headers right now is sometimes defining a conflicting macro we don't use
-#undef move32
-#endif
-    virtual int32_t      move32(int32_t delta, EOrigin origin) = 0;
-
-    /**
-     * Copies the text under iteration into the UnicodeString
-     * referred to by "result".  
-     * @param result Receives a copy of the text under iteration.  
-     * @stable ICU 2.0
-     */
-    virtual void            getText(UnicodeString&  result) = 0;
-
-protected:
-    /**
-     * Empty constructor.
-     * @stable ICU 2.0
-     */
-    CharacterIterator();
-
-    /**
-     * Constructor, just setting the length field in this base class.
-     * @stable ICU 2.0
-     */
-    CharacterIterator(int32_t length);
-
-    /**
-     * Constructor, just setting the length and position fields in this base class.
-     * @stable ICU 2.0
-     */
-    CharacterIterator(int32_t length, int32_t position);
-
-    /**
-     * Constructor, just setting the length, start, end, and position fields in this base class.
-     * @stable ICU 2.0
-     */
-    CharacterIterator(int32_t length, int32_t textBegin, int32_t textEnd, int32_t position);
-  
-    /**
-     * Copy constructor.
-     *
-     * @param that The CharacterIterator to be copied
-     * @stable ICU 2.0
-     */
-    CharacterIterator(const CharacterIterator &that);
-
-    /**
-     * Assignment operator.  Sets this CharacterIterator to have the same behavior,
-     * as the one passed in.
-     * @param that The CharacterIterator passed in.
-     * @return the newly set CharacterIterator.
-     * @stable ICU 2.0
-     */
-    CharacterIterator &operator=(const CharacterIterator &that);
-
-    /**
-     * Base class text length field.
-     * Necessary this for correct getText() and hashCode().
-     * @stable ICU 2.0
-     */
-    int32_t textLength;
-
-    /**
-     * Base class field for the current position.
-     * @stable ICU 2.0
-     */
-    int32_t  pos;
-
-    /**
-     * Base class field for the start of the iteration range.
-     * @stable ICU 2.0
-     */
-    int32_t  begin;
-
-    /**
-     * Base class field for the end of the iteration range.
-     * @stable ICU 2.0
-     */
-    int32_t  end;
-};
-
-inline UBool
-ForwardCharacterIterator::operator!=(const ForwardCharacterIterator& that) const {
-    return !operator==(that);
-}
-
-inline int32_t
-CharacterIterator::setToStart() {
-    return move(0, kStart);
-}
-
-inline int32_t
-CharacterIterator::setToEnd() {
-    return move(0, kEnd);
-}
-
-inline int32_t
-CharacterIterator::startIndex(void) const {
-    return begin;
-}
-
-inline int32_t
-CharacterIterator::endIndex(void) const {
-    return end;
-}
-
-inline int32_t
-CharacterIterator::getIndex(void) const {
-    return pos;
-}
-
-inline int32_t
-CharacterIterator::getLength(void) const {
-    return textLength;
-}
-
-U_NAMESPACE_END
-
-#endif /* U_SHOW_CPLUSPLUS_API */
-
-#endif

app/src/main/cpp/icu4c/include/unicode/localpointer.h

@@ -1,595 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-*******************************************************************************
-*
-*   Copyright (C) 2009-2016, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-*******************************************************************************
-*   file name:  localpointer.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:4
-*
-*   created on: 2009nov13
-*   created by: Markus W. Scherer
-*/
-
-#ifndef __LOCALPOINTER_H__
-#define __LOCALPOINTER_H__
-
-/**
- * \file
- * \brief C++ API: "Smart pointers" for use with and in ICU4C C++ code.
- *
- * These classes are inspired by
- * - std::auto_ptr
- * - boost::scoped_ptr & boost::scoped_array
- * - Taligent Safe Pointers (TOnlyPointerTo)
- *
- * but none of those provide for all of the goals for ICU smart pointers:
- * - Smart pointer owns the object and releases it when it goes out of scope.
- * - No transfer of ownership via copy/assignment to reduce misuse. Simpler & more robust.
- * - ICU-compatible: No exceptions.
- * - Need to be able to orphan/release the pointer and its ownership.
- * - Need variants for normal C++ object pointers, C++ arrays, and ICU C service objects.
- *
- * For details see http://site.icu-project.org/design/cpp/scoped_ptr
- */
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-
-#include <memory>
-
-U_NAMESPACE_BEGIN
-
-/**
- * "Smart pointer" base class; do not use directly: use LocalPointer etc.
- *
- * Base class for smart pointer classes that do not throw exceptions.
- *
- * Do not use this base class directly, since it does not delete its pointer.
- * A subclass must implement methods that delete the pointer:
- * Destructor and adoptInstead().
- *
- * There is no operator T *() provided because the programmer must decide
- * whether to use getAlias() (without transfer of ownership) or orphan()
- * (with transfer of ownership and NULLing of the pointer).
- *
- * @see LocalPointer
- * @see LocalArray
- * @see U_DEFINE_LOCAL_OPEN_POINTER
- * @stable ICU 4.4
- */
-template<typename T>
-class LocalPointerBase {
-public:
-    // No heap allocation. Use only on the stack.
-    static void* U_EXPORT2 operator new(size_t) = delete;
-    static void* U_EXPORT2 operator new[](size_t) = delete;
-#if U_HAVE_PLACEMENT_NEW
-    static void* U_EXPORT2 operator new(size_t, void*) = delete;
-#endif
-
-    /**
-     * Constructor takes ownership.
-     * @param p simple pointer to an object that is adopted
-     * @stable ICU 4.4
-     */
-    explicit LocalPointerBase(T *p=NULL) : ptr(p) {}
-    /**
-     * Destructor deletes the object it owns.
-     * Subclass must override: Base class does nothing.
-     * @stable ICU 4.4
-     */
-    ~LocalPointerBase() { /* delete ptr; */ }
-    /**
-     * NULL check.
-     * @return true if ==NULL
-     * @stable ICU 4.4
-     */
-    UBool isNull() const { return ptr==NULL; }
-    /**
-     * NULL check.
-     * @return true if !=NULL
-     * @stable ICU 4.4
-     */
-    UBool isValid() const { return ptr!=NULL; }
-    /**
-     * Comparison with a simple pointer, so that existing code
-     * with ==NULL need not be changed.
-     * @param other simple pointer for comparison
-     * @return true if this pointer value equals other
-     * @stable ICU 4.4
-     */
-    bool operator==(const T *other) const { return ptr==other; }
-    /**
-     * Comparison with a simple pointer, so that existing code
-     * with !=NULL need not be changed.
-     * @param other simple pointer for comparison
-     * @return true if this pointer value differs from other
-     * @stable ICU 4.4
-     */
-    bool operator!=(const T *other) const { return ptr!=other; }
-    /**
-     * Access without ownership change.
-     * @return the pointer value
-     * @stable ICU 4.4
-     */
-    T *getAlias() const { return ptr; }
-    /**
-     * Access without ownership change.
-     * @return the pointer value as a reference
-     * @stable ICU 4.4
-     */
-    T &operator*() const { return *ptr; }
-    /**
-     * Access without ownership change.
-     * @return the pointer value
-     * @stable ICU 4.4
-     */
-    T *operator->() const { return ptr; }
-    /**
-     * Gives up ownership; the internal pointer becomes NULL.
-     * @return the pointer value;
-     *         caller becomes responsible for deleting the object
-     * @stable ICU 4.4
-     */
-    T *orphan() {
-        T *p=ptr;
-        ptr=NULL;
-        return p;
-    }
-    /**
-     * Deletes the object it owns,
-     * and adopts (takes ownership of) the one passed in.
-     * Subclass must override: Base class does not delete the object.
-     * @param p simple pointer to an object that is adopted
-     * @stable ICU 4.4
-     */
-    void adoptInstead(T *p) {
-        // delete ptr;
-        ptr=p;
-    }
-protected:
-    /**
-     * Actual pointer.
-     * @internal
-     */
-    T *ptr;
-private:
-    // No comparison operators with other LocalPointerBases.
-    bool operator==(const LocalPointerBase<T> &other);
-    bool operator!=(const LocalPointerBase<T> &other);
-    // No ownership sharing: No copy constructor, no assignment operator.
-    LocalPointerBase(const LocalPointerBase<T> &other);
-    void operator=(const LocalPointerBase<T> &other);
-};
-
-/**
- * "Smart pointer" class, deletes objects via the standard C++ delete operator.
- * For most methods see the LocalPointerBase base class.
- *
- * Usage example:
- * \code
- * LocalPointer<UnicodeString> s(new UnicodeString((UChar32)0x50005));
- * int32_t length=s->length();  // 2
- * char16_t lead=s->charAt(0);  // 0xd900
- * if(some condition) { return; }  // no need to explicitly delete the pointer
- * s.adoptInstead(new UnicodeString((char16_t)0xfffc));
- * length=s->length();  // 1
- * // no need to explicitly delete the pointer
- * \endcode
- *
- * @see LocalPointerBase
- * @stable ICU 4.4
- */
-template<typename T>
-class LocalPointer : public LocalPointerBase<T> {
-public:
-    using LocalPointerBase<T>::operator*;
-    using LocalPointerBase<T>::operator->;
-    /**
-     * Constructor takes ownership.
-     * @param p simple pointer to an object that is adopted
-     * @stable ICU 4.4
-     */
-    explicit LocalPointer(T *p=NULL) : LocalPointerBase<T>(p) {}
-    /**
-     * Constructor takes ownership and reports an error if NULL.
-     *
-     * This constructor is intended to be used with other-class constructors
-     * that may report a failure UErrorCode,
-     * so that callers need to check only for U_FAILURE(errorCode)
-     * and not also separately for isNull().
-     *
-     * @param p simple pointer to an object that is adopted
-     * @param errorCode in/out UErrorCode, set to U_MEMORY_ALLOCATION_ERROR
-     *     if p==NULL and no other failure code had been set
-     * @stable ICU 55
-     */
-    LocalPointer(T *p, UErrorCode &errorCode) : LocalPointerBase<T>(p) {
-        if(p==NULL && U_SUCCESS(errorCode)) {
-            errorCode=U_MEMORY_ALLOCATION_ERROR;
-        }
-    }
-    /**
-     * Move constructor, leaves src with isNull().
-     * @param src source smart pointer
-     * @stable ICU 56
-     */
-    LocalPointer(LocalPointer<T> &&src) U_NOEXCEPT : LocalPointerBase<T>(src.ptr) {
-        src.ptr=NULL;
-    }
-
-    /**
-     * Constructs a LocalPointer from a C++11 std::unique_ptr.
-     * The LocalPointer steals the object owned by the std::unique_ptr.
-     *
-     * This constructor works via move semantics. If your std::unique_ptr is
-     * in a local variable, you must use std::move.
-     *
-     * @param p The std::unique_ptr from which the pointer will be stolen.
-     * @stable ICU 64
-     */
-    explicit LocalPointer(std::unique_ptr<T> &&p)
-        : LocalPointerBase<T>(p.release()) {}
-
-    /**
-     * Destructor deletes the object it owns.
-     * @stable ICU 4.4
-     */
-    ~LocalPointer() {
-        delete LocalPointerBase<T>::ptr;
-    }
-    /**
-     * Move assignment operator, leaves src with isNull().
-     * The behavior is undefined if *this and src are the same object.
-     * @param src source smart pointer
-     * @return *this
-     * @stable ICU 56
-     */
-    LocalPointer<T> &operator=(LocalPointer<T> &&src) U_NOEXCEPT {
-        delete LocalPointerBase<T>::ptr;
-        LocalPointerBase<T>::ptr=src.ptr;
-        src.ptr=NULL;
-        return *this;
-    }
-
-    /**
-     * Move-assign from an std::unique_ptr to this LocalPointer.
-     * Steals the pointer from the std::unique_ptr.
-     *
-     * @param p The std::unique_ptr from which the pointer will be stolen.
-     * @return *this
-     * @stable ICU 64
-     */
-    LocalPointer<T> &operator=(std::unique_ptr<T> &&p) U_NOEXCEPT {
-        adoptInstead(p.release());
-        return *this;
-    }
-
-    /**
-     * Swap pointers.
-     * @param other other smart pointer
-     * @stable ICU 56
-     */
-    void swap(LocalPointer<T> &other) U_NOEXCEPT {
-        T *temp=LocalPointerBase<T>::ptr;
-        LocalPointerBase<T>::ptr=other.ptr;
-        other.ptr=temp;
-    }
-    /**
-     * Non-member LocalPointer swap function.
-     * @param p1 will get p2's pointer
-     * @param p2 will get p1's pointer
-     * @stable ICU 56
-     */
-    friend inline void swap(LocalPointer<T> &p1, LocalPointer<T> &p2) U_NOEXCEPT {
-        p1.swap(p2);
-    }
-    /**
-     * Deletes the object it owns,
-     * and adopts (takes ownership of) the one passed in.
-     * @param p simple pointer to an object that is adopted
-     * @stable ICU 4.4
-     */
-    void adoptInstead(T *p) {
-        delete LocalPointerBase<T>::ptr;
-        LocalPointerBase<T>::ptr=p;
-    }
-    /**
-     * Deletes the object it owns,
-     * and adopts (takes ownership of) the one passed in.
-     *
-     * If U_FAILURE(errorCode), then the current object is retained and the new one deleted.
-     *
-     * If U_SUCCESS(errorCode) but the input pointer is NULL,
-     * then U_MEMORY_ALLOCATION_ERROR is set,
-     * the current object is deleted, and NULL is set.
-     *
-     * @param p simple pointer to an object that is adopted
-     * @param errorCode in/out UErrorCode, set to U_MEMORY_ALLOCATION_ERROR
-     *     if p==NULL and no other failure code had been set
-     * @stable ICU 55
-     */
-    void adoptInsteadAndCheckErrorCode(T *p, UErrorCode &errorCode) {
-        if(U_SUCCESS(errorCode)) {
-            delete LocalPointerBase<T>::ptr;
-            LocalPointerBase<T>::ptr=p;
-            if(p==NULL) {
-                errorCode=U_MEMORY_ALLOCATION_ERROR;
-            }
-        } else {
-            delete p;
-        }
-    }
-
-    /**
-     * Conversion operator to a C++11 std::unique_ptr.
-     * Disowns the object and gives it to the returned std::unique_ptr.
-     *
-     * This operator works via move semantics. If your LocalPointer is
-     * in a local variable, you must use std::move.
-     *
-     * @return An std::unique_ptr owning the pointer previously owned by this
-     *         icu::LocalPointer.
-     * @stable ICU 64
-     */
-    operator std::unique_ptr<T> () && {
-        return std::unique_ptr<T>(LocalPointerBase<T>::orphan());
-    }
-};
-
-/**
- * "Smart pointer" class, deletes objects via the C++ array delete[] operator.
- * For most methods see the LocalPointerBase base class.
- * Adds operator[] for array item access.
- *
- * Usage example:
- * \code
- * LocalArray<UnicodeString> a(new UnicodeString[2]);
- * a[0].append((char16_t)0x61);
- * if(some condition) { return; }  // no need to explicitly delete the array
- * a.adoptInstead(new UnicodeString[4]);
- * a[3].append((char16_t)0x62).append((char16_t)0x63).reverse();
- * // no need to explicitly delete the array
- * \endcode
- *
- * @see LocalPointerBase
- * @stable ICU 4.4
- */
-template<typename T>
-class LocalArray : public LocalPointerBase<T> {
-public:
-    using LocalPointerBase<T>::operator*;
-    using LocalPointerBase<T>::operator->;
-    /**
-     * Constructor takes ownership.
-     * @param p simple pointer to an array of T objects that is adopted
-     * @stable ICU 4.4
-     */
-    explicit LocalArray(T *p=NULL) : LocalPointerBase<T>(p) {}
-    /**
-     * Constructor takes ownership and reports an error if NULL.
-     *
-     * This constructor is intended to be used with other-class constructors
-     * that may report a failure UErrorCode,
-     * so that callers need to check only for U_FAILURE(errorCode)
-     * and not also separately for isNull().
-     *
-     * @param p simple pointer to an array of T objects that is adopted
-     * @param errorCode in/out UErrorCode, set to U_MEMORY_ALLOCATION_ERROR
-     *     if p==NULL and no other failure code had been set
-     * @stable ICU 56
-     */
-    LocalArray(T *p, UErrorCode &errorCode) : LocalPointerBase<T>(p) {
-        if(p==NULL && U_SUCCESS(errorCode)) {
-            errorCode=U_MEMORY_ALLOCATION_ERROR;
-        }
-    }
-    /**
-     * Move constructor, leaves src with isNull().
-     * @param src source smart pointer
-     * @stable ICU 56
-     */
-    LocalArray(LocalArray<T> &&src) U_NOEXCEPT : LocalPointerBase<T>(src.ptr) {
-        src.ptr=NULL;
-    }
-
-    /**
-     * Constructs a LocalArray from a C++11 std::unique_ptr of an array type.
-     * The LocalPointer steals the array owned by the std::unique_ptr.
-     *
-     * This constructor works via move semantics. If your std::unique_ptr is
-     * in a local variable, you must use std::move.
-     *
-     * @param p The std::unique_ptr from which the array will be stolen.
-     * @stable ICU 64
-     */
-    explicit LocalArray(std::unique_ptr<T[]> &&p)
-        : LocalPointerBase<T>(p.release()) {}
-
-    /**
-     * Destructor deletes the array it owns.
-     * @stable ICU 4.4
-     */
-    ~LocalArray() {
-        delete[] LocalPointerBase<T>::ptr;
-    }
-    /**
-     * Move assignment operator, leaves src with isNull().
-     * The behavior is undefined if *this and src are the same object.
-     * @param src source smart pointer
-     * @return *this
-     * @stable ICU 56
-     */
-    LocalArray<T> &operator=(LocalArray<T> &&src) U_NOEXCEPT {
-        delete[] LocalPointerBase<T>::ptr;
-        LocalPointerBase<T>::ptr=src.ptr;
-        src.ptr=NULL;
-        return *this;
-    }
-
-    /**
-     * Move-assign from an std::unique_ptr to this LocalPointer.
-     * Steals the array from the std::unique_ptr.
-     *
-     * @param p The std::unique_ptr from which the array will be stolen.
-     * @return *this
-     * @stable ICU 64
-     */
-    LocalArray<T> &operator=(std::unique_ptr<T[]> &&p) U_NOEXCEPT {
-        adoptInstead(p.release());
-        return *this;
-    }
-
-    /**
-     * Swap pointers.
-     * @param other other smart pointer
-     * @stable ICU 56
-     */
-    void swap(LocalArray<T> &other) U_NOEXCEPT {
-        T *temp=LocalPointerBase<T>::ptr;
-        LocalPointerBase<T>::ptr=other.ptr;
-        other.ptr=temp;
-    }
-    /**
-     * Non-member LocalArray swap function.
-     * @param p1 will get p2's pointer
-     * @param p2 will get p1's pointer
-     * @stable ICU 56
-     */
-    friend inline void swap(LocalArray<T> &p1, LocalArray<T> &p2) U_NOEXCEPT {
-        p1.swap(p2);
-    }
-    /**
-     * Deletes the array it owns,
-     * and adopts (takes ownership of) the one passed in.
-     * @param p simple pointer to an array of T objects that is adopted
-     * @stable ICU 4.4
-     */
-    void adoptInstead(T *p) {
-        delete[] LocalPointerBase<T>::ptr;
-        LocalPointerBase<T>::ptr=p;
-    }
-    /**
-     * Deletes the array it owns,
-     * and adopts (takes ownership of) the one passed in.
-     *
-     * If U_FAILURE(errorCode), then the current array is retained and the new one deleted.
-     *
-     * If U_SUCCESS(errorCode) but the input pointer is NULL,
-     * then U_MEMORY_ALLOCATION_ERROR is set,
-     * the current array is deleted, and NULL is set.
-     *
-     * @param p simple pointer to an array of T objects that is adopted
-     * @param errorCode in/out UErrorCode, set to U_MEMORY_ALLOCATION_ERROR
-     *     if p==NULL and no other failure code had been set
-     * @stable ICU 56
-     */
-    void adoptInsteadAndCheckErrorCode(T *p, UErrorCode &errorCode) {
-        if(U_SUCCESS(errorCode)) {
-            delete[] LocalPointerBase<T>::ptr;
-            LocalPointerBase<T>::ptr=p;
-            if(p==NULL) {
-                errorCode=U_MEMORY_ALLOCATION_ERROR;
-            }
-        } else {
-            delete[] p;
-        }
-    }
-    /**
-     * Array item access (writable).
-     * No index bounds check.
-     * @param i array index
-     * @return reference to the array item
-     * @stable ICU 4.4
-     */
-    T &operator[](ptrdiff_t i) const { return LocalPointerBase<T>::ptr[i]; }
-
-    /**
-     * Conversion operator to a C++11 std::unique_ptr.
-     * Disowns the object and gives it to the returned std::unique_ptr.
-     *
-     * This operator works via move semantics. If your LocalPointer is
-     * in a local variable, you must use std::move.
-     *
-     * @return An std::unique_ptr owning the pointer previously owned by this
-     *         icu::LocalPointer.
-     * @stable ICU 64
-     */
-    operator std::unique_ptr<T[]> () && {
-        return std::unique_ptr<T[]>(LocalPointerBase<T>::orphan());
-    }
-};
-
-/**
- * \def U_DEFINE_LOCAL_OPEN_POINTER
- * "Smart pointer" definition macro, deletes objects via the closeFunction.
- * Defines a subclass of LocalPointerBase which works just
- * like LocalPointer<Type> except that this subclass will use the closeFunction
- * rather than the C++ delete operator.
- *
- * Usage example:
- * \code
- * LocalUCaseMapPointer csm(ucasemap_open(localeID, options, &errorCode));
- * utf8OutLength=ucasemap_utf8ToLower(csm.getAlias(),
- *     utf8Out, (int32_t)sizeof(utf8Out),
- *     utf8In, utf8InLength, &errorCode);
- * if(U_FAILURE(errorCode)) { return; }  // no need to explicitly delete the UCaseMap
- * \endcode
- *
- * @see LocalPointerBase
- * @see LocalPointer
- * @stable ICU 4.4
- */
-#define U_DEFINE_LOCAL_OPEN_POINTER(LocalPointerClassName, Type, closeFunction) \
-    class LocalPointerClassName : public LocalPointerBase<Type> { \
-    public: \
-        using LocalPointerBase<Type>::operator*; \
-        using LocalPointerBase<Type>::operator->; \
-        explicit LocalPointerClassName(Type *p=NULL) : LocalPointerBase<Type>(p) {} \
-        LocalPointerClassName(LocalPointerClassName &&src) U_NOEXCEPT \
-                : LocalPointerBase<Type>(src.ptr) { \
-            src.ptr=NULL; \
-        } \
-        /* TODO: Be agnostic of the deleter function signature from the user-provided std::unique_ptr? */ \
-        explicit LocalPointerClassName(std::unique_ptr<Type, decltype(&closeFunction)> &&p) \
-                : LocalPointerBase<Type>(p.release()) {} \
-        ~LocalPointerClassName() { if (ptr != NULL) { closeFunction(ptr); } } \
-        LocalPointerClassName &operator=(LocalPointerClassName &&src) U_NOEXCEPT { \
-            if (ptr != NULL) { closeFunction(ptr); } \
-            LocalPointerBase<Type>::ptr=src.ptr; \
-            src.ptr=NULL; \
-            return *this; \
-        } \
-        /* TODO: Be agnostic of the deleter function signature from the user-provided std::unique_ptr? */ \
-        LocalPointerClassName &operator=(std::unique_ptr<Type, decltype(&closeFunction)> &&p) { \
-            adoptInstead(p.release()); \
-            return *this; \
-        } \
-        void swap(LocalPointerClassName &other) U_NOEXCEPT { \
-            Type *temp=LocalPointerBase<Type>::ptr; \
-            LocalPointerBase<Type>::ptr=other.ptr; \
-            other.ptr=temp; \
-        } \
-        friend inline void swap(LocalPointerClassName &p1, LocalPointerClassName &p2) U_NOEXCEPT { \
-            p1.swap(p2); \
-        } \
-        void adoptInstead(Type *p) { \
-            if (ptr != NULL) { closeFunction(ptr); } \
-            ptr=p; \
-        } \
-        operator std::unique_ptr<Type, decltype(&closeFunction)> () && { \
-            return std::unique_ptr<Type, decltype(&closeFunction)>(LocalPointerBase<Type>::orphan(), closeFunction); \
-        } \
-    }
-
-U_NAMESPACE_END
-
-#endif  /* U_SHOW_CPLUSPLUS_API */
-#endif  /* __LOCALPOINTER_H__ */

app/src/main/cpp/icu4c/include/unicode/parseerr.h

@@ -1,94 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-**********************************************************************
-*   Copyright (C) 1999-2005, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-**********************************************************************
-*   Date        Name        Description
-*   03/14/00    aliu        Creation.
-*   06/27/00    aliu        Change from C++ class to C struct
-**********************************************************************
-*/
-#ifndef PARSEERR_H
-#define PARSEERR_H
-
-#include "unicode/utypes.h"
-
-
-/**
- * \file
- * \brief C API: Parse Error Information
- */
-/**
- * The capacity of the context strings in UParseError.
- * @stable ICU 2.0
- */ 
-enum { U_PARSE_CONTEXT_LEN = 16 };
-
-/**
- * A UParseError struct is used to returned detailed information about
- * parsing errors.  It is used by ICU parsing engines that parse long
- * rules, patterns, or programs, where the text being parsed is long
- * enough that more information than a UErrorCode is needed to
- * localize the error.
- *
- * <p>The line, offset, and context fields are optional; parsing
- * engines may choose not to use to use them.
- *
- * <p>The preContext and postContext strings include some part of the
- * context surrounding the error.  If the source text is "let for=7"
- * and "for" is the error (e.g., because it is a reserved word), then
- * some examples of what a parser might produce are the following:
- *
- * <pre>
- * preContext   postContext
- * ""           ""            The parser does not support context
- * "let "       "=7"          Pre- and post-context only
- * "let "       "for=7"       Pre- and post-context and error text
- * ""           "for"         Error text only
- * </pre>
- *
- * <p>Examples of engines which use UParseError (or may use it in the
- * future) are Transliterator, RuleBasedBreakIterator, and
- * RegexPattern.
- * 
- * @stable ICU 2.0
- */
-typedef struct UParseError {
-
-    /**
-     * The line on which the error occurred.  If the parser uses this
-     * field, it sets it to the line number of the source text line on
-     * which the error appears, which will be a value >= 1.  If the
-     * parse does not support line numbers, the value will be <= 0.
-     * @stable ICU 2.0
-     */
-    int32_t        line;
-
-    /**
-     * The character offset to the error.  If the line field is >= 1,
-     * then this is the offset from the start of the line.  Otherwise,
-     * this is the offset from the start of the text.  If the parser
-     * does not support this field, it will have a value < 0.
-     * @stable ICU 2.0
-     */
-    int32_t        offset;
-
-    /**
-     * Textual context before the error.  Null-terminated.  The empty
-     * string if not supported by parser.
-     * @stable ICU 2.0   
-     */
-    UChar          preContext[U_PARSE_CONTEXT_LEN];
-
-    /**
-     * The error itself and/or textual context after the error.
-     * Null-terminated.  The empty string if not supported by parser.
-     * @stable ICU 2.0   
-     */
-    UChar          postContext[U_PARSE_CONTEXT_LEN];
-
-} UParseError;
-
-#endif

app/src/main/cpp/icu4c/include/unicode/platform.h

@@ -1,885 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-******************************************************************************
-*
-*   Copyright (C) 1997-2016, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-******************************************************************************
-*
-*  FILE NAME : platform.h
-*
-*   Date        Name        Description
-*   05/13/98    nos         Creation (content moved here from ptypes.h).
-*   03/02/99    stephen     Added AS400 support.
-*   03/30/99    stephen     Added Linux support.
-*   04/13/99    stephen     Reworked for autoconf.
-******************************************************************************
-*/
-
-#ifndef _PLATFORM_H
-#define _PLATFORM_H
-
-#include "unicode/uconfig.h"
-#include "unicode/uvernum.h"
-
-/**
- * \file
- * \brief Basic types for the platform.
- *
- * This file used to be generated by autoconf/configure.
- * Starting with ICU 49, platform.h is a normal source file,
- * to simplify cross-compiling and working with non-autoconf/make build systems.
- *
- * When a value in this file does not work on a platform, then please
- * try to derive it from the U_PLATFORM value
- * (for which we might need a new value constant in rare cases)
- * and/or from other macros that are predefined by the compiler
- * or defined in standard (POSIX or platform or compiler) headers.
- *
- * As a temporary workaround, you can add an explicit \#define for some macros
- * before it is first tested, or add an equivalent -D macro definition
- * to the compiler's command line.
- *
- * Note: Some compilers provide ways to show the predefined macros.
- * For example, with gcc you can compile an empty .c file and have the compiler
- * print the predefined macros with
- * \code
- * gcc -E -dM -x c /dev/null | sort
- * \endcode
- * (You can provide an actual empty .c file rather than /dev/null.
- * <code>-x c++</code> is for C++.)
- */
-
-/**
- * Define some things so that they can be documented.
- * @internal
- */
-#ifdef U_IN_DOXYGEN
-/*
- * Problem: "platform.h:335: warning: documentation for unknown define U_HAVE_STD_STRING found." means that U_HAVE_STD_STRING is not documented.
- * Solution: #define any defines for non @internal API here, so that they are visible in the docs.  If you just set PREDEFINED in Doxyfile.in,  they won't be documented.
- */
-
-/* None for now. */
-#endif
-
-/**
- * \def U_PLATFORM
- * The U_PLATFORM macro defines the platform we're on.
- *
- * We used to define one different, value-less macro per platform.
- * That made it hard to know the set of relevant platforms and macros,
- * and hard to deal with variants of platforms.
- *
- * Starting with ICU 49, we define platforms as numeric macros,
- * with ranges of values for related platforms and their variants.
- * The U_PLATFORM macro is set to one of these values.
- *
- * Historical note from the Solaris Wikipedia article:
- * AT&T and Sun collaborated on a project to merge the most popular Unix variants
- * on the market at that time: BSD, System V, and Xenix.
- * This became Unix System V Release 4 (SVR4).
- *
- * @internal
- */
-
-/** Unknown platform. @internal */
-#define U_PF_UNKNOWN 0
-/** Windows @internal */
-#define U_PF_WINDOWS 1000
-/** MinGW. Windows, calls to Win32 API, but using GNU gcc and binutils. @internal */
-#define U_PF_MINGW 1800
-/**
- * Cygwin. Windows, calls to cygwin1.dll for Posix functions,
- * using MSVC or GNU gcc and binutils.
- * @internal
- */
-#define U_PF_CYGWIN 1900
-/* Reserve 2000 for U_PF_UNIX? */
-/** HP-UX is based on UNIX System V. @internal */
-#define U_PF_HPUX 2100
-/** Solaris is a Unix operating system based on SVR4. @internal */
-#define U_PF_SOLARIS 2600
-/** BSD is a UNIX operating system derivative. @internal */
-#define U_PF_BSD 3000
-/** AIX is based on UNIX System V Releases and 4.3 BSD. @internal */
-#define U_PF_AIX 3100
-/** IRIX is based on UNIX System V with BSD extensions. @internal */
-#define U_PF_IRIX 3200
-/**
- * Darwin is a POSIX-compliant operating system, composed of code developed by Apple,
- * as well as code derived from NeXTSTEP, BSD, and other projects,
- * built around the Mach kernel.
- * Darwin forms the core set of components upon which Mac OS X, Apple TV, and iOS are based.
- * (Original description modified from WikiPedia.)
- * @internal
- */
-#define U_PF_DARWIN 3500
-/** iPhone OS (iOS) is a derivative of Mac OS X. @internal */
-#define U_PF_IPHONE 3550
-/** QNX is a commercial Unix-like real-time operating system related to BSD. @internal */
-#define U_PF_QNX 3700
-/** Linux is a Unix-like operating system. @internal */
-#define U_PF_LINUX 4000
-/**
- * Native Client is pretty close to Linux.
- * See https://developer.chrome.com/native-client and
- *  http://www.chromium.org/nativeclient
- *  @internal
- */
-#define U_PF_BROWSER_NATIVE_CLIENT 4020
-/** Android is based on Linux. @internal */
-#define U_PF_ANDROID 4050
-/** Fuchsia is a POSIX-ish platform. @internal */
-#define U_PF_FUCHSIA 4100
-/* Maximum value for Linux-based platform is 4499 */
-/**
- * Emscripten is a C++ transpiler for the Web that can target asm.js or
- * WebAssembly. It provides some POSIX-compatible wrappers and stubs and
- * some Linux-like functionality, but is not fully compatible with
- * either.
- * @internal
- */
-#define U_PF_EMSCRIPTEN 5010
-/** z/OS is the successor to OS/390 which was the successor to MVS. @internal */
-#define U_PF_OS390 9000
-/** "IBM i" is the current name of what used to be i5/OS and earlier OS/400. @internal */
-#define U_PF_OS400 9400
-
-#ifdef U_PLATFORM
-    /* Use the predefined value. */
-#elif defined(__MINGW32__)
-#   define U_PLATFORM U_PF_MINGW
-#elif defined(__CYGWIN__)
-#   define U_PLATFORM U_PF_CYGWIN
-#elif defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
-#   define U_PLATFORM U_PF_WINDOWS
-#elif defined(__ANDROID__)
-#   define U_PLATFORM U_PF_ANDROID
-    /* Android wchar_t support depends on the API level. */
-#   include <android/api-level.h>
-#elif defined(__pnacl__) || defined(__native_client__)
-#   define U_PLATFORM U_PF_BROWSER_NATIVE_CLIENT
-#elif defined(__Fuchsia__)
-#   define U_PLATFORM U_PF_FUCHSIA
-#elif defined(linux) || defined(__linux__) || defined(__linux)
-#   define U_PLATFORM U_PF_LINUX
-#elif defined(__APPLE__) && defined(__MACH__)
-#   include <TargetConditionals.h>
-#   if defined(TARGET_OS_IPHONE) && TARGET_OS_IPHONE  /* variant of TARGET_OS_MAC */
-#       define U_PLATFORM U_PF_IPHONE
-#   else
-#       define U_PLATFORM U_PF_DARWIN
-#   endif
-#elif defined(BSD) || defined(__FreeBSD__) || defined(__FreeBSD_kernel__) || defined(__NetBSD__) || defined(__OpenBSD__) || defined(__MirBSD__)
-#   if defined(__FreeBSD__)
-#       include <sys/endian.h>
-#   endif
-#   define U_PLATFORM U_PF_BSD
-#elif defined(sun) || defined(__sun)
-    /* Check defined(__SVR4) || defined(__svr4__) to distinguish Solaris from SunOS? */
-#   define U_PLATFORM U_PF_SOLARIS
-#   if defined(__GNUC__)
-        /* Solaris/GCC needs this header file to get the proper endianness. Normally, this
-         * header file is included with stddef.h but on Solairs/GCC, the GCC version of stddef.h
-         *  is included which does not include this header file.
-         */
-#       include <sys/isa_defs.h>
-#   endif
-#elif defined(_AIX) || defined(__TOS_AIX__)
-#   define U_PLATFORM U_PF_AIX
-#elif defined(_hpux) || defined(hpux) || defined(__hpux)
-#   define U_PLATFORM U_PF_HPUX
-#elif defined(sgi) || defined(__sgi)
-#   define U_PLATFORM U_PF_IRIX
-#elif defined(__QNX__) || defined(__QNXNTO__)
-#   define U_PLATFORM U_PF_QNX
-#elif defined(__TOS_MVS__)
-#   define U_PLATFORM U_PF_OS390
-#elif defined(__OS400__) || defined(__TOS_OS400__)
-#   define U_PLATFORM U_PF_OS400
-#elif defined(__EMSCRIPTEN__)
-#   define U_PLATFORM U_PF_EMSCRIPTEN
-#else
-#   define U_PLATFORM U_PF_UNKNOWN
-#endif
-
-/**
- * \def CYGWINMSVC
- * Defined if this is Windows with Cygwin, but using MSVC rather than gcc.
- * Otherwise undefined.
- * @internal
- */
-/* Commented out because this is already set in mh-cygwin-msvc
-#if U_PLATFORM == U_PF_CYGWIN && defined(_MSC_VER)
-#   define CYGWINMSVC
-#endif
-*/
-#ifdef U_IN_DOXYGEN
-#   define CYGWINMSVC
-#endif
-
-/**
- * \def U_PLATFORM_USES_ONLY_WIN32_API
- * Defines whether the platform uses only the Win32 API.
- * Set to 1 for Windows/MSVC and MinGW but not Cygwin.
- * @internal
- */
-#ifdef U_PLATFORM_USES_ONLY_WIN32_API
-    /* Use the predefined value. */
-#elif (U_PF_WINDOWS <= U_PLATFORM && U_PLATFORM <= U_PF_MINGW) || defined(CYGWINMSVC)
-#   define U_PLATFORM_USES_ONLY_WIN32_API 1
-#else
-    /* Cygwin implements POSIX. */
-#   define U_PLATFORM_USES_ONLY_WIN32_API 0
-#endif
-
-/**
- * \def U_PLATFORM_HAS_WIN32_API
- * Defines whether the Win32 API is available on the platform.
- * Set to 1 for Windows/MSVC, MinGW and Cygwin.
- * @internal
- */
-#ifdef U_PLATFORM_HAS_WIN32_API
-    /* Use the predefined value. */
-#elif U_PF_WINDOWS <= U_PLATFORM && U_PLATFORM <= U_PF_CYGWIN
-#   define U_PLATFORM_HAS_WIN32_API 1
-#else
-#   define U_PLATFORM_HAS_WIN32_API 0
-#endif
-
-/**
- * \def U_PLATFORM_HAS_WINUWP_API
- * Defines whether target is intended for Universal Windows Platform API
- * Set to 1 for Windows10 Release Solution Configuration
- * @internal
- */
-#ifdef U_PLATFORM_HAS_WINUWP_API
-    /* Use the predefined value. */
-#else
-#   define U_PLATFORM_HAS_WINUWP_API 0
-#endif
-
-/**
- * \def U_PLATFORM_IMPLEMENTS_POSIX
- * Defines whether the platform implements (most of) the POSIX API.
- * Set to 1 for Cygwin and most other platforms.
- * @internal
- */
-#ifdef U_PLATFORM_IMPLEMENTS_POSIX
-    /* Use the predefined value. */
-#elif U_PLATFORM_USES_ONLY_WIN32_API
-#   define U_PLATFORM_IMPLEMENTS_POSIX 0
-#else
-#   define U_PLATFORM_IMPLEMENTS_POSIX 1
-#endif
-
-/**
- * \def U_PLATFORM_IS_LINUX_BASED
- * Defines whether the platform is Linux or one of its derivatives.
- * @internal
- */
-#ifdef U_PLATFORM_IS_LINUX_BASED
-    /* Use the predefined value. */
-#elif U_PF_LINUX <= U_PLATFORM && U_PLATFORM <= 4499
-#   define U_PLATFORM_IS_LINUX_BASED 1
-#else
-#   define U_PLATFORM_IS_LINUX_BASED 0
-#endif
-
-/**
- * \def U_PLATFORM_IS_DARWIN_BASED
- * Defines whether the platform is Darwin or one of its derivatives.
- * @internal
- */
-#ifdef U_PLATFORM_IS_DARWIN_BASED
-    /* Use the predefined value. */
-#elif U_PF_DARWIN <= U_PLATFORM && U_PLATFORM <= U_PF_IPHONE
-#   define U_PLATFORM_IS_DARWIN_BASED 1
-#else
-#   define U_PLATFORM_IS_DARWIN_BASED 0
-#endif
-
-/**
- * \def U_HAVE_STDINT_H
- * Defines whether stdint.h is available. It is a C99 standard header.
- * We used to include inttypes.h which includes stdint.h but we usually do not need
- * the additional definitions from inttypes.h.
- * @internal
- */
-#ifdef U_HAVE_STDINT_H
-    /* Use the predefined value. */
-#elif U_PLATFORM_USES_ONLY_WIN32_API
-#   if defined(__BORLANDC__) || U_PLATFORM == U_PF_MINGW || (defined(_MSC_VER) && _MSC_VER>=1600)
-        /* Windows Visual Studio 9 and below do not have stdint.h & inttypes.h, but VS 2010 adds them. */
-#       define U_HAVE_STDINT_H 1
-#   else
-#       define U_HAVE_STDINT_H 0
-#   endif
-#elif U_PLATFORM == U_PF_SOLARIS
-    /* Solaris has inttypes.h but not stdint.h. */
-#   define U_HAVE_STDINT_H 0
-#elif U_PLATFORM == U_PF_AIX && !defined(_AIX51) && defined(_POWER)
-    /* PPC AIX <= 4.3 has inttypes.h but not stdint.h. */
-#   define U_HAVE_STDINT_H 0
-#else
-#   define U_HAVE_STDINT_H 1
-#endif
-
-/**
- * \def U_HAVE_INTTYPES_H
- * Defines whether inttypes.h is available. It is a C99 standard header.
- * We include inttypes.h where it is available but stdint.h is not.
- * @internal
- */
-#ifdef U_HAVE_INTTYPES_H
-    /* Use the predefined value. */
-#elif U_PLATFORM == U_PF_SOLARIS
-    /* Solaris has inttypes.h but not stdint.h. */
-#   define U_HAVE_INTTYPES_H 1
-#elif U_PLATFORM == U_PF_AIX && !defined(_AIX51) && defined(_POWER)
-    /* PPC AIX <= 4.3 has inttypes.h but not stdint.h. */
-#   define U_HAVE_INTTYPES_H 1
-#else
-    /* Most platforms have both inttypes.h and stdint.h, or neither. */
-#   define U_HAVE_INTTYPES_H U_HAVE_STDINT_H
-#endif
-
-/*===========================================================================*/
-/** @{ Compiler and environment features                                     */
-/*===========================================================================*/
-
-/**
- * \def U_GCC_MAJOR_MINOR
- * Indicates whether the compiler is gcc (test for != 0),
- * and if so, contains its major (times 100) and minor version numbers.
- * If the compiler is not gcc, then U_GCC_MAJOR_MINOR == 0.
- *
- * For example, for testing for whether we have gcc, and whether it's 4.6 or higher,
- * use "#if U_GCC_MAJOR_MINOR >= 406".
- * @internal
- */
-#ifdef __GNUC__
-#   define U_GCC_MAJOR_MINOR (__GNUC__ * 100 + __GNUC_MINOR__)
-#else
-#   define U_GCC_MAJOR_MINOR 0
-#endif
-
-/**
- * \def U_IS_BIG_ENDIAN
- * Determines the endianness of the platform.
- * @internal
- */
-#ifdef U_IS_BIG_ENDIAN
-    /* Use the predefined value. */
-#elif defined(BYTE_ORDER) && defined(BIG_ENDIAN)
-#   define U_IS_BIG_ENDIAN (BYTE_ORDER == BIG_ENDIAN)
-#elif defined(__BYTE_ORDER__) && defined(__ORDER_BIG_ENDIAN__)
-    /* gcc */
-#   define U_IS_BIG_ENDIAN (__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__)
-#elif defined(__BIG_ENDIAN__) || defined(_BIG_ENDIAN)
-#   define U_IS_BIG_ENDIAN 1
-#elif defined(__LITTLE_ENDIAN__) || defined(_LITTLE_ENDIAN)
-#   define U_IS_BIG_ENDIAN 0
-#elif U_PLATFORM == U_PF_OS390 || U_PLATFORM == U_PF_OS400 || defined(__s390__) || defined(__s390x__)
-    /* These platforms do not appear to predefine any endianness macros. */
-#   define U_IS_BIG_ENDIAN 1
-#elif defined(_PA_RISC1_0) || defined(_PA_RISC1_1) || defined(_PA_RISC2_0)
-    /* HPPA do not appear to predefine any endianness macros. */
-#   define U_IS_BIG_ENDIAN 1
-#elif defined(sparc) || defined(__sparc) || defined(__sparc__)
-    /* Some sparc based systems (e.g. Linux) do not predefine any endianness macros. */
-#   define U_IS_BIG_ENDIAN 1
-#else
-#   define U_IS_BIG_ENDIAN 0
-#endif
-
-/**
- * \def U_HAVE_PLACEMENT_NEW
- * Determines whether to override placement new and delete for STL.
- * @stable ICU 2.6
- */
-#ifdef U_HAVE_PLACEMENT_NEW
-    /* Use the predefined value. */
-#elif defined(__BORLANDC__)
-#   define U_HAVE_PLACEMENT_NEW 0
-#else
-#   define U_HAVE_PLACEMENT_NEW 1
-#endif
-
-/**
- * \def U_HAVE_DEBUG_LOCATION_NEW 
- * Define this to define the MFC debug version of the operator new.
- *
- * @stable ICU 3.4
- */
-#ifdef U_HAVE_DEBUG_LOCATION_NEW
-    /* Use the predefined value. */
-#elif defined(_MSC_VER)
-#   define U_HAVE_DEBUG_LOCATION_NEW 1
-#else
-#   define U_HAVE_DEBUG_LOCATION_NEW 0
-#endif
-
-/* Compatibility with compilers other than clang: http://clang.llvm.org/docs/LanguageExtensions.html */
-#ifdef __has_attribute
-#   define UPRV_HAS_ATTRIBUTE(x) __has_attribute(x)
-#else
-#   define UPRV_HAS_ATTRIBUTE(x) 0
-#endif
-#ifdef __has_cpp_attribute
-#   define UPRV_HAS_CPP_ATTRIBUTE(x) __has_cpp_attribute(x)
-#else
-#   define UPRV_HAS_CPP_ATTRIBUTE(x) 0
-#endif
-#ifdef __has_declspec_attribute
-#   define UPRV_HAS_DECLSPEC_ATTRIBUTE(x) __has_declspec_attribute(x)
-#else
-#   define UPRV_HAS_DECLSPEC_ATTRIBUTE(x) 0
-#endif
-#ifdef __has_builtin
-#   define UPRV_HAS_BUILTIN(x) __has_builtin(x)
-#else
-#   define UPRV_HAS_BUILTIN(x) 0
-#endif
-#ifdef __has_feature
-#   define UPRV_HAS_FEATURE(x) __has_feature(x)
-#else
-#   define UPRV_HAS_FEATURE(x) 0
-#endif
-#ifdef __has_extension
-#   define UPRV_HAS_EXTENSION(x) __has_extension(x)
-#else
-#   define UPRV_HAS_EXTENSION(x) 0
-#endif
-#ifdef __has_warning
-#   define UPRV_HAS_WARNING(x) __has_warning(x)
-#else
-#   define UPRV_HAS_WARNING(x) 0
-#endif
-
-/**
- * \def U_MALLOC_ATTR
- * Attribute to mark functions as malloc-like
- * @internal
- */
-#if defined(__GNUC__) && __GNUC__>=3
-#    define U_MALLOC_ATTR __attribute__ ((__malloc__))
-#else
-#    define U_MALLOC_ATTR
-#endif
-
-/**
- * \def U_ALLOC_SIZE_ATTR
- * Attribute to specify the size of the allocated buffer for malloc-like functions
- * @internal
- */
-#if (defined(__GNUC__) &&                                            \
-        (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3))) || \
-        UPRV_HAS_ATTRIBUTE(alloc_size)
-#   define U_ALLOC_SIZE_ATTR(X) __attribute__ ((alloc_size(X)))
-#   define U_ALLOC_SIZE_ATTR2(X,Y) __attribute__ ((alloc_size(X,Y)))
-#else
-#   define U_ALLOC_SIZE_ATTR(X)
-#   define U_ALLOC_SIZE_ATTR2(X,Y)
-#endif
-
-/**
- * \def U_CPLUSPLUS_VERSION
- * 0 if no C++; 1, 11, 14, ... if C++.
- * Support for specific features cannot always be determined by the C++ version alone.
- * @internal
- */
-#ifdef U_CPLUSPLUS_VERSION
-#   if U_CPLUSPLUS_VERSION != 0 && !defined(__cplusplus)
-#       undef U_CPLUSPLUS_VERSION
-#       define U_CPLUSPLUS_VERSION 0
-#   endif
-    /* Otherwise use the predefined value. */
-#elif !defined(__cplusplus)
-#   define U_CPLUSPLUS_VERSION 0
-#elif __cplusplus >= 201402L || (defined(_MSVC_LANG) && _MSVC_LANG >= 201402L)
-#   define U_CPLUSPLUS_VERSION 14
-#elif __cplusplus >= 201103L || (defined(_MSVC_LANG) && _MSVC_LANG >= 201103L)
-#   define U_CPLUSPLUS_VERSION 11
-#else
-    // C++98 or C++03
-#   define U_CPLUSPLUS_VERSION 1
-#endif
-
-#if (U_PLATFORM == U_PF_AIX || U_PLATFORM == U_PF_OS390) && defined(__cplusplus) &&(U_CPLUSPLUS_VERSION < 11)
-// add in std::nullptr_t
-namespace std {
-  typedef decltype(nullptr) nullptr_t;
-};
-#endif
-
-/**
- * \def U_NOEXCEPT
- * "noexcept" if supported, otherwise empty.
- * Some code, especially STL containers, uses move semantics of objects only
- * if the move constructor and the move operator are declared as not throwing exceptions.
- * @internal
- */
-#ifdef U_NOEXCEPT
-    /* Use the predefined value. */
-#else
-#   define U_NOEXCEPT noexcept
-#endif
-
-/**
- * \def U_FALLTHROUGH
- * Annotate intentional fall-through between switch labels.
- * http://clang.llvm.org/docs/AttributeReference.html#fallthrough-clang-fallthrough
- * @internal
- */
-#ifndef __cplusplus
-    // Not for C.
-#elif defined(U_FALLTHROUGH)
-    // Use the predefined value.
-#elif defined(__clang__)
-    // Test for compiler vs. feature separately.
-    // Other compilers might choke on the feature test.
-#    if UPRV_HAS_CPP_ATTRIBUTE(clang::fallthrough) || \
-             (UPRV_HAS_FEATURE(cxx_attributes) &&     \
-             UPRV_HAS_WARNING("-Wimplicit-fallthrough"))
-#       define U_FALLTHROUGH [[clang::fallthrough]]
-#   endif
-#elif defined(__GNUC__) && (__GNUC__ >= 7)
-#   define U_FALLTHROUGH __attribute__((fallthrough))
-#endif
-
-#ifndef U_FALLTHROUGH
-#   define U_FALLTHROUGH
-#endif
-
-/** @} */
-
-/*===========================================================================*/
-/** @{ Character data types                                                  */
-/*===========================================================================*/
-
-/**
- * U_CHARSET_FAMILY is equal to this value when the platform is an ASCII based platform.
- * @stable ICU 2.0
- */
-#define U_ASCII_FAMILY 0
-
-/**
- * U_CHARSET_FAMILY is equal to this value when the platform is an EBCDIC based platform.
- * @stable ICU 2.0
- */
-#define U_EBCDIC_FAMILY 1
-
-/**
- * \def U_CHARSET_FAMILY
- *
- * <p>These definitions allow to specify the encoding of text
- * in the char data type as defined by the platform and the compiler.
- * It is enough to determine the code point values of "invariant characters",
- * which are the ones shared by all encodings that are in use
- * on a given platform.</p>
- *
- * <p>Those "invariant characters" should be all the uppercase and lowercase
- * latin letters, the digits, the space, and "basic punctuation".
- * Also, '\\n', '\\r', '\\t' should be available.</p>
- *
- * <p>The list of "invariant characters" is:<br>
- * \code
- *    A-Z  a-z  0-9  SPACE  "  %  &amp;  '  (  )  *  +  ,  -  .  /  :  ;  <  =  >  ?  _
- * \endcode
- * <br>
- * (52 letters + 10 numbers + 20 punc/sym/space = 82 total)</p>
- *
- * <p>This matches the IBM Syntactic Character Set (CS 640).</p>
- *
- * <p>In other words, all the graphic characters in 7-bit ASCII should
- * be safely accessible except the following:</p>
- *
- * \code
- *    '\' <backslash>
- *    '[' <left bracket>
- *    ']' <right bracket>
- *    '{' <left brace>
- *    '}' <right brace>
- *    '^' <circumflex>
- *    '~' <tilde>
- *    '!' <exclamation mark>
- *    '#' <number sign>
- *    '|' <vertical line>
- *    '$' <dollar sign>
- *    '@' <commercial at>
- *    '`' <grave accent>
- * \endcode
- * @stable ICU 2.0
- */
-#ifdef U_CHARSET_FAMILY
-    /* Use the predefined value. */
-#elif U_PLATFORM == U_PF_OS390 && (!defined(__CHARSET_LIB) || !__CHARSET_LIB)
-#   define U_CHARSET_FAMILY U_EBCDIC_FAMILY
-#elif U_PLATFORM == U_PF_OS400 && !defined(__UTF32__)
-#   define U_CHARSET_FAMILY U_EBCDIC_FAMILY
-#else
-#   define U_CHARSET_FAMILY U_ASCII_FAMILY
-#endif
-
-/**
- * \def U_CHARSET_IS_UTF8
- *
- * Hardcode the default charset to UTF-8.
- *
- * If this is set to 1, then
- * - ICU will assume that all non-invariant char*, StringPiece, std::string etc.
- *   contain UTF-8 text, regardless of what the system API uses
- * - some ICU code will use fast functions like u_strFromUTF8()
- *   rather than the more general and more heavy-weight conversion API (ucnv.h)
- * - ucnv_getDefaultName() always returns "UTF-8"
- * - ucnv_setDefaultName() is disabled and will not change the default charset
- * - static builds of ICU are smaller
- * - more functionality is available with the UCONFIG_NO_CONVERSION build-time
- *   configuration option (see unicode/uconfig.h)
- * - the UCONFIG_NO_CONVERSION build option in uconfig.h is more usable
- *
- * @stable ICU 4.2
- * @see UCONFIG_NO_CONVERSION
- */
-#ifdef U_CHARSET_IS_UTF8
-    /* Use the predefined value. */
-#elif U_PLATFORM_IS_LINUX_BASED || U_PLATFORM_IS_DARWIN_BASED || \
-        U_PLATFORM == U_PF_EMSCRIPTEN
-#   define U_CHARSET_IS_UTF8 1
-#else
-#   define U_CHARSET_IS_UTF8 0
-#endif
-
-/** @} */
-
-/*===========================================================================*/
-/** @{ Information about wchar support                                       */
-/*===========================================================================*/
-
-/**
- * \def U_HAVE_WCHAR_H
- * Indicates whether <wchar.h> is available (1) or not (0). Set to 1 by default.
- *
- * @stable ICU 2.0
- */
-#ifdef U_HAVE_WCHAR_H
-    /* Use the predefined value. */
-#elif U_PLATFORM == U_PF_ANDROID && __ANDROID_API__ < 9
-    /*
-     * Android before Gingerbread (Android 2.3, API level 9) did not support wchar_t.
-     * The type and header existed, but the library functions did not work as expected.
-     * The size of wchar_t was 1 but L"xyz" string literals had 32-bit units anyway.
-     */
-#   define U_HAVE_WCHAR_H 0
-#else
-#   define U_HAVE_WCHAR_H 1
-#endif
-
-/**
- * \def U_SIZEOF_WCHAR_T
- * U_SIZEOF_WCHAR_T==sizeof(wchar_t)
- *
- * @stable ICU 2.0
- */
-#ifdef U_SIZEOF_WCHAR_T
-    /* Use the predefined value. */
-#elif (U_PLATFORM == U_PF_ANDROID && __ANDROID_API__ < 9)
-    /*
-     * Classic Mac OS and Mac OS X before 10.3 (Panther) did not support wchar_t or wstring.
-     * Newer Mac OS X has size 4.
-     */
-#   define U_SIZEOF_WCHAR_T 1
-#elif U_PLATFORM_HAS_WIN32_API || U_PLATFORM == U_PF_CYGWIN
-#   define U_SIZEOF_WCHAR_T 2
-#elif U_PLATFORM == U_PF_AIX
-    /*
-     * AIX 6.1 information, section "Wide character data representation":
-     * "... the wchar_t datatype is 32-bit in the 64-bit environment and
-     * 16-bit in the 32-bit environment."
-     * and
-     * "All locales use Unicode for their wide character code values (process code),
-     * except the IBM-eucTW codeset."
-     */
-#   ifdef __64BIT__
-#       define U_SIZEOF_WCHAR_T 4
-#   else
-#       define U_SIZEOF_WCHAR_T 2
-#   endif
-#elif U_PLATFORM == U_PF_OS390
-    /*
-     * z/OS V1R11 information center, section "LP64 | ILP32":
-     * "In 31-bit mode, the size of long and pointers is 4 bytes and the size of wchar_t is 2 bytes.
-     * Under LP64, the size of long and pointer is 8 bytes and the size of wchar_t is 4 bytes."
-     */
-#   ifdef _LP64
-#       define U_SIZEOF_WCHAR_T 4
-#   else
-#       define U_SIZEOF_WCHAR_T 2
-#   endif
-#elif U_PLATFORM == U_PF_OS400
-#   if defined(__UTF32__)
-        /*
-         * LOCALETYPE(*LOCALEUTF) is specified.
-         * Wide-character strings are in UTF-32,
-         * narrow-character strings are in UTF-8.
-         */
-#       define U_SIZEOF_WCHAR_T 4
-#   elif defined(__UCS2__)
-        /*
-         * LOCALETYPE(*LOCALEUCS2) is specified.
-         * Wide-character strings are in UCS-2,
-         * narrow-character strings are in EBCDIC.
-         */
-#       define U_SIZEOF_WCHAR_T 2
-#   else
-        /*
-         * LOCALETYPE(*CLD) or LOCALETYPE(*LOCALE) is specified.
-         * Wide-character strings are in 16-bit EBCDIC,
-         * narrow-character strings are in EBCDIC.
-         */
-#       define U_SIZEOF_WCHAR_T 2
-#   endif
-#else
-#   define U_SIZEOF_WCHAR_T 4
-#endif
-
-#ifndef U_HAVE_WCSCPY
-#define U_HAVE_WCSCPY U_HAVE_WCHAR_H
-#endif
-
-/** @} */
-
-/**
- * \def U_HAVE_CHAR16_T
- * Defines whether the char16_t type is available for UTF-16
- * and u"abc" UTF-16 string literals are supported.
- * This is a new standard type and standard string literal syntax in C++0x
- * but has been available in some compilers before.
- * @internal
- */
-#ifdef U_HAVE_CHAR16_T
-    /* Use the predefined value. */
-#else
-    /*
-     * Notes:
-     * Visual Studio 2010 (_MSC_VER==1600) defines char16_t as a typedef
-     * and does not support u"abc" string literals.
-     * Visual Studio 2015 (_MSC_VER>=1900) and above adds support for
-     * both char16_t and u"abc" string literals.
-     * gcc 4.4 defines the __CHAR16_TYPE__ macro to a usable type but
-     * does not support u"abc" string literals.
-     * C++11 and C11 require support for UTF-16 literals
-     * TODO: Fix for plain C. Doesn't work on Mac.
-     */
-#   if U_CPLUSPLUS_VERSION >= 11 || (defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L)
-#       define U_HAVE_CHAR16_T 1
-#   else
-#       define U_HAVE_CHAR16_T 0
-#   endif
-#endif
-
-/**
- * @{
- * \def U_DECLARE_UTF16
- * Do not use this macro because it is not defined on all platforms.
- * Use the UNICODE_STRING or U_STRING_DECL macros instead.
- * @internal
- */
-#ifdef U_DECLARE_UTF16
-    /* Use the predefined value. */
-#elif U_HAVE_CHAR16_T \
-    || (defined(__xlC__) && defined(__IBM_UTF_LITERAL) && U_SIZEOF_WCHAR_T != 2) \
-    || (defined(__HP_aCC) && __HP_aCC >= 035000) \
-    || (defined(__HP_cc) && __HP_cc >= 111106) \
-    || (defined(U_IN_DOXYGEN))
-#   define U_DECLARE_UTF16(string) u ## string
-#elif U_SIZEOF_WCHAR_T == 2 \
-    && (U_CHARSET_FAMILY == 0 || (U_PF_OS390 <= U_PLATFORM && U_PLATFORM <= U_PF_OS400 && defined(__UCS2__)))
-#   define U_DECLARE_UTF16(string) L ## string
-#else
-    /* Leave U_DECLARE_UTF16 undefined. See unistr.h. */
-#endif
-
-/** @} */
-
-/*===========================================================================*/
-/** @{ Symbol import-export control                                          */
-/*===========================================================================*/
-
-#ifdef U_EXPORT
-    /* Use the predefined value. */
-#elif defined(U_STATIC_IMPLEMENTATION)
-#   define U_EXPORT
-#elif defined(_MSC_VER) || (UPRV_HAS_DECLSPEC_ATTRIBUTE(dllexport) && \
-                            UPRV_HAS_DECLSPEC_ATTRIBUTE(dllimport))
-#   define U_EXPORT __declspec(dllexport)
-#elif defined(__GNUC__)
-#   define U_EXPORT __attribute__((visibility("default")))
-#elif (defined(__SUNPRO_CC) && __SUNPRO_CC >= 0x550) \
-   || (defined(__SUNPRO_C) && __SUNPRO_C >= 0x550) 
-#   define U_EXPORT __global
-/*#elif defined(__HP_aCC) || defined(__HP_cc)
-#   define U_EXPORT __declspec(dllexport)*/
-#else
-#   define U_EXPORT
-#endif
-
-/* U_CALLCONV is related to U_EXPORT2 */
-#ifdef U_EXPORT2
-    /* Use the predefined value. */
-#elif defined(_MSC_VER)
-#   define U_EXPORT2 __cdecl
-#else
-#   define U_EXPORT2
-#endif
-
-#ifdef U_IMPORT
-    /* Use the predefined value. */
-#elif defined(_MSC_VER) || (UPRV_HAS_DECLSPEC_ATTRIBUTE(dllexport) && \
-                            UPRV_HAS_DECLSPEC_ATTRIBUTE(dllimport))
-    /* Windows needs to export/import data. */
-#   define U_IMPORT __declspec(dllimport)
-#else
-#   define U_IMPORT 
-#endif
-
-/**
- * \def U_CALLCONV
- * Similar to U_CDECL_BEGIN/U_CDECL_END, this qualifier is necessary
- * in callback function typedefs to make sure that the calling convention
- * is compatible.
- *
- * This is only used for non-ICU-API functions.
- * When a function is a public ICU API,
- * you must use the U_CAPI and U_EXPORT2 qualifiers.
- *
- * Please note, you need to use U_CALLCONV after the *.
- *
- * NO : "static const char U_CALLCONV *func( . . . )"
- * YES: "static const char* U_CALLCONV func( . . . )"
- *
- * @stable ICU 2.0
- */
-#if U_PLATFORM == U_PF_OS390 && defined(__cplusplus)
-#    define U_CALLCONV __cdecl
-#else
-#    define U_CALLCONV U_EXPORT2
-#endif
-
-/**
- * \def U_CALLCONV_FPTR
- * Similar to U_CALLCONV, but only used on function pointers.
- * @internal
- */
-#if U_PLATFORM == U_PF_OS390 && defined(__cplusplus)
-#    define U_CALLCONV_FPTR U_CALLCONV
-#else
-#    define U_CALLCONV_FPTR
-#endif
-/** @} */
-
-#endif  // _PLATFORM_H

app/src/main/cpp/icu4c/include/unicode/ptypes.h

@@ -1,130 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-******************************************************************************
-*
-*   Copyright (C) 1997-2012, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-******************************************************************************
-*
-*  FILE NAME : ptypes.h
-*
-*   Date        Name        Description
-*   05/13/98    nos         Creation (content moved here from ptypes.h).
-*   03/02/99    stephen     Added AS400 support.
-*   03/30/99    stephen     Added Linux support.
-*   04/13/99    stephen     Reworked for autoconf.
-*   09/18/08    srl         Moved basic types back to ptypes.h from platform.h
-******************************************************************************
-*/
-
-/**
- * \file
- * \brief C API: Definitions of integer types of various widths
- */
-
-#ifndef _PTYPES_H
-#define _PTYPES_H
-
-/**
- * \def __STDC_LIMIT_MACROS
- * According to the Linux stdint.h, the ISO C99 standard specifies that in C++ implementations
- * macros like INT32_MIN and UINTPTR_MAX should only be defined if explicitly requested.
- * We need to define __STDC_LIMIT_MACROS before including stdint.h in C++ code
- * that uses such limit macros.
- * @internal
- */
-#ifndef __STDC_LIMIT_MACROS
-#define __STDC_LIMIT_MACROS
-#endif
-
-/* NULL, size_t, wchar_t */
-#include <stddef.h>
-
-/*
- * If all compilers provided all of the C99 headers and types,
- * we would just unconditionally #include <stdint.h> here
- * and not need any of the stuff after including platform.h.
- */
-
-/* Find out if we have stdint.h etc. */
-#include "unicode/platform.h"
-
-/*===========================================================================*/
-/* Generic data types                                                        */
-/*===========================================================================*/
-
-/* If your platform does not have the <stdint.h> header, you may
-   need to edit the typedefs in the #else section below.
-   Use #if...#else...#endif with predefined compiler macros if possible. */
-#if U_HAVE_STDINT_H
-
-/*
- * We mostly need <stdint.h> (which defines the standard integer types) but not <inttypes.h>.
- * <inttypes.h> includes <stdint.h> and adds the printf/scanf helpers PRId32, SCNx16 etc.
- * which we almost never use, plus stuff like imaxabs() which we never use.
- */
-#include <stdint.h>
-
-#if U_PLATFORM == U_PF_OS390
-/* The features header is needed to get (u)int64_t sometimes. */
-#include <features.h>
-/* z/OS has <stdint.h>, but some versions are missing uint8_t (APAR PK62248). */
-#if !defined(__uint8_t)
-#define __uint8_t 1
-typedef unsigned char uint8_t;
-#endif
-#endif /* U_PLATFORM == U_PF_OS390 */
-
-#elif U_HAVE_INTTYPES_H
-
-#   include <inttypes.h>
-
-#else /* neither U_HAVE_STDINT_H nor U_HAVE_INTTYPES_H */
-
-/// \cond
-#if ! U_HAVE_INT8_T
-typedef signed char int8_t;
-#endif
-
-#if ! U_HAVE_UINT8_T
-typedef unsigned char uint8_t;
-#endif
-
-#if ! U_HAVE_INT16_T
-typedef signed short int16_t;
-#endif
-
-#if ! U_HAVE_UINT16_T
-typedef unsigned short uint16_t;
-#endif
-
-#if ! U_HAVE_INT32_T
-typedef signed int int32_t;
-#endif
-
-#if ! U_HAVE_UINT32_T
-typedef unsigned int uint32_t;
-#endif
-
-#if ! U_HAVE_INT64_T
-#ifdef _MSC_VER
-    typedef signed __int64 int64_t;
-#else
-    typedef signed long long int64_t;
-#endif
-#endif
-
-#if ! U_HAVE_UINT64_T
-#ifdef _MSC_VER
-    typedef unsigned __int64 uint64_t;
-#else
-    typedef unsigned long long uint64_t;
-#endif
-#endif
-/// \endcond
-
-#endif /* U_HAVE_STDINT_H / U_HAVE_INTTYPES_H */
-
-#endif /* _PTYPES_H */

app/src/main/cpp/icu4c/include/unicode/putil.h

@@ -1,183 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-******************************************************************************
-*
-*   Copyright (C) 1997-2014, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-******************************************************************************
-*
-*  FILE NAME : putil.h
-*
-*   Date        Name        Description
-*   05/14/98    nos         Creation (content moved here from utypes.h).
-*   06/17/99    erm         Added IEEE_754
-*   07/22/98    stephen     Added IEEEremainder, max, min, trunc
-*   08/13/98    stephen     Added isNegativeInfinity, isPositiveInfinity
-*   08/24/98    stephen     Added longBitsFromDouble
-*   03/02/99    stephen     Removed openFile().  Added AS400 support.
-*   04/15/99    stephen     Converted to C
-*   11/15/99    helena      Integrated S/390 changes for IEEE support.
-*   01/11/00    helena      Added u_getVersion.
-******************************************************************************
-*/
-
-#ifndef PUTIL_H
-#define PUTIL_H
-
-#include "unicode/utypes.h"
- /**
-  * \file
-  * \brief C API: Platform Utilities
-  */
-
-/*==========================================================================*/
-/* Platform utilities                                                       */
-/*==========================================================================*/
-
-/**
- * Platform utilities isolates the platform dependencies of the
- * library.  For each platform which this code is ported to, these
- * functions may have to be re-implemented.
- */
-
-/**
- * Return the ICU data directory. 
- * The data directory is where common format ICU data files (.dat files)
- *   are loaded from.  Note that normal use of the built-in ICU
- *   facilities does not require loading of an external data file;
- *   unless you are adding custom data to ICU, the data directory
- *   does not need to be set.
- *
- * The data directory is determined as follows:
- *    If u_setDataDirectory() has been called, that is it, otherwise
- *    if the ICU_DATA environment variable is set, use that, otherwise
- *    If a data directory was specified at ICU build time
- *      <code>
- * \code
- *        #define ICU_DATA_DIR "path" 
- * \endcode
- * </code> use that,
- *    otherwise no data directory is available.
- *
- * @return the data directory, or an empty string ("") if no data directory has
- *         been specified.
- *   
- * @stable ICU 2.0
- */
-U_CAPI const char* U_EXPORT2 u_getDataDirectory(void);
-
-
-/** 
- * Set the ICU data directory. 
- * The data directory is where common format ICU data files (.dat files)
- *   are loaded from.  Note that normal use of the built-in ICU
- *   facilities does not require loading of an external data file;
- *   unless you are adding custom data to ICU, the data directory
- *   does not need to be set.
- *
- * This function should be called at most once in a process, before the
- * first ICU operation (e.g., u_init()) that will require the loading of an
- * ICU data file.
- * This function is not thread-safe. Use it before calling ICU APIs from
- * multiple threads.
- *
- * @param directory The directory to be set.
- *
- * @see u_init
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2 u_setDataDirectory(const char *directory);
-
-#ifndef U_HIDE_INTERNAL_API
-/**
-  * Return the time zone files override directory, or an empty string if
-  * no directory was specified. Certain time zone resources will be preferentially
-  * loaded from individual files in this directory.
-  *
-  * @return the time zone data override directory.
-  * @internal
-  */ 
-U_CAPI const char * U_EXPORT2 u_getTimeZoneFilesDirectory(UErrorCode *status);
-
-/**
-  * Set the time zone files override directory.
-  * This function is not thread safe; it must not be called concurrently with
-  *   u_getTimeZoneFilesDirectory() or any other use of ICU time zone functions.
-  * This function should only be called before using any ICU service that
-  *   will access the time zone data.
-  * @internal
-  */
-U_CAPI void U_EXPORT2 u_setTimeZoneFilesDirectory(const char *path, UErrorCode *status);
-#endif  /* U_HIDE_INTERNAL_API */
-
-
-/**
- * @{
- * Filesystem file and path separator characters.
- * Example: '/' and ':' on Unix, '\\' and ';' on Windows.
- * @stable ICU 2.0
- */
-#if U_PLATFORM_USES_ONLY_WIN32_API
-#   define U_FILE_SEP_CHAR '\\'
-#   define U_FILE_ALT_SEP_CHAR '/'
-#   define U_PATH_SEP_CHAR ';'
-#   define U_FILE_SEP_STRING "\\"
-#   define U_FILE_ALT_SEP_STRING "/"
-#   define U_PATH_SEP_STRING ";"
-#else
-#   define U_FILE_SEP_CHAR '/'
-#   define U_FILE_ALT_SEP_CHAR '/'
-#   define U_PATH_SEP_CHAR ':'
-#   define U_FILE_SEP_STRING "/"
-#   define U_FILE_ALT_SEP_STRING "/"
-#   define U_PATH_SEP_STRING ":"
-#endif
-
-/** @} */
-
-/**
- * Convert char characters to UChar characters.
- * This utility function is useful only for "invariant characters"
- * that are encoded in the platform default encoding.
- * They are a small, constant subset of the encoding and include
- * just the latin letters, digits, and some punctuation.
- * For details, see U_CHARSET_FAMILY.
- *
- * @param cs Input string, points to <code>length</code>
- *           character bytes from a subset of the platform encoding.
- * @param us Output string, points to memory for <code>length</code>
- *           Unicode characters.
- * @param length The number of characters to convert; this may
- *               include the terminating <code>NUL</code>.
- *
- * @see U_CHARSET_FAMILY
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2
-u_charsToUChars(const char *cs, UChar *us, int32_t length);
-
-/**
- * Convert UChar characters to char characters.
- * This utility function is useful only for "invariant characters"
- * that can be encoded in the platform default encoding.
- * They are a small, constant subset of the encoding and include
- * just the latin letters, digits, and some punctuation.
- * For details, see U_CHARSET_FAMILY.
- *
- * @param us Input string, points to <code>length</code>
- *           Unicode characters that can be encoded with the
- *           codepage-invariant subset of the platform encoding.
- * @param cs Output string, points to memory for <code>length</code>
- *           character bytes.
- * @param length The number of characters to convert; this may
- *               include the terminating <code>NUL</code>.
- *
- * @see U_CHARSET_FAMILY
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2
-u_UCharsToChars(const UChar *us, char *cs, int32_t length);
-
-#endif

app/src/main/cpp/icu4c/include/unicode/rep.h

@@ -1,266 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-**************************************************************************
-* Copyright (C) 1999-2012, International Business Machines Corporation and
-* others. All Rights Reserved.
-**************************************************************************
-*   Date        Name        Description
-*   11/17/99    aliu        Creation.  Ported from java.  Modified to
-*                           match current UnicodeString API.  Forced
-*                           to use name "handleReplaceBetween" because
-*                           of existing methods in UnicodeString.
-**************************************************************************
-*/
-
-#ifndef REP_H
-#define REP_H
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-
-#include "unicode/uobject.h"
-
-/**
- * \file 
- * \brief C++ API: Replaceable String
- */
- 
-U_NAMESPACE_BEGIN
-
-class UnicodeString;
-
-/**
- * <code>Replaceable</code> is an abstract base class representing a
- * string of characters that supports the replacement of a range of
- * itself with a new string of characters.  It is used by APIs that
- * change a piece of text while retaining metadata.  Metadata is data
- * other than the Unicode characters returned by char32At().  One
- * example of metadata is style attributes; another is an edit
- * history, marking each character with an author and revision number.
- *
- * <p>An implicit aspect of the <code>Replaceable</code> API is that
- * during a replace operation, new characters take on the metadata of
- * the old characters.  For example, if the string "the <b>bold</b>
- * font" has range (4, 8) replaced with "strong", then it becomes "the
- * <b>strong</b> font".
- *
- * <p><code>Replaceable</code> specifies ranges using a start
- * offset and a limit offset.  The range of characters thus specified
- * includes the characters at offset start..limit-1.  That is, the
- * start offset is inclusive, and the limit offset is exclusive.
- *
- * <p><code>Replaceable</code> also includes API to access characters
- * in the string: <code>length()</code>, <code>charAt()</code>,
- * <code>char32At()</code>, and <code>extractBetween()</code>.
- *
- * <p>For a subclass to support metadata, typical behavior of
- * <code>replace()</code> is the following:
- * <ul>
- *   <li>Set the metadata of the new text to the metadata of the first
- *   character replaced</li>
- *   <li>If no characters are replaced, use the metadata of the
- *   previous character</li>
- *   <li>If there is no previous character (i.e. start == 0), use the
- *   following character</li>
- *   <li>If there is no following character (i.e. the replaceable was
- *   empty), use default metadata.<br>
- *   <li>If the code point U+FFFF is seen, it should be interpreted as
- *   a special marker having no metadata<li>
- *   </li>
- * </ul>
- * If this is not the behavior, the subclass should document any differences.
- * @author Alan Liu
- * @stable ICU 2.0
- */
-class U_COMMON_API Replaceable : public UObject {
-
-public:
-    /**
-     * Destructor.
-     * @stable ICU 2.0
-     */
-    virtual ~Replaceable();
-
-    /**
-     * Returns the number of 16-bit code units in the text.
-     * @return number of 16-bit code units in text
-     * @stable ICU 1.8
-     */ 
-    inline int32_t length() const;
-
-    /**
-     * Returns the 16-bit code unit at the given offset into the text.
-     * @param offset an integer between 0 and <code>length()</code>-1
-     * inclusive
-     * @return 16-bit code unit of text at given offset
-     * @stable ICU 1.8
-     */
-    inline char16_t charAt(int32_t offset) const;
-
-    /**
-     * Returns the 32-bit code point at the given 16-bit offset into
-     * the text.  This assumes the text is stored as 16-bit code units
-     * with surrogate pairs intermixed.  If the offset of a leading or
-     * trailing code unit of a surrogate pair is given, return the
-     * code point of the surrogate pair.
-     *
-     * @param offset an integer between 0 and <code>length()</code>-1
-     * inclusive
-     * @return 32-bit code point of text at given offset
-     * @stable ICU 1.8
-     */
-    inline UChar32 char32At(int32_t offset) const;
-
-    /**
-     * Copies characters in the range [<tt>start</tt>, <tt>limit</tt>) 
-     * into the UnicodeString <tt>target</tt>.
-     * @param start offset of first character which will be copied
-     * @param limit offset immediately following the last character to
-     * be copied
-     * @param target UnicodeString into which to copy characters.
-     * @return A reference to <TT>target</TT>
-     * @stable ICU 2.1
-     */
-    virtual void extractBetween(int32_t start,
-                                int32_t limit,
-                                UnicodeString& target) const = 0;
-
-    /**
-     * Replaces a substring of this object with the given text.  If the
-     * characters being replaced have metadata, the new characters
-     * that replace them should be given the same metadata.
-     *
-     * <p>Subclasses must ensure that if the text between start and
-     * limit is equal to the replacement text, that replace has no
-     * effect. That is, any metadata
-     * should be unaffected. In addition, subclasses are encouraged to
-     * check for initial and trailing identical characters, and make a
-     * smaller replacement if possible. This will preserve as much
-     * metadata as possible.
-     * @param start the beginning index, inclusive; <code>0 <= start
-     * <= limit</code>.
-     * @param limit the ending index, exclusive; <code>start <= limit
-     * <= length()</code>.
-     * @param text the text to replace characters <code>start</code>
-     * to <code>limit - 1</code> 
-     * @stable ICU 2.0
-     */
-    virtual void handleReplaceBetween(int32_t start,
-                                      int32_t limit,
-                                      const UnicodeString& text) = 0;
-    // Note: All other methods in this class take the names of
-    // existing UnicodeString methods.  This method is the exception.
-    // It is named differently because all replace methods of
-    // UnicodeString return a UnicodeString&.  The 'between' is
-    // required in order to conform to the UnicodeString naming
-    // convention; API taking start/length are named <operation>, and
-    // those taking start/limit are named <operationBetween>.  The
-    // 'handle' is added because 'replaceBetween' and
-    // 'doReplaceBetween' are already taken.
-
-    /**
-     * Copies a substring of this object, retaining metadata.
-     * This method is used to duplicate or reorder substrings.
-     * The destination index must not overlap the source range.
-     * 
-     * @param start the beginning index, inclusive; <code>0 <= start <=
-     * limit</code>.
-     * @param limit the ending index, exclusive; <code>start <= limit <=
-     * length()</code>.
-     * @param dest the destination index.  The characters from
-     * <code>start..limit-1</code> will be copied to <code>dest</code>.
-     * Implementations of this method may assume that <code>dest <= start ||
-     * dest >= limit</code>.
-     * @stable ICU 2.0
-     */
-    virtual void copy(int32_t start, int32_t limit, int32_t dest) = 0;
-
-    /**
-     * Returns true if this object contains metadata.  If a
-     * Replaceable object has metadata, calls to the Replaceable API
-     * must be made so as to preserve metadata.  If it does not, calls
-     * to the Replaceable API may be optimized to improve performance.
-     * The default implementation returns true.
-     * @return true if this object contains metadata
-     * @stable ICU 2.2
-     */
-    virtual UBool hasMetaData() const;
-
-    /**
-     * Clone this object, an instance of a subclass of Replaceable.
-     * Clones can be used concurrently in multiple threads.
-     * If a subclass does not implement clone(), or if an error occurs,
-     * then NULL is returned.
-     * The caller must delete the clone.
-     *
-     * @return a clone of this object
-     *
-     * @see getDynamicClassID
-     * @stable ICU 2.6
-     */
-    virtual Replaceable *clone() const;
-
-protected:
-
-    /**
-     * Default constructor.
-     * @stable ICU 2.4
-     */
-    inline Replaceable();
-
-    /*
-     * Assignment operator not declared. The compiler will provide one
-     * which does nothing since this class does not contain any data members.
-     * API/code coverage may show the assignment operator as present and
-     * untested - ignore.
-     * Subclasses need this assignment operator if they use compiler-provided
-     * assignment operators of their own. An alternative to not declaring one
-     * here would be to declare and empty-implement a protected or public one.
-    Replaceable &Replaceable::operator=(const Replaceable &);
-     */
-
-    /**
-     * Virtual version of length().
-     * @stable ICU 2.4
-     */ 
-    virtual int32_t getLength() const = 0;
-
-    /**
-     * Virtual version of charAt().
-     * @stable ICU 2.4
-     */
-    virtual char16_t getCharAt(int32_t offset) const = 0;
-
-    /**
-     * Virtual version of char32At().
-     * @stable ICU 2.4
-     */
-    virtual UChar32 getChar32At(int32_t offset) const = 0;
-};
-
-inline Replaceable::Replaceable() {}
-
-inline int32_t
-Replaceable::length() const {
-    return getLength();
-}
-
-inline char16_t
-Replaceable::charAt(int32_t offset) const {
-    return getCharAt(offset);
-}
-
-inline UChar32
-Replaceable::char32At(int32_t offset) const {
-    return getChar32At(offset);
-}
-
-// There is no rep.cpp, see unistr.cpp for Replaceable function implementations.
-
-U_NAMESPACE_END
-
-#endif /* U_SHOW_CPLUSPLUS_API */
-
-#endif

app/src/main/cpp/icu4c/include/unicode/std_string.h

@@ -1,41 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-*******************************************************************************
-*
-*   Copyright (C) 2009-2014, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-*******************************************************************************
-*   file name:  std_string.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:4
-*
-*   created on: 2009feb19
-*   created by: Markus W. Scherer
-*/
-
-#ifndef __STD_STRING_H__
-#define __STD_STRING_H__
-
-/**
- * \file
- * \brief C++ API: Central ICU header for including the C++ standard <string>
- *                 header and for related definitions.
- */
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-
-// Workaround for a libstdc++ bug before libstdc++4.6 (2011).
-// https://bugs.llvm.org/show_bug.cgi?id=13364
-#if defined(__GLIBCXX__)
-namespace std { class type_info; }
-#endif
-#include <string>
-
-#endif /* U_SHOW_CPLUSPLUS_API */
-
-#endif  // __STD_STRING_H__

app/src/main/cpp/icu4c/include/unicode/strenum.h

@@ -1,281 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-*******************************************************************************
-*
-*   Copyright (C) 2002-2012, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-*******************************************************************************
-*/
-
-#ifndef STRENUM_H
-#define STRENUM_H
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-
-#include "unicode/uobject.h"
-#include "unicode/unistr.h"
-
-/**
- * \file 
- * \brief C++ API: String Enumeration
- */
- 
-U_NAMESPACE_BEGIN
-
-/**
- * Base class for 'pure' C++ implementations of uenum api.  Adds a
- * method that returns the next UnicodeString since in C++ this can
- * be a common storage format for strings.
- *
- * <p>The model is that the enumeration is over strings maintained by
- * a 'service.'  At any point, the service might change, invalidating
- * the enumerator (though this is expected to be rare).  The iterator
- * returns an error if this has occurred.  Lack of the error is no
- * guarantee that the service didn't change immediately after the
- * call, so the returned string still might not be 'valid' on
- * subsequent use.</p>
- *
- * <p>Strings may take the form of const char*, const char16_t*, or const
- * UnicodeString*.  The type you get is determine by the variant of
- * 'next' that you call.  In general the StringEnumeration is
- * optimized for one of these types, but all StringEnumerations can
- * return all types.  Returned strings are each terminated with a NUL.
- * Depending on the service data, they might also include embedded NUL
- * characters, so API is provided to optionally return the true
- * length, counting the embedded NULs but not counting the terminating
- * NUL.</p>
- *
- * <p>The pointers returned by next, unext, and snext become invalid
- * upon any subsequent call to the enumeration's destructor, next,
- * unext, snext, or reset.</p>
- *
- * ICU 2.8 adds some default implementations and helper functions
- * for subclasses.
- *
- * @stable ICU 2.4 
- */
-class U_COMMON_API StringEnumeration : public UObject { 
-public:
-    /**
-     * Destructor.
-     * @stable ICU 2.4
-     */
-    virtual ~StringEnumeration();
-
-    /**
-     * Clone this object, an instance of a subclass of StringEnumeration.
-     * Clones can be used concurrently in multiple threads.
-     * If a subclass does not implement clone(), or if an error occurs,
-     * then NULL is returned.
-     * The caller must delete the clone.
-     *
-     * @return a clone of this object
-     *
-     * @see getDynamicClassID
-     * @stable ICU 2.8
-     */
-    virtual StringEnumeration *clone() const;
-
-    /**
-     * <p>Return the number of elements that the iterator traverses.  If
-     * the iterator is out of sync with its service, status is set to
-     * U_ENUM_OUT_OF_SYNC_ERROR, and the return value is zero.</p>
-     *
-     * <p>The return value will not change except possibly as a result of
-     * a subsequent call to reset, or if the iterator becomes out of sync.</p>
-     *
-     * <p>This is a convenience function. It can end up being very
-     * expensive as all the items might have to be pre-fetched
-     * (depending on the storage format of the data being
-     * traversed).</p>
-     *
-     * @param status the error code.
-     * @return number of elements in the iterator.
-     *
-     * @stable ICU 2.4 */
-    virtual int32_t count(UErrorCode& status) const = 0;
-
-    /**
-     * <p>Returns the next element as a NUL-terminated char*.  If there
-     * are no more elements, returns NULL.  If the resultLength pointer
-     * is not NULL, the length of the string (not counting the
-     * terminating NUL) is returned at that address.  If an error
-     * status is returned, the value at resultLength is undefined.</p>
-     *
-     * <p>The returned pointer is owned by this iterator and must not be
-     * deleted by the caller.  The pointer is valid until the next call
-     * to next, unext, snext, reset, or the enumerator's destructor.</p>
-     *
-     * <p>If the iterator is out of sync with its service, status is set
-     * to U_ENUM_OUT_OF_SYNC_ERROR and NULL is returned.</p>
-     *
-     * <p>If the native service string is a char16_t* string, it is
-     * converted to char* with the invariant converter.  If the
-     * conversion fails (because a character cannot be converted) then
-     * status is set to U_INVARIANT_CONVERSION_ERROR and the return
-     * value is undefined (though not NULL).</p>
-     *
-     * Starting with ICU 2.8, the default implementation calls snext()
-     * and handles the conversion.
-     * Either next() or snext() must be implemented differently by a subclass.
-     *
-     * @param status the error code.
-     * @param resultLength a pointer to receive the length, can be NULL.
-     * @return a pointer to the string, or NULL.
-     *
-     * @stable ICU 2.4 
-     */
-    virtual const char* next(int32_t *resultLength, UErrorCode& status);
-
-    /**
-     * <p>Returns the next element as a NUL-terminated char16_t*.  If there
-     * are no more elements, returns NULL.  If the resultLength pointer
-     * is not NULL, the length of the string (not counting the
-     * terminating NUL) is returned at that address.  If an error
-     * status is returned, the value at resultLength is undefined.</p>
-     *
-     * <p>The returned pointer is owned by this iterator and must not be
-     * deleted by the caller.  The pointer is valid until the next call
-     * to next, unext, snext, reset, or the enumerator's destructor.</p>
-     *
-     * <p>If the iterator is out of sync with its service, status is set
-     * to U_ENUM_OUT_OF_SYNC_ERROR and NULL is returned.</p>
-     *
-     * Starting with ICU 2.8, the default implementation calls snext()
-     * and handles the conversion.
-     *
-     * @param status the error code.
-     * @param resultLength a ponter to receive the length, can be NULL.
-     * @return a pointer to the string, or NULL.
-     *
-     * @stable ICU 2.4 
-     */
-    virtual const char16_t* unext(int32_t *resultLength, UErrorCode& status);
-
-    /**
-     * <p>Returns the next element a UnicodeString*.  If there are no
-     * more elements, returns NULL.</p>
-     *
-     * <p>The returned pointer is owned by this iterator and must not be
-     * deleted by the caller.  The pointer is valid until the next call
-     * to next, unext, snext, reset, or the enumerator's destructor.</p>
-     *
-     * <p>If the iterator is out of sync with its service, status is set
-     * to U_ENUM_OUT_OF_SYNC_ERROR and NULL is returned.</p>
-     *
-     * Starting with ICU 2.8, the default implementation calls next()
-     * and handles the conversion.
-     * Either next() or snext() must be implemented differently by a subclass.
-     *
-     * @param status the error code.
-     * @return a pointer to the string, or NULL.
-     *
-     * @stable ICU 2.4 
-     */
-    virtual const UnicodeString* snext(UErrorCode& status);
-
-    /**
-     * <p>Resets the iterator.  This re-establishes sync with the
-     * service and rewinds the iterator to start at the first
-     * element.</p>
-     *
-     * <p>Previous pointers returned by next, unext, or snext become
-     * invalid, and the value returned by count might change.</p>
-     *
-     * @param status the error code.
-     *
-     * @stable ICU 2.4 
-     */
-    virtual void reset(UErrorCode& status) = 0;
-
-    /**
-     * Compares this enumeration to other to check if both are equal
-     *
-     * @param that The other string enumeration to compare this object to
-     * @return true if the enumerations are equal. false if not.
-     * @stable ICU 3.6 
-     */
-    virtual UBool operator==(const StringEnumeration& that)const;
-    /**
-     * Compares this enumeration to other to check if both are not equal
-     *
-     * @param that The other string enumeration to compare this object to
-     * @return true if the enumerations are equal. false if not.
-     * @stable ICU 3.6 
-     */
-    virtual UBool operator!=(const StringEnumeration& that)const;
-
-protected:
-    /**
-     * UnicodeString field for use with default implementations and subclasses.
-     * @stable ICU 2.8
-     */
-    UnicodeString unistr;
-    /**
-     * char * default buffer for use with default implementations and subclasses.
-     * @stable ICU 2.8
-     */
-    char charsBuffer[32];
-    /**
-     * char * buffer for use with default implementations and subclasses.
-     * Allocated in constructor and in ensureCharsCapacity().
-     * @stable ICU 2.8
-     */
-    char *chars;
-    /**
-     * Capacity of chars, for use with default implementations and subclasses.
-     * @stable ICU 2.8
-     */
-    int32_t charsCapacity;
-
-    /**
-     * Default constructor for use with default implementations and subclasses.
-     * @stable ICU 2.8
-     */
-    StringEnumeration();
-
-    /**
-     * Ensures that chars is at least as large as the requested capacity.
-     * For use with default implementations and subclasses.
-     *
-     * @param capacity Requested capacity.
-     * @param status ICU in/out error code.
-     * @stable ICU 2.8
-     */
-    void ensureCharsCapacity(int32_t capacity, UErrorCode &status);
-
-    /**
-     * Converts s to Unicode and sets unistr to the result.
-     * For use with default implementations and subclasses,
-     * especially for implementations of snext() in terms of next().
-     * This is provided with a helper function instead of a default implementation
-     * of snext() to avoid potential infinite loops between next() and snext().
-     *
-     * For example:
-     * \code
-     * const UnicodeString* snext(UErrorCode& status) {
-     *   int32_t resultLength=0;
-     *   const char *s=next(&resultLength, status);
-     *   return setChars(s, resultLength, status);
-     * }
-     * \endcode
-     *
-     * @param s String to be converted to Unicode.
-     * @param length Length of the string.
-     * @param status ICU in/out error code.
-     * @return A pointer to unistr.
-     * @stable ICU 2.8
-     */
-    UnicodeString *setChars(const char *s, int32_t length, UErrorCode &status);
-};
-
-U_NAMESPACE_END
-
-#endif /* U_SHOW_CPLUSPLUS_API */
-
-/* STRENUM_H */
-#endif

app/src/main/cpp/icu4c/include/unicode/stringoptions.h

@@ -1,190 +0,0 @@
-// © 2017 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-
-// stringoptions.h
-// created: 2017jun08 Markus W. Scherer
-
-#ifndef __STRINGOPTIONS_H__
-#define __STRINGOPTIONS_H__
-
-#include "unicode/utypes.h"
-
-/**
- * \file
- * \brief C API: Bit set option bit constants for various string and character processing functions.
- */
-
-/**
- * Option value for case folding: Use default mappings defined in CaseFolding.txt.
- *
- * @stable ICU 2.0
- */
-#define U_FOLD_CASE_DEFAULT 0
-
-/**
- * Option value for case folding:
- *
- * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I
- * and dotless i appropriately for Turkic languages (tr, az).
- *
- * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that
- * are to be included for default mappings and
- * excluded for the Turkic-specific mappings.
- *
- * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that
- * are to be excluded for default mappings and
- * included for the Turkic-specific mappings.
- *
- * @stable ICU 2.0
- */
-#define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1
-
-/**
- * Titlecase the string as a whole rather than each word.
- * (Titlecase only the character at index 0, possibly adjusted.)
- * Option bits value for titlecasing APIs that take an options bit set.
- *
- * It is an error to specify multiple titlecasing iterator options together,
- * including both an options bit and an explicit BreakIterator.
- *
- * @see U_TITLECASE_ADJUST_TO_CASED
- * @stable ICU 60
- */
-#define U_TITLECASE_WHOLE_STRING 0x20
-
-/**
- * Titlecase sentences rather than words.
- * (Titlecase only the first character of each sentence, possibly adjusted.)
- * Option bits value for titlecasing APIs that take an options bit set.
- *
- * It is an error to specify multiple titlecasing iterator options together,
- * including both an options bit and an explicit BreakIterator.
- *
- * @see U_TITLECASE_ADJUST_TO_CASED
- * @stable ICU 60
- */
-#define U_TITLECASE_SENTENCES 0x40
-
-/**
- * Do not lowercase non-initial parts of words when titlecasing.
- * Option bit for titlecasing APIs that take an options bit set.
- *
- * By default, titlecasing will titlecase the character at each
- * (possibly adjusted) BreakIterator index and
- * lowercase all other characters up to the next iterator index.
- * With this option, the other characters will not be modified.
- *
- * @see U_TITLECASE_ADJUST_TO_CASED
- * @see UnicodeString::toTitle
- * @see CaseMap::toTitle
- * @see ucasemap_setOptions
- * @see ucasemap_toTitle
- * @see ucasemap_utf8ToTitle
- * @stable ICU 3.8
- */
-#define U_TITLECASE_NO_LOWERCASE 0x100
-
-/**
- * Do not adjust the titlecasing BreakIterator indexes;
- * titlecase exactly the characters at breaks from the iterator.
- * Option bit for titlecasing APIs that take an options bit set.
- *
- * By default, titlecasing will take each break iterator index,
- * adjust it to the next relevant character (see U_TITLECASE_ADJUST_TO_CASED),
- * and titlecase that one.
- *
- * Other characters are lowercased.
- *
- * It is an error to specify multiple titlecasing adjustment options together.
- *
- * @see U_TITLECASE_ADJUST_TO_CASED
- * @see U_TITLECASE_NO_LOWERCASE
- * @see UnicodeString::toTitle
- * @see CaseMap::toTitle
- * @see ucasemap_setOptions
- * @see ucasemap_toTitle
- * @see ucasemap_utf8ToTitle
- * @stable ICU 3.8
- */
-#define U_TITLECASE_NO_BREAK_ADJUSTMENT 0x200
-
-/**
- * Adjust each titlecasing BreakIterator index to the next cased character.
- * (See the Unicode Standard, chapter 3, Default Case Conversion, R3 toTitlecase(X).)
- * Option bit for titlecasing APIs that take an options bit set.
- *
- * This used to be the default index adjustment in ICU.
- * Since ICU 60, the default index adjustment is to the next character that is
- * a letter, number, symbol, or private use code point.
- * (Uncased modifier letters are skipped.)
- * The difference in behavior is small for word titlecasing,
- * but the new adjustment is much better for whole-string and sentence titlecasing:
- * It yields "49ers" and "«丰(abc)»" instead of "49Ers" and "«丰(Abc)»".
- *
- * It is an error to specify multiple titlecasing adjustment options together.
- *
- * @see U_TITLECASE_NO_BREAK_ADJUSTMENT
- * @stable ICU 60
- */
-#define U_TITLECASE_ADJUST_TO_CASED 0x400
-
-/**
- * Option for string transformation functions to not first reset the Edits object.
- * Used for example in some case-mapping and normalization functions.
- *
- * @see CaseMap
- * @see Edits
- * @see Normalizer2
- * @stable ICU 60
- */
-#define U_EDITS_NO_RESET 0x2000
-
-/**
- * Omit unchanged text when recording how source substrings
- * relate to changed and unchanged result substrings.
- * Used for example in some case-mapping and normalization functions.
- *
- * @see CaseMap
- * @see Edits
- * @see Normalizer2
- * @stable ICU 60
- */
-#define U_OMIT_UNCHANGED_TEXT 0x4000
-
-/**
- * Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc:
- * Compare strings in code point order instead of code unit order.
- * @stable ICU 2.2
- */
-#define U_COMPARE_CODE_POINT_ORDER  0x8000
-
-/**
- * Option bit for unorm_compare:
- * Perform case-insensitive comparison.
- * @stable ICU 2.2
- */
-#define U_COMPARE_IGNORE_CASE       0x10000
-
-/**
- * Option bit for unorm_compare:
- * Both input strings are assumed to fulfill FCD conditions.
- * @stable ICU 2.2
- */
-#define UNORM_INPUT_IS_FCD          0x20000
-
-// Related definitions elsewhere.
-// Options that are not meaningful in the same functions
-// can share the same bits.
-//
-// Public:
-// unicode/unorm.h #define UNORM_COMPARE_NORM_OPTIONS_SHIFT 20
-//
-// Internal: (may change or be removed)
-// ucase.h #define _STRCASECMP_OPTIONS_MASK 0xffff
-// ucase.h #define _FOLD_CASE_OPTIONS_MASK 7
-// ucasemap_imp.h #define U_TITLECASE_ITERATOR_MASK 0xe0
-// ucasemap_imp.h #define U_TITLECASE_ADJUSTMENT_MASK 0x600
-// ustr_imp.h #define _STRNCMP_STYLE 0x1000
-// unormcmp.cpp #define _COMPARE_EQUIV 0x80000
-
-#endif  // __STRINGOPTIONS_H__

app/src/main/cpp/icu4c/include/unicode/stringpiece.h

@@ -1,343 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-// Copyright (C) 2009-2013, International Business Machines
-// Corporation and others. All Rights Reserved.
-//
-// Copyright 2001 and onwards Google Inc.
-// Author: Sanjay Ghemawat
-
-// This code is a contribution of Google code, and the style used here is
-// a compromise between the original Google code and the ICU coding guidelines.
-// For example, data types are ICU-ified (size_t,int->int32_t),
-// and API comments doxygen-ified, but function names and behavior are
-// as in the original, if possible.
-// Assertion-style error handling, not available in ICU, was changed to
-// parameter "pinning" similar to UnicodeString.
-//
-// In addition, this is only a partial port of the original Google code,
-// limited to what was needed so far. The (nearly) complete original code
-// is in the ICU svn repository at icuhtml/trunk/design/strings/contrib
-// (see ICU ticket 6765, r25517).
-
-#ifndef __STRINGPIECE_H__
-#define __STRINGPIECE_H__
-
-/**
- * \file 
- * \brief C++ API: StringPiece: Read-only byte string wrapper class.
- */
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-
-#include <cstddef>
-#include <type_traits>
-
-#include "unicode/uobject.h"
-#include "unicode/std_string.h"
-
-// Arghh!  I wish C++ literals were "string".
-
-U_NAMESPACE_BEGIN
-
-/**
- * A string-like object that points to a sized piece of memory.
- *
- * We provide non-explicit singleton constructors so users can pass
- * in a "const char*" or a "string" wherever a "StringPiece" is
- * expected.
- *
- * Functions or methods may use StringPiece parameters to accept either a
- * "const char*" or a "string" value that will be implicitly converted to a
- * StringPiece.
- *
- * Systematic usage of StringPiece is encouraged as it will reduce unnecessary
- * conversions from "const char*" to "string" and back again.
- *
- * @stable ICU 4.2
- */
-class U_COMMON_API StringPiece : public UMemory {
- private:
-  const char*   ptr_;
-  int32_t       length_;
-
- public:
-  /**
-   * Default constructor, creates an empty StringPiece.
-   * @stable ICU 4.2
-   */
-  StringPiece() : ptr_(nullptr), length_(0) { }
-
-  /**
-   * Constructs from a NUL-terminated const char * pointer.
-   * @param str a NUL-terminated const char * pointer
-   * @stable ICU 4.2
-   */
-  StringPiece(const char* str);
-#if defined(__cpp_char8_t) || defined(U_IN_DOXYGEN)
-  /**
-   * Constructs from a NUL-terminated const char8_t * pointer.
-   * @param str a NUL-terminated const char8_t * pointer
-   * @stable ICU 67
-   */
-  StringPiece(const char8_t* str) : StringPiece(reinterpret_cast<const char*>(str)) {}
-#endif
-  /**
-   * Constructs an empty StringPiece.
-   * Needed for type disambiguation from multiple other overloads.
-   * @param p nullptr
-   * @stable ICU 67
-   */
-  StringPiece(std::nullptr_t p) : ptr_(p), length_(0) {}
-
-  /**
-   * Constructs from a std::string.
-   * @stable ICU 4.2
-   */
-  StringPiece(const std::string& str)
-    : ptr_(str.data()), length_(static_cast<int32_t>(str.size())) { }
-#if defined(__cpp_lib_char8_t) || defined(U_IN_DOXYGEN)
-  /**
-   * Constructs from a std::u8string.
-   * @stable ICU 67
-   */
-  StringPiece(const std::u8string& str)
-    : ptr_(reinterpret_cast<const char*>(str.data())),
-      length_(static_cast<int32_t>(str.size())) { }
-#endif
-
-  /**
-   * Constructs from some other implementation of a string piece class, from any
-   * C++ record type that has these two methods:
-   *
-   * \code{.cpp}
-   *
-   *   struct OtherStringPieceClass {
-   *     const char* data();  // or const char8_t*
-   *     size_t size();
-   *   };
-   *
-   * \endcode
-   *
-   * The other string piece class will typically be std::string_view from C++17
-   * or absl::string_view from Abseil.
-   *
-   * Starting with C++20, data() may also return a const char8_t* pointer,
-   * as from std::u8string_view.
-   *
-   * @param str the other string piece
-   * @stable ICU 65
-   */
-  template <typename T,
-            typename = typename std::enable_if<
-                (std::is_same<decltype(T().data()), const char*>::value
-#if defined(__cpp_char8_t)
-                    || std::is_same<decltype(T().data()), const char8_t*>::value
-#endif
-                ) &&
-                std::is_same<decltype(T().size()), size_t>::value>::type>
-  StringPiece(T str)
-      : ptr_(reinterpret_cast<const char*>(str.data())),
-        length_(static_cast<int32_t>(str.size())) {}
-
-  /**
-   * Constructs from a const char * pointer and a specified length.
-   * @param offset a const char * pointer (need not be terminated)
-   * @param len the length of the string; must be non-negative
-   * @stable ICU 4.2
-   */
-  StringPiece(const char* offset, int32_t len) : ptr_(offset), length_(len) { }
-#if defined(__cpp_char8_t) || defined(U_IN_DOXYGEN)
-  /**
-   * Constructs from a const char8_t * pointer and a specified length.
-   * @param str a const char8_t * pointer (need not be terminated)
-   * @param len the length of the string; must be non-negative
-   * @stable ICU 67
-   */
-  StringPiece(const char8_t* str, int32_t len) :
-      StringPiece(reinterpret_cast<const char*>(str), len) {}
-#endif
-
-  /**
-   * Substring of another StringPiece.
-   * @param x the other StringPiece
-   * @param pos start position in x; must be non-negative and <= x.length().
-   * @stable ICU 4.2
-   */
-  StringPiece(const StringPiece& x, int32_t pos);
-  /**
-   * Substring of another StringPiece.
-   * @param x the other StringPiece
-   * @param pos start position in x; must be non-negative and <= x.length().
-   * @param len length of the substring;
-   *            must be non-negative and will be pinned to at most x.length() - pos.
-   * @stable ICU 4.2
-   */
-  StringPiece(const StringPiece& x, int32_t pos, int32_t len);
-
-  /**
-   * Returns the string pointer. May be nullptr if it is empty.
-   *
-   * data() may return a pointer to a buffer with embedded NULs, and the
-   * returned buffer may or may not be null terminated.  Therefore it is
-   * typically a mistake to pass data() to a routine that expects a NUL
-   * terminated string.
-   * @return the string pointer
-   * @stable ICU 4.2
-   */
-  const char* data() const { return ptr_; }
-  /**
-   * Returns the string length. Same as length().
-   * @return the string length
-   * @stable ICU 4.2
-   */
-  int32_t size() const { return length_; }
-  /**
-   * Returns the string length. Same as size().
-   * @return the string length
-   * @stable ICU 4.2
-   */
-  int32_t length() const { return length_; }
-  /**
-   * Returns whether the string is empty.
-   * @return true if the string is empty
-   * @stable ICU 4.2
-   */
-  UBool empty() const { return length_ == 0; }
-
-  /**
-   * Sets to an empty string.
-   * @stable ICU 4.2
-   */
-  void clear() { ptr_ = nullptr; length_ = 0; }
-
-  /**
-   * Reset the stringpiece to refer to new data.
-   * @param xdata pointer the new string data.  Need not be nul terminated.
-   * @param len the length of the new data
-   * @stable ICU 4.8
-   */
-  void set(const char* xdata, int32_t len) { ptr_ = xdata; length_ = len; }
-
-  /**
-   * Reset the stringpiece to refer to new data.
-   * @param str a pointer to a NUL-terminated string. 
-   * @stable ICU 4.8
-   */
-  void set(const char* str);
-
-#if defined(__cpp_char8_t) || defined(U_IN_DOXYGEN)
-  /**
-   * Resets the stringpiece to refer to new data.
-   * @param xdata pointer the new string data. Need not be NUL-terminated.
-   * @param len the length of the new data
-   * @stable ICU 67
-   */
-  inline void set(const char8_t* xdata, int32_t len) {
-      set(reinterpret_cast<const char*>(xdata), len);
-  }
-
-  /**
-   * Resets the stringpiece to refer to new data.
-   * @param str a pointer to a NUL-terminated string.
-   * @stable ICU 67
-   */
-  inline void set(const char8_t* str) {
-      set(reinterpret_cast<const char*>(str));
-  }
-#endif
-
-  /**
-   * Removes the first n string units.
-   * @param n prefix length, must be non-negative and <=length()
-   * @stable ICU 4.2
-   */
-  void remove_prefix(int32_t n) {
-    if (n >= 0) {
-      if (n > length_) {
-        n = length_;
-      }
-      ptr_ += n;
-      length_ -= n;
-    }
-  }
-
-  /**
-   * Removes the last n string units.
-   * @param n suffix length, must be non-negative and <=length()
-   * @stable ICU 4.2
-   */
-  void remove_suffix(int32_t n) {
-    if (n >= 0) {
-      if (n <= length_) {
-        length_ -= n;
-      } else {
-        length_ = 0;
-      }
-    }
-  }
-
-  /**
-   * Searches the StringPiece for the given search string (needle);
-   * @param needle The string for which to search.
-   * @param offset Where to start searching within this string (haystack).
-   * @return The offset of needle in haystack, or -1 if not found.
-   * @stable ICU 67
-   */
-  int32_t find(StringPiece needle, int32_t offset);
-
-  /**
-   * Compares this StringPiece with the other StringPiece, with semantics
-   * similar to std::string::compare().
-   * @param other The string to compare to.
-   * @return below zero if this < other; above zero if this > other; 0 if this == other.
-   * @stable ICU 67
-   */
-  int32_t compare(StringPiece other);
-
-  /**
-   * Maximum integer, used as a default value for substring methods.
-   * @stable ICU 4.2
-   */
-  static const int32_t npos; // = 0x7fffffff;
-
-  /**
-   * Returns a substring of this StringPiece.
-   * @param pos start position; must be non-negative and <= length().
-   * @param len length of the substring;
-   *            must be non-negative and will be pinned to at most length() - pos.
-   * @return the substring StringPiece
-   * @stable ICU 4.2
-   */
-  StringPiece substr(int32_t pos, int32_t len = npos) const {
-    return StringPiece(*this, pos, len);
-  }
-};
-
-/**
- * Global operator == for StringPiece
- * @param x The first StringPiece to compare.
- * @param y The second StringPiece to compare.
- * @return true if the string data is equal
- * @stable ICU 4.8
- */
-U_EXPORT UBool U_EXPORT2 
-operator==(const StringPiece& x, const StringPiece& y);
-
-/**
- * Global operator != for StringPiece
- * @param x The first StringPiece to compare.
- * @param y The second StringPiece to compare.
- * @return true if the string data is not equal
- * @stable ICU 4.8
- */
-inline UBool operator!=(const StringPiece& x, const StringPiece& y) {
-  return !(x == y);
-}
-
-U_NAMESPACE_END
-
-#endif /* U_SHOW_CPLUSPLUS_API */
-
-#endif  // __STRINGPIECE_H__

app/src/main/cpp/icu4c/include/unicode/ubrk.h

@@ -1,650 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-******************************************************************************
-* Copyright (C) 1996-2015, International Business Machines Corporation and others.
-* All Rights Reserved.
-******************************************************************************
-*/
-
-#ifndef UBRK_H
-#define UBRK_H
-
-#include "unicode/utypes.h"
-#include "unicode/uloc.h"
-#include "unicode/utext.h"
-
-#if U_SHOW_CPLUSPLUS_API
-#include "unicode/localpointer.h"
-#endif   // U_SHOW_CPLUSPLUS_API
-
-/**
- * A text-break iterator.
- *  For usage in C programs.
- */
-#ifndef UBRK_TYPEDEF_UBREAK_ITERATOR
-#   define UBRK_TYPEDEF_UBREAK_ITERATOR
-    /**
-     *  Opaque type representing an ICU Break iterator object.
-     *  @stable ICU 2.0
-     */
-    typedef struct UBreakIterator UBreakIterator;
-#endif
-
-#if !UCONFIG_NO_BREAK_ITERATION
-
-#include "unicode/parseerr.h"
-
-/**
- * \file
- * \brief C API: BreakIterator
- *
- * <h2> BreakIterator C API </h2>
- *
- * The BreakIterator C API defines  methods for finding the location
- * of boundaries in text. Pointer to a UBreakIterator maintain a
- * current position and scan over text returning the index of characters
- * where boundaries occur.
- * <p>
- * Line boundary analysis determines where a text string can be broken
- * when line-wrapping. The mechanism correctly handles punctuation and
- * hyphenated words.
- * <p>
- * Note: The locale keyword "lb" can be used to modify line break
- * behavior according to the CSS level 3 line-break options, see
- * <http://dev.w3.org/csswg/css-text/#line-breaking>. For example:
- * "ja@lb=strict", "zh@lb=loose".
- * <p>
- * Sentence boundary analysis allows selection with correct
- * interpretation of periods within numbers and abbreviations, and
- * trailing punctuation marks such as quotation marks and parentheses.
- * <p>
- * Note: The locale keyword "ss" can be used to enable use of
- * segmentation suppression data (preventing breaks in English after
- * abbreviations such as "Mr." or "Est.", for example), as follows:
- * "en@ss=standard".
- * <p>
- * Word boundary analysis is used by search and replace functions, as
- * well as within text editing applications that allow the user to
- * select words with a double click. Word selection provides correct
- * interpretation of punctuation marks within and following
- * words. Characters that are not part of a word, such as symbols or
- * punctuation marks, have word-breaks on both sides.
- * <p>
- * Character boundary analysis identifies the boundaries of
- * "Extended Grapheme Clusters", which are groupings of codepoints
- * that should be treated as character-like units for many text operations.
- * Please see Unicode Standard Annex #29, Unicode Text Segmentation,
- * http://www.unicode.org/reports/tr29/ for additional information
- * on grapheme clusters and guidelines on their use.
- * <p>
- * Title boundary analysis locates all positions,
- * typically starts of words, that should be set to Title Case
- * when title casing the text.
- * <p>
- * The text boundary positions are found according to the rules
- * described in Unicode Standard Annex #29, Text Boundaries, and
- * Unicode Standard Annex #14, Line Breaking Properties.  These
- * are available at http://www.unicode.org/reports/tr14/ and
- * http://www.unicode.org/reports/tr29/.
- * <p>
- * In addition to the plain C API defined in this header file, an
- * object oriented C++ API with equivalent functionality is defined in the
- * file brkiter.h.
- * <p>
- * Code snippets illustrating the use of the Break Iterator APIs
- * are available in the ICU User Guide,
- * http://icu-project.org/userguide/boundaryAnalysis.html
- * and in the sample program icu/source/samples/break/break.cpp
- */
-
-/** The possible types of text boundaries.  @stable ICU 2.0 */
-typedef enum UBreakIteratorType {
-  /** Character breaks  @stable ICU 2.0 */
-  UBRK_CHARACTER = 0,
-  /** Word breaks @stable ICU 2.0 */
-  UBRK_WORD = 1,
-  /** Line breaks @stable ICU 2.0 */
-  UBRK_LINE = 2,
-  /** Sentence breaks @stable ICU 2.0 */
-  UBRK_SENTENCE = 3,
-
-#ifndef U_HIDE_DEPRECATED_API
-  /**
-   * Title Case breaks
-   * The iterator created using this type locates title boundaries as described for
-   * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration,
-   * please use Word Boundary iterator.
-   *
-   * @deprecated ICU 2.8 Use the word break iterator for titlecasing for Unicode 4 and later.
-   */
-  UBRK_TITLE = 4,
-    /**
-     * One more than the highest normal UBreakIteratorType value.
-     * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
-     */
-    UBRK_COUNT = 5
-#endif  // U_HIDE_DEPRECATED_API
-} UBreakIteratorType;
-
-/** Value indicating all text boundaries have been returned.
- *  @stable ICU 2.0
- */
-#define UBRK_DONE ((int32_t) -1)
-
-
-/**
- *  Enum constants for the word break tags returned by
- *  getRuleStatus().  A range of values is defined for each category of
- *  word, to allow for further subdivisions of a category in future releases.
- *  Applications should check for tag values falling within the range, rather
- *  than for single individual values.
- *
- * The numeric values of all of these constants are stable (will not change).
- *
- * @stable ICU 2.2
-*/
-typedef enum UWordBreak {
-    /** Tag value for "words" that do not fit into any of other categories.
-     *  Includes spaces and most punctuation. */
-    UBRK_WORD_NONE           = 0,
-    /** Upper bound for tags for uncategorized words. */
-    UBRK_WORD_NONE_LIMIT     = 100,
-    /** Tag value for words that appear to be numbers, lower limit.    */
-    UBRK_WORD_NUMBER         = 100,
-    /** Tag value for words that appear to be numbers, upper limit.    */
-    UBRK_WORD_NUMBER_LIMIT   = 200,
-    /** Tag value for words that contain letters, excluding
-     *  hiragana, katakana or ideographic characters, lower limit.    */
-    UBRK_WORD_LETTER         = 200,
-    /** Tag value for words containing letters, upper limit  */
-    UBRK_WORD_LETTER_LIMIT   = 300,
-    /** Tag value for words containing kana characters, lower limit */
-    UBRK_WORD_KANA           = 300,
-    /** Tag value for words containing kana characters, upper limit */
-    UBRK_WORD_KANA_LIMIT     = 400,
-    /** Tag value for words containing ideographic characters, lower limit */
-    UBRK_WORD_IDEO           = 400,
-    /** Tag value for words containing ideographic characters, upper limit */
-    UBRK_WORD_IDEO_LIMIT     = 500
-} UWordBreak;
-
-/**
- *  Enum constants for the line break tags returned by getRuleStatus().
- *  A range of values is defined for each category of
- *  word, to allow for further subdivisions of a category in future releases.
- *  Applications should check for tag values falling within the range, rather
- *  than for single individual values.
- *
- * The numeric values of all of these constants are stable (will not change).
- *
- * @stable ICU 2.8
-*/
-typedef enum ULineBreakTag {
-    /** Tag value for soft line breaks, positions at which a line break
-      *  is acceptable but not required                */
-    UBRK_LINE_SOFT            = 0,
-    /** Upper bound for soft line breaks.              */
-    UBRK_LINE_SOFT_LIMIT      = 100,
-    /** Tag value for a hard, or mandatory line break  */
-    UBRK_LINE_HARD            = 100,
-    /** Upper bound for hard line breaks.              */
-    UBRK_LINE_HARD_LIMIT      = 200
-} ULineBreakTag;
-
-
-
-/**
- *  Enum constants for the sentence break tags returned by getRuleStatus().
- *  A range of values is defined for each category of
- *  sentence, to allow for further subdivisions of a category in future releases.
- *  Applications should check for tag values falling within the range, rather
- *  than for single individual values.
- *
- * The numeric values of all of these constants are stable (will not change).
- *
- * @stable ICU 2.8
-*/
-typedef enum USentenceBreakTag {
-    /** Tag value for for sentences  ending with a sentence terminator
-      * ('.', '?', '!', etc.) character, possibly followed by a
-      * hard separator (CR, LF, PS, etc.)
-      */
-    UBRK_SENTENCE_TERM       = 0,
-    /** Upper bound for tags for sentences ended by sentence terminators.    */
-    UBRK_SENTENCE_TERM_LIMIT = 100,
-    /** Tag value for for sentences that do not contain an ending
-      * sentence terminator ('.', '?', '!', etc.) character, but
-      * are ended only by a hard separator (CR, LF, PS, etc.) or end of input.
-      */
-    UBRK_SENTENCE_SEP        = 100,
-    /** Upper bound for tags for sentences ended by a separator.              */
-    UBRK_SENTENCE_SEP_LIMIT  = 200
-    /** Tag value for a hard, or mandatory line break  */
-} USentenceBreakTag;
-
-
-/**
- * Open a new UBreakIterator for locating text boundaries for a specified locale.
- * A UBreakIterator may be used for detecting character, line, word,
- * and sentence breaks in text.
- * @param type The type of UBreakIterator to open: one of UBRK_CHARACTER, UBRK_WORD,
- * UBRK_LINE, UBRK_SENTENCE
- * @param locale The locale specifying the text-breaking conventions. Note that
- * locale keys such as "lb" and "ss" may be used to modify text break behavior,
- * see general discussion of BreakIterator C API.
- * @param text The text to be iterated over. May be null, in which case ubrk_setText() is
- *        used to specify the text to be iterated.
- * @param textLength The number of characters in text, or -1 if null-terminated.
- * @param status A UErrorCode to receive any errors.
- * @return A UBreakIterator for the specified locale.
- * @see ubrk_openRules
- * @stable ICU 2.0
- */
-U_CAPI UBreakIterator* U_EXPORT2
-ubrk_open(UBreakIteratorType type,
-      const char *locale,
-      const UChar *text,
-      int32_t textLength,
-      UErrorCode *status);
-
-/**
- * Open a new UBreakIterator for locating text boundaries using specified breaking rules.
- * The rule syntax is ... (TBD)
- * @param rules A set of rules specifying the text breaking conventions.
- * @param rulesLength The number of characters in rules, or -1 if null-terminated.
- * @param text The text to be iterated over.  May be null, in which case ubrk_setText() is
- *        used to specify the text to be iterated.
- * @param textLength The number of characters in text, or -1 if null-terminated.
- * @param parseErr   Receives position and context information for any syntax errors
- *                   detected while parsing the rules.
- * @param status A UErrorCode to receive any errors.
- * @return A UBreakIterator for the specified rules.
- * @see ubrk_open
- * @stable ICU 2.2
- */
-U_CAPI UBreakIterator* U_EXPORT2
-ubrk_openRules(const UChar     *rules,
-               int32_t         rulesLength,
-               const UChar     *text,
-               int32_t          textLength,
-               UParseError     *parseErr,
-               UErrorCode      *status);
-
-/**
- * Open a new UBreakIterator for locating text boundaries using precompiled binary rules.
- * Opening a UBreakIterator this way is substantially faster than using ubrk_openRules.
- * Binary rules may be obtained using ubrk_getBinaryRules. The compiled rules are not
- * compatible across different major versions of ICU, nor across platforms of different
- * endianness or different base character set family (ASCII vs EBCDIC).
- * @param binaryRules A set of compiled binary rules specifying the text breaking
- *                    conventions. Ownership of the storage containing the compiled
- *                    rules remains with the caller of this function. The compiled
- *                    rules must not be modified or deleted during the life of the
- *                    break iterator.
- * @param rulesLength The length of binaryRules in bytes; must be >= 0.
- * @param text        The text to be iterated over.  May be null, in which case
- *                    ubrk_setText() is used to specify the text to be iterated.
- * @param textLength  The number of characters in text, or -1 if null-terminated.
- * @param status      Pointer to UErrorCode to receive any errors.
- * @return            UBreakIterator for the specified rules.
- * @see ubrk_getBinaryRules
- * @stable ICU 59
- */
-U_CAPI UBreakIterator* U_EXPORT2
-ubrk_openBinaryRules(const uint8_t *binaryRules, int32_t rulesLength,
-                     const UChar *  text, int32_t textLength,
-                     UErrorCode *   status);
-
-#ifndef U_HIDE_DEPRECATED_API
-
-/**
- * Thread safe cloning operation
- * @param bi iterator to be cloned
- * @param stackBuffer <em>Deprecated functionality as of ICU 52, use NULL.</em><br>
- *  user allocated space for the new clone. If NULL new memory will be allocated.
- *  If buffer is not large enough, new memory will be allocated.
- *  Clients can use the U_BRK_SAFECLONE_BUFFERSIZE.
- * @param pBufferSize <em>Deprecated functionality as of ICU 52, use NULL or 1.</em><br>
- *  pointer to size of allocated space.
- *  If *pBufferSize == 0, a sufficient size for use in cloning will
- *  be returned ('pre-flighting')
- *  If *pBufferSize is not enough for a stack-based safe clone,
- *  new memory will be allocated.
- * @param status to indicate whether the operation went on smoothly or there were errors
- *  An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were necessary.
- * @return pointer to the new clone
- * @deprecated ICU 69 Use ubrk_clone() instead.
- */
-U_CAPI UBreakIterator * U_EXPORT2
-ubrk_safeClone(
-          const UBreakIterator *bi,
-          void *stackBuffer,
-          int32_t *pBufferSize,
-          UErrorCode *status);
-
-#endif /* U_HIDE_DEPRECATED_API */
-
-#ifndef U_HIDE_DRAFT_API
-
-/**
- * Thread safe cloning operation.
- * @param bi iterator to be cloned
- * @param status to indicate whether the operation went on smoothly or there were errors
- * @return pointer to the new clone
- * @draft ICU 69
- */
-U_CAPI UBreakIterator * U_EXPORT2
-ubrk_clone(const UBreakIterator *bi,
-           UErrorCode *status);
-
-#endif  // U_HIDE_DRAFT_API
-
-#ifndef U_HIDE_DEPRECATED_API
-
-/**
-  * A recommended size (in bytes) for the memory buffer to be passed to ubrk_saveClone().
-  * @deprecated ICU 52. Do not rely on ubrk_safeClone() cloning into any provided buffer.
-  */
-#define U_BRK_SAFECLONE_BUFFERSIZE 1
-
-#endif /* U_HIDE_DEPRECATED_API */
-
-/**
-* Close a UBreakIterator.
-* Once closed, a UBreakIterator may no longer be used.
-* @param bi The break iterator to close.
- * @stable ICU 2.0
-*/
-U_CAPI void U_EXPORT2
-ubrk_close(UBreakIterator *bi);
-
-#if U_SHOW_CPLUSPLUS_API
-
-U_NAMESPACE_BEGIN
-
-/**
- * \class LocalUBreakIteratorPointer
- * "Smart pointer" class, closes a UBreakIterator via ubrk_close().
- * For most methods see the LocalPointerBase base class.
- *
- * @see LocalPointerBase
- * @see LocalPointer
- * @stable ICU 4.4
- */
-U_DEFINE_LOCAL_OPEN_POINTER(LocalUBreakIteratorPointer, UBreakIterator, ubrk_close);
-
-U_NAMESPACE_END
-
-#endif
-
-/**
- * Sets an existing iterator to point to a new piece of text.
- * The break iterator retains a pointer to the supplied text.
- * The caller must not modify or delete the text while the BreakIterator
- * retains the reference.
- *
- * @param bi The iterator to use
- * @param text The text to be set
- * @param textLength The length of the text
- * @param status The error code
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2
-ubrk_setText(UBreakIterator* bi,
-             const UChar*    text,
-             int32_t         textLength,
-             UErrorCode*     status);
-
-
-/**
- * Sets an existing iterator to point to a new piece of text.
- *
- * All index positions returned by break iterator functions are
- * native indices from the UText. For example, when breaking UTF-8
- * encoded text, the break positions returned by \ref ubrk_next, \ref ubrk_previous, etc.
- * will be UTF-8 string indices, not UTF-16 positions.
- *
- * @param bi The iterator to use
- * @param text The text to be set.
- *             This function makes a shallow clone of the supplied UText.  This means
- *             that the caller is free to immediately close or otherwise reuse the
- *             UText that was passed as a parameter, but that the underlying text itself
- *             must not be altered while being referenced by the break iterator.
- * @param status The error code
- * @stable ICU 3.4
- */
-U_CAPI void U_EXPORT2
-ubrk_setUText(UBreakIterator* bi,
-             UText*          text,
-             UErrorCode*     status);
-
-
-
-/**
- * Determine the most recently-returned text boundary.
- *
- * @param bi The break iterator to use.
- * @return The character index most recently returned by \ref ubrk_next, \ref ubrk_previous,
- * \ref ubrk_first, or \ref ubrk_last.
- * @stable ICU 2.0
- */
-U_CAPI int32_t U_EXPORT2
-ubrk_current(const UBreakIterator *bi);
-
-/**
- * Advance the iterator to the boundary following the current boundary.
- *
- * @param bi The break iterator to use.
- * @return The character index of the next text boundary, or UBRK_DONE
- * if all text boundaries have been returned.
- * @see ubrk_previous
- * @stable ICU 2.0
- */
-U_CAPI int32_t U_EXPORT2
-ubrk_next(UBreakIterator *bi);
-
-/**
- * Set the iterator position to the boundary preceding the current boundary.
- *
- * @param bi The break iterator to use.
- * @return The character index of the preceding text boundary, or UBRK_DONE
- * if all text boundaries have been returned.
- * @see ubrk_next
- * @stable ICU 2.0
- */
-U_CAPI int32_t U_EXPORT2
-ubrk_previous(UBreakIterator *bi);
-
-/**
- * Set the iterator position to zero, the start of the text being scanned.
- * @param bi The break iterator to use.
- * @return The new iterator position (zero).
- * @see ubrk_last
- * @stable ICU 2.0
- */
-U_CAPI int32_t U_EXPORT2
-ubrk_first(UBreakIterator *bi);
-
-/**
- * Set the iterator position to the index immediately <EM>beyond</EM> the last character in the text being scanned.
- * This is not the same as the last character.
- * @param bi The break iterator to use.
- * @return The character offset immediately <EM>beyond</EM> the last character in the
- * text being scanned.
- * @see ubrk_first
- * @stable ICU 2.0
- */
-U_CAPI int32_t U_EXPORT2
-ubrk_last(UBreakIterator *bi);
-
-/**
- * Set the iterator position to the first boundary preceding the specified offset.
- * The new position is always smaller than offset, or UBRK_DONE.
- * @param bi The break iterator to use.
- * @param offset The offset to begin scanning.
- * @return The text boundary preceding offset, or UBRK_DONE.
- * @see ubrk_following
- * @stable ICU 2.0
- */
-U_CAPI int32_t U_EXPORT2
-ubrk_preceding(UBreakIterator *bi,
-           int32_t offset);
-
-/**
- * Advance the iterator to the first boundary following the specified offset.
- * The value returned is always greater than offset, or UBRK_DONE.
- * @param bi The break iterator to use.
- * @param offset The offset to begin scanning.
- * @return The text boundary following offset, or UBRK_DONE.
- * @see ubrk_preceding
- * @stable ICU 2.0
- */
-U_CAPI int32_t U_EXPORT2
-ubrk_following(UBreakIterator *bi,
-           int32_t offset);
-
-/**
-* Get a locale for which text breaking information is available.
-* A UBreakIterator in a locale returned by this function will perform the correct
-* text breaking for the locale.
-* @param index The index of the desired locale.
-* @return A locale for which number text breaking information is available, or 0 if none.
-* @see ubrk_countAvailable
-* @stable ICU 2.0
-*/
-U_CAPI const char* U_EXPORT2
-ubrk_getAvailable(int32_t index);
-
-/**
-* Determine how many locales have text breaking information available.
-* This function is most useful as determining the loop ending condition for
-* calls to \ref ubrk_getAvailable.
-* @return The number of locales for which text breaking information is available.
-* @see ubrk_getAvailable
-* @stable ICU 2.0
-*/
-U_CAPI int32_t U_EXPORT2
-ubrk_countAvailable(void);
-
-
-/**
-* Returns true if the specified position is a boundary position.  As a side
-* effect, leaves the iterator pointing to the first boundary position at
-* or after "offset".
-* @param bi The break iterator to use.
-* @param offset the offset to check.
-* @return True if "offset" is a boundary position.
-* @stable ICU 2.0
-*/
-U_CAPI  UBool U_EXPORT2
-ubrk_isBoundary(UBreakIterator *bi, int32_t offset);
-
-/**
- * Return the status from the break rule that determined the most recently
- * returned break position.  The values appear in the rule source
- * within brackets, {123}, for example.  For rules that do not specify a
- * status, a default value of 0 is returned.
- * <p>
- * For word break iterators, the possible values are defined in enum UWordBreak.
- * @stable ICU 2.2
- */
-U_CAPI  int32_t U_EXPORT2
-ubrk_getRuleStatus(UBreakIterator *bi);
-
-/**
- * Get the statuses from the break rules that determined the most recently
- * returned break position.  The values appear in the rule source
- * within brackets, {123}, for example.  The default status value for rules
- * that do not explicitly provide one is zero.
- * <p>
- * For word break iterators, the possible values are defined in enum UWordBreak.
- * @param bi        The break iterator to use
- * @param fillInVec an array to be filled in with the status values.
- * @param capacity  the length of the supplied vector.  A length of zero causes
- *                  the function to return the number of status values, in the
- *                  normal way, without attempting to store any values.
- * @param status    receives error codes.
- * @return          The number of rule status values from rules that determined
- *                  the most recent boundary returned by the break iterator.
- * @stable ICU 3.0
- */
-U_CAPI  int32_t U_EXPORT2
-ubrk_getRuleStatusVec(UBreakIterator *bi, int32_t *fillInVec, int32_t capacity, UErrorCode *status);
-
-/**
- * Return the locale of the break iterator. You can choose between the valid and
- * the actual locale.
- * @param bi break iterator
- * @param type locale type (valid or actual)
- * @param status error code
- * @return locale string
- * @stable ICU 2.8
- */
-U_CAPI const char* U_EXPORT2
-ubrk_getLocaleByType(const UBreakIterator *bi, ULocDataLocaleType type, UErrorCode* status);
-
-/**
-  *  Set the subject text string upon which the break iterator is operating
-  *  without changing any other aspect of the state.
-  *  The new and previous text strings must have the same content.
-  *
-  *  This function is intended for use in environments where ICU is operating on
-  *  strings that may move around in memory.  It provides a mechanism for notifying
-  *  ICU that the string has been relocated, and providing a new UText to access the
-  *  string in its new position.
-  *
-  *  Note that the break iterator never copies the underlying text
-  *  of a string being processed, but always operates directly on the original text
-  *  provided by the user. Refreshing simply drops the references to the old text
-  *  and replaces them with references to the new.
-  *
-  *  Caution:  this function is normally used only by very specialized
-  *            system-level code.   One example use case is with garbage collection
-  *            that moves the text in memory.
-  *
-  * @param bi         The break iterator.
-  * @param text       The new (moved) text string.
-  * @param status     Receives errors detected by this function.
-  *
-  * @stable ICU 49
-  */
-U_CAPI void U_EXPORT2
-ubrk_refreshUText(UBreakIterator *bi,
-                       UText          *text,
-                       UErrorCode     *status);
-
-
-/**
- * Get a compiled binary version of the rules specifying the behavior of a UBreakIterator.
- * The binary rules may be used with ubrk_openBinaryRules to open a new UBreakIterator
- * more quickly than using ubrk_openRules. The compiled rules are not compatible across
- * different major versions of ICU, nor across platforms of different endianness or
- * different base character set family (ASCII vs EBCDIC). Supports preflighting (with
- * binaryRules=NULL and rulesCapacity=0) to get the rules length without copying them to
- * the binaryRules buffer. However, whether preflighting or not, if the actual length
- * is greater than INT32_MAX, then the function returns 0 and sets *status to
- * U_INDEX_OUTOFBOUNDS_ERROR.
-
- * @param bi            The break iterator to use.
- * @param binaryRules   Buffer to receive the compiled binary rules; set to NULL for
- *                      preflighting.
- * @param rulesCapacity Capacity (in bytes) of the binaryRules buffer; set to 0 for
- *                      preflighting. Must be >= 0.
- * @param status        Pointer to UErrorCode to receive any errors, such as
- *                      U_BUFFER_OVERFLOW_ERROR, U_INDEX_OUTOFBOUNDS_ERROR, or
- *                      U_ILLEGAL_ARGUMENT_ERROR.
- * @return              The actual byte length of the binary rules, if <= INT32_MAX;
- *                      otherwise 0. If not preflighting and this is larger than
- *                      rulesCapacity, *status will be set to an error.
- * @see ubrk_openBinaryRules
- * @stable ICU 59
- */
-U_CAPI int32_t U_EXPORT2
-ubrk_getBinaryRules(UBreakIterator *bi,
-                    uint8_t *       binaryRules, int32_t rulesCapacity,
-                    UErrorCode *    status);
-
-#endif /* #if !UCONFIG_NO_BREAK_ITERATION */
-
-#endif

app/src/main/cpp/icu4c/include/unicode/ucnv_err.h

@@ -1,465 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-**********************************************************************
-*   Copyright (C) 1999-2009, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-**********************************************************************
- *
- *
- *   ucnv_err.h:
- */
-
-/**
- * \file
- * \brief C UConverter predefined error callbacks
- *
- *  <h2>Error Behaviour Functions</h2>
- *  Defines some error behaviour functions called by ucnv_{from,to}Unicode
- *  These are provided as part of ICU and many are stable, but they
- *  can also be considered only as an example of what can be done with
- *  callbacks.  You may of course write your own.
- *
- *  If you want to write your own, you may also find the functions from
- *  ucnv_cb.h useful when writing your own callbacks.
- *
- *  These functions, although public, should NEVER be called directly.
- *  They should be used as parameters to the ucnv_setFromUCallback
- *  and ucnv_setToUCallback functions, to set the behaviour of a converter
- *  when it encounters ILLEGAL/UNMAPPED/INVALID sequences.
- *
- *  usage example:  'STOP' doesn't need any context, but newContext
- *    could be set to something other than 'NULL' if needed. The available
- *    contexts in this header can modify the default behavior of the callback.
- *
- *  \code
- *  UErrorCode err = U_ZERO_ERROR;
- *  UConverter *myConverter = ucnv_open("ibm-949", &err);
- *  const void *oldContext;
- *  UConverterFromUCallback oldAction;
- *
- *
- *  if (U_SUCCESS(err))
- *  {
- *      ucnv_setFromUCallBack(myConverter,
- *                       UCNV_FROM_U_CALLBACK_STOP,
- *                       NULL,
- *                       &oldAction,
- *                       &oldContext,
- *                       &status);
- *  }
- *  \endcode
- *
- *  The code above tells "myConverter" to stop when it encounters an
- *  ILLEGAL/TRUNCATED/INVALID sequences when it is used to convert from
- *  Unicode -> Codepage. The behavior from Codepage to Unicode is not changed,
- *  and ucnv_setToUCallBack would need to be called in order to change
- *  that behavior too.
- *
- *  Here is an example with a context:
- *
- *  \code
- *  UErrorCode err = U_ZERO_ERROR;
- *  UConverter *myConverter = ucnv_open("ibm-949", &err);
- *  const void *oldContext;
- *  UConverterFromUCallback oldAction;
- *
- *
- *  if (U_SUCCESS(err))
- *  {
- *      ucnv_setToUCallBack(myConverter,
- *                       UCNV_TO_U_CALLBACK_SUBSTITUTE,
- *                       UCNV_SUB_STOP_ON_ILLEGAL,
- *                       &oldAction,
- *                       &oldContext,
- *                       &status);
- *  }
- *  \endcode
- *
- *  The code above tells "myConverter" to stop when it encounters an
- *  ILLEGAL/TRUNCATED/INVALID sequences when it is used to convert from
- *  Codepage -> Unicode. Any unmapped and legal characters will be
- *  substituted to be the default substitution character.
- */
-
-#ifndef UCNV_ERR_H
-#define UCNV_ERR_H
-
-#include "unicode/utypes.h"
-
-#if !UCONFIG_NO_CONVERSION
-
-/** Forward declaring the UConverter structure. @stable ICU 2.0 */
-struct UConverter;
-
-/** @stable ICU 2.0 */
-typedef struct UConverter UConverter;
-
-/**
- * FROM_U, TO_U context options for sub callback
- * @stable ICU 2.0
- */
-#define UCNV_SUB_STOP_ON_ILLEGAL "i"
-
-/**
- * FROM_U, TO_U context options for skip callback
- * @stable ICU 2.0
- */
-#define UCNV_SKIP_STOP_ON_ILLEGAL "i"
-
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to ICU (%UXXXX) 
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_ICU       NULL
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to JAVA (\\uXXXX)
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_JAVA      "J"
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to C (\\uXXXX \\UXXXXXXXX)
- * TO_U_CALLBACK_ESCAPE option to escape the character value according to C (\\xXXXX)
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_C         "C"
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to XML Decimal escape \htmlonly(&amp;#DDDD;)\endhtmlonly
- * TO_U_CALLBACK_ESCAPE context option to escape the character value according to XML Decimal escape \htmlonly(&amp;#DDDD;)\endhtmlonly
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_XML_DEC   "D"
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to XML Hex escape \htmlonly(&amp;#xXXXX;)\endhtmlonly
- * TO_U_CALLBACK_ESCAPE context option to escape the character value according to XML Hex escape \htmlonly(&amp;#xXXXX;)\endhtmlonly
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_XML_HEX   "X"
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to Unicode (U+XXXXX)
- * @stable ICU 2.0
- */
-#define UCNV_ESCAPE_UNICODE   "U"
-
-/**
- * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to CSS2 conventions (\\HH..H<space>, that is,
- * a backslash, 1..6 hex digits, and a space)
- * @stable ICU 4.0
- */
-#define UCNV_ESCAPE_CSS2   "S"
-
-/** 
- * The process condition code to be used with the callbacks.  
- * Codes which are greater than UCNV_IRREGULAR should be 
- * passed on to any chained callbacks.
- * @stable ICU 2.0
- */
-typedef enum {
-    UCNV_UNASSIGNED = 0,  /**< The code point is unassigned.
-                             The error code U_INVALID_CHAR_FOUND will be set. */
-    UCNV_ILLEGAL = 1,     /**< The code point is illegal. For example, 
-                             \\x81\\x2E is illegal in SJIS because \\x2E
-                             is not a valid trail byte for the \\x81 
-                             lead byte.
-                             Also, starting with Unicode 3.0.1, non-shortest byte sequences
-                             in UTF-8 (like \\xC1\\xA1 instead of \\x61 for U+0061)
-                             are also illegal, not just irregular.
-                             The error code U_ILLEGAL_CHAR_FOUND will be set. */
-    UCNV_IRREGULAR = 2,   /**< The codepoint is not a regular sequence in 
-                             the encoding. For example, \\xED\\xA0\\x80..\\xED\\xBF\\xBF
-                             are irregular UTF-8 byte sequences for single surrogate
-                             code points.
-                             The error code U_INVALID_CHAR_FOUND will be set. */
-    UCNV_RESET = 3,       /**< The callback is called with this reason when a
-                             'reset' has occurred. Callback should reset all
-                             state. */
-    UCNV_CLOSE = 4,        /**< Called when the converter is closed. The
-                             callback should release any allocated memory.*/
-    UCNV_CLONE = 5         /**< Called when ucnv_safeClone() is called on the
-                              converter. the pointer available as the
-                              'context' is an alias to the original converters'
-                              context pointer. If the context must be owned
-                              by the new converter, the callback must clone 
-                              the data and call ucnv_setFromUCallback 
-                              (or setToUCallback) with the correct pointer.
-                              @stable ICU 2.2
-                           */
-} UConverterCallbackReason;
-
-
-/**
- * The structure for the fromUnicode callback function parameter.
- * @stable ICU 2.0
- */
-typedef struct {
-    uint16_t size;              /**< The size of this struct. @stable ICU 2.0 */
-    UBool flush;                /**< The internal state of converter will be reset and data flushed if set to true. @stable ICU 2.0    */
-    UConverter *converter;      /**< Pointer to the converter that is opened and to which this struct is passed as an argument. @stable ICU 2.0  */
-    const UChar *source;        /**< Pointer to the source source buffer. @stable ICU 2.0    */
-    const UChar *sourceLimit;   /**< Pointer to the limit (end + 1) of source buffer. @stable ICU 2.0    */
-    char *target;               /**< Pointer to the target buffer. @stable ICU 2.0    */
-    const char *targetLimit;    /**< Pointer to the limit (end + 1) of target buffer. @stable ICU 2.0     */
-    int32_t *offsets;           /**< Pointer to the buffer that receives the offsets. *offset = blah ; offset++;. @stable ICU 2.0  */
-} UConverterFromUnicodeArgs;
-
-
-/**
- * The structure for the toUnicode callback function parameter.
- * @stable ICU 2.0
- */
-typedef struct {
-    uint16_t size;              /**< The size of this struct   @stable ICU 2.0 */
-    UBool flush;                /**< The internal state of converter will be reset and data flushed if set to true. @stable ICU 2.0   */
-    UConverter *converter;      /**< Pointer to the converter that is opened and to which this struct is passed as an argument. @stable ICU 2.0 */
-    const char *source;         /**< Pointer to the source source buffer. @stable ICU 2.0    */
-    const char *sourceLimit;    /**< Pointer to the limit (end + 1) of source buffer. @stable ICU 2.0    */
-    UChar *target;              /**< Pointer to the target buffer. @stable ICU 2.0    */
-    const UChar *targetLimit;   /**< Pointer to the limit (end + 1) of target buffer. @stable ICU 2.0     */
-    int32_t *offsets;           /**< Pointer to the buffer that receives the offsets. *offset = blah ; offset++;. @stable ICU 2.0  */
-} UConverterToUnicodeArgs;
-
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This From Unicode callback STOPS at the ILLEGAL_SEQUENCE,
- * returning the error code back to the caller immediately.
- *
- * @param context Pointer to the callback's private data
- * @param fromUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint.
- * @param reason Defines the reason the callback was invoked
- * @param err This should always be set to a failure status prior to calling.
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_STOP (
-                  const void *context,
-                  UConverterFromUnicodeArgs *fromUArgs,
-                  const UChar* codeUnits,
-                  int32_t length,
-                  UChar32 codePoint,
-                  UConverterCallbackReason reason,
-                  UErrorCode * err);
-
-
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This To Unicode callback STOPS at the ILLEGAL_SEQUENCE,
- * returning the error code back to the caller immediately.
- *
- * @param context Pointer to the callback's private data
- * @param toUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' bytes of the concerned codepage sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param reason Defines the reason the callback was invoked
- * @param err This should always be set to a failure status prior to calling.
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_STOP (
-                  const void *context,
-                  UConverterToUnicodeArgs *toUArgs,
-                  const char* codeUnits,
-                  int32_t length,
-                  UConverterCallbackReason reason,
-                  UErrorCode * err);
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This From Unicode callback skips any ILLEGAL_SEQUENCE, or
- * skips only UNASSINGED_SEQUENCE depending on the context parameter
- * simply ignoring those characters. 
- *
- * @param context  The function currently recognizes the callback options:
- *                 UCNV_SKIP_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE,
- *                      returning the error code back to the caller immediately.
- *                 NULL: Skips any ILLEGAL_SEQUENCE
- * @param fromUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint.
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- *      otherwise this value will be set to a failure status.
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SKIP (
-                  const void *context,
-                  UConverterFromUnicodeArgs *fromUArgs,
-                  const UChar* codeUnits,
-                  int32_t length,
-                  UChar32 codePoint,
-                  UConverterCallbackReason reason,
-                  UErrorCode * err);
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This From Unicode callback will Substitute the ILLEGAL SEQUENCE, or 
- * UNASSIGNED_SEQUENCE depending on context parameter, with the
- * current substitution string for the converter. This is the default
- * callback.
- *
- * @param context The function currently recognizes the callback options:
- *                 UCNV_SUB_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE,
- *                      returning the error code back to the caller immediately.
- *                 NULL: Substitutes any ILLEGAL_SEQUENCE
- * @param fromUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint.
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- *      otherwise this value will be set to a failure status.
- * @see ucnv_setSubstChars
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SUBSTITUTE (
-                  const void *context,
-                  UConverterFromUnicodeArgs *fromUArgs,
-                  const UChar* codeUnits,
-                  int32_t length,
-                  UChar32 codePoint,
-                  UConverterCallbackReason reason,
-                  UErrorCode * err);
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This From Unicode callback will Substitute the ILLEGAL SEQUENCE with the
- * hexadecimal representation of the illegal codepoints
- *
- * @param context The function currently recognizes the callback options:
- *        <ul>
- *        <li>UCNV_ESCAPE_ICU: Substitues the  ILLEGAL SEQUENCE with the hexadecimal 
- *          representation in the format  %UXXXX, e.g. "%uFFFE%u00AC%uC8FE"). 
- *          In the Event the converter doesn't support the characters {%,U}[A-F][0-9], 
- *          it will  substitute  the illegal sequence with the substitution characters.
- *          Note that  codeUnit(32bit int eg: unit of a surrogate pair) is represented as
- *          %UD84D%UDC56</li>
- *        <li>UCNV_ESCAPE_JAVA: Substitues the  ILLEGAL SEQUENCE with the hexadecimal 
- *          representation in the format  \\uXXXX, e.g. "\\uFFFE\\u00AC\\uC8FE"). 
- *          In the Event the converter doesn't support the characters {\,u}[A-F][0-9], 
- *          it will  substitute  the illegal sequence with the substitution characters.
- *          Note that  codeUnit(32bit int eg: unit of a surrogate pair) is represented as
- *          \\uD84D\\uDC56</li>
- *        <li>UCNV_ESCAPE_C: Substitues the  ILLEGAL SEQUENCE with the hexadecimal 
- *          representation in the format  \\uXXXX, e.g. "\\uFFFE\\u00AC\\uC8FE"). 
- *          In the Event the converter doesn't support the characters {\,u,U}[A-F][0-9], 
- *          it will  substitute  the illegal sequence with the substitution characters.
- *          Note that  codeUnit(32bit int eg: unit of a surrogate pair) is represented as
- *          \\U00023456</li>
- *        <li>UCNV_ESCAPE_XML_DEC: Substitues the  ILLEGAL SEQUENCE with the decimal 
- *          representation in the format \htmlonly&amp;#DDDDDDDD;, e.g. "&amp;#65534;&amp;#172;&amp;#51454;")\endhtmlonly. 
- *          In the Event the converter doesn't support the characters {&amp;,#}[0-9], 
- *          it will  substitute  the illegal sequence with the substitution characters.
- *          Note that  codeUnit(32bit int eg: unit of a surrogate pair) is represented as
- *          &amp;#144470; and Zero padding is ignored.</li>
- *        <li>UCNV_ESCAPE_XML_HEX:Substitues the  ILLEGAL SEQUENCE with the decimal 
- *          representation in the format \htmlonly&amp;#xXXXX; e.g. "&amp;#xFFFE;&amp;#x00AC;&amp;#xC8FE;")\endhtmlonly. 
- *          In the Event the converter doesn't support the characters {&,#,x}[0-9], 
- *          it will  substitute  the illegal sequence with the substitution characters.
- *          Note that  codeUnit(32bit int eg: unit of a surrogate pair) is represented as
- *          \htmlonly&amp;#x23456;\endhtmlonly</li>
- *        </ul>
- * @param fromUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint.
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- *      otherwise this value will be set to a failure status.
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_ESCAPE (
-                  const void *context,
-                  UConverterFromUnicodeArgs *fromUArgs,
-                  const UChar* codeUnits,
-                  int32_t length,
-                  UChar32 codePoint,
-                  UConverterCallbackReason reason,
-                  UErrorCode * err);
-
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This To Unicode callback skips any ILLEGAL_SEQUENCE, or
- * skips only UNASSINGED_SEQUENCE depending on the context parameter
- * simply ignoring those characters. 
- *
- * @param context  The function currently recognizes the callback options:
- *                 UCNV_SKIP_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE,
- *                      returning the error code back to the caller immediately.
- *                 NULL: Skips any ILLEGAL_SEQUENCE
- * @param toUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' bytes of the concerned codepage sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- *      otherwise this value will be set to a failure status.
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_SKIP (
-                  const void *context,
-                  UConverterToUnicodeArgs *toUArgs,
-                  const char* codeUnits,
-                  int32_t length,
-                  UConverterCallbackReason reason,
-                  UErrorCode * err);
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This To Unicode callback will Substitute the ILLEGAL SEQUENCE,or 
- * UNASSIGNED_SEQUENCE depending on context parameter,  with the
- * Unicode substitution character, U+FFFD.
- *
- * @param context  The function currently recognizes the callback options:
- *                 UCNV_SUB_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE,
- *                      returning the error code back to the caller immediately.
- *                 NULL: Substitutes any ILLEGAL_SEQUENCE
- * @param toUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' bytes of the concerned codepage sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- *      otherwise this value will be set to a failure status.
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_SUBSTITUTE (
-                  const void *context,
-                  UConverterToUnicodeArgs *toUArgs,
-                  const char* codeUnits,
-                  int32_t length,
-                  UConverterCallbackReason reason,
-                  UErrorCode * err);
-
-/**
- * DO NOT CALL THIS FUNCTION DIRECTLY!
- * This To Unicode callback will Substitute the ILLEGAL SEQUENCE with the
- * hexadecimal representation of the illegal bytes
- *  (in the format  %XNN, e.g. "%XFF%X0A%XC8%X03").
- *
- * @param context This function currently recognizes the callback options:
- *      UCNV_ESCAPE_ICU, UCNV_ESCAPE_JAVA, UCNV_ESCAPE_C, UCNV_ESCAPE_XML_DEC,
- *      UCNV_ESCAPE_XML_HEX and UCNV_ESCAPE_UNICODE.
- * @param toUArgs Information about the conversion in progress
- * @param codeUnits Points to 'length' bytes of the concerned codepage sequence
- * @param length Size (in bytes) of the concerned codepage sequence
- * @param reason Defines the reason the callback was invoked
- * @param err Return value will be set to success if the callback was handled,
- *      otherwise this value will be set to a failure status.
- * @stable ICU 2.0
- */
-
-U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_ESCAPE (
-                  const void *context,
-                  UConverterToUnicodeArgs *toUArgs,
-                  const char* codeUnits,
-                  int32_t length,
-                  UConverterCallbackReason reason,
-                  UErrorCode * err);
-
-#endif
-
-#endif
-
-/*UCNV_ERR_H*/ 

app/src/main/cpp/icu4c/include/unicode/uconfig.h

@@ -1,456 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*  
-**********************************************************************
-*   Copyright (C) 2002-2016, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-**********************************************************************
-*   file name:  uconfig.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:4
-*
-*   created on: 2002sep19
-*   created by: Markus W. Scherer
-*/
-
-#ifndef __UCONFIG_H__
-#define __UCONFIG_H__
-
-
-/*!
- * \file
- * \brief User-configurable settings
- *
- * Miscellaneous switches:
- *
- * A number of macros affect a variety of minor aspects of ICU.
- * Most of them used to be defined elsewhere (e.g., in utypes.h or platform.h)
- * and moved here to make them easier to find.
- *
- * Switches for excluding parts of ICU library code modules:
- *
- * Changing these macros allows building partial, smaller libraries for special purposes.
- * By default, all modules are built.
- * The switches are fairly coarse, controlling large modules.
- * Basic services cannot be turned off.
- *
- * Building with any of these options does not guarantee that the
- * ICU build process will completely work. It is recommended that
- * the ICU libraries and data be built using the normal build.
- * At that time you should remove the data used by those services.
- * After building the ICU data library, you should rebuild the ICU
- * libraries with these switches customized to your needs.
- *
- * @stable ICU 2.4
- */
-
-/**
- * If this switch is defined, ICU will attempt to load a header file named "uconfig_local.h"
- * prior to determining default settings for uconfig variables.
- *
- * @internal ICU 4.0
- */
-#if defined(UCONFIG_USE_LOCAL)
-#include "uconfig_local.h"
-#endif
-
-/**
- * \def U_DEBUG
- * Determines whether to include debugging code.
- * Automatically set on Windows, but most compilers do not have
- * related predefined macros.
- * @internal
- */
-#ifdef U_DEBUG
-    /* Use the predefined value. */
-#elif defined(_DEBUG)
-    /*
-     * _DEBUG is defined by Visual Studio debug compilation.
-     * Do *not* test for its NDEBUG macro: It is an orthogonal macro
-     * which disables assert().
-     */
-#   define U_DEBUG 1
-# else
-#   define U_DEBUG 0
-#endif
-
-/**
- * Determines whether to enable auto cleanup of libraries. 
- * @internal
- */
-#ifndef UCLN_NO_AUTO_CLEANUP
-#define UCLN_NO_AUTO_CLEANUP 1
-#endif
-
-/**
- * \def U_DISABLE_RENAMING
- * Determines whether to disable renaming or not.
- * @internal
- */
-#ifndef U_DISABLE_RENAMING
-#define U_DISABLE_RENAMING 0
-#endif
-
-/**
- * \def U_NO_DEFAULT_INCLUDE_UTF_HEADERS
- * Determines whether utypes.h includes utf.h, utf8.h, utf16.h and utf_old.h.
- * utypes.h includes those headers if this macro is defined to 0.
- * Otherwise, each those headers must be included explicitly when using one of their macros.
- * Defaults to 0 for backward compatibility, except inside ICU.
- * @stable ICU 49
- */
-#ifdef U_NO_DEFAULT_INCLUDE_UTF_HEADERS
-    /* Use the predefined value. */
-#elif defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || defined(U_I18N_IMPLEMENTATION) || \
-      defined(U_IO_IMPLEMENTATION) || defined(U_LAYOUT_IMPLEMENTATION) || defined(U_LAYOUTEX_IMPLEMENTATION) || \
-      defined(U_TOOLUTIL_IMPLEMENTATION)
-#   define U_NO_DEFAULT_INCLUDE_UTF_HEADERS 1
-#else
-#   define U_NO_DEFAULT_INCLUDE_UTF_HEADERS 0
-#endif
-
-/**
- * \def U_OVERRIDE_CXX_ALLOCATION
- * Determines whether to override new and delete.
- * ICU is normally built such that all of its C++ classes, via their UMemory base,
- * override operators new and delete to use its internal, customizable,
- * non-exception-throwing memory allocation functions. (Default value 1 for this macro.)
- *
- * This is especially important when the application and its libraries use multiple heaps.
- * For example, on Windows, this allows the ICU DLL to be used by
- * applications that statically link the C Runtime library.
- *
- * @stable ICU 2.2
- */
-#ifndef U_OVERRIDE_CXX_ALLOCATION
-#define U_OVERRIDE_CXX_ALLOCATION 1
-#endif
-
-/**
- * \def U_ENABLE_TRACING
- * Determines whether to enable tracing.
- * @internal
- */
-#ifndef U_ENABLE_TRACING
-#define U_ENABLE_TRACING 0
-#endif
-
-/**
- * \def UCONFIG_ENABLE_PLUGINS
- * Determines whether to enable ICU plugins.
- * @internal
- */
-#ifndef UCONFIG_ENABLE_PLUGINS
-#define UCONFIG_ENABLE_PLUGINS 0
-#endif
-
-/**
- * \def U_ENABLE_DYLOAD
- * Whether to enable Dynamic loading in ICU.
- * @internal
- */
-#ifndef U_ENABLE_DYLOAD
-#define U_ENABLE_DYLOAD 1
-#endif
-
-/**
- * \def U_CHECK_DYLOAD
- * Whether to test Dynamic loading as an OS capability.
- * @internal
- */
-#ifndef U_CHECK_DYLOAD
-#define U_CHECK_DYLOAD 1
-#endif
-
-/**
- * \def U_DEFAULT_SHOW_DRAFT
- * Do we allow ICU users to use the draft APIs by default?
- * @internal
- */
-#ifndef U_DEFAULT_SHOW_DRAFT
-#define U_DEFAULT_SHOW_DRAFT 1
-#endif
-
-/*===========================================================================*/
-/* Custom icu entry point renaming                                           */
-/*===========================================================================*/
-
-/**
- * \def U_HAVE_LIB_SUFFIX
- * 1 if a custom library suffix is set.
- * @internal
- */
-#ifdef U_HAVE_LIB_SUFFIX
-    /* Use the predefined value. */
-#elif defined(U_LIB_SUFFIX_C_NAME) || defined(U_IN_DOXYGEN)
-#   define U_HAVE_LIB_SUFFIX 1
-#endif
-
-/**
- * \def U_LIB_SUFFIX_C_NAME_STRING
- * Defines the library suffix as a string with C syntax.
- * @internal
- */
-#ifdef U_LIB_SUFFIX_C_NAME_STRING
-    /* Use the predefined value. */
-#elif defined(U_LIB_SUFFIX_C_NAME)
-#   define CONVERT_TO_STRING(s) #s
-#   define U_LIB_SUFFIX_C_NAME_STRING CONVERT_TO_STRING(U_LIB_SUFFIX_C_NAME)
-#else
-#   define U_LIB_SUFFIX_C_NAME_STRING ""
-#endif
-
-/* common/i18n library switches --------------------------------------------- */
-
-/**
- * \def UCONFIG_ONLY_COLLATION
- * This switch turns off modules that are not needed for collation.
- *
- * It does not turn off legacy conversion because that is necessary
- * for ICU to work on EBCDIC platforms (for the default converter).
- * If you want "only collation" and do not build for EBCDIC,
- * then you can define UCONFIG_NO_CONVERSION or UCONFIG_NO_LEGACY_CONVERSION to 1 as well.
- *
- * @stable ICU 2.4
- */
-#ifndef UCONFIG_ONLY_COLLATION
-#   define UCONFIG_ONLY_COLLATION 0
-#endif
-
-#if UCONFIG_ONLY_COLLATION
-    /* common library */
-#   define UCONFIG_NO_BREAK_ITERATION 1
-#   define UCONFIG_NO_IDNA 1
-
-    /* i18n library */
-#   if UCONFIG_NO_COLLATION
-#       error Contradictory collation switches in uconfig.h.
-#   endif
-#   define UCONFIG_NO_FORMATTING 1
-#   define UCONFIG_NO_TRANSLITERATION 1
-#   define UCONFIG_NO_REGULAR_EXPRESSIONS 1
-#endif
-
-/* common library switches -------------------------------------------------- */
-
-/**
- * \def UCONFIG_NO_FILE_IO
- * This switch turns off all file access in the common library
- * where file access is only used for data loading.
- * ICU data must then be provided in the form of a data DLL (or with an
- * equivalent way to link to the data residing in an executable,
- * as in building a combined library with both the common library's code and
- * the data), or via udata_setCommonData().
- * Application data must be provided via udata_setAppData() or by using
- * "open" functions that take pointers to data, for example ucol_openBinary().
- *
- * File access is not used at all in the i18n library.
- *
- * File access cannot be turned off for the icuio library or for the ICU
- * test suites and ICU tools.
- *
- * @stable ICU 3.6
- */
-#ifndef UCONFIG_NO_FILE_IO
-#   define UCONFIG_NO_FILE_IO 0
-#endif
-
-#if UCONFIG_NO_FILE_IO && defined(U_TIMEZONE_FILES_DIR) 
-#   error Contradictory file io switches in uconfig.h.
-#endif
-
-/**
- * \def UCONFIG_NO_CONVERSION
- * ICU will not completely build (compiling the tools fails) with this
- * switch turned on.
- * This switch turns off all converters.
- *
- * You may want to use this together with U_CHARSET_IS_UTF8 defined to 1
- * in utypes.h if char* strings in your environment are always in UTF-8.
- *
- * @stable ICU 3.2
- * @see U_CHARSET_IS_UTF8
- */
-#ifndef UCONFIG_NO_CONVERSION
-#   define UCONFIG_NO_CONVERSION 0
-#endif
-
-#if UCONFIG_NO_CONVERSION
-#   define UCONFIG_NO_LEGACY_CONVERSION 1
-#endif
-
-/**
- * \def UCONFIG_ONLY_HTML_CONVERSION
- * This switch turns off all of the converters NOT listed in
- * the HTML encoding standard:
- * http://www.w3.org/TR/encoding/#names-and-labels
- *
- * This is not possible on EBCDIC platforms
- * because they need ibm-37 or ibm-1047 default converters.
- *
- * @stable ICU 55
- */
-#ifndef UCONFIG_ONLY_HTML_CONVERSION
-#   define UCONFIG_ONLY_HTML_CONVERSION 0
-#endif
-
-/**
- * \def UCONFIG_NO_LEGACY_CONVERSION
- * This switch turns off all converters except for
- * - Unicode charsets (UTF-7/8/16/32, CESU-8, SCSU, BOCU-1)
- * - US-ASCII
- * - ISO-8859-1
- *
- * Turning off legacy conversion is not possible on EBCDIC platforms
- * because they need ibm-37 or ibm-1047 default converters.
- *
- * @stable ICU 2.4
- */
-#ifndef UCONFIG_NO_LEGACY_CONVERSION
-#   define UCONFIG_NO_LEGACY_CONVERSION 0
-#endif
-
-/**
- * \def UCONFIG_NO_NORMALIZATION
- * This switch turns off normalization.
- * It implies turning off several other services as well, for example
- * collation and IDNA.
- *
- * @stable ICU 2.6
- */
-#ifndef UCONFIG_NO_NORMALIZATION
-#   define UCONFIG_NO_NORMALIZATION 0
-#endif
-
-#if UCONFIG_NO_NORMALIZATION
-    /* common library */
-    /* ICU 50 CJK dictionary BreakIterator uses normalization */
-#   define UCONFIG_NO_BREAK_ITERATION 1
-    /* IDNA (UTS #46) is implemented via normalization */
-#   define UCONFIG_NO_IDNA 1
-
-    /* i18n library */
-#   if UCONFIG_ONLY_COLLATION
-#       error Contradictory collation switches in uconfig.h.
-#   endif
-#   define UCONFIG_NO_COLLATION 1
-#   define UCONFIG_NO_TRANSLITERATION 1
-#endif
-
-/**
- * \def UCONFIG_NO_BREAK_ITERATION
- * This switch turns off break iteration.
- *
- * @stable ICU 2.4
- */
-#ifndef UCONFIG_NO_BREAK_ITERATION
-#   define UCONFIG_NO_BREAK_ITERATION 0
-#endif
-
-/**
- * \def UCONFIG_NO_IDNA
- * This switch turns off IDNA.
- *
- * @stable ICU 2.6
- */
-#ifndef UCONFIG_NO_IDNA
-#   define UCONFIG_NO_IDNA 0
-#endif
-
-/**
- * \def UCONFIG_MSGPAT_DEFAULT_APOSTROPHE_MODE
- * Determines the default UMessagePatternApostropheMode.
- * See the documentation for that enum.
- *
- * @stable ICU 4.8
- */
-#ifndef UCONFIG_MSGPAT_DEFAULT_APOSTROPHE_MODE
-#   define UCONFIG_MSGPAT_DEFAULT_APOSTROPHE_MODE UMSGPAT_APOS_DOUBLE_OPTIONAL
-#endif
-
-/**
- * \def UCONFIG_USE_WINDOWS_LCID_MAPPING_API
- * On platforms where U_PLATFORM_HAS_WIN32_API is true, this switch determines
- * if the Windows platform APIs are used for LCID<->Locale Name conversions.
- * Otherwise, only the built-in ICU tables are used.
- * 
- * @internal ICU 64
- */
-#ifndef UCONFIG_USE_WINDOWS_LCID_MAPPING_API
-#   define UCONFIG_USE_WINDOWS_LCID_MAPPING_API 1
-#endif
-
-/* i18n library switches ---------------------------------------------------- */
-
-/**
- * \def UCONFIG_NO_COLLATION
- * This switch turns off collation and collation-based string search.
- *
- * @stable ICU 2.4
- */
-#ifndef UCONFIG_NO_COLLATION
-#   define UCONFIG_NO_COLLATION 0
-#endif
-
-/**
- * \def UCONFIG_NO_FORMATTING
- * This switch turns off formatting and calendar/timezone services.
- *
- * @stable ICU 2.4
- */
-#ifndef UCONFIG_NO_FORMATTING
-#   define UCONFIG_NO_FORMATTING 0
-#endif
-
-/**
- * \def UCONFIG_NO_TRANSLITERATION
- * This switch turns off transliteration.
- *
- * @stable ICU 2.4
- */
-#ifndef UCONFIG_NO_TRANSLITERATION
-#   define UCONFIG_NO_TRANSLITERATION 0
-#endif
-
-/**
- * \def UCONFIG_NO_REGULAR_EXPRESSIONS
- * This switch turns off regular expressions.
- *
- * @stable ICU 2.4
- */
-#ifndef UCONFIG_NO_REGULAR_EXPRESSIONS
-#   define UCONFIG_NO_REGULAR_EXPRESSIONS 0
-#endif
-
-/**
- * \def UCONFIG_NO_SERVICE
- * This switch turns off service registration.
- *
- * @stable ICU 3.2
- */
-#ifndef UCONFIG_NO_SERVICE
-#   define UCONFIG_NO_SERVICE 0
-#endif
-
-/**
- * \def UCONFIG_HAVE_PARSEALLINPUT
- * This switch turns on the "parse all input" attribute. Binary incompatible.
- *
- * @internal
- */
-#ifndef UCONFIG_HAVE_PARSEALLINPUT
-#   define UCONFIG_HAVE_PARSEALLINPUT 1
-#endif
-
-/**
- * \def UCONFIG_NO_FILTERED_BREAK_ITERATION
- * This switch turns off filtered break iteration code.
- *
- * @internal
- */
-#ifndef UCONFIG_NO_FILTERED_BREAK_ITERATION
-#   define UCONFIG_NO_FILTERED_BREAK_ITERATION 0
-#endif
-
-#endif  // __UCONFIG_H__

app/src/main/cpp/icu4c/include/unicode/ucpmap.h

@@ -1,159 +0,0 @@
-// © 2018 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-
-// ucpmap.h
-// created: 2018sep03 Markus W. Scherer
-
-#ifndef __UCPMAP_H__
-#define __UCPMAP_H__
-
-#include "unicode/utypes.h"
-
-U_CDECL_BEGIN
-
-/**
- * \file
- *
- * This file defines an abstract map from Unicode code points to integer values.
- *
- * @see UCPMap
- * @see UCPTrie
- * @see UMutableCPTrie
- */
-
-/**
- * Abstract map from Unicode code points (U+0000..U+10FFFF) to integer values.
- *
- * @see UCPTrie
- * @see UMutableCPTrie
- * @stable ICU 63
- */
-typedef struct UCPMap UCPMap;
-
-/**
- * Selectors for how ucpmap_getRange() etc. should report value ranges overlapping with surrogates.
- * Most users should use UCPMAP_RANGE_NORMAL.
- *
- * @see ucpmap_getRange
- * @see ucptrie_getRange
- * @see umutablecptrie_getRange
- * @stable ICU 63
- */
-enum UCPMapRangeOption {
-    /**
-     * ucpmap_getRange() enumerates all same-value ranges as stored in the map.
-     * Most users should use this option.
-     * @stable ICU 63
-     */
-    UCPMAP_RANGE_NORMAL,
-    /**
-     * ucpmap_getRange() enumerates all same-value ranges as stored in the map,
-     * except that lead surrogates (U+D800..U+DBFF) are treated as having the
-     * surrogateValue, which is passed to getRange() as a separate parameter.
-     * The surrogateValue is not transformed via filter().
-     * See U_IS_LEAD(c).
-     *
-     * Most users should use UCPMAP_RANGE_NORMAL instead.
-     *
-     * This option is useful for maps that map surrogate code *units* to
-     * special values optimized for UTF-16 string processing
-     * or for special error behavior for unpaired surrogates,
-     * but those values are not to be associated with the lead surrogate code *points*.
-     * @stable ICU 63
-     */
-    UCPMAP_RANGE_FIXED_LEAD_SURROGATES,
-    /**
-     * ucpmap_getRange() enumerates all same-value ranges as stored in the map,
-     * except that all surrogates (U+D800..U+DFFF) are treated as having the
-     * surrogateValue, which is passed to getRange() as a separate parameter.
-     * The surrogateValue is not transformed via filter().
-     * See U_IS_SURROGATE(c).
-     *
-     * Most users should use UCPMAP_RANGE_NORMAL instead.
-     *
-     * This option is useful for maps that map surrogate code *units* to
-     * special values optimized for UTF-16 string processing
-     * or for special error behavior for unpaired surrogates,
-     * but those values are not to be associated with the lead surrogate code *points*.
-     * @stable ICU 63
-     */
-    UCPMAP_RANGE_FIXED_ALL_SURROGATES
-};
-#ifndef U_IN_DOXYGEN
-typedef enum UCPMapRangeOption UCPMapRangeOption;
-#endif
-
-/**
- * Returns the value for a code point as stored in the map, with range checking.
- * Returns an implementation-defined error value if c is not in the range 0..U+10FFFF.
- *
- * @param map the map
- * @param c the code point
- * @return the map value,
- *         or an implementation-defined error value if the code point is not in the range 0..U+10FFFF
- * @stable ICU 63
- */
-U_CAPI uint32_t U_EXPORT2
-ucpmap_get(const UCPMap *map, UChar32 c);
-
-/**
- * Callback function type: Modifies a map value.
- * Optionally called by ucpmap_getRange()/ucptrie_getRange()/umutablecptrie_getRange().
- * The modified value will be returned by the getRange function.
- *
- * Can be used to ignore some of the value bits,
- * make a filter for one of several values,
- * return a value index computed from the map value, etc.
- *
- * @param context an opaque pointer, as passed into the getRange function
- * @param value a value from the map
- * @return the modified value
- * @stable ICU 63
- */
-typedef uint32_t U_CALLCONV
-UCPMapValueFilter(const void *context, uint32_t value);
-
-/**
- * Returns the last code point such that all those from start to there have the same value.
- * Can be used to efficiently iterate over all same-value ranges in a map.
- * (This is normally faster than iterating over code points and get()ting each value,
- * but much slower than a data structure that stores ranges directly.)
- *
- * If the UCPMapValueFilter function pointer is not NULL, then
- * the value to be delivered is passed through that function, and the return value is the end
- * of the range where all values are modified to the same actual value.
- * The value is unchanged if that function pointer is NULL.
- *
- * Example:
- * \code
- * UChar32 start = 0, end;
- * uint32_t value;
- * while ((end = ucpmap_getRange(map, start, UCPMAP_RANGE_NORMAL, 0,
- *                               NULL, NULL, &value)) >= 0) {
- *     // Work with the range start..end and its value.
- *     start = end + 1;
- * }
- * \endcode
- *
- * @param map the map
- * @param start range start
- * @param option defines whether surrogates are treated normally,
- *               or as having the surrogateValue; usually UCPMAP_RANGE_NORMAL
- * @param surrogateValue value for surrogates; ignored if option==UCPMAP_RANGE_NORMAL
- * @param filter a pointer to a function that may modify the map data value,
- *     or NULL if the values from the map are to be used unmodified
- * @param context an opaque pointer that is passed on to the filter function
- * @param pValue if not NULL, receives the value that every code point start..end has;
- *     may have been modified by filter(context, map value)
- *     if that function pointer is not NULL
- * @return the range end code point, or -1 if start is not a valid code point
- * @stable ICU 63
- */
-U_CAPI UChar32 U_EXPORT2
-ucpmap_getRange(const UCPMap *map, UChar32 start,
-                UCPMapRangeOption option, uint32_t surrogateValue,
-                UCPMapValueFilter *filter, const void *context, uint32_t *pValue);
-
-U_CDECL_END
-
-#endif

app/src/main/cpp/icu4c/include/unicode/uenum.h

@@ -1,209 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-*******************************************************************************
-*
-*   Copyright (C) 2002-2013, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-*******************************************************************************
-*   file name:  uenum.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:2
-*
-*   created on: 2002jul08
-*   created by: Vladimir Weinstein
-*/
-
-#ifndef __UENUM_H
-#define __UENUM_H
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-#include "unicode/localpointer.h"
-
-U_NAMESPACE_BEGIN
-class StringEnumeration;
-U_NAMESPACE_END
-#endif   // U_SHOW_CPLUSPLUS_API
-
-/**
- * \file
- * \brief C API: String Enumeration 
- */
- 
-/**
- * An enumeration object.
- * For usage in C programs.
- * @stable ICU 2.2
- */
-struct UEnumeration;
-/** structure representing an enumeration object instance @stable ICU 2.2 */
-typedef struct UEnumeration UEnumeration;
-
-/**
- * Disposes of resources in use by the iterator.  If en is NULL,
- * does nothing.  After this call, any char* or UChar* pointer
- * returned by uenum_unext() or uenum_next() is invalid.
- * @param en UEnumeration structure pointer
- * @stable ICU 2.2
- */
-U_CAPI void U_EXPORT2
-uenum_close(UEnumeration* en);
-
-#if U_SHOW_CPLUSPLUS_API
-
-U_NAMESPACE_BEGIN
-
-/**
- * \class LocalUEnumerationPointer
- * "Smart pointer" class, closes a UEnumeration via uenum_close().
- * For most methods see the LocalPointerBase base class.
- *
- * @see LocalPointerBase
- * @see LocalPointer
- * @stable ICU 4.4
- */
-U_DEFINE_LOCAL_OPEN_POINTER(LocalUEnumerationPointer, UEnumeration, uenum_close);
-
-U_NAMESPACE_END
-
-#endif
-
-/**
- * Returns the number of elements that the iterator traverses.  If
- * the iterator is out-of-sync with its service, status is set to
- * U_ENUM_OUT_OF_SYNC_ERROR.
- * This is a convenience function. It can end up being very
- * expensive as all the items might have to be pre-fetched (depending
- * on the type of data being traversed). Use with caution and only 
- * when necessary.
- * @param en UEnumeration structure pointer
- * @param status error code, can be U_ENUM_OUT_OF_SYNC_ERROR if the
- *               iterator is out of sync.
- * @return number of elements in the iterator
- * @stable ICU 2.2
- */
-U_CAPI int32_t U_EXPORT2
-uenum_count(UEnumeration* en, UErrorCode* status);
-
-/**
- * Returns the next element in the iterator's list.  If there are
- * no more elements, returns NULL.  If the iterator is out-of-sync
- * with its service, status is set to U_ENUM_OUT_OF_SYNC_ERROR and
- * NULL is returned.  If the native service string is a char* string,
- * it is converted to UChar* with the invariant converter.
- * The result is terminated by (UChar)0.
- * @param en the iterator object
- * @param resultLength pointer to receive the length of the result
- *                     (not including the terminating \\0).
- *                     If the pointer is NULL it is ignored.
- * @param status the error code, set to U_ENUM_OUT_OF_SYNC_ERROR if
- *               the iterator is out of sync with its service.
- * @return a pointer to the string.  The string will be
- *         zero-terminated.  The return pointer is owned by this iterator
- *         and must not be deleted by the caller.  The pointer is valid
- *         until the next call to any uenum_... method, including
- *         uenum_next() or uenum_unext().  When all strings have been
- *         traversed, returns NULL.
- * @stable ICU 2.2
- */
-U_CAPI const UChar* U_EXPORT2
-uenum_unext(UEnumeration* en,
-            int32_t* resultLength,
-            UErrorCode* status);
-
-/**
- * Returns the next element in the iterator's list.  If there are
- * no more elements, returns NULL.  If the iterator is out-of-sync
- * with its service, status is set to U_ENUM_OUT_OF_SYNC_ERROR and
- * NULL is returned.  If the native service string is a UChar*
- * string, it is converted to char* with the invariant converter.
- * The result is terminated by (char)0.  If the conversion fails
- * (because a character cannot be converted) then status is set to
- * U_INVARIANT_CONVERSION_ERROR and the return value is undefined
- * (but non-NULL).
- * @param en the iterator object
- * @param resultLength pointer to receive the length of the result
- *                     (not including the terminating \\0).
- *                     If the pointer is NULL it is ignored.
- * @param status the error code, set to U_ENUM_OUT_OF_SYNC_ERROR if
- *               the iterator is out of sync with its service.  Set to
- *               U_INVARIANT_CONVERSION_ERROR if the underlying native string is
- *               UChar* and conversion to char* with the invariant converter
- *               fails. This error pertains only to current string, so iteration
- *               might be able to continue successfully.
- * @return a pointer to the string.  The string will be
- *         zero-terminated.  The return pointer is owned by this iterator
- *         and must not be deleted by the caller.  The pointer is valid
- *         until the next call to any uenum_... method, including
- *         uenum_next() or uenum_unext().  When all strings have been
- *         traversed, returns NULL.
- * @stable ICU 2.2
- */
-U_CAPI const char* U_EXPORT2
-uenum_next(UEnumeration* en,
-           int32_t* resultLength,
-           UErrorCode* status);
-
-/**
- * Resets the iterator to the current list of service IDs.  This
- * re-establishes sync with the service and rewinds the iterator
- * to start at the first element.
- * @param en the iterator object
- * @param status the error code, set to U_ENUM_OUT_OF_SYNC_ERROR if
- *               the iterator is out of sync with its service.  
- * @stable ICU 2.2
- */
-U_CAPI void U_EXPORT2
-uenum_reset(UEnumeration* en, UErrorCode* status);
-
-#if U_SHOW_CPLUSPLUS_API
-
-/**
- * Given a StringEnumeration, wrap it in a UEnumeration.  The
- * StringEnumeration is adopted; after this call, the caller must not
- * delete it (regardless of error status).
- * @param adopted the C++ StringEnumeration to be wrapped in a UEnumeration.
- * @param ec the error code.
- * @return a UEnumeration wrapping the adopted StringEnumeration.
- * @stable ICU 4.2
- */
-U_CAPI UEnumeration* U_EXPORT2
-uenum_openFromStringEnumeration(icu::StringEnumeration* adopted, UErrorCode* ec);
-
-#endif
-
-/**
- * Given an array of const UChar* strings, return a UEnumeration.  String pointers from 0..count-1 must not be null.
- * Do not free or modify either the string array or the characters it points to until this object has been destroyed with uenum_close.
- * \snippet test/cintltst/uenumtst.c uenum_openUCharStringsEnumeration
- * @param strings array of const UChar* strings (each null terminated). All storage is owned by the caller.
- * @param count length of the array
- * @param ec error code
- * @return the new UEnumeration object. Caller is responsible for calling uenum_close to free memory.
- * @see uenum_close
- * @stable ICU 50
- */
-U_CAPI UEnumeration* U_EXPORT2
-uenum_openUCharStringsEnumeration(const UChar* const strings[], int32_t count,
-                                 UErrorCode* ec);
-
-/**
- * Given an array of const char* strings (invariant chars only), return a UEnumeration.  String pointers from 0..count-1 must not be null.
- * Do not free or modify either the string array or the characters it points to until this object has been destroyed with uenum_close.
- * \snippet test/cintltst/uenumtst.c uenum_openCharStringsEnumeration
- * @param strings array of char* strings (each null terminated).  All storage is owned by the caller.
- * @param count length of the array
- * @param ec error code
- * @return the new UEnumeration object. Caller is responsible for calling uenum_close to free memory
- * @see uenum_close
- * @stable ICU 50
- */
-U_CAPI UEnumeration* U_EXPORT2
-uenum_openCharStringsEnumeration(const char* const strings[], int32_t count,
-                                 UErrorCode* ec);
-
-#endif

app/src/main/cpp/icu4c/include/unicode/uiter.h

@@ -1,709 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-*******************************************************************************
-*
-*   Copyright (C) 2002-2011 International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-*******************************************************************************
-*   file name:  uiter.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:4
-*
-*   created on: 2002jan18
-*   created by: Markus W. Scherer
-*/
-
-#ifndef __UITER_H__
-#define __UITER_H__
-
-/**
- * \file
- * \brief C API: Unicode Character Iteration
- *
- * @see UCharIterator
- */
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-    U_NAMESPACE_BEGIN
-
-    class CharacterIterator;
-    class Replaceable;
-
-    U_NAMESPACE_END
-#endif
-
-U_CDECL_BEGIN
-
-struct UCharIterator;
-typedef struct UCharIterator UCharIterator; /**< C typedef for struct UCharIterator. @stable ICU 2.1 */
-
-/**
- * Origin constants for UCharIterator.getIndex() and UCharIterator.move().
- * @see UCharIteratorMove
- * @see UCharIterator
- * @stable ICU 2.1
- */
-typedef enum UCharIteratorOrigin {
-    UITER_START, UITER_CURRENT, UITER_LIMIT, UITER_ZERO, UITER_LENGTH
-} UCharIteratorOrigin;
-
-/** Constants for UCharIterator. @stable ICU 2.6 */
-enum {
-    /**
-     * Constant value that may be returned by UCharIteratorMove
-     * indicating that the final UTF-16 index is not known, but that the move succeeded.
-     * This can occur when moving relative to limit or length, or
-     * when moving relative to the current index after a setState()
-     * when the current UTF-16 index is not known.
-     *
-     * It would be very inefficient to have to count from the beginning of the text
-     * just to get the current/limit/length index after moving relative to it.
-     * The actual index can be determined with getIndex(UITER_CURRENT)
-     * which will count the UChars if necessary.
-     *
-     * @stable ICU 2.6
-     */
-    UITER_UNKNOWN_INDEX=-2
-};
-
-
-/**
- * Constant for UCharIterator getState() indicating an error or
- * an unknown state.
- * Returned by uiter_getState()/UCharIteratorGetState
- * when an error occurs.
- * Also, some UCharIterator implementations may not be able to return
- * a valid state for each position. This will be clearly documented
- * for each such iterator (none of the public ones here).
- *
- * @stable ICU 2.6
- */
-#define UITER_NO_STATE ((uint32_t)0xffffffff)
-
-/**
- * Function type declaration for UCharIterator.getIndex().
- *
- * Gets the current position, or the start or limit of the
- * iteration range.
- *
- * This function may perform slowly for UITER_CURRENT after setState() was called,
- * or for UITER_LENGTH, because an iterator implementation may have to count
- * UChars if the underlying storage is not UTF-16.
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @param origin get the 0, start, limit, length, or current index
- * @return the requested index, or U_SENTINEL in an error condition
- *
- * @see UCharIteratorOrigin
- * @see UCharIterator
- * @stable ICU 2.1
- */
-typedef int32_t U_CALLCONV
-UCharIteratorGetIndex(UCharIterator *iter, UCharIteratorOrigin origin);
-
-/**
- * Function type declaration for UCharIterator.move().
- *
- * Use iter->move(iter, index, UITER_ZERO) like CharacterIterator::setIndex(index).
- *
- * Moves the current position relative to the start or limit of the
- * iteration range, or relative to the current position itself.
- * The movement is expressed in numbers of code units forward
- * or backward by specifying a positive or negative delta.
- * Out of bounds movement will be pinned to the start or limit.
- *
- * This function may perform slowly for moving relative to UITER_LENGTH
- * because an iterator implementation may have to count the rest of the
- * UChars if the native storage is not UTF-16.
- *
- * When moving relative to the limit or length, or
- * relative to the current position after setState() was called,
- * move() may return UITER_UNKNOWN_INDEX (-2) to avoid an inefficient
- * determination of the actual UTF-16 index.
- * The actual index can be determined with getIndex(UITER_CURRENT)
- * which will count the UChars if necessary.
- * See UITER_UNKNOWN_INDEX for details.
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @param delta can be positive, zero, or negative
- * @param origin move relative to the 0, start, limit, length, or current index
- * @return the new index, or U_SENTINEL on an error condition,
- *         or UITER_UNKNOWN_INDEX when the index is not known.
- *
- * @see UCharIteratorOrigin
- * @see UCharIterator
- * @see UITER_UNKNOWN_INDEX
- * @stable ICU 2.1
- */
-typedef int32_t U_CALLCONV
-UCharIteratorMove(UCharIterator *iter, int32_t delta, UCharIteratorOrigin origin);
-
-/**
- * Function type declaration for UCharIterator.hasNext().
- *
- * Check if current() and next() can still
- * return another code unit.
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @return boolean value for whether current() and next() can still return another code unit
- *
- * @see UCharIterator
- * @stable ICU 2.1
- */
-typedef UBool U_CALLCONV
-UCharIteratorHasNext(UCharIterator *iter);
-
-/**
- * Function type declaration for UCharIterator.hasPrevious().
- *
- * Check if previous() can still return another code unit.
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @return boolean value for whether previous() can still return another code unit
- *
- * @see UCharIterator
- * @stable ICU 2.1
- */
-typedef UBool U_CALLCONV
-UCharIteratorHasPrevious(UCharIterator *iter);
- 
-/**
- * Function type declaration for UCharIterator.current().
- *
- * Return the code unit at the current position,
- * or U_SENTINEL if there is none (index is at the limit).
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @return the current code unit
- *
- * @see UCharIterator
- * @stable ICU 2.1
- */
-typedef UChar32 U_CALLCONV
-UCharIteratorCurrent(UCharIterator *iter);
-
-/**
- * Function type declaration for UCharIterator.next().
- *
- * Return the code unit at the current index and increment
- * the index (post-increment, like s[i++]),
- * or return U_SENTINEL if there is none (index is at the limit).
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @return the current code unit (and post-increment the current index)
- *
- * @see UCharIterator
- * @stable ICU 2.1
- */
-typedef UChar32 U_CALLCONV
-UCharIteratorNext(UCharIterator *iter);
-
-/**
- * Function type declaration for UCharIterator.previous().
- *
- * Decrement the index and return the code unit from there
- * (pre-decrement, like s[--i]),
- * or return U_SENTINEL if there is none (index is at the start).
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @return the previous code unit (after pre-decrementing the current index)
- *
- * @see UCharIterator
- * @stable ICU 2.1
- */
-typedef UChar32 U_CALLCONV
-UCharIteratorPrevious(UCharIterator *iter);
-
-/**
- * Function type declaration for UCharIterator.reservedFn().
- * Reserved for future use.
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @param something some integer argument
- * @return some integer
- *
- * @see UCharIterator
- * @stable ICU 2.1
- */
-typedef int32_t U_CALLCONV
-UCharIteratorReserved(UCharIterator *iter, int32_t something);
-
-/**
- * Function type declaration for UCharIterator.getState().
- *
- * Get the "state" of the iterator in the form of a single 32-bit word.
- * It is recommended that the state value be calculated to be as small as
- * is feasible. For strings with limited lengths, fewer than 32 bits may
- * be sufficient.
- *
- * This is used together with setState()/UCharIteratorSetState
- * to save and restore the iterator position more efficiently than with
- * getIndex()/move().
- *
- * The iterator state is defined as a uint32_t value because it is designed
- * for use in ucol_nextSortKeyPart() which provides 32 bits to store the state
- * of the character iterator.
- *
- * With some UCharIterator implementations (e.g., UTF-8),
- * getting and setting the UTF-16 index with existing functions
- * (getIndex(UITER_CURRENT) followed by move(pos, UITER_ZERO)) is possible but
- * relatively slow because the iterator has to "walk" from a known index
- * to the requested one.
- * This takes more time the farther it needs to go.
- *
- * An opaque state value allows an iterator implementation to provide
- * an internal index (UTF-8: the source byte array index) for
- * fast, constant-time restoration.
- *
- * After calling setState(), a getIndex(UITER_CURRENT) may be slow because
- * the UTF-16 index may not be restored as well, but the iterator can deliver
- * the correct text contents and move relative to the current position
- * without performance degradation.
- *
- * Some UCharIterator implementations may not be able to return
- * a valid state for each position, in which case they return UITER_NO_STATE instead.
- * This will be clearly documented for each such iterator (none of the public ones here).
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @return the state word
- *
- * @see UCharIterator
- * @see UCharIteratorSetState
- * @see UITER_NO_STATE
- * @stable ICU 2.6
- */
-typedef uint32_t U_CALLCONV
-UCharIteratorGetState(const UCharIterator *iter);
-
-/**
- * Function type declaration for UCharIterator.setState().
- *
- * Restore the "state" of the iterator using a state word from a getState() call.
- * The iterator object need not be the same one as for which getState() was called,
- * but it must be of the same type (set up using the same uiter_setXYZ function)
- * and it must iterate over the same string
- * (binary identical regardless of memory address).
- * For more about the state word see UCharIteratorGetState.
- *
- * After calling setState(), a getIndex(UITER_CURRENT) may be slow because
- * the UTF-16 index may not be restored as well, but the iterator can deliver
- * the correct text contents and move relative to the current position
- * without performance degradation.
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @param state the state word from a getState() call
- *              on a same-type, same-string iterator
- * @param pErrorCode Must be a valid pointer to an error code value,
- *                   which must not indicate a failure before the function call.
- *
- * @see UCharIterator
- * @see UCharIteratorGetState
- * @stable ICU 2.6
- */
-typedef void U_CALLCONV
-UCharIteratorSetState(UCharIterator *iter, uint32_t state, UErrorCode *pErrorCode);
-
-
-/**
- * C API for code unit iteration.
- * This can be used as a C wrapper around
- * CharacterIterator, Replaceable, or implemented using simple strings, etc.
- *
- * There are two roles for using UCharIterator:
- *
- * A "provider" sets the necessary function pointers and controls the "protected"
- * fields of the UCharIterator structure. A "provider" passes a UCharIterator
- * into C APIs that need a UCharIterator as an abstract, flexible string interface.
- *
- * Implementations of such C APIs are "callers" of UCharIterator functions;
- * they only use the "public" function pointers and never access the "protected"
- * fields directly.
- *
- * The current() and next() functions only check the current index against the
- * limit, and previous() only checks the current index against the start,
- * to see if the iterator already reached the end of the iteration range.
- *
- * The assumption - in all iterators - is that the index is moved via the API,
- * which means it won't go out of bounds, or the index is modified by
- * user code that knows enough about the iterator implementation to set valid
- * index values.
- *
- * UCharIterator functions return code unit values 0..0xffff,
- * or U_SENTINEL if the iteration bounds are reached.
- *
- * @stable ICU 2.1
- */
-struct UCharIterator {
-    /**
-     * (protected) Pointer to string or wrapped object or similar.
-     * Not used by caller.
-     * @stable ICU 2.1
-     */
-    const void *context;
-
-    /**
-     * (protected) Length of string or similar.
-     * Not used by caller.
-     * @stable ICU 2.1
-     */
-    int32_t length;
-
-    /**
-     * (protected) Start index or similar.
-     * Not used by caller.
-     * @stable ICU 2.1
-     */
-    int32_t start;
-
-    /**
-     * (protected) Current index or similar.
-     * Not used by caller.
-     * @stable ICU 2.1
-     */
-    int32_t index;
-
-    /**
-     * (protected) Limit index or similar.
-     * Not used by caller.
-     * @stable ICU 2.1
-     */
-    int32_t limit;
-
-    /**
-     * (protected) Used by UTF-8 iterators and possibly others.
-     * @stable ICU 2.1
-     */
-    int32_t reservedField;
-
-    /**
-     * (public) Returns the current position or the
-     * start or limit index of the iteration range.
-     *
-     * @see UCharIteratorGetIndex
-     * @stable ICU 2.1
-     */
-    UCharIteratorGetIndex *getIndex;
-
-    /**
-     * (public) Moves the current position relative to the start or limit of the
-     * iteration range, or relative to the current position itself.
-     * The movement is expressed in numbers of code units forward
-     * or backward by specifying a positive or negative delta.
-     *
-     * @see UCharIteratorMove
-     * @stable ICU 2.1
-     */
-    UCharIteratorMove *move;
-
-    /**
-     * (public) Check if current() and next() can still
-     * return another code unit.
-     *
-     * @see UCharIteratorHasNext
-     * @stable ICU 2.1
-     */
-    UCharIteratorHasNext *hasNext;
-
-    /**
-     * (public) Check if previous() can still return another code unit.
-     *
-     * @see UCharIteratorHasPrevious
-     * @stable ICU 2.1
-     */
-    UCharIteratorHasPrevious *hasPrevious;
-
-    /**
-     * (public) Return the code unit at the current position,
-     * or U_SENTINEL if there is none (index is at the limit).
-     *
-     * @see UCharIteratorCurrent
-     * @stable ICU 2.1
-     */
-    UCharIteratorCurrent *current;
-
-    /**
-     * (public) Return the code unit at the current index and increment
-     * the index (post-increment, like s[i++]),
-     * or return U_SENTINEL if there is none (index is at the limit).
-     *
-     * @see UCharIteratorNext
-     * @stable ICU 2.1
-     */
-    UCharIteratorNext *next;
-
-    /**
-     * (public) Decrement the index and return the code unit from there
-     * (pre-decrement, like s[--i]),
-     * or return U_SENTINEL if there is none (index is at the start).
-     *
-     * @see UCharIteratorPrevious
-     * @stable ICU 2.1
-     */
-    UCharIteratorPrevious *previous;
-
-    /**
-     * (public) Reserved for future use. Currently NULL.
-     *
-     * @see UCharIteratorReserved
-     * @stable ICU 2.1
-     */
-    UCharIteratorReserved *reservedFn;
-
-    /**
-     * (public) Return the state of the iterator, to be restored later with setState().
-     * This function pointer is NULL if the iterator does not implement it.
-     *
-     * @see UCharIteratorGet
-     * @stable ICU 2.6
-     */
-    UCharIteratorGetState *getState;
-
-    /**
-     * (public) Restore the iterator state from the state word from a call
-     * to getState().
-     * This function pointer is NULL if the iterator does not implement it.
-     *
-     * @see UCharIteratorSet
-     * @stable ICU 2.6
-     */
-    UCharIteratorSetState *setState;
-};
-
-/**
- * Helper function for UCharIterator to get the code point
- * at the current index.
- *
- * Return the code point that includes the code unit at the current position,
- * or U_SENTINEL if there is none (index is at the limit).
- * If the current code unit is a lead or trail surrogate,
- * then the following or preceding surrogate is used to form
- * the code point value.
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @return the current code point
- *
- * @see UCharIterator
- * @see U16_GET
- * @see UnicodeString::char32At()
- * @stable ICU 2.1
- */
-U_CAPI UChar32 U_EXPORT2
-uiter_current32(UCharIterator *iter);
-
-/**
- * Helper function for UCharIterator to get the next code point.
- *
- * Return the code point at the current index and increment
- * the index (post-increment, like s[i++]),
- * or return U_SENTINEL if there is none (index is at the limit).
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @return the current code point (and post-increment the current index)
- *
- * @see UCharIterator
- * @see U16_NEXT
- * @stable ICU 2.1
- */
-U_CAPI UChar32 U_EXPORT2
-uiter_next32(UCharIterator *iter);
-
-/**
- * Helper function for UCharIterator to get the previous code point.
- *
- * Decrement the index and return the code point from there
- * (pre-decrement, like s[--i]),
- * or return U_SENTINEL if there is none (index is at the start).
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @return the previous code point (after pre-decrementing the current index)
- *
- * @see UCharIterator
- * @see U16_PREV
- * @stable ICU 2.1
- */
-U_CAPI UChar32 U_EXPORT2
-uiter_previous32(UCharIterator *iter);
-
-/**
- * Get the "state" of the iterator in the form of a single 32-bit word.
- * This is a convenience function that calls iter->getState(iter)
- * if iter->getState is not NULL;
- * if it is NULL or any other error occurs, then UITER_NO_STATE is returned.
- *
- * Some UCharIterator implementations may not be able to return
- * a valid state for each position, in which case they return UITER_NO_STATE instead.
- * This will be clearly documented for each such iterator (none of the public ones here).
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @return the state word
- *
- * @see UCharIterator
- * @see UCharIteratorGetState
- * @see UITER_NO_STATE
- * @stable ICU 2.6
- */
-U_CAPI uint32_t U_EXPORT2
-uiter_getState(const UCharIterator *iter);
-
-/**
- * Restore the "state" of the iterator using a state word from a getState() call.
- * This is a convenience function that calls iter->setState(iter, state, pErrorCode)
- * if iter->setState is not NULL; if it is NULL, then U_UNSUPPORTED_ERROR is set.
- *
- * @param iter the UCharIterator structure ("this pointer")
- * @param state the state word from a getState() call
- *              on a same-type, same-string iterator
- * @param pErrorCode Must be a valid pointer to an error code value,
- *                   which must not indicate a failure before the function call.
- *
- * @see UCharIterator
- * @see UCharIteratorSetState
- * @stable ICU 2.6
- */
-U_CAPI void U_EXPORT2
-uiter_setState(UCharIterator *iter, uint32_t state, UErrorCode *pErrorCode);
-
-/**
- * Set up a UCharIterator to iterate over a string.
- *
- * Sets the UCharIterator function pointers for iteration over the string s
- * with iteration boundaries start=index=0 and length=limit=string length.
- * The "provider" may set the start, index, and limit values at any time
- * within the range 0..length.
- * The length field will be ignored.
- *
- * The string pointer s is set into UCharIterator.context without copying
- * or reallocating the string contents.
- *
- * getState() simply returns the current index.
- * move() will always return the final index.
- *
- * @param iter UCharIterator structure to be set for iteration
- * @param s String to iterate over
- * @param length Length of s, or -1 if NUL-terminated
- *
- * @see UCharIterator
- * @stable ICU 2.1
- */
-U_CAPI void U_EXPORT2
-uiter_setString(UCharIterator *iter, const UChar *s, int32_t length);
-
-/**
- * Set up a UCharIterator to iterate over a UTF-16BE string
- * (byte vector with a big-endian pair of bytes per UChar).
- *
- * Everything works just like with a normal UChar iterator (uiter_setString),
- * except that UChars are assembled from byte pairs,
- * and that the length argument here indicates an even number of bytes.
- *
- * getState() simply returns the current index.
- * move() will always return the final index.
- *
- * @param iter UCharIterator structure to be set for iteration
- * @param s UTF-16BE string to iterate over
- * @param length Length of s as an even number of bytes, or -1 if NUL-terminated
- *               (NUL means pair of 0 bytes at even index from s)
- *
- * @see UCharIterator
- * @see uiter_setString
- * @stable ICU 2.6
- */
-U_CAPI void U_EXPORT2
-uiter_setUTF16BE(UCharIterator *iter, const char *s, int32_t length);
-
-/**
- * Set up a UCharIterator to iterate over a UTF-8 string.
- *
- * Sets the UCharIterator function pointers for iteration over the UTF-8 string s
- * with UTF-8 iteration boundaries 0 and length.
- * The implementation counts the UTF-16 index on the fly and
- * lazily evaluates the UTF-16 length of the text.
- *
- * The start field is used as the UTF-8 offset, the limit field as the UTF-8 length.
- * When the reservedField is not 0, then it contains a supplementary code point
- * and the UTF-16 index is between the two corresponding surrogates.
- * At that point, the UTF-8 index is behind that code point.
- *
- * The UTF-8 string pointer s is set into UCharIterator.context without copying
- * or reallocating the string contents.
- *
- * getState() returns a state value consisting of
- * - the current UTF-8 source byte index (bits 31..1)
- * - a flag (bit 0) that indicates whether the UChar position is in the middle
- *   of a surrogate pair
- *   (from a 4-byte UTF-8 sequence for the corresponding supplementary code point)
- *
- * getState() cannot also encode the UTF-16 index in the state value.
- * move(relative to limit or length), or
- * move(relative to current) after setState(), may return UITER_UNKNOWN_INDEX.
- *
- * @param iter UCharIterator structure to be set for iteration
- * @param s UTF-8 string to iterate over
- * @param length Length of s in bytes, or -1 if NUL-terminated
- *
- * @see UCharIterator
- * @stable ICU 2.6
- */
-U_CAPI void U_EXPORT2
-uiter_setUTF8(UCharIterator *iter, const char *s, int32_t length);
-
-#if U_SHOW_CPLUSPLUS_API
-
-/**
- * Set up a UCharIterator to wrap around a C++ CharacterIterator.
- *
- * Sets the UCharIterator function pointers for iteration using the
- * CharacterIterator charIter.
- *
- * The CharacterIterator pointer charIter is set into UCharIterator.context
- * without copying or cloning the CharacterIterator object.
- * The other "protected" UCharIterator fields are set to 0 and will be ignored.
- * The iteration index and boundaries are controlled by the CharacterIterator.
- *
- * getState() simply returns the current index.
- * move() will always return the final index.
- *
- * @param iter UCharIterator structure to be set for iteration
- * @param charIter CharacterIterator to wrap
- *
- * @see UCharIterator
- * @stable ICU 2.1
- */
-U_CAPI void U_EXPORT2
-uiter_setCharacterIterator(UCharIterator *iter, icu::CharacterIterator *charIter);
-
-/**
- * Set up a UCharIterator to iterate over a C++ Replaceable.
- *
- * Sets the UCharIterator function pointers for iteration over the
- * Replaceable rep with iteration boundaries start=index=0 and
- * length=limit=rep->length().
- * The "provider" may set the start, index, and limit values at any time
- * within the range 0..length=rep->length().
- * The length field will be ignored.
- *
- * The Replaceable pointer rep is set into UCharIterator.context without copying
- * or cloning/reallocating the Replaceable object.
- *
- * getState() simply returns the current index.
- * move() will always return the final index.
- *
- * @param iter UCharIterator structure to be set for iteration
- * @param rep Replaceable to iterate over
- *
- * @see UCharIterator
- * @stable ICU 2.1
- */
-U_CAPI void U_EXPORT2
-uiter_setReplaceable(UCharIterator *iter, const icu::Replaceable *rep);
-
-#endif
-
-U_CDECL_END
-
-#endif

app/src/main/cpp/icu4c/include/unicode/umachine.h

@@ -1,491 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-******************************************************************************
-*
-*   Copyright (C) 1999-2015, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-******************************************************************************
-*   file name:  umachine.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:4
-*
-*   created on: 1999sep13
-*   created by: Markus W. Scherer
-*
-*   This file defines basic types and constants for ICU to be
-*   platform-independent. umachine.h and utf.h are included into
-*   utypes.h to provide all the general definitions for ICU.
-*   All of these definitions used to be in utypes.h before
-*   the UTF-handling macros made this unmaintainable.
-*/
-
-#ifndef __UMACHINE_H__
-#define __UMACHINE_H__
-
-
-/**
- * \file
- * \brief Basic types and constants for UTF
- *
- * <h2> Basic types and constants for UTF </h2>
- *   This file defines basic types and constants for utf.h to be
- *   platform-independent. umachine.h and utf.h are included into
- *   utypes.h to provide all the general definitions for ICU.
- *   All of these definitions used to be in utypes.h before
- *   the UTF-handling macros made this unmaintainable.
- *
- */
-/*==========================================================================*/
-/* Include platform-dependent definitions                                   */
-/* which are contained in the platform-specific file platform.h             */
-/*==========================================================================*/
-
-#include "unicode/ptypes.h" /* platform.h is included in ptypes.h */
-
-/*
- * ANSI C headers:
- * stddef.h defines wchar_t
- */
-#include <stdbool.h>
-#include <stddef.h>
-
-/*==========================================================================*/
-/* For C wrappers, we use the symbol U_CAPI.                                */
-/* This works properly if the includer is C or C++.                         */
-/* Functions are declared   U_CAPI return-type U_EXPORT2 function-name()... */
-/*==========================================================================*/
-
-/**
- * \def U_CFUNC
- * This is used in a declaration of a library private ICU C function.
- * @stable ICU 2.4
- */
-
-/**
- * \def U_CDECL_BEGIN
- * This is used to begin a declaration of a library private ICU C API.
- * @stable ICU 2.4
- */
-
-/**
- * \def U_CDECL_END
- * This is used to end a declaration of a library private ICU C API
- * @stable ICU 2.4
- */
-
-#ifdef __cplusplus
-#   define U_CFUNC extern "C"
-#   define U_CDECL_BEGIN extern "C" {
-#   define U_CDECL_END   }
-#else
-#   define U_CFUNC extern
-#   define U_CDECL_BEGIN
-#   define U_CDECL_END
-#endif
-
-#ifndef U_ATTRIBUTE_DEPRECATED
-/**
- * \def U_ATTRIBUTE_DEPRECATED
- *  This is used for GCC specific attributes
- * @internal
- */
-#if U_GCC_MAJOR_MINOR >= 302
-#    define U_ATTRIBUTE_DEPRECATED __attribute__ ((deprecated))
-/**
- * \def U_ATTRIBUTE_DEPRECATED
- * This is used for Visual C++ specific attributes 
- * @internal
- */
-#elif defined(_MSC_VER) && (_MSC_VER >= 1400)
-#    define U_ATTRIBUTE_DEPRECATED __declspec(deprecated)
-#else
-#    define U_ATTRIBUTE_DEPRECATED
-#endif
-#endif
-
-/** This is used to declare a function as a public ICU C API @stable ICU 2.0*/
-#define U_CAPI U_CFUNC U_EXPORT
-/** Obsolete/same as U_CAPI; was used to declare a function as a stable public ICU C API*/
-#define U_STABLE U_CAPI
-/** Obsolete/same as U_CAPI; was used to declare a function as a draft public ICU C API  */
-#define U_DRAFT  U_CAPI
-/** This is used to declare a function as a deprecated public ICU C API  */
-#define U_DEPRECATED U_CAPI U_ATTRIBUTE_DEPRECATED
-/** Obsolete/same as U_CAPI; was used to declare a function as an obsolete public ICU C API  */
-#define U_OBSOLETE U_CAPI
-/** Obsolete/same as U_CAPI; was used to declare a function as an internal ICU C API  */
-#define U_INTERNAL U_CAPI
-
-/**
- * \def U_OVERRIDE
- * Defined to the C++11 "override" keyword if available.
- * Denotes a class or member which is an override of the base class.
- * May result in an error if it applied to something not an override.
- * @internal
- */
-#ifndef U_OVERRIDE
-#define U_OVERRIDE override
-#endif
-
-/**
- * \def U_FINAL
- * Defined to the C++11 "final" keyword if available.
- * Denotes a class or member which may not be overridden in subclasses.
- * May result in an error if subclasses attempt to override.
- * @internal
- */
-#if !defined(U_FINAL) || defined(U_IN_DOXYGEN)
-#define U_FINAL final
-#endif
-
-// Before ICU 65, function-like, multi-statement ICU macros were just defined as
-// series of statements wrapped in { } blocks and the caller could choose to
-// either treat them as if they were actual functions and end the invocation
-// with a trailing ; creating an empty statement after the block or else omit
-// this trailing ; using the knowledge that the macro would expand to { }.
-//
-// But doing so doesn't work well with macros that look like functions and
-// compiler warnings about empty statements (ICU-20601) and ICU 65 therefore
-// switches to the standard solution of wrapping such macros in do { } while.
-//
-// This will however break existing code that depends on being able to invoke
-// these macros without a trailing ; so to be able to remain compatible with
-// such code the wrapper is itself defined as macros so that it's possible to
-// build ICU 65 and later with the old macro behaviour, like this:
-//
-// export CPPFLAGS='-DUPRV_BLOCK_MACRO_BEGIN="" -DUPRV_BLOCK_MACRO_END=""'
-// runConfigureICU ...
-//
-
-/**
- * \def UPRV_BLOCK_MACRO_BEGIN
- * Defined as the "do" keyword by default.
- * @internal
- */
-#ifndef UPRV_BLOCK_MACRO_BEGIN
-#define UPRV_BLOCK_MACRO_BEGIN do
-#endif
-
-/**
- * \def UPRV_BLOCK_MACRO_END
- * Defined as "while (false)" by default.
- * @internal
- */
-#ifndef UPRV_BLOCK_MACRO_END
-#define UPRV_BLOCK_MACRO_END while (false)
-#endif
-
-/*==========================================================================*/
-/* limits for int32_t etc., like in POSIX inttypes.h                        */
-/*==========================================================================*/
-
-#ifndef INT8_MIN
-/** The smallest value an 8 bit signed integer can hold @stable ICU 2.0 */
-#   define INT8_MIN        ((int8_t)(-128))
-#endif
-#ifndef INT16_MIN
-/** The smallest value a 16 bit signed integer can hold @stable ICU 2.0 */
-#   define INT16_MIN       ((int16_t)(-32767-1))
-#endif
-#ifndef INT32_MIN
-/** The smallest value a 32 bit signed integer can hold @stable ICU 2.0 */
-#   define INT32_MIN       ((int32_t)(-2147483647-1))
-#endif
-
-#ifndef INT8_MAX
-/** The largest value an 8 bit signed integer can hold @stable ICU 2.0 */
-#   define INT8_MAX        ((int8_t)(127))
-#endif
-#ifndef INT16_MAX
-/** The largest value a 16 bit signed integer can hold @stable ICU 2.0 */
-#   define INT16_MAX       ((int16_t)(32767))
-#endif
-#ifndef INT32_MAX
-/** The largest value a 32 bit signed integer can hold @stable ICU 2.0 */
-#   define INT32_MAX       ((int32_t)(2147483647))
-#endif
-
-#ifndef UINT8_MAX
-/** The largest value an 8 bit unsigned integer can hold @stable ICU 2.0 */
-#   define UINT8_MAX       ((uint8_t)(255U))
-#endif
-#ifndef UINT16_MAX
-/** The largest value a 16 bit unsigned integer can hold @stable ICU 2.0 */
-#   define UINT16_MAX      ((uint16_t)(65535U))
-#endif
-#ifndef UINT32_MAX
-/** The largest value a 32 bit unsigned integer can hold @stable ICU 2.0 */
-#   define UINT32_MAX      ((uint32_t)(4294967295U))
-#endif
-
-#if defined(U_INT64_T_UNAVAILABLE)
-# error int64_t is required for decimal format and rule-based number format.
-#else
-# ifndef INT64_C
-/**
- * Provides a platform independent way to specify a signed 64-bit integer constant.
- * note: may be wrong for some 64 bit platforms - ensure your compiler provides INT64_C
- * @stable ICU 2.8
- */
-#   define INT64_C(c) c ## LL
-# endif
-# ifndef UINT64_C
-/**
- * Provides a platform independent way to specify an unsigned 64-bit integer constant.
- * note: may be wrong for some 64 bit platforms - ensure your compiler provides UINT64_C
- * @stable ICU 2.8
- */
-#   define UINT64_C(c) c ## ULL
-# endif
-# ifndef U_INT64_MIN
-/** The smallest value a 64 bit signed integer can hold @stable ICU 2.8 */
-#     define U_INT64_MIN       ((int64_t)(INT64_C(-9223372036854775807)-1))
-# endif
-# ifndef U_INT64_MAX
-/** The largest value a 64 bit signed integer can hold @stable ICU 2.8 */
-#     define U_INT64_MAX       ((int64_t)(INT64_C(9223372036854775807)))
-# endif
-# ifndef U_UINT64_MAX
-/** The largest value a 64 bit unsigned integer can hold @stable ICU 2.8 */
-#     define U_UINT64_MAX      ((uint64_t)(UINT64_C(18446744073709551615)))
-# endif
-#endif
-
-/*==========================================================================*/
-/* Boolean data type                                                        */
-/*==========================================================================*/
-
-/**
- * The ICU boolean type, a signed-byte integer.
- * ICU-specific for historical reasons: The C and C++ standards used to not define type bool.
- * Also provides a fixed type definition, as opposed to
- * type bool whose details (e.g., sizeof) may vary by compiler and between C and C++.
- *
- * @stable ICU 2.0
- */
-typedef int8_t UBool;
-
-/**
- * \def U_DEFINE_FALSE_AND_TRUE
- * Normally turns off defining macros FALSE=0 & TRUE=1 in public ICU headers.
- * These obsolete macros sometimes break compilation of other code that
- * defines enum constants or similar with these names.
- * C++ has long defined bool/false/true.
- * C99 also added definitions for these, although as macros; see stdbool.h.
- *
- * You may transitionally define U_DEFINE_FALSE_AND_TRUE=1 if you need time to migrate code.
- *
- * @internal ICU 68
- */
-#ifdef U_DEFINE_FALSE_AND_TRUE
-    // Use the predefined value.
-#elif defined(U_COMBINED_IMPLEMENTATION) || \
-        defined(U_COMMON_IMPLEMENTATION) || defined(U_I18N_IMPLEMENTATION) || \
-        defined(U_IO_IMPLEMENTATION) || defined(U_LAYOUTEX_IMPLEMENTATION) || \
-        defined(U_TOOLUTIL_IMPLEMENTATION)
-    // Inside ICU: Keep FALSE & TRUE available.
-#   define U_DEFINE_FALSE_AND_TRUE 1
-#else
-    // Outside ICU: Avoid collision with non-macro definitions of FALSE & TRUE.
-#   define U_DEFINE_FALSE_AND_TRUE 0
-#endif
-
-#if U_DEFINE_FALSE_AND_TRUE || defined(U_IN_DOXYGEN)
-#ifndef TRUE
-/**
- * The TRUE value of a UBool.
- *
- * @deprecated ICU 68 Use standard "true" instead.
- */
-#   define TRUE  1
-#endif
-#ifndef FALSE
-/**
- * The FALSE value of a UBool.
- *
- * @deprecated ICU 68 Use standard "false" instead.
- */
-#   define FALSE 0
-#endif
-#endif  // U_DEFINE_FALSE_AND_TRUE
-
-/*==========================================================================*/
-/* Unicode data types                                                       */
-/*==========================================================================*/
-
-/* wchar_t-related definitions -------------------------------------------- */
-
-/*
- * \def U_WCHAR_IS_UTF16
- * Defined if wchar_t uses UTF-16.
- *
- * @stable ICU 2.0
- */
-/*
- * \def U_WCHAR_IS_UTF32
- * Defined if wchar_t uses UTF-32.
- *
- * @stable ICU 2.0
- */
-#if !defined(U_WCHAR_IS_UTF16) && !defined(U_WCHAR_IS_UTF32)
-#   ifdef __STDC_ISO_10646__
-#       if (U_SIZEOF_WCHAR_T==2)
-#           define U_WCHAR_IS_UTF16
-#       elif (U_SIZEOF_WCHAR_T==4)
-#           define  U_WCHAR_IS_UTF32
-#       endif
-#   elif defined __UCS2__
-#       if (U_PF_OS390 <= U_PLATFORM && U_PLATFORM <= U_PF_OS400) && (U_SIZEOF_WCHAR_T==2)
-#           define U_WCHAR_IS_UTF16
-#       endif
-#   elif defined(__UCS4__) || (U_PLATFORM == U_PF_OS400 && defined(__UTF32__))
-#       if (U_SIZEOF_WCHAR_T==4)
-#           define U_WCHAR_IS_UTF32
-#       endif
-#   elif U_PLATFORM_IS_DARWIN_BASED || (U_SIZEOF_WCHAR_T==4 && U_PLATFORM_IS_LINUX_BASED)
-#       define U_WCHAR_IS_UTF32
-#   elif U_PLATFORM_HAS_WIN32_API
-#       define U_WCHAR_IS_UTF16
-#   endif
-#endif
-
-/* UChar and UChar32 definitions -------------------------------------------- */
-
-/** Number of bytes in a UChar. @stable ICU 2.0 */
-#define U_SIZEOF_UCHAR 2
-
-/**
- * \def U_CHAR16_IS_TYPEDEF
- * If 1, then char16_t is a typedef and not a real type (yet)
- * @internal
- */
-#if (U_PLATFORM == U_PF_AIX) && defined(__cplusplus) &&(U_CPLUSPLUS_VERSION < 11)
-// for AIX, uchar.h needs to be included
-# include <uchar.h>
-# define U_CHAR16_IS_TYPEDEF 1
-#elif defined(_MSC_VER) && (_MSC_VER < 1900)
-// Versions of Visual Studio/MSVC below 2015 do not support char16_t as a real type,
-// and instead use a typedef.  https://msdn.microsoft.com/library/bb531344.aspx
-# define U_CHAR16_IS_TYPEDEF 1
-#else
-# define U_CHAR16_IS_TYPEDEF 0
-#endif
-
-
-/**
- * \var UChar
- *
- * The base type for UTF-16 code units and pointers.
- * Unsigned 16-bit integer.
- * Starting with ICU 59, C++ API uses char16_t directly, while C API continues to use UChar.
- *
- * UChar is configurable by defining the macro UCHAR_TYPE
- * on the preprocessor or compiler command line:
- * -DUCHAR_TYPE=uint16_t or -DUCHAR_TYPE=wchar_t (if U_SIZEOF_WCHAR_T==2) etc.
- * (The UCHAR_TYPE can also be \#defined earlier in this file, for outside the ICU library code.)
- * This is for transitional use from application code that uses uint16_t or wchar_t for UTF-16.
- *
- * The default is UChar=char16_t.
- *
- * C++11 defines char16_t as bit-compatible with uint16_t, but as a distinct type.
- *
- * In C, char16_t is a simple typedef of uint_least16_t.
- * ICU requires uint_least16_t=uint16_t for data memory mapping.
- * On macOS, char16_t is not available because the uchar.h standard header is missing.
- *
- * @stable ICU 4.4
- */
-
-#if 1
-    // #if 1 is normal. UChar defaults to char16_t in C++.
-    // For configuration testing of UChar=uint16_t temporarily change this to #if 0.
-    // The intltest Makefile #defines UCHAR_TYPE=char16_t,
-    // so we only #define it to uint16_t if it is undefined so far.
-#elif !defined(UCHAR_TYPE)
-#   define UCHAR_TYPE uint16_t
-#endif
-
-#if defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || \
-        defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION)
-    // Inside the ICU library code, never configurable.
-    typedef char16_t UChar;
-#elif defined(UCHAR_TYPE)
-    typedef UCHAR_TYPE UChar;
-#elif (U_CPLUSPLUS_VERSION >= 11)
-    typedef char16_t UChar;
-#else
-    typedef uint16_t UChar;
-#endif
-
-/**
- * \var OldUChar
- * Default ICU 58 definition of UChar.
- * A base type for UTF-16 code units and pointers.
- * Unsigned 16-bit integer.
- *
- * Define OldUChar to be wchar_t if that is 16 bits wide.
- * If wchar_t is not 16 bits wide, then define UChar to be uint16_t.
- *
- * This makes the definition of OldUChar platform-dependent
- * but allows direct string type compatibility with platforms with
- * 16-bit wchar_t types.
- *
- * This is how UChar was defined in ICU 58, for transition convenience.
- * Exception: ICU 58 UChar was defined to UCHAR_TYPE if that macro was defined.
- * The current UChar responds to UCHAR_TYPE but OldUChar does not.
- *
- * @stable ICU 59
- */
-#if U_SIZEOF_WCHAR_T==2
-    typedef wchar_t OldUChar;
-#elif defined(__CHAR16_TYPE__)
-    typedef __CHAR16_TYPE__ OldUChar;
-#else
-    typedef uint16_t OldUChar;
-#endif
-
-/**
- * Define UChar32 as a type for single Unicode code points.
- * UChar32 is a signed 32-bit integer (same as int32_t).
- *
- * The Unicode code point range is 0..0x10ffff.
- * All other values (negative or >=0x110000) are illegal as Unicode code points.
- * They may be used as sentinel values to indicate "done", "error"
- * or similar non-code point conditions.
- *
- * Before ICU 2.4 (Jitterbug 2146), UChar32 was defined
- * to be wchar_t if that is 32 bits wide (wchar_t may be signed or unsigned)
- * or else to be uint32_t.
- * That is, the definition of UChar32 was platform-dependent.
- *
- * @see U_SENTINEL
- * @stable ICU 2.4
- */
-typedef int32_t UChar32;
-
-/**
- * This value is intended for sentinel values for APIs that
- * (take or) return single code points (UChar32).
- * It is outside of the Unicode code point range 0..0x10ffff.
- * 
- * For example, a "done" or "error" value in a new API
- * could be indicated with U_SENTINEL.
- *
- * ICU APIs designed before ICU 2.4 usually define service-specific "done"
- * values, mostly 0xffff.
- * Those may need to be distinguished from
- * actual U+ffff text contents by calling functions like
- * CharacterIterator::hasNext() or UnicodeString::length().
- *
- * @return -1
- * @see UChar32
- * @stable ICU 2.4
- */
-#define U_SENTINEL (-1)
-
-#include "unicode/urename.h"
-
-#endif

app/src/main/cpp/icu4c/include/unicode/umisc.h

@@ -1,62 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-**********************************************************************
-*   Copyright (C) 1999-2006, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-**********************************************************************
-*   file name:  umisc.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:4
-*
-*   created on: 1999oct15
-*   created by: Markus W. Scherer
-*/
-
-#ifndef UMISC_H
-#define UMISC_H
-
-#include "unicode/utypes.h"
-
-/**
- * \file
- * \brief  C API:misc definitions 
- *
- *  This file contains miscellaneous definitions for the C APIs. 
- */
-
-U_CDECL_BEGIN
-
-/** A struct representing a range of text containing a specific field 
- *  @stable ICU 2.0
- */
-typedef struct UFieldPosition {
-  /**
-   * The field 
-   * @stable ICU 2.0
-   */
-  int32_t field;
-  /**
-   * The start of the text range containing field 
-   * @stable ICU 2.0
-   */
-  int32_t beginIndex;
-  /** 
-   * The limit of the text range containing field 
-   * @stable ICU 2.0
-   */
-  int32_t endIndex;
-} UFieldPosition;
-
-#if !UCONFIG_NO_SERVICE
-/**
- * Opaque type returned by registerInstance, registerFactory and unregister for service registration.
- * @stable ICU 2.6
- */
-typedef const void* URegistryKey;
-#endif
-
-U_CDECL_END
-
-#endif

app/src/main/cpp/icu4c/include/unicode/uobject.h

@@ -1,324 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-******************************************************************************
-*
-*   Copyright (C) 2002-2012, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-******************************************************************************
-*   file name:  uobject.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:4
-*
-*   created on: 2002jun26
-*   created by: Markus W. Scherer
-*/
-
-#ifndef __UOBJECT_H__
-#define __UOBJECT_H__
-
-#include "unicode/utypes.h"
-
-#if U_SHOW_CPLUSPLUS_API
-
-#include "unicode/platform.h"
-
-/**
- * \file
- * \brief C++ API: Common ICU base class UObject.
- */
-
-/**
- * \def U_NO_THROW
- *         Since ICU 64, use U_NOEXCEPT instead.
- *
- *         Previously, define this to define the throw() specification so
- *                 certain functions do not throw any exceptions
- *
- *         UMemory operator new methods should have the throw() specification 
- *         appended to them, so that the compiler adds the additional NULL check 
- *         before calling constructors. Without, if <code>operator new</code> returns NULL the 
- *         constructor is still called, and if the constructor references member 
- *         data, (which it typically does), the result is a segmentation violation.
- *
- * @stable ICU 4.2. Since ICU 64, Use U_NOEXCEPT instead. See ICU-20422.
- */
-#ifndef U_NO_THROW
-#define U_NO_THROW U_NOEXCEPT
-#endif
-
-/*===========================================================================*/
-/* UClassID-based RTTI */
-/*===========================================================================*/
-
-/**
- * UClassID is used to identify classes without using the compiler's RTTI.
- * This was used before C++ compilers consistently supported RTTI.
- * ICU 4.6 requires compiler RTTI to be turned on.
- *
- * Each class hierarchy which needs
- * to implement polymorphic clone() or operator==() defines two methods,
- * described in detail below.  UClassID values can be compared using
- * operator==(). Nothing else should be done with them.
- *
- * \par
- * In class hierarchies that implement "poor man's RTTI",
- * each concrete subclass implements getDynamicClassID() in the same way:
- *
- * \code
- *      class Derived {
- *      public:
- *          virtual UClassID getDynamicClassID() const
- *            { return Derived::getStaticClassID(); }
- *      }
- * \endcode
- *
- * Each concrete class implements getStaticClassID() as well, which allows
- * clients to test for a specific type.
- *
- * \code
- *      class Derived {
- *      public:
- *          static UClassID U_EXPORT2 getStaticClassID();
- *      private:
- *          static char fgClassID;
- *      }
- *
- *      // In Derived.cpp:
- *      UClassID Derived::getStaticClassID()
- *        { return (UClassID)&Derived::fgClassID; }
- *      char Derived::fgClassID = 0; // Value is irrelevant
- * \endcode
- * @stable ICU 2.0
- */
-typedef void* UClassID;
-
-U_NAMESPACE_BEGIN
-
-/**
- * UMemory is the common ICU base class.
- * All other ICU C++ classes are derived from UMemory (starting with ICU 2.4).
- *
- * This is primarily to make it possible and simple to override the
- * C++ memory management by adding new/delete operators to this base class.
- *
- * To override ALL ICU memory management, including that from plain C code,
- * replace the allocation functions declared in cmemory.h
- *
- * UMemory does not contain any virtual functions.
- * Common "boilerplate" functions are defined in UObject.
- *
- * @stable ICU 2.4
- */
-class U_COMMON_API UMemory {
-public:
-
-/* test versions for debugging shaper heap memory problems */
-#ifdef SHAPER_MEMORY_DEBUG  
-    static void * NewArray(int size, int count);
-    static void * GrowArray(void * array, int newSize );
-    static void   FreeArray(void * array );
-#endif
-
-#if U_OVERRIDE_CXX_ALLOCATION
-    /**
-     * Override for ICU4C C++ memory management.
-     * simple, non-class types are allocated using the macros in common/cmemory.h
-     * (uprv_malloc(), uprv_free(), uprv_realloc());
-     * they or something else could be used here to implement C++ new/delete
-     * for ICU4C C++ classes
-     * @stable ICU 2.4
-     */
-    static void * U_EXPORT2 operator new(size_t size) U_NOEXCEPT;
-
-    /**
-     * Override for ICU4C C++ memory management.
-     * See new().
-     * @stable ICU 2.4
-     */
-    static void * U_EXPORT2 operator new[](size_t size) U_NOEXCEPT;
-
-    /**
-     * Override for ICU4C C++ memory management.
-     * simple, non-class types are allocated using the macros in common/cmemory.h
-     * (uprv_malloc(), uprv_free(), uprv_realloc());
-     * they or something else could be used here to implement C++ new/delete
-     * for ICU4C C++ classes
-     * @stable ICU 2.4
-     */
-    static void U_EXPORT2 operator delete(void *p) U_NOEXCEPT;
-
-    /**
-     * Override for ICU4C C++ memory management.
-     * See delete().
-     * @stable ICU 2.4
-     */
-    static void U_EXPORT2 operator delete[](void *p) U_NOEXCEPT;
-
-#if U_HAVE_PLACEMENT_NEW
-    /**
-     * Override for ICU4C C++ memory management for STL.
-     * See new().
-     * @stable ICU 2.6
-     */
-    static inline void * U_EXPORT2 operator new(size_t, void *ptr) U_NOEXCEPT { return ptr; }
-
-    /**
-     * Override for ICU4C C++ memory management for STL.
-     * See delete().
-     * @stable ICU 2.6
-     */
-    static inline void U_EXPORT2 operator delete(void *, void *) U_NOEXCEPT {}
-#endif /* U_HAVE_PLACEMENT_NEW */
-#if U_HAVE_DEBUG_LOCATION_NEW
-    /**
-      * This method overrides the MFC debug version of the operator new
-      * 
-      * @param size   The requested memory size
-      * @param file   The file where the allocation was requested
-      * @param line   The line where the allocation was requested 
-      */ 
-    static void * U_EXPORT2 operator new(size_t size, const char* file, int line) U_NOEXCEPT;
-    /**
-      * This method provides a matching delete for the MFC debug new
-      * 
-      * @param p      The pointer to the allocated memory
-      * @param file   The file where the allocation was requested
-      * @param line   The line where the allocation was requested 
-      */ 
-    static void U_EXPORT2 operator delete(void* p, const char* file, int line) U_NOEXCEPT;
-#endif /* U_HAVE_DEBUG_LOCATION_NEW */
-#endif /* U_OVERRIDE_CXX_ALLOCATION */
-
-    /*
-     * Assignment operator not declared. The compiler will provide one
-     * which does nothing since this class does not contain any data members.
-     * API/code coverage may show the assignment operator as present and
-     * untested - ignore.
-     * Subclasses need this assignment operator if they use compiler-provided
-     * assignment operators of their own. An alternative to not declaring one
-     * here would be to declare and empty-implement a protected or public one.
-    UMemory &UMemory::operator=(const UMemory &);
-     */
-};
-
-/**
- * UObject is the common ICU "boilerplate" class.
- * UObject inherits UMemory (starting with ICU 2.4),
- * and all other public ICU C++ classes
- * are derived from UObject (starting with ICU 2.2).
- *
- * UObject contains common virtual functions, in particular a virtual destructor.
- *
- * The clone() function is not available in UObject because it is not
- * implemented by all ICU classes.
- * Many ICU services provide a clone() function for their class trees,
- * defined on the service's C++ base class
- * (which itself is a subclass of UObject).
- *
- * @stable ICU 2.2
- */
-class U_COMMON_API UObject : public UMemory {
-public:
-    /**
-     * Destructor.
-     *
-     * @stable ICU 2.2
-     */
-    virtual ~UObject();
-
-    /**
-     * ICU4C "poor man's RTTI", returns a UClassID for the actual ICU class.
-     * The base class implementation returns a dummy value.
-     *
-     * Use compiler RTTI rather than ICU's "poor man's RTTI".
-     * Since ICU 4.6, new ICU C++ class hierarchies do not implement "poor man's RTTI".
-     *
-     * @stable ICU 2.2
-     */
-    virtual UClassID getDynamicClassID() const;
-
-protected:
-    // the following functions are protected to prevent instantiation and
-    // direct use of UObject itself
-
-    // default constructor
-    // inline UObject() {}
-
-    // copy constructor
-    // inline UObject(const UObject &other) {}
-
-#if 0
-    // TODO Sometime in the future. Implement operator==().
-    // (This comment inserted in 2.2)
-    // some or all of the following "boilerplate" functions may be made public
-    // in a future ICU4C release when all subclasses implement them
-
-    // assignment operator
-    // (not virtual, see "Taligent's Guide to Designing Programs" pp.73..74)
-    // commented out because the implementation is the same as a compiler's default
-    // UObject &operator=(const UObject &other) { return *this; }
-
-    // comparison operators
-    virtual inline UBool operator==(const UObject &other) const { return this==&other; }
-    inline UBool operator!=(const UObject &other) const { return !operator==(other); }
-
-    // clone() commented out from the base class:
-    // some compilers do not support co-variant return types
-    // (i.e., subclasses would have to return UObject * as well, instead of SubClass *)
-    // see also UObject class documentation.
-    // virtual UObject *clone() const;
-#endif
-
-    /*
-     * Assignment operator not declared. The compiler will provide one
-     * which does nothing since this class does not contain any data members.
-     * API/code coverage may show the assignment operator as present and
-     * untested - ignore.
-     * Subclasses need this assignment operator if they use compiler-provided
-     * assignment operators of their own. An alternative to not declaring one
-     * here would be to declare and empty-implement a protected or public one.
-    UObject &UObject::operator=(const UObject &);
-     */
-};
-
-#ifndef U_HIDE_INTERNAL_API
-/**
- * This is a simple macro to add ICU RTTI to an ICU object implementation.
- * This does not go into the header. This should only be used in *.cpp files.
- *
- * @param myClass The name of the class that needs RTTI defined.
- * @internal
- */
-#define UOBJECT_DEFINE_RTTI_IMPLEMENTATION(myClass) \
-    UClassID U_EXPORT2 myClass::getStaticClassID() { \
-        static char classID = 0; \
-        return (UClassID)&classID; \
-    } \
-    UClassID myClass::getDynamicClassID() const \
-    { return myClass::getStaticClassID(); }
-
-
-/**
- * This macro adds ICU RTTI to an ICU abstract class implementation.
- * This macro should be invoked in *.cpp files.  The corresponding
- * header should declare getStaticClassID.
- *
- * @param myClass The name of the class that needs RTTI defined.
- * @internal
- */
-#define UOBJECT_DEFINE_ABSTRACT_RTTI_IMPLEMENTATION(myClass) \
-    UClassID U_EXPORT2 myClass::getStaticClassID() { \
-        static char classID = 0; \
-        return (UClassID)&classID; \
-    }
-
-#endif  /* U_HIDE_INTERNAL_API */
-
-U_NAMESPACE_END
-
-#endif /* U_SHOW_CPLUSPLUS_API */
-
-#endif

app/src/main/cpp/icu4c/include/unicode/utf16.h

@@ -1,734 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-*******************************************************************************
-*
-*   Copyright (C) 1999-2012, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-*******************************************************************************
-*   file name:  utf16.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:4
-*
-*   created on: 1999sep09
-*   created by: Markus W. Scherer
-*/
-
-/**
- * \file
- * \brief C API: 16-bit Unicode handling macros
- * 
- * This file defines macros to deal with 16-bit Unicode (UTF-16) code units and strings.
- *
- * For more information see utf.h and the ICU User Guide Strings chapter
- * (https://unicode-org.github.io/icu/userguide/strings).
- *
- * <em>Usage:</em>
- * ICU coding guidelines for if() statements should be followed when using these macros.
- * Compound statements (curly braces {}) must be used  for if-else-while... 
- * bodies and all macro statements should be terminated with semicolon.
- */
-
-#ifndef __UTF16_H__
-#define __UTF16_H__
-
-#include <stdbool.h>
-#include "unicode/umachine.h"
-#ifndef __UTF_H__
-#   include "unicode/utf.h"
-#endif
-
-/* single-code point definitions -------------------------------------------- */
-
-/**
- * Does this code unit alone encode a code point (BMP, not a surrogate)?
- * @param c 16-bit code unit
- * @return true or false
- * @stable ICU 2.4
- */
-#define U16_IS_SINGLE(c) !U_IS_SURROGATE(c)
-
-/**
- * Is this code unit a lead surrogate (U+d800..U+dbff)?
- * @param c 16-bit code unit
- * @return true or false
- * @stable ICU 2.4
- */
-#define U16_IS_LEAD(c) (((c)&0xfffffc00)==0xd800)
-
-/**
- * Is this code unit a trail surrogate (U+dc00..U+dfff)?
- * @param c 16-bit code unit
- * @return true or false
- * @stable ICU 2.4
- */
-#define U16_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00)
-
-/**
- * Is this code unit a surrogate (U+d800..U+dfff)?
- * @param c 16-bit code unit
- * @return true or false
- * @stable ICU 2.4
- */
-#define U16_IS_SURROGATE(c) U_IS_SURROGATE(c)
-
-/**
- * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)),
- * is it a lead surrogate?
- * @param c 16-bit code unit
- * @return true or false
- * @stable ICU 2.4
- */
-#define U16_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)
-
-/**
- * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)),
- * is it a trail surrogate?
- * @param c 16-bit code unit
- * @return true or false
- * @stable ICU 4.2
- */
-#define U16_IS_SURROGATE_TRAIL(c) (((c)&0x400)!=0)
-
-/**
- * Helper constant for U16_GET_SUPPLEMENTARY.
- * @internal
- */
-#define U16_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000)
-
-/**
- * Get a supplementary code point value (U+10000..U+10ffff)
- * from its lead and trail surrogates.
- * The result is undefined if the input values are not
- * lead and trail surrogates.
- *
- * @param lead lead surrogate (U+d800..U+dbff)
- * @param trail trail surrogate (U+dc00..U+dfff)
- * @return supplementary code point (U+10000..U+10ffff)
- * @stable ICU 2.4
- */
-#define U16_GET_SUPPLEMENTARY(lead, trail) \
-    (((UChar32)(lead)<<10UL)+(UChar32)(trail)-U16_SURROGATE_OFFSET)
-
-
-/**
- * Get the lead surrogate (0xd800..0xdbff) for a
- * supplementary code point (0x10000..0x10ffff).
- * @param supplementary 32-bit code point (U+10000..U+10ffff)
- * @return lead surrogate (U+d800..U+dbff) for supplementary
- * @stable ICU 2.4
- */
-#define U16_LEAD(supplementary) (UChar)(((supplementary)>>10)+0xd7c0)
-
-/**
- * Get the trail surrogate (0xdc00..0xdfff) for a
- * supplementary code point (0x10000..0x10ffff).
- * @param supplementary 32-bit code point (U+10000..U+10ffff)
- * @return trail surrogate (U+dc00..U+dfff) for supplementary
- * @stable ICU 2.4
- */
-#define U16_TRAIL(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00)
-
-/**
- * How many 16-bit code units are used to encode this Unicode code point? (1 or 2)
- * The result is not defined if c is not a Unicode code point (U+0000..U+10ffff).
- * @param c 32-bit code point
- * @return 1 or 2
- * @stable ICU 2.4
- */
-#define U16_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2)
-
-/**
- * The maximum number of 16-bit code units per Unicode code point (U+0000..U+10ffff).
- * @return 2
- * @stable ICU 2.4
- */
-#define U16_MAX_LENGTH 2
-
-/**
- * Get a code point from a string at a random-access offset,
- * without changing the offset.
- * "Unsafe" macro, assumes well-formed UTF-16.
- *
- * The offset may point to either the lead or trail surrogate unit
- * for a supplementary code point, in which case the macro will read
- * the adjacent matching surrogate as well.
- * The result is undefined if the offset points to a single, unpaired surrogate.
- * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT.
- *
- * @param s const UChar * string
- * @param i string offset
- * @param c output UChar32 variable
- * @see U16_GET
- * @stable ICU 2.4
- */
-#define U16_GET_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(s)[i]; \
-    if(U16_IS_SURROGATE(c)) { \
-        if(U16_IS_SURROGATE_LEAD(c)) { \
-            (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)+1]); \
-        } else { \
-            (c)=U16_GET_SUPPLEMENTARY((s)[(i)-1], (c)); \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Get a code point from a string at a random-access offset,
- * without changing the offset.
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * The offset may point to either the lead or trail surrogate unit
- * for a supplementary code point, in which case the macro will read
- * the adjacent matching surrogate as well.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * If the offset points to a single, unpaired surrogate, then
- * c is set to that unpaired surrogate.
- * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT.
- *
- * @param s const UChar * string
- * @param start starting string offset (usually 0)
- * @param i string offset, must be start<=i<length
- * @param length string length
- * @param c output UChar32 variable
- * @see U16_GET_UNSAFE
- * @stable ICU 2.4
- */
-#define U16_GET(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(s)[i]; \
-    if(U16_IS_SURROGATE(c)) { \
-        uint16_t __c2; \
-        if(U16_IS_SURROGATE_LEAD(c)) { \
-            if((i)+1!=(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \
-                (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
-            } \
-        } else { \
-            if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
-                (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
-            } \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Get a code point from a string at a random-access offset,
- * without changing the offset.
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * The offset may point to either the lead or trail surrogate unit
- * for a supplementary code point, in which case the macro will read
- * the adjacent matching surrogate as well.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * If the offset points to a single, unpaired surrogate, then
- * c is set to U+FFFD.
- * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT_OR_FFFD.
- *
- * @param s const UChar * string
- * @param start starting string offset (usually 0)
- * @param i string offset, must be start<=i<length
- * @param length string length
- * @param c output UChar32 variable
- * @see U16_GET_UNSAFE
- * @stable ICU 60
- */
-#define U16_GET_OR_FFFD(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(s)[i]; \
-    if(U16_IS_SURROGATE(c)) { \
-        uint16_t __c2; \
-        if(U16_IS_SURROGATE_LEAD(c)) { \
-            if((i)+1!=(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \
-                (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
-            } else { \
-                (c)=0xfffd; \
-            } \
-        } else { \
-            if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
-                (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
-            } else { \
-                (c)=0xfffd; \
-            } \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/* definitions with forward iteration --------------------------------------- */
-
-/**
- * Get a code point from a string at a code point boundary offset,
- * and advance the offset to the next code point boundary.
- * (Post-incrementing forward iteration.)
- * "Unsafe" macro, assumes well-formed UTF-16.
- *
- * The offset may point to the lead surrogate unit
- * for a supplementary code point, in which case the macro will read
- * the following trail surrogate as well.
- * If the offset points to a trail surrogate, then that itself
- * will be returned as the code point.
- * The result is undefined if the offset points to a single, unpaired lead surrogate.
- *
- * @param s const UChar * string
- * @param i string offset
- * @param c output UChar32 variable
- * @see U16_NEXT
- * @stable ICU 2.4
- */
-#define U16_NEXT_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(s)[(i)++]; \
-    if(U16_IS_LEAD(c)) { \
-        (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)++]); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Get a code point from a string at a code point boundary offset,
- * and advance the offset to the next code point boundary.
- * (Post-incrementing forward iteration.)
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * The offset may point to the lead surrogate unit
- * for a supplementary code point, in which case the macro will read
- * the following trail surrogate as well.
- * If the offset points to a trail surrogate or
- * to a single, unpaired lead surrogate, then c is set to that unpaired surrogate.
- *
- * @param s const UChar * string
- * @param i string offset, must be i<length
- * @param length string length
- * @param c output UChar32 variable
- * @see U16_NEXT_UNSAFE
- * @stable ICU 2.4
- */
-#define U16_NEXT(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(s)[(i)++]; \
-    if(U16_IS_LEAD(c)) { \
-        uint16_t __c2; \
-        if((i)!=(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \
-            ++(i); \
-            (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Get a code point from a string at a code point boundary offset,
- * and advance the offset to the next code point boundary.
- * (Post-incrementing forward iteration.)
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * The offset may point to the lead surrogate unit
- * for a supplementary code point, in which case the macro will read
- * the following trail surrogate as well.
- * If the offset points to a trail surrogate or
- * to a single, unpaired lead surrogate, then c is set to U+FFFD.
- *
- * @param s const UChar * string
- * @param i string offset, must be i<length
- * @param length string length
- * @param c output UChar32 variable
- * @see U16_NEXT_UNSAFE
- * @stable ICU 60
- */
-#define U16_NEXT_OR_FFFD(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(s)[(i)++]; \
-    if(U16_IS_SURROGATE(c)) { \
-        uint16_t __c2; \
-        if(U16_IS_SURROGATE_LEAD(c) && (i)!=(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \
-            ++(i); \
-            (c)=U16_GET_SUPPLEMENTARY((c), __c2); \
-        } else { \
-            (c)=0xfffd; \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Append a code point to a string, overwriting 1 or 2 code units.
- * The offset points to the current end of the string contents
- * and is advanced (post-increment).
- * "Unsafe" macro, assumes a valid code point and sufficient space in the string.
- * Otherwise, the result is undefined.
- *
- * @param s const UChar * string buffer
- * @param i string offset
- * @param c code point to append
- * @see U16_APPEND
- * @stable ICU 2.4
- */
-#define U16_APPEND_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    if((uint32_t)(c)<=0xffff) { \
-        (s)[(i)++]=(uint16_t)(c); \
-    } else { \
-        (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
-        (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Append a code point to a string, overwriting 1 or 2 code units.
- * The offset points to the current end of the string contents
- * and is advanced (post-increment).
- * "Safe" macro, checks for a valid code point.
- * If a surrogate pair is written, checks for sufficient space in the string.
- * If the code point is not valid or a trail surrogate does not fit,
- * then isError is set to true.
- *
- * @param s const UChar * string buffer
- * @param i string offset, must be i<capacity
- * @param capacity size of the string buffer
- * @param c code point to append
- * @param isError output UBool set to true if an error occurs, otherwise not modified
- * @see U16_APPEND_UNSAFE
- * @stable ICU 2.4
- */
-#define U16_APPEND(s, i, capacity, c, isError) UPRV_BLOCK_MACRO_BEGIN { \
-    if((uint32_t)(c)<=0xffff) { \
-        (s)[(i)++]=(uint16_t)(c); \
-    } else if((uint32_t)(c)<=0x10ffff && (i)+1<(capacity)) { \
-        (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
-        (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
-    } else /* c>0x10ffff or not enough space */ { \
-        (isError)=true; \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Advance the string offset from one code point boundary to the next.
- * (Post-incrementing iteration.)
- * "Unsafe" macro, assumes well-formed UTF-16.
- *
- * @param s const UChar * string
- * @param i string offset
- * @see U16_FWD_1
- * @stable ICU 2.4
- */
-#define U16_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \
-    if(U16_IS_LEAD((s)[(i)++])) { \
-        ++(i); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Advance the string offset from one code point boundary to the next.
- * (Post-incrementing iteration.)
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * @param s const UChar * string
- * @param i string offset, must be i<length
- * @param length string length
- * @see U16_FWD_1_UNSAFE
- * @stable ICU 2.4
- */
-#define U16_FWD_1(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \
-    if(U16_IS_LEAD((s)[(i)++]) && (i)!=(length) && U16_IS_TRAIL((s)[i])) { \
-        ++(i); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Advance the string offset from one code point boundary to the n-th next one,
- * i.e., move forward by n code points.
- * (Post-incrementing iteration.)
- * "Unsafe" macro, assumes well-formed UTF-16.
- *
- * @param s const UChar * string
- * @param i string offset
- * @param n number of code points to skip
- * @see U16_FWD_N
- * @stable ICU 2.4
- */
-#define U16_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \
-    int32_t __N=(n); \
-    while(__N>0) { \
-        U16_FWD_1_UNSAFE(s, i); \
-        --__N; \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Advance the string offset from one code point boundary to the n-th next one,
- * i.e., move forward by n code points.
- * (Post-incrementing iteration.)
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * @param s const UChar * string
- * @param i int32_t string offset, must be i<length
- * @param length int32_t string length
- * @param n number of code points to skip
- * @see U16_FWD_N_UNSAFE
- * @stable ICU 2.4
- */
-#define U16_FWD_N(s, i, length, n) UPRV_BLOCK_MACRO_BEGIN { \
-    int32_t __N=(n); \
-    while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \
-        U16_FWD_1(s, i, length); \
-        --__N; \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Adjust a random-access offset to a code point boundary
- * at the start of a code point.
- * If the offset points to the trail surrogate of a surrogate pair,
- * then the offset is decremented.
- * Otherwise, it is not modified.
- * "Unsafe" macro, assumes well-formed UTF-16.
- *
- * @param s const UChar * string
- * @param i string offset
- * @see U16_SET_CP_START
- * @stable ICU 2.4
- */
-#define U16_SET_CP_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \
-    if(U16_IS_TRAIL((s)[i])) { \
-        --(i); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Adjust a random-access offset to a code point boundary
- * at the start of a code point.
- * If the offset points to the trail surrogate of a surrogate pair,
- * then the offset is decremented.
- * Otherwise, it is not modified.
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * @param s const UChar * string
- * @param start starting string offset (usually 0)
- * @param i string offset, must be start<=i
- * @see U16_SET_CP_START_UNSAFE
- * @stable ICU 2.4
- */
-#define U16_SET_CP_START(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \
-    if(U16_IS_TRAIL((s)[i]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \
-        --(i); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/* definitions with backward iteration -------------------------------------- */
-
-/**
- * Move the string offset from one code point boundary to the previous one
- * and get the code point between them.
- * (Pre-decrementing backward iteration.)
- * "Unsafe" macro, assumes well-formed UTF-16.
- *
- * The input offset may be the same as the string length.
- * If the offset is behind a trail surrogate unit
- * for a supplementary code point, then the macro will read
- * the preceding lead surrogate as well.
- * If the offset is behind a lead surrogate, then that itself
- * will be returned as the code point.
- * The result is undefined if the offset is behind a single, unpaired trail surrogate.
- *
- * @param s const UChar * string
- * @param i string offset
- * @param c output UChar32 variable
- * @see U16_PREV
- * @stable ICU 2.4
- */
-#define U16_PREV_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(s)[--(i)]; \
-    if(U16_IS_TRAIL(c)) { \
-        (c)=U16_GET_SUPPLEMENTARY((s)[--(i)], (c)); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the previous one
- * and get the code point between them.
- * (Pre-decrementing backward iteration.)
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * The input offset may be the same as the string length.
- * If the offset is behind a trail surrogate unit
- * for a supplementary code point, then the macro will read
- * the preceding lead surrogate as well.
- * If the offset is behind a lead surrogate or behind a single, unpaired
- * trail surrogate, then c is set to that unpaired surrogate.
- *
- * @param s const UChar * string
- * @param start starting string offset (usually 0)
- * @param i string offset, must be start<i
- * @param c output UChar32 variable
- * @see U16_PREV_UNSAFE
- * @stable ICU 2.4
- */
-#define U16_PREV(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(s)[--(i)]; \
-    if(U16_IS_TRAIL(c)) { \
-        uint16_t __c2; \
-        if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
-            --(i); \
-            (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the previous one
- * and get the code point between them.
- * (Pre-decrementing backward iteration.)
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * The input offset may be the same as the string length.
- * If the offset is behind a trail surrogate unit
- * for a supplementary code point, then the macro will read
- * the preceding lead surrogate as well.
- * If the offset is behind a lead surrogate or behind a single, unpaired
- * trail surrogate, then c is set to U+FFFD.
- *
- * @param s const UChar * string
- * @param start starting string offset (usually 0)
- * @param i string offset, must be start<i
- * @param c output UChar32 variable
- * @see U16_PREV_UNSAFE
- * @stable ICU 60
- */
-#define U16_PREV_OR_FFFD(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(s)[--(i)]; \
-    if(U16_IS_SURROGATE(c)) { \
-        uint16_t __c2; \
-        if(U16_IS_SURROGATE_TRAIL(c) && (i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
-            --(i); \
-            (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
-        } else { \
-            (c)=0xfffd; \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the previous one.
- * (Pre-decrementing backward iteration.)
- * The input offset may be the same as the string length.
- * "Unsafe" macro, assumes well-formed UTF-16.
- *
- * @param s const UChar * string
- * @param i string offset
- * @see U16_BACK_1
- * @stable ICU 2.4
- */
-#define U16_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \
-    if(U16_IS_TRAIL((s)[--(i)])) { \
-        --(i); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the previous one.
- * (Pre-decrementing backward iteration.)
- * The input offset may be the same as the string length.
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * @param s const UChar * string
- * @param start starting string offset (usually 0)
- * @param i string offset, must be start<i
- * @see U16_BACK_1_UNSAFE
- * @stable ICU 2.4
- */
-#define U16_BACK_1(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \
-    if(U16_IS_TRAIL((s)[--(i)]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \
-        --(i); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the n-th one before it,
- * i.e., move backward by n code points.
- * (Pre-decrementing backward iteration.)
- * The input offset may be the same as the string length.
- * "Unsafe" macro, assumes well-formed UTF-16.
- *
- * @param s const UChar * string
- * @param i string offset
- * @param n number of code points to skip
- * @see U16_BACK_N
- * @stable ICU 2.4
- */
-#define U16_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \
-    int32_t __N=(n); \
-    while(__N>0) { \
-        U16_BACK_1_UNSAFE(s, i); \
-        --__N; \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the n-th one before it,
- * i.e., move backward by n code points.
- * (Pre-decrementing backward iteration.)
- * The input offset may be the same as the string length.
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * @param s const UChar * string
- * @param start start of string
- * @param i string offset, must be start<i
- * @param n number of code points to skip
- * @see U16_BACK_N_UNSAFE
- * @stable ICU 2.4
- */
-#define U16_BACK_N(s, start, i, n) UPRV_BLOCK_MACRO_BEGIN { \
-    int32_t __N=(n); \
-    while(__N>0 && (i)>(start)) { \
-        U16_BACK_1(s, start, i); \
-        --__N; \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Adjust a random-access offset to a code point boundary after a code point.
- * If the offset is behind the lead surrogate of a surrogate pair,
- * then the offset is incremented.
- * Otherwise, it is not modified.
- * The input offset may be the same as the string length.
- * "Unsafe" macro, assumes well-formed UTF-16.
- *
- * @param s const UChar * string
- * @param i string offset
- * @see U16_SET_CP_LIMIT
- * @stable ICU 2.4
- */
-#define U16_SET_CP_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \
-    if(U16_IS_LEAD((s)[(i)-1])) { \
-        ++(i); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Adjust a random-access offset to a code point boundary after a code point.
- * If the offset is behind the lead surrogate of a surrogate pair,
- * then the offset is incremented.
- * Otherwise, it is not modified.
- * The input offset may be the same as the string length.
- * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * @param s const UChar * string
- * @param start int32_t starting string offset (usually 0)
- * @param i int32_t string offset, start<=i<=length
- * @param length int32_t string length
- * @see U16_SET_CP_LIMIT_UNSAFE
- * @stable ICU 2.4
- */
-#define U16_SET_CP_LIMIT(s, start, i, length) UPRV_BLOCK_MACRO_BEGIN { \
-    if((start)<(i) && ((i)<(length) || (length)<0) && U16_IS_LEAD((s)[(i)-1]) && U16_IS_TRAIL((s)[i])) { \
-        ++(i); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-#endif

app/src/main/cpp/icu4c/include/unicode/utf8.h

@@ -1,882 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-*******************************************************************************
-*
-*   Copyright (C) 1999-2015, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*
-*******************************************************************************
-*   file name:  utf8.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:4
-*
-*   created on: 1999sep13
-*   created by: Markus W. Scherer
-*/
-
-/**
- * \file
- * \brief C API: 8-bit Unicode handling macros
- * 
- * This file defines macros to deal with 8-bit Unicode (UTF-8) code units (bytes) and strings.
- *
- * For more information see utf.h and the ICU User Guide Strings chapter
- * (https://unicode-org.github.io/icu/userguide/strings).
- *
- * <em>Usage:</em>
- * ICU coding guidelines for if() statements should be followed when using these macros.
- * Compound statements (curly braces {}) must be used  for if-else-while... 
- * bodies and all macro statements should be terminated with semicolon.
- */
-
-#ifndef __UTF8_H__
-#define __UTF8_H__
-
-#include <stdbool.h>
-#include "unicode/umachine.h"
-#ifndef __UTF_H__
-#   include "unicode/utf.h"
-#endif
-
-/* internal definitions ----------------------------------------------------- */
-
-/**
- * Counts the trail bytes for a UTF-8 lead byte.
- * Returns 0 for 0..0xc1 as well as for 0xf5..0xff.
- * leadByte might be evaluated multiple times.
- *
- * This is internal since it is not meant to be called directly by external clients;
- * however it is called by public macros in this file and thus must remain stable.
- *
- * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff.
- * @internal
- */
-#define U8_COUNT_TRAIL_BYTES(leadByte) \
-    (U8_IS_LEAD(leadByte) ? \
-        ((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)+1 : 0)
-
-/**
- * Counts the trail bytes for a UTF-8 lead byte of a valid UTF-8 sequence.
- * Returns 0 for 0..0xc1. Undefined for 0xf5..0xff.
- * leadByte might be evaluated multiple times.
- *
- * This is internal since it is not meant to be called directly by external clients;
- * however it is called by public macros in this file and thus must remain stable.
- *
- * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff.
- * @internal
- */
-#define U8_COUNT_TRAIL_BYTES_UNSAFE(leadByte) \
-    (((uint8_t)(leadByte)>=0xc2)+((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0))
-
-/**
- * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value.
- *
- * This is internal since it is not meant to be called directly by external clients;
- * however it is called by public macros in this file and thus must remain stable.
- * @internal
- */
-#define U8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1)
-
-/**
- * Internal bit vector for 3-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD3_AND_T1.
- * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence.
- * Lead byte E0..EF bits 3..0 are used as byte index,
- * first trail byte bits 7..5 are used as bit index into that byte.
- * @see U8_IS_VALID_LEAD3_AND_T1
- * @internal
- */
-#define U8_LEAD3_T1_BITS "\x20\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x10\x30\x30"
-
-/**
- * Internal 3-byte UTF-8 validity check.
- * Non-zero if lead byte E0..EF and first trail byte 00..FF start a valid sequence.
- * @internal
- */
-#define U8_IS_VALID_LEAD3_AND_T1(lead, t1) (U8_LEAD3_T1_BITS[(lead)&0xf]&(1<<((uint8_t)(t1)>>5)))
-
-/**
- * Internal bit vector for 4-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD4_AND_T1.
- * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence.
- * First trail byte bits 7..4 are used as byte index,
- * lead byte F0..F4 bits 2..0 are used as bit index into that byte.
- * @see U8_IS_VALID_LEAD4_AND_T1
- * @internal
- */
-#define U8_LEAD4_T1_BITS "\x00\x00\x00\x00\x00\x00\x00\x00\x1E\x0F\x0F\x0F\x00\x00\x00\x00"
-
-/**
- * Internal 4-byte UTF-8 validity check.
- * Non-zero if lead byte F0..F4 and first trail byte 00..FF start a valid sequence.
- * @internal
- */
-#define U8_IS_VALID_LEAD4_AND_T1(lead, t1) (U8_LEAD4_T1_BITS[(uint8_t)(t1)>>4]&(1<<((lead)&7)))
-
-/**
- * Function for handling "next code point" with error-checking.
- *
- * This is internal since it is not meant to be called directly by external clients;
- * however it is called by public macros in this
- * file and thus must remain stable, and should not be hidden when other internal
- * functions are hidden (otherwise public macros would fail to compile).
- * @internal
- */
-U_CAPI UChar32 U_EXPORT2
-utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict);
-
-/**
- * Function for handling "append code point" with error-checking.
- *
- * This is internal since it is not meant to be called directly by external clients;
- * however it is called by public macros in this
- * file and thus must remain stable, and should not be hidden when other internal
- * functions are hidden (otherwise public macros would fail to compile).
- * @internal
- */
-U_CAPI int32_t U_EXPORT2
-utf8_appendCharSafeBody(uint8_t *s, int32_t i, int32_t length, UChar32 c, UBool *pIsError);
-
-/**
- * Function for handling "previous code point" with error-checking.
- *
- * This is internal since it is not meant to be called directly by external clients;
- * however it is called by public macros in this
- * file and thus must remain stable, and should not be hidden when other internal
- * functions are hidden (otherwise public macros would fail to compile).
- * @internal
- */
-U_CAPI UChar32 U_EXPORT2
-utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, UBool strict);
-
-/**
- * Function for handling "skip backward one code point" with error-checking.
- *
- * This is internal since it is not meant to be called directly by external clients;
- * however it is called by public macros in this
- * file and thus must remain stable, and should not be hidden when other internal
- * functions are hidden (otherwise public macros would fail to compile).
- * @internal
- */
-U_CAPI int32_t U_EXPORT2
-utf8_back1SafeBody(const uint8_t *s, int32_t start, int32_t i);
-
-/* single-code point definitions -------------------------------------------- */
-
-/**
- * Does this code unit (byte) encode a code point by itself (US-ASCII 0..0x7f)?
- * @param c 8-bit code unit (byte)
- * @return true or false
- * @stable ICU 2.4
- */
-#define U8_IS_SINGLE(c) (((c)&0x80)==0)
-
-/**
- * Is this code unit (byte) a UTF-8 lead byte? (0xC2..0xF4)
- * @param c 8-bit code unit (byte)
- * @return true or false
- * @stable ICU 2.4
- */
-#define U8_IS_LEAD(c) ((uint8_t)((c)-0xc2)<=0x32)
-// 0x32=0xf4-0xc2
-
-/**
- * Is this code unit (byte) a UTF-8 trail byte? (0x80..0xBF)
- * @param c 8-bit code unit (byte)
- * @return true or false
- * @stable ICU 2.4
- */
-#define U8_IS_TRAIL(c) ((int8_t)(c)<-0x40)
-
-/**
- * How many code units (bytes) are used for the UTF-8 encoding
- * of this Unicode code point?
- * @param c 32-bit code point
- * @return 1..4, or 0 if c is a surrogate or not a Unicode code point
- * @stable ICU 2.4
- */
-#define U8_LENGTH(c) \
-    ((uint32_t)(c)<=0x7f ? 1 : \
-        ((uint32_t)(c)<=0x7ff ? 2 : \
-            ((uint32_t)(c)<=0xd7ff ? 3 : \
-                ((uint32_t)(c)<=0xdfff || (uint32_t)(c)>0x10ffff ? 0 : \
-                    ((uint32_t)(c)<=0xffff ? 3 : 4)\
-                ) \
-            ) \
-        ) \
-    )
-
-/**
- * The maximum number of UTF-8 code units (bytes) per Unicode code point (U+0000..U+10ffff).
- * @return 4
- * @stable ICU 2.4
- */
-#define U8_MAX_LENGTH 4
-
-/**
- * Get a code point from a string at a random-access offset,
- * without changing the offset.
- * The offset may point to either the lead byte or one of the trail bytes
- * for a code point, in which case the macro will read all of the bytes
- * for the code point.
- * The result is undefined if the offset points to an illegal UTF-8
- * byte sequence.
- * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @param c output UChar32 variable
- * @see U8_GET
- * @stable ICU 2.4
- */
-#define U8_GET_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    int32_t _u8_get_unsafe_index=(int32_t)(i); \
-    U8_SET_CP_START_UNSAFE(s, _u8_get_unsafe_index); \
-    U8_NEXT_UNSAFE(s, _u8_get_unsafe_index, c); \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Get a code point from a string at a random-access offset,
- * without changing the offset.
- * The offset may point to either the lead byte or one of the trail bytes
- * for a code point, in which case the macro will read all of the bytes
- * for the code point.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * If the offset points to an illegal UTF-8 byte sequence, then
- * c is set to a negative value.
- * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT.
- *
- * @param s const uint8_t * string
- * @param start int32_t starting string offset
- * @param i int32_t string offset, must be start<=i<length
- * @param length int32_t string length
- * @param c output UChar32 variable, set to <0 in case of an error
- * @see U8_GET_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_GET(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \
-    int32_t _u8_get_index=(i); \
-    U8_SET_CP_START(s, start, _u8_get_index); \
-    U8_NEXT(s, _u8_get_index, length, c); \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Get a code point from a string at a random-access offset,
- * without changing the offset.
- * The offset may point to either the lead byte or one of the trail bytes
- * for a code point, in which case the macro will read all of the bytes
- * for the code point.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * If the offset points to an illegal UTF-8 byte sequence, then
- * c is set to U+FFFD.
- * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT_OR_FFFD.
- *
- * This macro does not distinguish between a real U+FFFD in the text
- * and U+FFFD returned for an ill-formed sequence.
- * Use U8_GET() if that distinction is important.
- *
- * @param s const uint8_t * string
- * @param start int32_t starting string offset
- * @param i int32_t string offset, must be start<=i<length
- * @param length int32_t string length
- * @param c output UChar32 variable, set to U+FFFD in case of an error
- * @see U8_GET
- * @stable ICU 51
- */
-#define U8_GET_OR_FFFD(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \
-    int32_t _u8_get_index=(i); \
-    U8_SET_CP_START(s, start, _u8_get_index); \
-    U8_NEXT_OR_FFFD(s, _u8_get_index, length, c); \
-} UPRV_BLOCK_MACRO_END
-
-/* definitions with forward iteration --------------------------------------- */
-
-/**
- * Get a code point from a string at a code point boundary offset,
- * and advance the offset to the next code point boundary.
- * (Post-incrementing forward iteration.)
- * "Unsafe" macro, assumes well-formed UTF-8.
- *
- * The offset may point to the lead byte of a multi-byte sequence,
- * in which case the macro will read the whole sequence.
- * The result is undefined if the offset points to a trail byte
- * or an illegal UTF-8 sequence.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @param c output UChar32 variable
- * @see U8_NEXT
- * @stable ICU 2.4
- */
-#define U8_NEXT_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(uint8_t)(s)[(i)++]; \
-    if(!U8_IS_SINGLE(c)) { \
-        if((c)<0xe0) { \
-            (c)=(((c)&0x1f)<<6)|((s)[(i)++]&0x3f); \
-        } else if((c)<0xf0) { \
-            /* no need for (c&0xf) because the upper bits are truncated after <<12 in the cast to (UChar) */ \
-            (c)=(UChar)(((c)<<12)|(((s)[i]&0x3f)<<6)|((s)[(i)+1]&0x3f)); \
-            (i)+=2; \
-        } else { \
-            (c)=(((c)&7)<<18)|(((s)[i]&0x3f)<<12)|(((s)[(i)+1]&0x3f)<<6)|((s)[(i)+2]&0x3f); \
-            (i)+=3; \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Get a code point from a string at a code point boundary offset,
- * and advance the offset to the next code point boundary.
- * (Post-incrementing forward iteration.)
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * The offset may point to the lead byte of a multi-byte sequence,
- * in which case the macro will read the whole sequence.
- * If the offset points to a trail byte or an illegal UTF-8 sequence, then
- * c is set to a negative value.
- *
- * @param s const uint8_t * string
- * @param i int32_t string offset, must be i<length
- * @param length int32_t string length
- * @param c output UChar32 variable, set to <0 in case of an error
- * @see U8_NEXT_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_NEXT(s, i, length, c) U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, U_SENTINEL)
-
-/**
- * Get a code point from a string at a code point boundary offset,
- * and advance the offset to the next code point boundary.
- * (Post-incrementing forward iteration.)
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * The offset may point to the lead byte of a multi-byte sequence,
- * in which case the macro will read the whole sequence.
- * If the offset points to a trail byte or an illegal UTF-8 sequence, then
- * c is set to U+FFFD.
- *
- * This macro does not distinguish between a real U+FFFD in the text
- * and U+FFFD returned for an ill-formed sequence.
- * Use U8_NEXT() if that distinction is important.
- *
- * @param s const uint8_t * string
- * @param i int32_t string offset, must be i<length
- * @param length int32_t string length
- * @param c output UChar32 variable, set to U+FFFD in case of an error
- * @see U8_NEXT
- * @stable ICU 51
- */
-#define U8_NEXT_OR_FFFD(s, i, length, c) U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, 0xfffd)
-
-/** @internal */
-#define U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, sub) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(uint8_t)(s)[(i)++]; \
-    if(!U8_IS_SINGLE(c)) { \
-        uint8_t __t = 0; \
-        if((i)!=(length) && \
-            /* fetch/validate/assemble all but last trail byte */ \
-            ((c)>=0xe0 ? \
-                ((c)<0xf0 ?  /* U+0800..U+FFFF except surrogates */ \
-                    U8_LEAD3_T1_BITS[(c)&=0xf]&(1<<((__t=(s)[i])>>5)) && \
-                    (__t&=0x3f, 1) \
-                :  /* U+10000..U+10FFFF */ \
-                    ((c)-=0xf0)<=4 && \
-                    U8_LEAD4_T1_BITS[(__t=(s)[i])>>4]&(1<<(c)) && \
-                    ((c)=((c)<<6)|(__t&0x3f), ++(i)!=(length)) && \
-                    (__t=(s)[i]-0x80)<=0x3f) && \
-                /* valid second-to-last trail byte */ \
-                ((c)=((c)<<6)|__t, ++(i)!=(length)) \
-            :  /* U+0080..U+07FF */ \
-                (c)>=0xc2 && ((c)&=0x1f, 1)) && \
-            /* last trail byte */ \
-            (__t=(s)[i]-0x80)<=0x3f && \
-            ((c)=((c)<<6)|__t, ++(i), 1)) { \
-        } else { \
-            (c)=(sub);  /* ill-formed*/ \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Append a code point to a string, overwriting 1 to 4 bytes.
- * The offset points to the current end of the string contents
- * and is advanced (post-increment).
- * "Unsafe" macro, assumes a valid code point and sufficient space in the string.
- * Otherwise, the result is undefined.
- *
- * @param s const uint8_t * string buffer
- * @param i string offset
- * @param c code point to append
- * @see U8_APPEND
- * @stable ICU 2.4
- */
-#define U8_APPEND_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    uint32_t __uc=(c); \
-    if(__uc<=0x7f) { \
-        (s)[(i)++]=(uint8_t)__uc; \
-    } else { \
-        if(__uc<=0x7ff) { \
-            (s)[(i)++]=(uint8_t)((__uc>>6)|0xc0); \
-        } else { \
-            if(__uc<=0xffff) { \
-                (s)[(i)++]=(uint8_t)((__uc>>12)|0xe0); \
-            } else { \
-                (s)[(i)++]=(uint8_t)((__uc>>18)|0xf0); \
-                (s)[(i)++]=(uint8_t)(((__uc>>12)&0x3f)|0x80); \
-            } \
-            (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \
-        } \
-        (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Append a code point to a string, overwriting 1 to 4 bytes.
- * The offset points to the current end of the string contents
- * and is advanced (post-increment).
- * "Safe" macro, checks for a valid code point.
- * If a non-ASCII code point is written, checks for sufficient space in the string.
- * If the code point is not valid or trail bytes do not fit,
- * then isError is set to true.
- *
- * @param s const uint8_t * string buffer
- * @param i int32_t string offset, must be i<capacity
- * @param capacity int32_t size of the string buffer
- * @param c UChar32 code point to append
- * @param isError output UBool set to true if an error occurs, otherwise not modified
- * @see U8_APPEND_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_APPEND(s, i, capacity, c, isError) UPRV_BLOCK_MACRO_BEGIN { \
-    uint32_t __uc=(c); \
-    if(__uc<=0x7f) { \
-        (s)[(i)++]=(uint8_t)__uc; \
-    } else if(__uc<=0x7ff && (i)+1<(capacity)) { \
-        (s)[(i)++]=(uint8_t)((__uc>>6)|0xc0); \
-        (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \
-    } else if((__uc<=0xd7ff || (0xe000<=__uc && __uc<=0xffff)) && (i)+2<(capacity)) { \
-        (s)[(i)++]=(uint8_t)((__uc>>12)|0xe0); \
-        (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \
-        (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \
-    } else if(0xffff<__uc && __uc<=0x10ffff && (i)+3<(capacity)) { \
-        (s)[(i)++]=(uint8_t)((__uc>>18)|0xf0); \
-        (s)[(i)++]=(uint8_t)(((__uc>>12)&0x3f)|0x80); \
-        (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \
-        (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \
-    } else { \
-        (isError)=true; \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Advance the string offset from one code point boundary to the next.
- * (Post-incrementing iteration.)
- * "Unsafe" macro, assumes well-formed UTF-8.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @see U8_FWD_1
- * @stable ICU 2.4
- */
-#define U8_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \
-    (i)+=1+U8_COUNT_TRAIL_BYTES_UNSAFE((s)[i]); \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Advance the string offset from one code point boundary to the next.
- * (Post-incrementing iteration.)
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * @param s const uint8_t * string
- * @param i int32_t string offset, must be i<length
- * @param length int32_t string length
- * @see U8_FWD_1_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_FWD_1(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \
-    uint8_t __b=(s)[(i)++]; \
-    if(U8_IS_LEAD(__b) && (i)!=(length)) { \
-        uint8_t __t1=(s)[i]; \
-        if((0xe0<=__b && __b<0xf0)) { \
-            if(U8_IS_VALID_LEAD3_AND_T1(__b, __t1) && \
-                    ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \
-                ++(i); \
-            } \
-        } else if(__b<0xe0) { \
-            if(U8_IS_TRAIL(__t1)) { \
-                ++(i); \
-            } \
-        } else /* c>=0xf0 */ { \
-            if(U8_IS_VALID_LEAD4_AND_T1(__b, __t1) && \
-                    ++(i)!=(length) && U8_IS_TRAIL((s)[i]) && \
-                    ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \
-                ++(i); \
-            } \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Advance the string offset from one code point boundary to the n-th next one,
- * i.e., move forward by n code points.
- * (Post-incrementing iteration.)
- * "Unsafe" macro, assumes well-formed UTF-8.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @param n number of code points to skip
- * @see U8_FWD_N
- * @stable ICU 2.4
- */
-#define U8_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \
-    int32_t __N=(n); \
-    while(__N>0) { \
-        U8_FWD_1_UNSAFE(s, i); \
-        --__N; \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Advance the string offset from one code point boundary to the n-th next one,
- * i.e., move forward by n code points.
- * (Post-incrementing iteration.)
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * @param s const uint8_t * string
- * @param i int32_t string offset, must be i<length
- * @param length int32_t string length
- * @param n number of code points to skip
- * @see U8_FWD_N_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_FWD_N(s, i, length, n) UPRV_BLOCK_MACRO_BEGIN { \
-    int32_t __N=(n); \
-    while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \
-        U8_FWD_1(s, i, length); \
-        --__N; \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Adjust a random-access offset to a code point boundary
- * at the start of a code point.
- * If the offset points to a UTF-8 trail byte,
- * then the offset is moved backward to the corresponding lead byte.
- * Otherwise, it is not modified.
- * "Unsafe" macro, assumes well-formed UTF-8.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @see U8_SET_CP_START
- * @stable ICU 2.4
- */
-#define U8_SET_CP_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \
-    while(U8_IS_TRAIL((s)[i])) { --(i); } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Adjust a random-access offset to a code point boundary
- * at the start of a code point.
- * If the offset points to a UTF-8 trail byte,
- * then the offset is moved backward to the corresponding lead byte.
- * Otherwise, it is not modified.
- *
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- * Unlike U8_TRUNCATE_IF_INCOMPLETE(), this macro always reads s[i].
- *
- * @param s const uint8_t * string
- * @param start int32_t starting string offset (usually 0)
- * @param i int32_t string offset, must be start<=i
- * @see U8_SET_CP_START_UNSAFE
- * @see U8_TRUNCATE_IF_INCOMPLETE
- * @stable ICU 2.4
- */
-#define U8_SET_CP_START(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \
-    if(U8_IS_TRAIL((s)[(i)])) { \
-        (i)=utf8_back1SafeBody(s, start, (i)); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * If the string ends with a UTF-8 byte sequence that is valid so far
- * but incomplete, then reduce the length of the string to end before
- * the lead byte of that incomplete sequence.
- * For example, if the string ends with E1 80, the length is reduced by 2.
- *
- * In all other cases (the string ends with a complete sequence, or it is not
- * possible for any further trail byte to extend the trailing sequence)
- * the length remains unchanged.
- *
- * Useful for processing text split across multiple buffers
- * (save the incomplete sequence for later)
- * and for optimizing iteration
- * (check for string length only once per character).
- *
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- * Unlike U8_SET_CP_START(), this macro never reads s[length].
- *
- * (In UTF-16, simply check for U16_IS_LEAD(last code unit).)
- *
- * @param s const uint8_t * string
- * @param start int32_t starting string offset (usually 0)
- * @param length int32_t string length (usually start<=length)
- * @see U8_SET_CP_START
- * @stable ICU 61
- */
-#define U8_TRUNCATE_IF_INCOMPLETE(s, start, length) UPRV_BLOCK_MACRO_BEGIN { \
-    if((length)>(start)) { \
-        uint8_t __b1=s[(length)-1]; \
-        if(U8_IS_SINGLE(__b1)) { \
-            /* common ASCII character */ \
-        } else if(U8_IS_LEAD(__b1)) { \
-            --(length); \
-        } else if(U8_IS_TRAIL(__b1) && ((length)-2)>=(start)) { \
-            uint8_t __b2=s[(length)-2]; \
-            if(0xe0<=__b2 && __b2<=0xf4) { \
-                if(__b2<0xf0 ? U8_IS_VALID_LEAD3_AND_T1(__b2, __b1) : \
-                        U8_IS_VALID_LEAD4_AND_T1(__b2, __b1)) { \
-                    (length)-=2; \
-                } \
-            } else if(U8_IS_TRAIL(__b2) && ((length)-3)>=(start)) { \
-                uint8_t __b3=s[(length)-3]; \
-                if(0xf0<=__b3 && __b3<=0xf4 && U8_IS_VALID_LEAD4_AND_T1(__b3, __b2)) { \
-                    (length)-=3; \
-                } \
-            } \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/* definitions with backward iteration -------------------------------------- */
-
-/**
- * Move the string offset from one code point boundary to the previous one
- * and get the code point between them.
- * (Pre-decrementing backward iteration.)
- * "Unsafe" macro, assumes well-formed UTF-8.
- *
- * The input offset may be the same as the string length.
- * If the offset is behind a multi-byte sequence, then the macro will read
- * the whole sequence.
- * If the offset is behind a lead byte, then that itself
- * will be returned as the code point.
- * The result is undefined if the offset is behind an illegal UTF-8 sequence.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @param c output UChar32 variable
- * @see U8_PREV
- * @stable ICU 2.4
- */
-#define U8_PREV_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(uint8_t)(s)[--(i)]; \
-    if(U8_IS_TRAIL(c)) { \
-        uint8_t __b, __count=1, __shift=6; \
-\
-        /* c is a trail byte */ \
-        (c)&=0x3f; \
-        for(;;) { \
-            __b=(s)[--(i)]; \
-            if(__b>=0xc0) { \
-                U8_MASK_LEAD_BYTE(__b, __count); \
-                (c)|=(UChar32)__b<<__shift; \
-                break; \
-            } else { \
-                (c)|=(UChar32)(__b&0x3f)<<__shift; \
-                ++__count; \
-                __shift+=6; \
-            } \
-        } \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the previous one
- * and get the code point between them.
- * (Pre-decrementing backward iteration.)
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * The input offset may be the same as the string length.
- * If the offset is behind a multi-byte sequence, then the macro will read
- * the whole sequence.
- * If the offset is behind a lead byte, then that itself
- * will be returned as the code point.
- * If the offset is behind an illegal UTF-8 sequence, then c is set to a negative value.
- *
- * @param s const uint8_t * string
- * @param start int32_t starting string offset (usually 0)
- * @param i int32_t string offset, must be start<i
- * @param c output UChar32 variable, set to <0 in case of an error
- * @see U8_PREV_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_PREV(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(uint8_t)(s)[--(i)]; \
-    if(!U8_IS_SINGLE(c)) { \
-        (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -1); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the previous one
- * and get the code point between them.
- * (Pre-decrementing backward iteration.)
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * The input offset may be the same as the string length.
- * If the offset is behind a multi-byte sequence, then the macro will read
- * the whole sequence.
- * If the offset is behind a lead byte, then that itself
- * will be returned as the code point.
- * If the offset is behind an illegal UTF-8 sequence, then c is set to U+FFFD.
- *
- * This macro does not distinguish between a real U+FFFD in the text
- * and U+FFFD returned for an ill-formed sequence.
- * Use U8_PREV() if that distinction is important.
- *
- * @param s const uint8_t * string
- * @param start int32_t starting string offset (usually 0)
- * @param i int32_t string offset, must be start<i
- * @param c output UChar32 variable, set to U+FFFD in case of an error
- * @see U8_PREV
- * @stable ICU 51
- */
-#define U8_PREV_OR_FFFD(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \
-    (c)=(uint8_t)(s)[--(i)]; \
-    if(!U8_IS_SINGLE(c)) { \
-        (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -3); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the previous one.
- * (Pre-decrementing backward iteration.)
- * The input offset may be the same as the string length.
- * "Unsafe" macro, assumes well-formed UTF-8.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @see U8_BACK_1
- * @stable ICU 2.4
- */
-#define U8_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \
-    while(U8_IS_TRAIL((s)[--(i)])) {} \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the previous one.
- * (Pre-decrementing backward iteration.)
- * The input offset may be the same as the string length.
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * @param s const uint8_t * string
- * @param start int32_t starting string offset (usually 0)
- * @param i int32_t string offset, must be start<i
- * @see U8_BACK_1_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_BACK_1(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \
-    if(U8_IS_TRAIL((s)[--(i)])) { \
-        (i)=utf8_back1SafeBody(s, start, (i)); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the n-th one before it,
- * i.e., move backward by n code points.
- * (Pre-decrementing backward iteration.)
- * The input offset may be the same as the string length.
- * "Unsafe" macro, assumes well-formed UTF-8.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @param n number of code points to skip
- * @see U8_BACK_N
- * @stable ICU 2.4
- */
-#define U8_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \
-    int32_t __N=(n); \
-    while(__N>0) { \
-        U8_BACK_1_UNSAFE(s, i); \
-        --__N; \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Move the string offset from one code point boundary to the n-th one before it,
- * i.e., move backward by n code points.
- * (Pre-decrementing backward iteration.)
- * The input offset may be the same as the string length.
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * @param s const uint8_t * string
- * @param start int32_t index of the start of the string
- * @param i int32_t string offset, must be start<i
- * @param n number of code points to skip
- * @see U8_BACK_N_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_BACK_N(s, start, i, n) UPRV_BLOCK_MACRO_BEGIN { \
-    int32_t __N=(n); \
-    while(__N>0 && (i)>(start)) { \
-        U8_BACK_1(s, start, i); \
-        --__N; \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Adjust a random-access offset to a code point boundary after a code point.
- * If the offset is behind a partial multi-byte sequence,
- * then the offset is incremented to behind the whole sequence.
- * Otherwise, it is not modified.
- * The input offset may be the same as the string length.
- * "Unsafe" macro, assumes well-formed UTF-8.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @see U8_SET_CP_LIMIT
- * @stable ICU 2.4
- */
-#define U8_SET_CP_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \
-    U8_BACK_1_UNSAFE(s, i); \
-    U8_FWD_1_UNSAFE(s, i); \
-} UPRV_BLOCK_MACRO_END
-
-/**
- * Adjust a random-access offset to a code point boundary after a code point.
- * If the offset is behind a partial multi-byte sequence,
- * then the offset is incremented to behind the whole sequence.
- * Otherwise, it is not modified.
- * The input offset may be the same as the string length.
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * The length can be negative for a NUL-terminated string.
- *
- * @param s const uint8_t * string
- * @param start int32_t starting string offset (usually 0)
- * @param i int32_t string offset, must be start<=i<=length
- * @param length int32_t string length
- * @see U8_SET_CP_LIMIT_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_SET_CP_LIMIT(s, start, i, length) UPRV_BLOCK_MACRO_BEGIN { \
-    if((start)<(i) && ((i)<(length) || (length)<0)) { \
-        U8_BACK_1(s, start, i); \
-        U8_FWD_1(s, i, length); \
-    } \
-} UPRV_BLOCK_MACRO_END
-
-#endif

app/src/main/cpp/icu4c/include/unicode/utypes.h

@@ -1,732 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-**********************************************************************
-*   Copyright (C) 1996-2016, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-**********************************************************************
-*
-*  FILE NAME : UTYPES.H (formerly ptypes.h)
-*
-*   Date        Name        Description
-*   12/11/96    helena      Creation.
-*   02/27/97    aliu        Added typedefs for UClassID, int8, int16, int32,
-*                           uint8, uint16, and uint32.
-*   04/01/97    aliu        Added XP_CPLUSPLUS and modified to work under C as
-*                            well as C++.
-*                           Modified to use memcpy() for uprv_arrayCopy() fns.
-*   04/14/97    aliu        Added TPlatformUtilities.
-*   05/07/97    aliu        Added import/export specifiers (replacing the old
-*                           broken EXT_CLASS).  Added version number for our
-*                           code.  Cleaned up header.
-*    6/20/97    helena      Java class name change.
-*   08/11/98    stephen     UErrorCode changed from typedef to enum
-*   08/12/98    erm         Changed T_ANALYTIC_PACKAGE_VERSION to 3
-*   08/14/98    stephen     Added uprv_arrayCopy() for int8_t, int16_t, int32_t
-*   12/09/98    jfitz       Added BUFFER_OVERFLOW_ERROR (bug 1100066)
-*   04/20/99    stephen     Cleaned up & reworked for autoconf.
-*                           Renamed to utypes.h.
-*   05/05/99    stephen     Changed to use <inttypes.h>
-*   12/07/99    helena      Moved copyright notice string from ucnv_bld.h here.
-*******************************************************************************
-*/
-
-#ifndef UTYPES_H
-#define UTYPES_H
-
-
-#include "unicode/umachine.h"
-#include "unicode/uversion.h"
-#include "unicode/uconfig.h"
-#include <float.h>
-
-#if !U_NO_DEFAULT_INCLUDE_UTF_HEADERS
-#   include "unicode/utf.h"
-#endif
-
-/*!
- * \file
- * \brief Basic definitions for ICU, for both C and C++ APIs
- *
- * This file defines basic types, constants, and enumerations directly or
- * indirectly by including other header files, especially utf.h for the
- * basic character and string definitions and umachine.h for consistent
- * integer and other types.
- */
-
-
-/**
- * \def U_SHOW_CPLUSPLUS_API
- * @internal
- */
-#ifdef __cplusplus
-#   ifndef U_SHOW_CPLUSPLUS_API
-#       define U_SHOW_CPLUSPLUS_API 1
-#   endif
-#else
-#   undef U_SHOW_CPLUSPLUS_API
-#   define U_SHOW_CPLUSPLUS_API 0
-#endif
-
-/** @{ API visibility control */
-
-/**
- * \def U_HIDE_DRAFT_API
- * Define this to 1 to request that draft API be "hidden"
- * @internal
- */
-/**
- * \def U_HIDE_INTERNAL_API
- * Define this to 1 to request that internal API be "hidden"
- * @internal
- */
-#if !U_DEFAULT_SHOW_DRAFT && !defined(U_SHOW_DRAFT_API)
-#define U_HIDE_DRAFT_API 1
-#endif
-#if !U_DEFAULT_SHOW_DRAFT && !defined(U_SHOW_INTERNAL_API)
-#define U_HIDE_INTERNAL_API 1
-#endif
-
-/** @} */
-
-/*===========================================================================*/
-/* ICUDATA naming scheme                                                     */
-/*===========================================================================*/
-
-/**
- * \def U_ICUDATA_TYPE_LETTER
- *
- * This is a platform-dependent string containing one letter:
- * - b for big-endian, ASCII-family platforms
- * - l for little-endian, ASCII-family platforms
- * - e for big-endian, EBCDIC-family platforms
- * This letter is part of the common data file name.
- * @stable ICU 2.0
- */
-
-/**
- * \def U_ICUDATA_TYPE_LITLETTER
- * The non-string form of U_ICUDATA_TYPE_LETTER
- * @stable ICU 2.0
- */
-#if U_CHARSET_FAMILY
-#   if U_IS_BIG_ENDIAN
-   /* EBCDIC - should always be BE */
-#     define U_ICUDATA_TYPE_LETTER "e"
-#     define U_ICUDATA_TYPE_LITLETTER e
-#   else
-#     error "Don't know what to do with little endian EBCDIC!"
-#     define U_ICUDATA_TYPE_LETTER "x"
-#     define U_ICUDATA_TYPE_LITLETTER x
-#   endif
-#else
-#   if U_IS_BIG_ENDIAN
-      /* Big-endian ASCII */
-#     define U_ICUDATA_TYPE_LETTER "b"
-#     define U_ICUDATA_TYPE_LITLETTER b
-#   else
-      /* Little-endian ASCII */
-#     define U_ICUDATA_TYPE_LETTER "l"
-#     define U_ICUDATA_TYPE_LITLETTER l
-#   endif
-#endif
-
-/**
- * A single string literal containing the icudata stub name. i.e. 'icudt18e' for
- * ICU 1.8.x on EBCDIC, etc..
- * @stable ICU 2.0
- */
-#define U_ICUDATA_NAME    "icudt" U_ICU_VERSION_SHORT U_ICUDATA_TYPE_LETTER
-#ifndef U_HIDE_INTERNAL_API
-#define U_USRDATA_NAME    "usrdt" U_ICU_VERSION_SHORT U_ICUDATA_TYPE_LETTER  /**< @internal */
-#define U_USE_USRDATA     0  /**< @internal */
-#endif  /* U_HIDE_INTERNAL_API */
-
-/**
- *  U_ICU_ENTRY_POINT is the name of the DLL entry point to the ICU data library.
- *    Defined as a literal, not a string.
- *    Tricky Preprocessor use - ## operator replaces macro parameters with the literal string
- *                              from the corresponding macro invocation, _before_ other macro substitutions.
- *                              Need a nested \#defines to get the actual version numbers rather than
- *                              the literal text U_ICU_VERSION_MAJOR_NUM into the name.
- *                              The net result will be something of the form
- *                                  \#define U_ICU_ENTRY_POINT icudt19_dat
- * @stable ICU 2.4
- */
-#define U_ICUDATA_ENTRY_POINT  U_DEF2_ICUDATA_ENTRY_POINT(U_ICU_VERSION_MAJOR_NUM,U_LIB_SUFFIX_C_NAME)
-
-#ifndef U_HIDE_INTERNAL_API
-/**
- * Do not use. Note that it's OK for the 2nd argument to be undefined (literal).
- * @internal
- */
-#define U_DEF2_ICUDATA_ENTRY_POINT(major,suff) U_DEF_ICUDATA_ENTRY_POINT(major,suff)
-
-/**
- * Do not use.
- * @internal
- */
-#ifndef U_DEF_ICUDATA_ENTRY_POINT
-/* affected by symbol renaming. See platform.h */
-#ifndef U_LIB_SUFFIX_C_NAME
-#define U_DEF_ICUDATA_ENTRY_POINT(major, suff) icudt##major##_dat
-#else
-#define U_DEF_ICUDATA_ENTRY_POINT(major, suff) icudt##suff ## major##_dat
-#endif
-#endif
-#endif  /* U_HIDE_INTERNAL_API */
-
-/**
- * \def NULL
- * Define NULL if necessary, to nullptr for C++ and to ((void *)0) for C.
- * @stable ICU 2.0
- */
-#ifndef NULL
-#ifdef __cplusplus
-#define NULL    nullptr
-#else
-#define NULL    ((void *)0)
-#endif
-#endif
-
-/*===========================================================================*/
-/* Calendar/TimeZone data types                                              */
-/*===========================================================================*/
-
-/**
- * Date and Time data type.
- * This is a primitive data type that holds the date and time
- * as the number of milliseconds since 1970-jan-01, 00:00 UTC.
- * UTC leap seconds are ignored.
- * @stable ICU 2.0
- */
-typedef double UDate;
-
-/** The number of milliseconds per second @stable ICU 2.0 */
-#define U_MILLIS_PER_SECOND        (1000)
-/** The number of milliseconds per minute @stable ICU 2.0 */
-#define U_MILLIS_PER_MINUTE       (60000)
-/** The number of milliseconds per hour @stable ICU 2.0 */
-#define U_MILLIS_PER_HOUR       (3600000)
-/** The number of milliseconds per day @stable ICU 2.0 */
-#define U_MILLIS_PER_DAY       (86400000)
-
-/** 
- * Maximum UDate value 
- * @stable ICU 4.8 
- */ 
-#define U_DATE_MAX DBL_MAX
-
-/**
- * Minimum UDate value 
- * @stable ICU 4.8 
- */ 
-#define U_DATE_MIN -U_DATE_MAX
-
-/*===========================================================================*/
-/* Shared library/DLL import-export API control                              */
-/*===========================================================================*/
-
-/*
- * Control of symbol import/export.
- * ICU is separated into three libraries.
- */
-
-/**
- * \def U_COMBINED_IMPLEMENTATION
- * Set to export library symbols from inside the ICU library
- * when all of ICU is in a single library.
- * This can be set as a compiler option while building ICU, and it
- * needs to be the first one tested to override U_COMMON_API, U_I18N_API, etc.
- * @stable ICU 2.0
- */
-
-/**
- * \def U_DATA_API
- * Set to export library symbols from inside the stubdata library,
- * and to import them from outside.
- * @stable ICU 3.0
- */
-
-/**
- * \def U_COMMON_API
- * Set to export library symbols from inside the common library,
- * and to import them from outside.
- * @stable ICU 2.0
- */
-
-/**
- * \def U_I18N_API
- * Set to export library symbols from inside the i18n library,
- * and to import them from outside.
- * @stable ICU 2.0
- */
-
-/**
- * \def U_LAYOUT_API
- * Set to export library symbols from inside the layout engine library,
- * and to import them from outside.
- * @stable ICU 2.0
- */
-
-/**
- * \def U_LAYOUTEX_API
- * Set to export library symbols from inside the layout extensions library,
- * and to import them from outside.
- * @stable ICU 2.6
- */
-
-/**
- * \def U_IO_API
- * Set to export library symbols from inside the ustdio library,
- * and to import them from outside.
- * @stable ICU 2.0
- */
-
-/**
- * \def U_TOOLUTIL_API
- * Set to export library symbols from inside the toolutil library,
- * and to import them from outside.
- * @stable ICU 3.4
- */
-
-#ifdef U_IN_DOXYGEN
-// This definition is required when generating the API docs.
-#define U_COMBINED_IMPLEMENTATION 1
-#endif
-
-#if defined(U_COMBINED_IMPLEMENTATION)
-#define U_DATA_API     U_EXPORT
-#define U_COMMON_API   U_EXPORT
-#define U_I18N_API     U_EXPORT
-#define U_LAYOUT_API   U_EXPORT
-#define U_LAYOUTEX_API U_EXPORT
-#define U_IO_API       U_EXPORT
-#define U_TOOLUTIL_API U_EXPORT
-#elif defined(U_STATIC_IMPLEMENTATION)
-#define U_DATA_API
-#define U_COMMON_API
-#define U_I18N_API
-#define U_LAYOUT_API
-#define U_LAYOUTEX_API
-#define U_IO_API
-#define U_TOOLUTIL_API
-#elif defined(U_COMMON_IMPLEMENTATION)
-#define U_DATA_API     U_IMPORT
-#define U_COMMON_API   U_EXPORT
-#define U_I18N_API     U_IMPORT
-#define U_LAYOUT_API   U_IMPORT
-#define U_LAYOUTEX_API U_IMPORT
-#define U_IO_API       U_IMPORT
-#define U_TOOLUTIL_API U_IMPORT
-#elif defined(U_I18N_IMPLEMENTATION)
-#define U_DATA_API     U_IMPORT
-#define U_COMMON_API   U_IMPORT
-#define U_I18N_API     U_EXPORT
-#define U_LAYOUT_API   U_IMPORT
-#define U_LAYOUTEX_API U_IMPORT
-#define U_IO_API       U_IMPORT
-#define U_TOOLUTIL_API U_IMPORT
-#elif defined(U_LAYOUT_IMPLEMENTATION)
-#define U_DATA_API     U_IMPORT
-#define U_COMMON_API   U_IMPORT
-#define U_I18N_API     U_IMPORT
-#define U_LAYOUT_API   U_EXPORT
-#define U_LAYOUTEX_API U_IMPORT
-#define U_IO_API       U_IMPORT
-#define U_TOOLUTIL_API U_IMPORT
-#elif defined(U_LAYOUTEX_IMPLEMENTATION)
-#define U_DATA_API     U_IMPORT
-#define U_COMMON_API   U_IMPORT
-#define U_I18N_API     U_IMPORT
-#define U_LAYOUT_API   U_IMPORT
-#define U_LAYOUTEX_API U_EXPORT
-#define U_IO_API       U_IMPORT
-#define U_TOOLUTIL_API U_IMPORT
-#elif defined(U_IO_IMPLEMENTATION)
-#define U_DATA_API     U_IMPORT
-#define U_COMMON_API   U_IMPORT
-#define U_I18N_API     U_IMPORT
-#define U_LAYOUT_API   U_IMPORT
-#define U_LAYOUTEX_API U_IMPORT
-#define U_IO_API       U_EXPORT
-#define U_TOOLUTIL_API U_IMPORT
-#elif defined(U_TOOLUTIL_IMPLEMENTATION)
-#define U_DATA_API     U_IMPORT
-#define U_COMMON_API   U_IMPORT
-#define U_I18N_API     U_IMPORT
-#define U_LAYOUT_API   U_IMPORT
-#define U_LAYOUTEX_API U_IMPORT
-#define U_IO_API       U_IMPORT
-#define U_TOOLUTIL_API U_EXPORT
-#else
-#define U_DATA_API     U_IMPORT
-#define U_COMMON_API   U_IMPORT
-#define U_I18N_API     U_IMPORT
-#define U_LAYOUT_API   U_IMPORT
-#define U_LAYOUTEX_API U_IMPORT
-#define U_IO_API       U_IMPORT
-#define U_TOOLUTIL_API U_IMPORT
-#endif
-
-/**
- * \def U_STANDARD_CPP_NAMESPACE
- * Control of C++ Namespace
- * @stable ICU 2.0
- */
-#ifdef __cplusplus
-#define U_STANDARD_CPP_NAMESPACE        ::
-#else
-#define U_STANDARD_CPP_NAMESPACE
-#endif
-
-/*===========================================================================*/
-/* UErrorCode */
-/*===========================================================================*/
-
-/**
- * Standard ICU4C error code type, a substitute for exceptions.
- *
- * Initialize the UErrorCode with U_ZERO_ERROR, and check for success or
- * failure using U_SUCCESS() or U_FAILURE():
- *
- *     UErrorCode errorCode = U_ZERO_ERROR;
- *     // call ICU API that needs an error code parameter.
- *     if (U_FAILURE(errorCode)) {
- *         // An error occurred. Handle it here.
- *     }
- *
- * C++ code should use icu::ErrorCode, available in unicode/errorcode.h, or a
- * suitable subclass.
- *
- * For more information, see:
- * http://icu-project.org/userguide/conventions
- *
- * Note: By convention, ICU functions that take a reference (C++) or a pointer
- * (C) to a UErrorCode first test:
- *
- *     if (U_FAILURE(errorCode)) { return immediately; }
- *
- * so that in a chain of such functions the first one that sets an error code
- * causes the following ones to not perform any operations.
- *
- * @stable ICU 2.0
- */
-typedef enum UErrorCode {
-    /* The ordering of U_ERROR_INFO_START Vs U_USING_FALLBACK_WARNING looks weird
-     * and is that way because VC++ debugger displays first encountered constant,
-     * which is not the what the code is used for
-     */
-
-    U_USING_FALLBACK_WARNING  = -128,   /**< A resource bundle lookup returned a fallback result (not an error) */
-
-    U_ERROR_WARNING_START     = -128,   /**< Start of information results (semantically successful) */
-
-    U_USING_DEFAULT_WARNING   = -127,   /**< A resource bundle lookup returned a result from the root locale (not an error) */
-
-    U_SAFECLONE_ALLOCATED_WARNING = -126, /**< A SafeClone operation required allocating memory (informational only) */
-
-    U_STATE_OLD_WARNING       = -125,   /**< ICU has to use compatibility layer to construct the service. Expect performance/memory usage degradation. Consider upgrading */
-
-    U_STRING_NOT_TERMINATED_WARNING = -124,/**< An output string could not be NUL-terminated because output length==destCapacity. */
-
-    U_SORT_KEY_TOO_SHORT_WARNING = -123, /**< Number of levels requested in getBound is higher than the number of levels in the sort key */
-
-    U_AMBIGUOUS_ALIAS_WARNING = -122,   /**< This converter alias can go to different converter implementations */
-
-    U_DIFFERENT_UCA_VERSION = -121,     /**< ucol_open encountered a mismatch between UCA version and collator image version, so the collator was constructed from rules. No impact to further function */
-    
-    U_PLUGIN_CHANGED_LEVEL_WARNING = -120, /**< A plugin caused a level change. May not be an error, but later plugins may not load. */
-
-#ifndef U_HIDE_DEPRECATED_API
-    /**
-     * One more than the highest normal UErrorCode warning value.
-     * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
-     */
-    U_ERROR_WARNING_LIMIT,
-#endif  // U_HIDE_DEPRECATED_API
-
-    U_ZERO_ERROR              =  0,     /**< No error, no warning. */
-
-    U_ILLEGAL_ARGUMENT_ERROR  =  1,     /**< Start of codes indicating failure */
-    U_MISSING_RESOURCE_ERROR  =  2,     /**< The requested resource cannot be found */
-    U_INVALID_FORMAT_ERROR    =  3,     /**< Data format is not what is expected */
-    U_FILE_ACCESS_ERROR       =  4,     /**< The requested file cannot be found */
-    U_INTERNAL_PROGRAM_ERROR  =  5,     /**< Indicates a bug in the library code */
-    U_MESSAGE_PARSE_ERROR     =  6,     /**< Unable to parse a message (message format) */
-    U_MEMORY_ALLOCATION_ERROR =  7,     /**< Memory allocation error */
-    U_INDEX_OUTOFBOUNDS_ERROR =  8,     /**< Trying to access the index that is out of bounds */
-    U_PARSE_ERROR             =  9,     /**< Equivalent to Java ParseException */
-    U_INVALID_CHAR_FOUND      = 10,     /**< Character conversion: Unmappable input sequence. In other APIs: Invalid character. */
-    U_TRUNCATED_CHAR_FOUND    = 11,     /**< Character conversion: Incomplete input sequence. */
-    U_ILLEGAL_CHAR_FOUND      = 12,     /**< Character conversion: Illegal input sequence/combination of input units. */
-    U_INVALID_TABLE_FORMAT    = 13,     /**< Conversion table file found, but corrupted */
-    U_INVALID_TABLE_FILE      = 14,     /**< Conversion table file not found */
-    U_BUFFER_OVERFLOW_ERROR   = 15,     /**< A result would not fit in the supplied buffer */
-    U_UNSUPPORTED_ERROR       = 16,     /**< Requested operation not supported in current context */
-    U_RESOURCE_TYPE_MISMATCH  = 17,     /**< an operation is requested over a resource that does not support it */
-    U_ILLEGAL_ESCAPE_SEQUENCE = 18,     /**< ISO-2022 illegal escape sequence */
-    U_UNSUPPORTED_ESCAPE_SEQUENCE = 19, /**< ISO-2022 unsupported escape sequence */
-    U_NO_SPACE_AVAILABLE      = 20,     /**< No space available for in-buffer expansion for Arabic shaping */
-    U_CE_NOT_FOUND_ERROR      = 21,     /**< Currently used only while setting variable top, but can be used generally */
-    U_PRIMARY_TOO_LONG_ERROR  = 22,     /**< User tried to set variable top to a primary that is longer than two bytes */
-    U_STATE_TOO_OLD_ERROR     = 23,     /**< ICU cannot construct a service from this state, as it is no longer supported */
-    U_TOO_MANY_ALIASES_ERROR  = 24,     /**< There are too many aliases in the path to the requested resource.
-                                             It is very possible that a circular alias definition has occurred */
-    U_ENUM_OUT_OF_SYNC_ERROR  = 25,     /**< UEnumeration out of sync with underlying collection */
-    U_INVARIANT_CONVERSION_ERROR = 26,  /**< Unable to convert a UChar* string to char* with the invariant converter. */
-    U_INVALID_STATE_ERROR     = 27,     /**< Requested operation can not be completed with ICU in its current state */
-    U_COLLATOR_VERSION_MISMATCH = 28,   /**< Collator version is not compatible with the base version */
-    U_USELESS_COLLATOR_ERROR  = 29,     /**< Collator is options only and no base is specified */
-    U_NO_WRITE_PERMISSION     = 30,     /**< Attempt to modify read-only or constant data. */
-#ifndef U_HIDE_DRAFT_API
-    /**
-     * The input is impractically long for an operation.
-     * It is rejected because it may lead to problems such as excessive
-     * processing time, stack depth, or heap memory requirements.
-     *
-     * @draft ICU 68
-     */
-    U_INPUT_TOO_LONG_ERROR = 31,
-#endif  // U_HIDE_DRAFT_API
-
-#ifndef U_HIDE_DEPRECATED_API
-    /**
-     * One more than the highest standard error code.
-     * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
-     */
-    U_STANDARD_ERROR_LIMIT = 32,
-#endif  // U_HIDE_DEPRECATED_API
-
-    /*
-     * Error codes in the range 0x10000 0x10100 are reserved for Transliterator.
-     */
-    U_BAD_VARIABLE_DEFINITION=0x10000,/**< Missing '$' or duplicate variable name */
-    U_PARSE_ERROR_START = 0x10000,    /**< Start of Transliterator errors */
-    U_MALFORMED_RULE,                 /**< Elements of a rule are misplaced */
-    U_MALFORMED_SET,                  /**< A UnicodeSet pattern is invalid*/
-    U_MALFORMED_SYMBOL_REFERENCE,     /**< UNUSED as of ICU 2.4 */
-    U_MALFORMED_UNICODE_ESCAPE,       /**< A Unicode escape pattern is invalid*/
-    U_MALFORMED_VARIABLE_DEFINITION,  /**< A variable definition is invalid */
-    U_MALFORMED_VARIABLE_REFERENCE,   /**< A variable reference is invalid */
-    U_MISMATCHED_SEGMENT_DELIMITERS,  /**< UNUSED as of ICU 2.4 */
-    U_MISPLACED_ANCHOR_START,         /**< A start anchor appears at an illegal position */
-    U_MISPLACED_CURSOR_OFFSET,        /**< A cursor offset occurs at an illegal position */
-    U_MISPLACED_QUANTIFIER,           /**< A quantifier appears after a segment close delimiter */
-    U_MISSING_OPERATOR,               /**< A rule contains no operator */
-    U_MISSING_SEGMENT_CLOSE,          /**< UNUSED as of ICU 2.4 */
-    U_MULTIPLE_ANTE_CONTEXTS,         /**< More than one ante context */
-    U_MULTIPLE_CURSORS,               /**< More than one cursor */
-    U_MULTIPLE_POST_CONTEXTS,         /**< More than one post context */
-    U_TRAILING_BACKSLASH,             /**< A dangling backslash */
-    U_UNDEFINED_SEGMENT_REFERENCE,    /**< A segment reference does not correspond to a defined segment */
-    U_UNDEFINED_VARIABLE,             /**< A variable reference does not correspond to a defined variable */
-    U_UNQUOTED_SPECIAL,               /**< A special character was not quoted or escaped */
-    U_UNTERMINATED_QUOTE,             /**< A closing single quote is missing */
-    U_RULE_MASK_ERROR,                /**< A rule is hidden by an earlier more general rule */
-    U_MISPLACED_COMPOUND_FILTER,      /**< A compound filter is in an invalid location */
-    U_MULTIPLE_COMPOUND_FILTERS,      /**< More than one compound filter */
-    U_INVALID_RBT_SYNTAX,             /**< A "::id" rule was passed to the RuleBasedTransliterator parser */
-    U_INVALID_PROPERTY_PATTERN,       /**< UNUSED as of ICU 2.4 */
-    U_MALFORMED_PRAGMA,               /**< A 'use' pragma is invalid */
-    U_UNCLOSED_SEGMENT,               /**< A closing ')' is missing */
-    U_ILLEGAL_CHAR_IN_SEGMENT,        /**< UNUSED as of ICU 2.4 */
-    U_VARIABLE_RANGE_EXHAUSTED,       /**< Too many stand-ins generated for the given variable range */
-    U_VARIABLE_RANGE_OVERLAP,         /**< The variable range overlaps characters used in rules */
-    U_ILLEGAL_CHARACTER,              /**< A special character is outside its allowed context */
-    U_INTERNAL_TRANSLITERATOR_ERROR,  /**< Internal transliterator system error */
-    U_INVALID_ID,                     /**< A "::id" rule specifies an unknown transliterator */
-    U_INVALID_FUNCTION,               /**< A "&fn()" rule specifies an unknown transliterator */
-#ifndef U_HIDE_DEPRECATED_API
-    /**
-     * One more than the highest normal Transliterator error code.
-     * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
-     */
-    U_PARSE_ERROR_LIMIT,
-#endif  // U_HIDE_DEPRECATED_API
-
-    /*
-     * Error codes in the range 0x10100 0x10200 are reserved for the formatting API.
-     */
-    U_UNEXPECTED_TOKEN=0x10100,       /**< Syntax error in format pattern */
-    U_FMT_PARSE_ERROR_START=0x10100,  /**< Start of format library errors */
-    U_MULTIPLE_DECIMAL_SEPARATORS,    /**< More than one decimal separator in number pattern */
-    U_MULTIPLE_DECIMAL_SEPERATORS = U_MULTIPLE_DECIMAL_SEPARATORS, /**< Typo: kept for backward compatibility. Use U_MULTIPLE_DECIMAL_SEPARATORS */
-    U_MULTIPLE_EXPONENTIAL_SYMBOLS,   /**< More than one exponent symbol in number pattern */
-    U_MALFORMED_EXPONENTIAL_PATTERN,  /**< Grouping symbol in exponent pattern */
-    U_MULTIPLE_PERCENT_SYMBOLS,       /**< More than one percent symbol in number pattern */
-    U_MULTIPLE_PERMILL_SYMBOLS,       /**< More than one permill symbol in number pattern */
-    U_MULTIPLE_PAD_SPECIFIERS,        /**< More than one pad symbol in number pattern */
-    U_PATTERN_SYNTAX_ERROR,           /**< Syntax error in format pattern */
-    U_ILLEGAL_PAD_POSITION,           /**< Pad symbol misplaced in number pattern */
-    U_UNMATCHED_BRACES,               /**< Braces do not match in message pattern */
-    U_UNSUPPORTED_PROPERTY,           /**< UNUSED as of ICU 2.4 */
-    U_UNSUPPORTED_ATTRIBUTE,          /**< UNUSED as of ICU 2.4 */
-    U_ARGUMENT_TYPE_MISMATCH,         /**< Argument name and argument index mismatch in MessageFormat functions */
-    U_DUPLICATE_KEYWORD,              /**< Duplicate keyword in PluralFormat */
-    U_UNDEFINED_KEYWORD,              /**< Undefined Plural keyword */
-    U_DEFAULT_KEYWORD_MISSING,        /**< Missing DEFAULT rule in plural rules */
-    U_DECIMAL_NUMBER_SYNTAX_ERROR,    /**< Decimal number syntax error */
-    U_FORMAT_INEXACT_ERROR,           /**< Cannot format a number exactly and rounding mode is ROUND_UNNECESSARY @stable ICU 4.8 */
-    U_NUMBER_ARG_OUTOFBOUNDS_ERROR,   /**< The argument to a NumberFormatter helper method was out of bounds; the bounds are usually 0 to 999. @stable ICU 61 */
-    U_NUMBER_SKELETON_SYNTAX_ERROR,   /**< The number skeleton passed to C++ NumberFormatter or C UNumberFormatter was invalid or contained a syntax error. @stable ICU 62 */
-#ifndef U_HIDE_DEPRECATED_API
-    /**
-     * One more than the highest normal formatting API error code.
-     * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
-     */
-    U_FMT_PARSE_ERROR_LIMIT = 0x10114,
-#endif  // U_HIDE_DEPRECATED_API
-
-    /*
-     * Error codes in the range 0x10200 0x102ff are reserved for BreakIterator.
-     */
-    U_BRK_INTERNAL_ERROR=0x10200,          /**< An internal error (bug) was detected.             */
-    U_BRK_ERROR_START=0x10200,             /**< Start of codes indicating Break Iterator failures */
-    U_BRK_HEX_DIGITS_EXPECTED,             /**< Hex digits expected as part of a escaped char in a rule. */
-    U_BRK_SEMICOLON_EXPECTED,              /**< Missing ';' at the end of a RBBI rule.            */
-    U_BRK_RULE_SYNTAX,                     /**< Syntax error in RBBI rule.                        */
-    U_BRK_UNCLOSED_SET,                    /**< UnicodeSet writing an RBBI rule missing a closing ']'. */
-    U_BRK_ASSIGN_ERROR,                    /**< Syntax error in RBBI rule assignment statement.   */
-    U_BRK_VARIABLE_REDFINITION,            /**< RBBI rule $Variable redefined.                    */
-    U_BRK_MISMATCHED_PAREN,                /**< Mis-matched parentheses in an RBBI rule.          */
-    U_BRK_NEW_LINE_IN_QUOTED_STRING,       /**< Missing closing quote in an RBBI rule.            */
-    U_BRK_UNDEFINED_VARIABLE,              /**< Use of an undefined $Variable in an RBBI rule.    */
-    U_BRK_INIT_ERROR,                      /**< Initialization failure.  Probable missing ICU Data. */
-    U_BRK_RULE_EMPTY_SET,                  /**< Rule contains an empty Unicode Set.               */
-    U_BRK_UNRECOGNIZED_OPTION,             /**< !!option in RBBI rules not recognized.            */
-    U_BRK_MALFORMED_RULE_TAG,              /**< The {nnn} tag on a rule is malformed              */
-#ifndef U_HIDE_DEPRECATED_API
-    /**
-     * One more than the highest normal BreakIterator error code.
-     * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
-     */
-    U_BRK_ERROR_LIMIT,
-#endif  // U_HIDE_DEPRECATED_API
-
-    /*
-     * Error codes in the range 0x10300-0x103ff are reserved for regular expression related errors.
-     */
-    U_REGEX_INTERNAL_ERROR=0x10300,       /**< An internal error (bug) was detected.              */
-    U_REGEX_ERROR_START=0x10300,          /**< Start of codes indicating Regexp failures          */
-    U_REGEX_RULE_SYNTAX,                  /**< Syntax error in regexp pattern.                    */
-    U_REGEX_INVALID_STATE,                /**< RegexMatcher in invalid state for requested operation */
-    U_REGEX_BAD_ESCAPE_SEQUENCE,          /**< Unrecognized backslash escape sequence in pattern  */
-    U_REGEX_PROPERTY_SYNTAX,              /**< Incorrect Unicode property                         */
-    U_REGEX_UNIMPLEMENTED,                /**< Use of regexp feature that is not yet implemented. */
-    U_REGEX_MISMATCHED_PAREN,             /**< Incorrectly nested parentheses in regexp pattern.  */
-    U_REGEX_NUMBER_TOO_BIG,               /**< Decimal number is too large.                       */
-    U_REGEX_BAD_INTERVAL,                 /**< Error in {min,max} interval                        */
-    U_REGEX_MAX_LT_MIN,                   /**< In {min,max}, max is less than min.                */
-    U_REGEX_INVALID_BACK_REF,             /**< Back-reference to a non-existent capture group.    */
-    U_REGEX_INVALID_FLAG,                 /**< Invalid value for match mode flags.                */
-    U_REGEX_LOOK_BEHIND_LIMIT,            /**< Look-Behind pattern matches must have a bounded maximum length.    */
-    U_REGEX_SET_CONTAINS_STRING,          /**< Regexps cannot have UnicodeSets containing strings.*/
-#ifndef U_HIDE_DEPRECATED_API
-    U_REGEX_OCTAL_TOO_BIG,                /**< Octal character constants must be <= 0377. @deprecated ICU 54. This error cannot occur. */
-#endif  /* U_HIDE_DEPRECATED_API */
-    U_REGEX_MISSING_CLOSE_BRACKET=U_REGEX_SET_CONTAINS_STRING+2, /**< Missing closing bracket on a bracket expression. */
-    U_REGEX_INVALID_RANGE,                /**< In a character range [x-y], x is greater than y.   */
-    U_REGEX_STACK_OVERFLOW,               /**< Regular expression backtrack stack overflow.       */
-    U_REGEX_TIME_OUT,                     /**< Maximum allowed match time exceeded                */
-    U_REGEX_STOPPED_BY_CALLER,            /**< Matching operation aborted by user callback fn.    */
-    U_REGEX_PATTERN_TOO_BIG,              /**< Pattern exceeds limits on size or complexity. @stable ICU 55 */
-    U_REGEX_INVALID_CAPTURE_GROUP_NAME,   /**< Invalid capture group name. @stable ICU 55 */
-#ifndef U_HIDE_DEPRECATED_API
-    /**
-     * One more than the highest normal regular expression error code.
-     * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
-     */
-    U_REGEX_ERROR_LIMIT=U_REGEX_STOPPED_BY_CALLER+3,
-#endif  // U_HIDE_DEPRECATED_API
-
-    /*
-     * Error codes in the range 0x10400-0x104ff are reserved for IDNA related error codes.
-     */
-    U_IDNA_PROHIBITED_ERROR=0x10400,
-    U_IDNA_ERROR_START=0x10400,
-    U_IDNA_UNASSIGNED_ERROR,
-    U_IDNA_CHECK_BIDI_ERROR,
-    U_IDNA_STD3_ASCII_RULES_ERROR,
-    U_IDNA_ACE_PREFIX_ERROR,
-    U_IDNA_VERIFICATION_ERROR,
-    U_IDNA_LABEL_TOO_LONG_ERROR,
-    U_IDNA_ZERO_LENGTH_LABEL_ERROR,
-    U_IDNA_DOMAIN_NAME_TOO_LONG_ERROR,
-#ifndef U_HIDE_DEPRECATED_API
-    /**
-     * One more than the highest normal IDNA error code.
-     * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
-     */
-    U_IDNA_ERROR_LIMIT,
-#endif  // U_HIDE_DEPRECATED_API
-    /*
-     * Aliases for StringPrep
-     */
-    U_STRINGPREP_PROHIBITED_ERROR = U_IDNA_PROHIBITED_ERROR,
-    U_STRINGPREP_UNASSIGNED_ERROR = U_IDNA_UNASSIGNED_ERROR,
-    U_STRINGPREP_CHECK_BIDI_ERROR = U_IDNA_CHECK_BIDI_ERROR,
-    
-    /*
-     * Error codes in the range 0x10500-0x105ff are reserved for Plugin related error codes.
-     */
-    U_PLUGIN_ERROR_START=0x10500,         /**< Start of codes indicating plugin failures */
-    U_PLUGIN_TOO_HIGH=0x10500,            /**< The plugin's level is too high to be loaded right now. */
-    U_PLUGIN_DIDNT_SET_LEVEL,             /**< The plugin didn't call uplug_setPlugLevel in response to a QUERY */
-#ifndef U_HIDE_DEPRECATED_API
-    /**
-     * One more than the highest normal plug-in error code.
-     * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
-     */
-    U_PLUGIN_ERROR_LIMIT,
-#endif  // U_HIDE_DEPRECATED_API
-
-#ifndef U_HIDE_DEPRECATED_API
-    /**
-     * One more than the highest normal error code.
-     * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
-     */
-    U_ERROR_LIMIT=U_PLUGIN_ERROR_LIMIT
-#endif  // U_HIDE_DEPRECATED_API
-} UErrorCode;
-
-/* Use the following to determine if an UErrorCode represents */
-/* operational success or failure. */
-
-#ifdef __cplusplus
-    /**
-     * Does the error code indicate success?
-     * @stable ICU 2.0
-     */
-    static
-    inline UBool U_SUCCESS(UErrorCode code) { return (UBool)(code<=U_ZERO_ERROR); }
-    /**
-     * Does the error code indicate a failure?
-     * @stable ICU 2.0
-     */
-    static
-    inline UBool U_FAILURE(UErrorCode code) { return (UBool)(code>U_ZERO_ERROR); }
-#else
-    /**
-     * Does the error code indicate success?
-     * @stable ICU 2.0
-     */
-#   define U_SUCCESS(x) ((x)<=U_ZERO_ERROR)
-    /**
-     * Does the error code indicate a failure?
-     * @stable ICU 2.0
-     */
-#   define U_FAILURE(x) ((x)>U_ZERO_ERROR)
-#endif
-
-/**
- * Return a string for a UErrorCode value.
- * The string will be the same as the name of the error code constant
- * in the UErrorCode enum above.
- * @stable ICU 2.0
- */
-U_CAPI const char * U_EXPORT2
-u_errorName(UErrorCode code);
-
-
-#endif /* _UTYPES */

app/src/main/cpp/icu4c/include/unicode/uvernum.h

@@ -1,198 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-*******************************************************************************
-*   Copyright (C) 2000-2016, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*******************************************************************************
-*
-*   file name:  uvernum.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:4
-*
-*   Created by: Vladimir Weinstein
-*   Updated by: Steven R. Loomis
-*
-*/
-
-/**
- * \file
- * \brief C API: definitions of ICU version numbers
- *
- * This file is included by uversion.h and other files. This file contains only
- * macros and definitions. The actual version numbers are defined here.
- */
-
- /*
-  * IMPORTANT: When updating version, the following things need to be done:
-  * source/common/unicode/uvernum.h - this file: update major, minor,
-  *        patchlevel, suffix, version, short version constants, namespace,
-  *                    renaming macro, and copyright
-  *
-  * The following files need to be updated as well, which can be done
-  *  by running the UNIX makefile target 'update-windows-makefiles' in icu/source.
-  *
-  *
-  * source/common/common_uwp.vcxproj
-  * source/common/common.vcxproj - update 'Output file name' on the link tab so
-  *                   that it contains the new major/minor combination
-  * source/i18n/i18n.vcxproj - same as for the common.vcxproj
-  * source/i18n/i18n_uwp.vcxproj - same as for the common_uwp.vcxproj
-  * source/layoutex/layoutex.vcproj - same
-  * source/stubdata/stubdata.vcproj - same as for the common.vcxproj
-  * source/io/io.vcproj - same as for the common.vcxproj
-  * source/data/makedata.mak - change U_ICUDATA_NAME so that it contains
-  *                            the new major/minor combination and the Unicode version.
-  */
-
-#ifndef UVERNUM_H
-#define UVERNUM_H
-
-/** The standard copyright notice that gets compiled into each library.
- *  This value will change in the subsequent releases of ICU
- *  @stable ICU 2.4
- */
-#define U_COPYRIGHT_STRING \
-  " Copyright (C) 2016 and later: Unicode, Inc. and others. License & terms of use: http://www.unicode.org/copyright.html "
-
-/** The current ICU major version as an integer.
- *  This value will change in the subsequent releases of ICU
- *  @stable ICU 2.4
- */
-#define U_ICU_VERSION_MAJOR_NUM 69
-
-/** The current ICU minor version as an integer.
- *  This value will change in the subsequent releases of ICU
- *  @stable ICU 2.6
- */
-#define U_ICU_VERSION_MINOR_NUM 1
-
-/** The current ICU patchlevel version as an integer.
- *  This value will change in the subsequent releases of ICU
- *  @stable ICU 2.4
- */
-#define U_ICU_VERSION_PATCHLEVEL_NUM 0
-
-/** The current ICU build level version as an integer.
- *  This value is for use by ICU clients. It defaults to 0.
- *  @stable ICU 4.0
- */
-#ifndef U_ICU_VERSION_BUILDLEVEL_NUM
-#define U_ICU_VERSION_BUILDLEVEL_NUM 0
-#endif
-
-/** Glued version suffix for renamers
- *  This value will change in the subsequent releases of ICU
- *  @stable ICU 2.6
- */
-#define U_ICU_VERSION_SUFFIX _69
-
-/**
- * \def U_DEF2_ICU_ENTRY_POINT_RENAME
- * @internal
- */
-/**
- * \def U_DEF_ICU_ENTRY_POINT_RENAME
- * @internal
- */
-/** Glued version suffix function for renamers
- *  This value will change in the subsequent releases of ICU.
- *  If a custom suffix (such as matching library suffixes) is desired, this can be modified.
- *  Note that if present, platform.h may contain an earlier definition of this macro.
- *  \def U_ICU_ENTRY_POINT_RENAME
- *  @stable ICU 4.2
- */
-/**
- * Disable the version suffix. Use the custom suffix if exists.
- * \def U_DISABLE_VERSION_SUFFIX
- * @internal
- */
-#ifndef U_DISABLE_VERSION_SUFFIX
-#define U_DISABLE_VERSION_SUFFIX 0
-#endif
-
-#ifndef U_ICU_ENTRY_POINT_RENAME
-#ifdef U_HAVE_LIB_SUFFIX
-#   if !U_DISABLE_VERSION_SUFFIX
-#       define U_DEF_ICU_ENTRY_POINT_RENAME(x,y,z) x ## y ##  z
-#       define U_DEF2_ICU_ENTRY_POINT_RENAME(x,y,z) U_DEF_ICU_ENTRY_POINT_RENAME(x,y,z)
-#       define U_ICU_ENTRY_POINT_RENAME(x)    U_DEF2_ICU_ENTRY_POINT_RENAME(x,U_ICU_VERSION_SUFFIX,U_LIB_SUFFIX_C_NAME)
-#   else
-#       define U_DEF_ICU_ENTRY_POINT_RENAME(x,y) x ## y
-#       define U_DEF2_ICU_ENTRY_POINT_RENAME(x,y) U_DEF_ICU_ENTRY_POINT_RENAME(x,y)
-#       define U_ICU_ENTRY_POINT_RENAME(x)    U_DEF2_ICU_ENTRY_POINT_RENAME(x,U_LIB_SUFFIX_C_NAME)
-#   endif
-#else
-#   if !U_DISABLE_VERSION_SUFFIX
-#       define U_DEF_ICU_ENTRY_POINT_RENAME(x,y) x ## y
-#       define U_DEF2_ICU_ENTRY_POINT_RENAME(x,y) U_DEF_ICU_ENTRY_POINT_RENAME(x,y)
-#       define U_ICU_ENTRY_POINT_RENAME(x)    U_DEF2_ICU_ENTRY_POINT_RENAME(x,U_ICU_VERSION_SUFFIX)
-#   else
-#       define U_ICU_ENTRY_POINT_RENAME(x)    x
-#   endif
-#endif
-#endif
-
-/** The current ICU library version as a dotted-decimal string. The patchlevel
- *  only appears in this string if it non-zero.
- *  This value will change in the subsequent releases of ICU
- *  @stable ICU 2.4
- */
-#define U_ICU_VERSION "69.1"
-
-/**
- * The current ICU library major version number as a string, for library name suffixes.
- * This value will change in subsequent releases of ICU.
- *
- * Until ICU 4.8, this was the combination of the single-digit major and minor ICU version numbers
- * into one string without dots ("48").
- * Since ICU 49, it is the double-digit major ICU version number.
- * See https://unicode-org.github.io/icu/userguide/design#version-numbers-in-icu
- *
- * @stable ICU 2.6
- */
-#define U_ICU_VERSION_SHORT "69"
-
-#ifndef U_HIDE_INTERNAL_API
-/** Data version in ICU4C.
- * @internal ICU 4.4 Internal Use Only
- **/
-#define U_ICU_DATA_VERSION "69.1"
-#endif  /* U_HIDE_INTERNAL_API */
-
-/*===========================================================================
- * ICU collation framework version information
- * Version info that can be obtained from a collator is affected by these
- * numbers in a secret and magic way. Please use collator version as whole
- *===========================================================================
- */
-
-/**
- * Collation runtime version (sort key generator, strcoll).
- * If the version is different, sort keys for the same string could be different.
- * This value may change in subsequent releases of ICU.
- * @stable ICU 2.4
- */
-#define UCOL_RUNTIME_VERSION 9
-
-/**
- * Collation builder code version.
- * When this is different, the same tailoring might result
- * in assigning different collation elements to code points.
- * This value may change in subsequent releases of ICU.
- * @stable ICU 2.4
- */
-#define UCOL_BUILDER_VERSION 9
-
-#ifndef U_HIDE_DEPRECATED_API
-/**
- * Constant 1.
- * This was intended to be the version of collation tailorings,
- * but instead the tailoring data carries a version number.
- * @deprecated ICU 54
- */
-#define UCOL_TAILORINGS_VERSION 1
-#endif  /* U_HIDE_DEPRECATED_API */
-
-#endif

app/src/main/cpp/icu4c/include/unicode/uversion.h

@@ -1,187 +0,0 @@
-// © 2016 and later: Unicode, Inc. and others.
-// License & terms of use: http://www.unicode.org/copyright.html
-/*
-*******************************************************************************
-*   Copyright (C) 2000-2011, International Business Machines
-*   Corporation and others.  All Rights Reserved.
-*******************************************************************************
-*
-*   file name:  uversion.h
-*   encoding:   UTF-8
-*   tab size:   8 (not used)
-*   indentation:4
-*
-*   Created by: Vladimir Weinstein
-*
-*  Gets included by utypes.h and Windows .rc files
-*/
-
-/**
- * \file
- * \brief C API: API for accessing ICU version numbers. 
- */
-/*===========================================================================*/
-/* Main ICU version information                                              */
-/*===========================================================================*/
-
-#ifndef UVERSION_H
-#define UVERSION_H
-
-#include "unicode/umachine.h"
-
-/* Actual version info lives in uvernum.h */
-#include "unicode/uvernum.h"
-
-/** Maximum length of the copyright string.
- *  @stable ICU 2.4
- */
-#define U_COPYRIGHT_STRING_LENGTH  128
-
-/** An ICU version consists of up to 4 numbers from 0..255.
- *  @stable ICU 2.4
- */
-#define U_MAX_VERSION_LENGTH 4
-
-/** In a string, ICU version fields are delimited by dots.
- *  @stable ICU 2.4
- */
-#define U_VERSION_DELIMITER '.'
-
-/** The maximum length of an ICU version string.
- *  @stable ICU 2.4
- */
-#define U_MAX_VERSION_STRING_LENGTH 20
-
-/** The binary form of a version on ICU APIs is an array of 4 uint8_t.
- *  To compare two versions, use memcmp(v1,v2,sizeof(UVersionInfo)).
- *  @stable ICU 2.4
- */
-typedef uint8_t UVersionInfo[U_MAX_VERSION_LENGTH];
-
-/*===========================================================================*/
-/* C++ namespace if supported. Versioned unless versioning is disabled.      */
-/*===========================================================================*/
-
-/* Define C++ namespace symbols. */
-#ifdef __cplusplus
-
-/**
- * \def U_NAMESPACE_BEGIN
- * This is used to begin a declaration of a public ICU C++ API within
- * versioned-ICU-namespace block.
- *
- * @stable ICU 2.4
- */
-
-/**
- * \def U_NAMESPACE_END
- * This is used to end a declaration of a public ICU C++ API.
- * It ends the versioned-ICU-namespace block begun by U_NAMESPACE_BEGIN.
- *
- * @stable ICU 2.4
- */
-
-/**
- * \def U_NAMESPACE_USE
- * This is used to specify that the rest of the code uses the
- * public ICU C++ API namespace.
- * @stable ICU 2.4
- */
-
-/**
- * \def U_NAMESPACE_QUALIFIER
- * This is used to qualify that a function or class is part of
- * the public ICU C++ API namespace.
- *
- * This macro is unnecessary since ICU 49 requires namespace support.
- * You can just use "icu::" instead.
- * @stable ICU 2.4
- */
-
-#   if U_DISABLE_RENAMING
-#       define U_ICU_NAMESPACE icu
-        namespace U_ICU_NAMESPACE { }
-#   else
-#       define U_ICU_NAMESPACE U_ICU_ENTRY_POINT_RENAME(icu)
-        namespace U_ICU_NAMESPACE { }
-        namespace icu = U_ICU_NAMESPACE;
-#   endif
-
-#   define U_NAMESPACE_BEGIN namespace U_ICU_NAMESPACE {
-#   define U_NAMESPACE_END }
-#   define U_NAMESPACE_USE using namespace U_ICU_NAMESPACE;
-#   define U_NAMESPACE_QUALIFIER U_ICU_NAMESPACE::
-
-#   ifndef U_USING_ICU_NAMESPACE
-#       if defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || \
-                defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION) || \
-                defined(U_LAYOUTEX_IMPLEMENTATION) || defined(U_TOOLUTIL_IMPLEMENTATION)
-#           define U_USING_ICU_NAMESPACE 0
-#       else
-#           define U_USING_ICU_NAMESPACE 0
-#       endif
-#   endif
-#   if U_USING_ICU_NAMESPACE
-        U_NAMESPACE_USE
-#   endif
-#endif /* __cplusplus */
-
-/*===========================================================================*/
-/* General version helper functions. Definitions in putil.c                  */
-/*===========================================================================*/
-
-/**
- * Parse a string with dotted-decimal version information and
- * fill in a UVersionInfo structure with the result.
- * Definition of this function lives in putil.c
- *
- * @param versionArray The destination structure for the version information.
- * @param versionString A string with dotted-decimal version information,
- *                      with up to four non-negative number fields with
- *                      values of up to 255 each.
- * @stable ICU 2.4
- */
-U_CAPI void U_EXPORT2
-u_versionFromString(UVersionInfo versionArray, const char *versionString);
-
-/**
- * Parse a Unicode string with dotted-decimal version information and
- * fill in a UVersionInfo structure with the result.
- * Definition of this function lives in putil.c
- *
- * @param versionArray The destination structure for the version information.
- * @param versionString A Unicode string with dotted-decimal version
- *                      information, with up to four non-negative number
- *                      fields with values of up to 255 each.
- * @stable ICU 4.2
- */
-U_CAPI void U_EXPORT2
-u_versionFromUString(UVersionInfo versionArray, const UChar *versionString);
-
-
-/**
- * Write a string with dotted-decimal version information according
- * to the input UVersionInfo.
- * Definition of this function lives in putil.c
- *
- * @param versionArray The version information to be written as a string.
- * @param versionString A string buffer that will be filled in with
- *                      a string corresponding to the numeric version
- *                      information in versionArray.
- *                      The buffer size must be at least U_MAX_VERSION_STRING_LENGTH.
- * @stable ICU 2.4
- */
-U_CAPI void U_EXPORT2
-u_versionToString(const UVersionInfo versionArray, char *versionString);
-
-/**
- * Gets the ICU release version.  The version array stores the version information
- * for ICU.  For example, release "1.3.31.2" is then represented as 0x01031F02.
- * Definition of this function lives in putil.c
- *
- * @param versionArray the version # information, the result will be filled in
- * @stable ICU 2.0
- */
-U_CAPI void U_EXPORT2
-u_getVersion(UVersionInfo versionArray);
-#endif

app/src/main/cpp/nuspell/CMakeLists.txt

@@ -3,59 +3,8 @@ aff_data.cxx     aff_data.hxx
 checker.cxx      checker.hxx
 suggester.cxx    suggester.hxx
 dictionary.cxx   dictionary.hxx
-finder.cxx       finder.hxx
                  unicode.hxx
 utils.cxx        utils.hxx
                  structures.hxx)
 
 add_library(Nuspell::nuspell ALIAS nuspell)
-
-#include(GenerateExportHeader)
-#generate_export_header(nuspell)
-
-#set(nuspell_headers aff_data.hxx checker.hxx suggester.hxx dictionary.hxx
-#    finder.hxx structures.hxx unicode.hxx
-#    ${CMAKE_CURRENT_BINARY_DIR}/nuspell_export.h)
-#[[set_target_properties(nuspell PROPERTIES
-    PUBLIC_HEADER "${nuspell_headers}"
-    VERSION ${PROJECT_VERSION}
-    SOVERSION ${PROJECT_VERSION_MAJOR}f
-    CXX_VISIBILITY_PRESET hidden)]]
-
-#target_compile_features(nuspell PUBLIC cxx_std_17)
-
-#[[target_include_directories(nuspell
-    PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_BINARY_DIR}>
-    INTERFACE $<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/src>
-              $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>)
-
-target_link_libraries(nuspell PUBLIC ICU::uc ICU::data)
-
-add_executable(nuspell-bin main.cxx)
-set_target_properties(nuspell-bin PROPERTIES
-    RUNTIME_OUTPUT_DIRECTORY ../tools
-    RUNTIME_OUTPUT_NAME nuspell)
-target_compile_definitions(nuspell-bin PRIVATE
-    PROJECT_VERSION=\"${PROJECT_VERSION}\")
-target_link_libraries(nuspell-bin nuspell)
-if (BUILD_SHARED_LIBS AND WIN32)
-    # This should be PRE_LINK (or PRE_BUILD), so Vcpkg's POST_BUILD
-    # step (see VCPKG_APPLOCAL_DEPS) that copies dll can pick up nuspell.dll
-    # inside the folder ../tools.
-    add_custom_command(TARGET nuspell-bin PRE_LINK
-    COMMAND ${CMAKE_COMMAND} -E copy_if_different
-            $<TARGET_FILE:nuspell> $<TARGET_FILE_DIR:nuspell-bin>)
-endif()
-
-if (NOT subproject)
-    install(TARGETS nuspell
-        EXPORT NuspellTargets
-        ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
-        LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
-        RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR}
-        PUBLIC_HEADER DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/nuspell)
-    install(EXPORT NuspellTargets
-        DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/nuspell
-        NAMESPACE Nuspell::)
-    install(TARGETS nuspell-bin DESTINATION ${CMAKE_INSTALL_BINDIR})
-endif()]]

app/src/main/cpp/nuspell/LICENSE.txt

@@ -0,0 +1,165 @@
+                   GNU LESSER GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+
+  This version of the GNU Lesser General Public License incorporates
+the terms and conditions of version 3 of the GNU General Public
+License, supplemented by the additional permissions listed below.
+
+  0. Additional Definitions.
+
+  As used herein, "this License" refers to version 3 of the GNU Lesser
+General Public License, and the "GNU GPL" refers to version 3 of the GNU
+General Public License.
+
+  "The Library" refers to a covered work governed by this License,
+other than an Application or a Combined Work as defined below.
+
+  An "Application" is any work that makes use of an interface provided
+by the Library, but which is not otherwise based on the Library.
+Defining a subclass of a class defined by the Library is deemed a mode
+of using an interface provided by the Library.
+
+  A "Combined Work" is a work produced by combining or linking an
+Application with the Library.  The particular version of the Library
+with which the Combined Work was made is also called the "Linked
+Version".
+
+  The "Minimal Corresponding Source" for a Combined Work means the
+Corresponding Source for the Combined Work, excluding any source code
+for portions of the Combined Work that, considered in isolation, are
+based on the Application, and not on the Linked Version.
+
+  The "Corresponding Application Code" for a Combined Work means the
+object code and/or source code for the Application, including any data
+and utility programs needed for reproducing the Combined Work from the
+Application, but excluding the System Libraries of the Combined Work.
+
+  1. Exception to Section 3 of the GNU GPL.
+
+  You may convey a covered work under sections 3 and 4 of this License
+without being bound by section 3 of the GNU GPL.
+
+  2. Conveying Modified Versions.
+
+  If you modify a copy of the Library, and, in your modifications, a
+facility refers to a function or data to be supplied by an Application
+that uses the facility (other than as an argument passed when the
+facility is invoked), then you may convey a copy of the modified
+version:
+
+   a) under this License, provided that you make a good faith effort to
+   ensure that, in the event an Application does not supply the
+   function or data, the facility still operates, and performs
+   whatever part of its purpose remains meaningful, or
+
+   b) under the GNU GPL, with none of the additional permissions of
+   this License applicable to that copy.
+
+  3. Object Code Incorporating Material from Library Header Files.
+
+  The object code form of an Application may incorporate material from
+a header file that is part of the Library.  You may convey such object
+code under terms of your choice, provided that, if the incorporated
+material is not limited to numerical parameters, data structure
+layouts and accessors, or small macros, inline functions and templates
+(ten or fewer lines in length), you do both of the following:
+
+   a) Give prominent notice with each copy of the object code that the
+   Library is used in it and that the Library and its use are
+   covered by this License.
+
+   b) Accompany the object code with a copy of the GNU GPL and this license
+   document.
+
+  4. Combined Works.
+
+  You may convey a Combined Work under terms of your choice that,
+taken together, effectively do not restrict modification of the
+portions of the Library contained in the Combined Work and reverse
+engineering for debugging such modifications, if you also do each of
+the following:
+
+   a) Give prominent notice with each copy of the Combined Work that
+   the Library is used in it and that the Library and its use are
+   covered by this License.
+
+   b) Accompany the Combined Work with a copy of the GNU GPL and this license
+   document.
+
+   c) For a Combined Work that displays copyright notices during
+   execution, include the copyright notice for the Library among
+   these notices, as well as a reference directing the user to the
+   copies of the GNU GPL and this license document.
+
+   d) Do one of the following:
+
+       0) Convey the Minimal Corresponding Source under the terms of this
+       License, and the Corresponding Application Code in a form
+       suitable for, and under terms that permit, the user to
+       recombine or relink the Application with a modified version of
+       the Linked Version to produce a modified Combined Work, in the
+       manner specified by section 6 of the GNU GPL for conveying
+       Corresponding Source.
+
+       1) Use a suitable shared library mechanism for linking with the
+       Library.  A suitable mechanism is one that (a) uses at run time
+       a copy of the Library already present on the user's computer
+       system, and (b) will operate properly with a modified version
+       of the Library that is interface-compatible with the Linked
+       Version.
+
+   e) Provide Installation Information, but only if you would otherwise
+   be required to provide such information under section 6 of the
+   GNU GPL, and only to the extent that such information is
+   necessary to install and execute a modified version of the
+   Combined Work produced by recombining or relinking the
+   Application with a modified version of the Linked Version. (If
+   you use option 4d0, the Installation Information must accompany
+   the Minimal Corresponding Source and Corresponding Application
+   Code. If you use option 4d1, you must provide the Installation
+   Information in the manner specified by section 6 of the GNU GPL
+   for conveying Corresponding Source.)
+
+  5. Combined Libraries.
+
+  You may place library facilities that are a work based on the
+Library side by side in a single library together with other library
+facilities that are not Applications and are not covered by this
+License, and convey such a combined library under terms of your
+choice, if you do both of the following:
+
+   a) Accompany the combined library with a copy of the same work based
+   on the Library, uncombined with any other library facilities,
+   conveyed under the terms of this License.
+
+   b) Give prominent notice with the combined library that part of it
+   is a work based on the Library, and explaining where to find the
+   accompanying uncombined form of the same work.
+
+  6. Revised Versions of the GNU Lesser General Public License.
+
+  The Free Software Foundation may publish revised and/or new versions
+of the GNU Lesser General Public License from time to time. Such new
+versions will be similar in spirit to the present version, but may
+differ in detail to address new problems or concerns.
+
+  Each version is given a distinguishing version number. If the
+Library as you received it specifies that a certain numbered version
+of the GNU Lesser General Public License "or any later version"
+applies to it, you have the option of following the terms and
+conditions either of that published version or of any later version
+published by the Free Software Foundation. If the Library as you
+received it does not specify a version number of the GNU Lesser
+General Public License, you may choose any version of the GNU Lesser
+General Public License ever published by the Free Software Foundation.
+
+  If the Library as you received it specifies that a proxy can decide
+whether future versions of the GNU Lesser General Public License shall
+apply, that proxy's public statement of acceptance of any version is
+permanent authorization for you to choose that version for the
+Library.

app/src/main/cpp/nuspell/finder.cxx

@@ -1,574 +0,0 @@
-/* Copyright 2016-2021 Dimitrij Mijoski
- *
- * This file is part of Nuspell.
- *
- * Nuspell is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Nuspell is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public License
- * along with Nuspell.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "finder.hxx"
-#include "utils.hxx"
-
-#include <algorithm>
-#include <array>
-#include <iostream>
-#include <iterator>
-#include <sstream>
-#include <unordered_set>
-#include <utility>
-
-#if !defined(_WIN32) &&                                                        \
-    (defined(__unix__) || defined(__unix) ||                                   \
-     (defined(__APPLE__) && defined(__MACH__)) || defined(__HAIKU__))
-#include <unistd.h>
-#ifdef _POSIX_VERSION
-#include <dirent.h>
-#include "glob_ndk/glob_ndk.h"
-#include <sys/stat.h>
-#include <sys/types.h>
-#endif
-
-#elif defined(_WIN32)
-
-#include <io.h>
-#include <windows.h>
-
-#ifdef __MINGW32__
-#include <dirent.h>
-//#include <glob.h> //not present in mingw-w64. present in vanilla mingw
-#include <sys/stat.h>
-#include <sys/types.h>
-#endif //__MINGW32__
-
-#endif
-
-using namespace std;
-
-namespace nuspell {
-inline namespace v5 {
-#ifdef _WIN32
-const auto PATHSEP = ';';
-const auto DIRSEP = '\\';
-#else
-const auto PATHSEP = ':';
-const auto DIRSEP = '/';
-#endif
-
-/**
- * @brief Append the paths of the default directories to be searched for
- * dictionaries.
- * @param paths vector of directory paths to append to
- */
-auto append_default_dir_paths(std::vector<string>& paths) -> void
-{
-	auto dicpath = getenv("DICPATH");
-	if (dicpath && *dicpath)
-		split(dicpath, PATHSEP, paths);
-
-#ifdef _POSIX_VERSION
-	auto home = getenv("HOME");
-	auto xdg_data_home = getenv("XDG_DATA_HOME");
-	if (xdg_data_home && *xdg_data_home)
-		paths.push_back(xdg_data_home + string("/hunspell"));
-	else if (home)
-		paths.push_back(home + string("/.local/share/hunspell"));
-
-	auto xdg_data_dirs = getenv("XDG_DATA_DIRS");
-	if (xdg_data_dirs && *xdg_data_dirs) {
-		auto data_dirs = string_view(xdg_data_dirs);
-
-		auto i = paths.size();
-		split(data_dirs, PATHSEP, paths);
-		for (; i != paths.size(); ++i)
-			paths[i] += "/hunspell";
-
-		i = paths.size();
-		split(data_dirs, PATHSEP, paths);
-		for (; i != paths.size(); ++i)
-			paths[i] += "/myspell";
-	}
-	else {
-		paths.push_back("/usr/local/share/hunspell");
-		paths.push_back("/usr/share/hunspell");
-		paths.push_back("/usr/local/share/myspell");
-		paths.push_back("/usr/share/myspell");
-	}
-#if defined(__APPLE__) && defined(__MACH__)
-	auto osx = string("/Library/Spelling");
-	if (home) {
-		paths.push_back(home + osx);
-	}
-	paths.push_back(osx);
-#endif
-#endif
-#ifdef _WIN32
-	auto winpaths = {getenv("LOCALAPPDATA"), getenv("PROGRAMDATA")};
-	for (auto& p : winpaths) {
-		if (p) {
-			paths.push_back(string(p) + "\\hunspell");
-		}
-	}
-#endif
-}
-
-#ifdef _WIN32
-class FileListerWindows {
-	struct _finddata_t data = {};
-	intptr_t handle = -1;
-	bool goodbit = false;
-
-      public:
-	FileListerWindows() {}
-	FileListerWindows(const char* pattern) { first(pattern); }
-	FileListerWindows(const string& pattern) { first(pattern); }
-	FileListerWindows(const FileListerWindows& d) = delete;
-	void operator=(const FileListerWindows& d) = delete;
-	~FileListerWindows() { close(); }
-
-	auto first(const char* pattern) -> bool
-	{
-		close();
-		handle = _findfirst(pattern, &data);
-		goodbit = handle != -1;
-		return goodbit;
-	}
-	auto first(const string& pattern) -> bool
-	{
-		return first(pattern.c_str());
-	}
-
-	auto name() const -> const char* { return data.name; }
-	auto good() const -> bool { return goodbit; }
-	auto next() -> bool
-	{
-		goodbit = _findnext(handle, &data) == 0;
-		return goodbit;
-	}
-	auto close() -> void
-	{
-		if (handle == -1)
-			return;
-		_findclose(handle);
-		handle = -1;
-		goodbit = false;
-	}
-	auto list_all() -> vector<string>
-	{
-		vector<string> ret;
-		for (; good(); next()) {
-			ret.push_back(name());
-		}
-		return ret;
-	}
-};
-#endif
-
-#ifdef _POSIX_VERSION
-class Globber {
-      private:
-	glob_t g = {};
-	int ret = 1;
-
-      public:
-	Globber(const char* pattern) { ret = ::glob(pattern, 0, nullptr, &g); }
-	Globber(const string& pattern) : Globber(pattern.c_str()) {}
-	Globber(const Globber&) = delete;
-	auto operator=(const Globber&) = delete;
-	auto glob(const char* pattern) -> bool
-	{
-		globfree(&g);
-		ret = ::glob(pattern, 0, nullptr, &g);
-		return ret == 0;
-	}
-	auto glob(const string& pattern) -> bool
-	{
-		return glob(pattern.c_str());
-	}
-	auto begin() -> const char* const* { return g.gl_pathv; }
-	auto end() -> const char* const* { return begin() + g.gl_pathc; }
-	auto append_glob_paths_to(vector<string>& out) -> void
-	{
-		if (ret == 0)
-			out.insert(out.end(), begin(), end());
-	}
-	~Globber() { globfree(&g); }
-};
-#elif defined(_WIN32)
-class Globber {
-	vector<string> data;
-
-      public:
-	Globber(const char* pattern) { glob(pattern); }
-	Globber(const string& pattern) { glob(pattern); }
-	auto glob(const char* pattern) -> bool { return glob(string(pattern)); }
-	auto glob(const string& pattern) -> bool
-	{
-		data.clear();
-
-		if (pattern.empty())
-			return false;
-		auto first_two = pattern.substr(0, 2);
-		if (first_two == "\\\\" || first_two == "//" ||
-		    first_two == "\\/" || first_two == "//")
-			return false;
-
-		auto q1 = vector<string>();
-		auto q2 = q1;
-		auto v = q1;
-
-		split_on_any_of(pattern, "\\/", v);
-		auto i = v.begin();
-		if (i == v.end())
-			return false;
-
-		FileListerWindows fl;
-
-		if (i->find(':') != i->npos) {
-			// absolute path
-			q1.push_back(*i++);
-		}
-		else if (pattern[0] == '\\' || pattern[0] == '/') {
-			// relative to drive
-			q1.push_back("");
-		}
-		else {
-			// relative
-			q1.push_back(".");
-		}
-		for (; i != v.end(); ++i) {
-			if (i->empty())
-				continue;
-			for (auto& q1e : q1) {
-				auto p = q1e + DIRSEP + *i;
-				// cout << "P " << p << endl;
-				fl.first(p.c_str());
-				for (; fl.good(); fl.next()) {
-
-					if (fl.name() == string(".") ||
-					    fl.name() == string(".."))
-						continue;
-					auto n = q1e + DIRSEP + fl.name();
-					q2.push_back(n);
-					// cout << "Q2 " << n << endl;
-				}
-			}
-			q1.clear();
-			q1.swap(q2);
-		}
-		data.insert(data.end(), q1.begin(), q1.end());
-		return true;
-	}
-	auto begin() -> vector<string>::iterator { return data.begin(); }
-	auto end() -> vector<string>::iterator { return data.end(); }
-	auto append_glob_paths_to(vector<string>& out) -> void
-	{
-		out.insert(out.end(), begin(), end());
-	}
-};
-#else
-// unimplemented
-struct Globber {
-	Globber(const char* pattern) {}
-	Globber(const string& pattern) {}
-	auto glob(const char* pattern) -> bool { return false; }
-	auto glob(const string& pattern) -> bool { return false; }
-	auto begin() -> char** { return nullptr; }
-	auto end() -> char** { return nullptr; }
-	auto append_glob_paths_to(vector<string>& out) -> void {}
-};
-#endif
-
-/**
- * @brief Append the paths of the LibreOffice's directories to be searched for
- * dictionaries.
- *
- * @warning This function shall not be called from LibreOffice or modules that
- * may end up being used by LibreOffice. It is mainly intended to be used by
- * the CLI tool.
- *
- * @param paths vector of directory paths to append to
- */
-auto append_libreoffice_dir_paths(std::vector<std::string>& paths) -> void
-{
-	auto lo_user_glob = string();
-#ifdef _POSIX_VERSION
-	// add LibreOffice Linux global paths
-	auto prefixes = {"/usr/local/lib/libreoffice", "/usr/lib/libreoffice",
-	                 "/opt/libreoffice*"};
-	for (auto& prefix : prefixes) {
-		Globber g(string(prefix) + "/share/extensions/dict-*");
-		g.append_glob_paths_to(paths);
-	}
-
-	// add LibreOffice Linux local
-
-	auto home = getenv("HOME");
-	if (home == nullptr)
-		return;
-	lo_user_glob = home;
-	lo_user_glob += "/.config/libreoffice/?/user/uno_packages/cache"
-	                "/uno_packages/*/*.oxt/";
-#elif defined(_WIN32)
-	// add Libreoffice Windows global paths
-	auto prefixes = {getenv("PROGRAMFILES"), getenv("PROGRAMFILES(x86)")};
-	for (auto& prefix : prefixes) {
-		if (prefix == nullptr)
-			continue;
-		Globber g(string(prefix) +
-		          "\\LibreOffice ?\\share\\extensions\\dict-*");
-		g.append_glob_paths_to(paths);
-	}
-
-	auto home = getenv("APPDATA");
-	if (home == nullptr)
-		return;
-	lo_user_glob = home;
-	lo_user_glob += "\\libreoffice\\?\\user\\uno_packages\\cache"
-	                "\\uno_packages\\*\\*.oxt\\";
-#else
-	return;
-#endif
-	// finish adding LibreOffice user path dicts (Linux and Windows)
-	Globber g(lo_user_glob + "dict*");
-	g.append_glob_paths_to(paths);
-
-	g.glob(lo_user_glob + "*.aff");
-	auto path_str = string();
-	for (auto& path : g) {
-		path_str = path;
-		path_str.erase(path_str.rfind(DIRSEP));
-		paths.push_back(path_str);
-	}
-}
-
-#if defined(_POSIX_VERSION) || defined(__MINGW32__)
-class Directory {
-	DIR* dp = nullptr;
-	struct dirent* ent_p = nullptr;
-
-      public:
-	Directory() = default;
-	Directory(const Directory& d) = delete;
-	void operator=(const Directory& d) = delete;
-	auto open(const string& dirname) -> bool
-	{
-		close();
-		dp = opendir(dirname.c_str());
-		return dp;
-	}
-	auto next() -> bool { return (ent_p = readdir(dp)); }
-	auto entry_name() const -> const char* { return ent_p->d_name; }
-	auto close() -> void
-	{
-		if (dp) {
-			(void)closedir(dp);
-			dp = nullptr;
-		}
-	}
-	~Directory() { close(); }
-};
-#elif defined(_WIN32)
-class Directory {
-	FileListerWindows fl;
-	bool first = true;
-
-      public:
-	Directory() {}
-	Directory(const Directory& d) = delete;
-	void operator=(const Directory& d) = delete;
-	auto open(const string& dirname) -> bool
-	{
-		fl.first(dirname + "\\*");
-		first = true;
-		return fl.good();
-	}
-	auto next() -> bool
-	{
-		if (first)
-			first = false;
-		else
-			fl.next();
-		return fl.good();
-	}
-	auto entry_name() const -> const char* { return fl.name(); }
-	auto close() -> void { fl.close(); }
-};
-#else
-struct Directory {
-	Directory() {}
-	Directory(const Directory& d) = delete;
-	void operator=(const Directory& d) = delete;
-	auto open(const string& dirname) -> bool { return false; }
-	auto next() -> bool { return false; }
-	auto entry_name() const -> const char* { return nullptr; }
-	auto close() -> void {}
-};
-#endif
-
-/**
- * @brief Search a directory for dictionaries.
- *
- * This function searches the directory for files that represent a dictionary
- * and for each one found it appends the pair of dictionary name and filepath to
- * dictionary, both without the filename extension (.aff or .dic).
- *
- * For example for the files /dict/dir/en_US.dic and /dict/dir/en_US.aff the
- * following pair will be appended ("en_US", "/dict/dir/en_US").
- *
- * @todo At some point this API should be made to be more strongly typed.
- * Instead of using that pair of strings to represent the dictionary files, a
- * new class should be created with three public functions, getters, that would
- * return the name, the path to the .aff file (with filename extension to avoid
- * confusions) and the path to the .dic file. The C++ 17 std::filesystem::path
- * should probably be used. It is unspecified to the public what this class
- * holds privately, but it should probably hold only one path to the aff file.
- * For the directory paths, it is simple, just use the type
- * std::filesystem::path. When this API is created, the same function names
- * should be used, added as overloads. The old API should be marked as
- * deprecated. This should be done when we start requiring GCC 9 which supports
- * C++ 17 filesystem out of the box. GCC 8 has this too, but it is somewhat
- * experimental and requires manually linking to additional static library.
- *
- * @param dir_path path to directory
- * @param dict_list vector to append the found dictionaries to
- */
-auto search_dir_for_dicts(const string& dir_path,
-                          vector<pair<string, string>>& dict_list) -> void
-{
-	Directory d;
-	if (d.open(dir_path) == false)
-		return;
-
-	unordered_set<string> dics;
-	string file_name;
-	while (d.next()) {
-		file_name = d.entry_name();
-		auto sz = file_name.size();
-		if (sz < 4)
-			continue;
-
-		if (file_name.compare(sz - 4, 4, ".dic") == 0) {
-			dics.insert(file_name);
-			file_name.replace(sz - 4, 4, ".aff");
-		}
-		else if (file_name.compare(sz - 4, 4, ".aff") == 0) {
-			dics.insert(file_name);
-			file_name.replace(sz - 4, 4, ".dic");
-		}
-		else {
-			continue;
-		}
-		if (dics.count(file_name)) {
-			file_name.erase(sz - 4);
-			auto full_path = dir_path + DIRSEP + file_name;
-			dict_list.emplace_back(move(file_name),
-			                       move(full_path));
-		}
-	}
-}
-
-/**
- * @brief Search the directories for dictionaries.
- *
- * @see search_dir_for_dicts()
- *
- * @param dir_paths list of paths to directories
- * @param dict_list vector to append the found dictionaries to
- */
-auto search_dirs_for_dicts(const std::vector<string>& dir_paths,
-                           std::vector<std::pair<string, string>>& dict_list)
-    -> void
-{
-	for (auto& p : dir_paths)
-		search_dir_for_dicts(p, dict_list);
-}
-
-/**
- * @brief Search the default directories for dictionaries.
- *
- * @see append_default_dir_paths()
- * @see search_dirs_for_dicts()
- *
- * @param dict_list vector to append the found dictionaries to
- */
-auto search_default_dirs_for_dicts(
-    std::vector<std::pair<std::string, std::string>>& dict_list) -> void
-{
-	auto dir_paths = vector<string>();
-	append_default_dir_paths(dir_paths);
-	search_dirs_for_dicts(dir_paths, dict_list);
-}
-
-/**
- * @brief Find dictionary path given the name.
- *
- * Find the first dictionary whose name matches @p dict_name.
- *
- * @param dict_list vector of pairs with name and paths
- * @param dict_name dictionary name
- * @return iterator of @p dict_list that points to the found dictionary or end
- * if not found.
- */
-auto find_dictionary(
-    const std::vector<std::pair<std::string, std::string>>& dict_list,
-    const std::string& dict_name)
-    -> std::vector<std::pair<std::string, std::string>>::const_iterator
-{
-	return find_if(begin(dict_list), end(dict_list),
-	               [&](auto& e) { return e.first == dict_name; });
-}
-
-Dict_Finder_For_CLI_Tool::Dict_Finder_For_CLI_Tool()
-{
-	append_default_dir_paths(dir_paths);
-	append_libreoffice_dir_paths(dir_paths);
-	dir_paths.push_back(".");
-	search_dirs_for_dicts(dir_paths, dict_multimap);
-	stable_sort(begin(dict_multimap), end(dict_multimap),
-	            [](auto& a, auto& b) { return a.first < b.first; });
-}
-
-/**
- * @internal
- * @brief Gets the dictionary path.
- *
- * If path is given (contains slash) it returns the input argument,
- * otherwise searches the found dictionaries by their name and returns their
- * path.
- *
- * @param dict name or path of dictionary without the trailing .aff/.dic.
- * @return the path to dictionary or empty if does not exists.
- */
-auto Dict_Finder_For_CLI_Tool::get_dictionary_path(
-    const std::string& dict) const -> std::string
-{
-#ifdef _WIN32
-	const auto SEPARATORS = "\\/";
-#else
-	const auto SEPARATORS = '/';
-#endif
-	// first check if it is a path
-	if (dict.find_first_of(SEPARATORS) != dict.npos) {
-		// a path
-		return dict;
-	}
-	else {
-		// search list
-		auto x = find_dictionary(dict_multimap, dict);
-		if (x != end(dict_multimap))
-			return x->second;
-	}
-	return {};
-}
-} // namespace v5
-} // namespace nuspell

app/src/main/cpp/nuspell/finder.hxx

@@ -1,84 +0,0 @@
-/* Copyright 2016-2021 Dimitrij Mijoski
- *
- * This file is part of Nuspell.
- *
- * Nuspell is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Nuspell is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public License
- * along with Nuspell.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-/**
- * @file
- * @brief Finding dictionaries.
- */
-
-#ifndef NUSPELL_FINDER_HXX
-#define NUSPELL_FINDER_HXX
-
-#include "nuspell_export.h"
-
-#include <string>
-#include <utility>
-#include <vector>
-
-#ifdef _MSC_VER
-#define NUSPELL_MSVC_PRAGMA_WARNING(x) __pragma(warning(x))
-#else
-#define NUSPELL_MSVC_PRAGMA_WARNING(x)
-#endif
-NUSPELL_MSVC_PRAGMA_WARNING(push)
-NUSPELL_MSVC_PRAGMA_WARNING(disable : 4251)
-
-namespace nuspell {
-inline namespace v5 {
-
-NUSPELL_EXPORT auto append_default_dir_paths(std::vector<std::string>& paths)
-    -> void;
-
-NUSPELL_EXPORT auto
-append_libreoffice_dir_paths(std::vector<std::string>& paths) -> void;
-
-NUSPELL_EXPORT auto search_dir_for_dicts(
-    const std::string& dir_path,
-    std::vector<std::pair<std::string, std::string>>& dict_list) -> void;
-
-NUSPELL_EXPORT auto search_dirs_for_dicts(
-    const std::vector<std::string>& dir_paths,
-    std::vector<std::pair<std::string, std::string>>& dict_list) -> void;
-
-NUSPELL_EXPORT auto search_default_dirs_for_dicts(
-    std::vector<std::pair<std::string, std::string>>& dict_list) -> void;
-
-NUSPELL_EXPORT auto find_dictionary(
-    const std::vector<std::pair<std::string, std::string>>& dict_list,
-    const std::string& dict_name)
-    -> std::vector<std::pair<std::string, std::string>>::const_iterator;
-
-/**
- * @brief Don't use this except from Nuspell CLI tool.
- *
- * There are no promises of the API.
- */
-class NUSPELL_EXPORT Dict_Finder_For_CLI_Tool {
-	std::vector<std::string> dir_paths;
-	std::vector<std::pair<std::string, std::string>> dict_multimap;
-
-      public:
-	Dict_Finder_For_CLI_Tool();
-	auto& get_dir_paths() const { return dir_paths; }
-	auto& get_dictionaries() const { return dict_multimap; }
-	auto get_dictionary_path(const std::string& dict) const -> std::string;
-};
-} // namespace v5
-} // namespace nuspell
-NUSPELL_MSVC_PRAGMA_WARNING(pop)
-#endif // NUSPELL_FINDER_HXX

app/src/main/cpp/nuspell/main.cxx

@@ -1,718 +0,0 @@
-/* Copyright 2016-2021 Dimitrij Mijoski, Sander van Geloven
- *
- * This file is part of Nuspell.
- *
- * Nuspell is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Nuspell is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public License
- * along with Nuspell.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "dictionary.hxx"
-#include "finder.hxx"
-
-#include <cassert>
-#include <fstream>
-#include <iomanip>
-#include <iostream>
-#include <unicode/brkiter.h>
-#include <unicode/ucnv.h>
-
-#if defined(__MINGW32__) || defined(__unix__) || defined(__unix) ||            \
-    (defined(__APPLE__) && defined(__MACH__)) || defined(__HAIKU__)
-#include <getopt.h>
-#include <unistd.h>
-#endif
-#ifdef _POSIX_VERSION
-#include <langinfo.h>
-#endif
-#ifdef _WIN32
-#include <io.h>
-#define NOMINMAX
-#define WIN32_LEAN_AND_MEAN
-#include <windows.h>
-#endif
-
-// manually define if not supplied by the build system
-#ifndef PROJECT_VERSION
-#define PROJECT_VERSION "unknown.version"
-#endif
-#define PACKAGE_STRING "nuspell " PROJECT_VERSION
-
-using namespace std;
-using namespace nuspell;
-
-enum Mode {
-	DEFAULT_MODE /**< printing correct and misspelled words with
-	                suggestions */
-	,
-	MISSPELLED_WORDS_MODE /**< printing only misspelled words */,
-	MISSPELLED_LINES_MODE /**< printing only lines with misspelled word(s)*/
-	,
-	CORRECT_WORDS_MODE /**< printing only correct words */,
-	CORRECT_LINES_MODE /**< printing only fully correct lines */,
-	LINES_MODE, /**< intermediate mode used while parsing command line
-	               arguments, otherwise unused */
-	LIST_DICTIONARIES_MODE /**< printing available dictionaries */,
-	HELP_MODE /**< printing help information */,
-	VERSION_MODE /**< printing version information */,
-	ERROR_MODE
-};
-
-struct Args_t {
-	Mode mode = DEFAULT_MODE;
-	bool whitespace_segmentation = false;
-	string program_name = "nuspell";
-	string dictionary;
-	string encoding;
-	vector<string> other_dicts;
-	vector<string> files;
-
-	Args_t() = default;
-	Args_t(int argc, char* argv[]) { parse_args(argc, argv); }
-	auto parse_args(int argc, char* argv[]) -> void;
-};
-
-/**
- * @brief Parses command line arguments.
- *
- * @param argc command-line argument count.
- * @param argv command-line argument vector.
- */
-auto Args_t::parse_args(int argc, char* argv[]) -> void
-{
-	if (argc != 0 && argv[0] && argv[0][0] != '\0')
-		program_name = argv[0];
-// See POSIX Utility argument syntax
-// http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap12.html
-#if defined(_POSIX_VERSION) || defined(__MINGW32__)
-	int c;
-	// The program can run in various modes depending on the
-	// command line options. mode is FSM state, this while loop is FSM.
-	const char* shortopts = ":d:i:aDGLslhv";
-	const struct option longopts[] = {
-	    {"version", 0, nullptr, 'v'},
-	    {"help", 0, nullptr, 'h'},
-	    {nullptr, 0, nullptr, 0},
-	};
-	while ((c = getopt_long(argc, argv, shortopts, longopts, nullptr)) !=
-	       -1) {
-		switch (c) {
-		case 'a':
-			// ispell pipe mode, same as default mode
-			if (mode != DEFAULT_MODE)
-				mode = ERROR_MODE;
-			break;
-		case 'd':
-			if (dictionary.empty())
-				dictionary = optarg;
-			else
-				cerr << "WARNING: Detected not yet supported "
-				        "other dictionary "
-				     << optarg << '\n';
-			other_dicts.emplace_back(optarg);
-
-			break;
-		case 'i':
-			encoding = optarg;
-
-			break;
-		case 'D':
-			if (mode == DEFAULT_MODE)
-				mode = LIST_DICTIONARIES_MODE;
-			else
-				mode = ERROR_MODE;
-
-			break;
-		case 'G':
-			if (mode == DEFAULT_MODE)
-				mode = CORRECT_WORDS_MODE;
-			else if (mode == LINES_MODE)
-				mode = CORRECT_LINES_MODE;
-			else
-				mode = ERROR_MODE;
-
-			break;
-		case 'l':
-			if (mode == DEFAULT_MODE)
-				mode = MISSPELLED_WORDS_MODE;
-			else if (mode == LINES_MODE)
-				mode = MISSPELLED_LINES_MODE;
-			else
-				mode = ERROR_MODE;
-
-			break;
-		case 'L':
-			if (mode == DEFAULT_MODE)
-				mode = LINES_MODE;
-			else if (mode == MISSPELLED_WORDS_MODE)
-				mode = MISSPELLED_LINES_MODE;
-			else if (mode == CORRECT_WORDS_MODE)
-				mode = CORRECT_LINES_MODE;
-			else
-				mode = ERROR_MODE;
-
-			break;
-		case 's':
-			whitespace_segmentation = true;
-
-			break;
-		case 'h':
-			if (mode == DEFAULT_MODE)
-				mode = HELP_MODE;
-			else
-				mode = ERROR_MODE;
-
-			break;
-		case 'v':
-			if (mode == DEFAULT_MODE)
-				mode = VERSION_MODE;
-			else
-				mode = ERROR_MODE;
-
-			break;
-		case ':':
-			cerr << "Option -" << static_cast<char>(optopt)
-			     << " requires an operand\n";
-			mode = ERROR_MODE;
-
-			break;
-		case '?':
-			cerr << "Unrecognized option: '-"
-			     << static_cast<char>(optopt) << "'\n";
-			mode = ERROR_MODE;
-
-			break;
-		}
-	}
-	files.insert(files.end(), argv + optind, argv + argc);
-	if (mode == LINES_MODE) {
-		// in v1 this defaults to MISSPELLED_LINES_MODE
-		// we will make it error here
-		mode = ERROR_MODE;
-	}
-#endif
-}
-
-/**
- * @brief Prints help information to standard output.
- *
- * @param program_name pass argv[0] here.
- */
-auto print_help(const string& program_name) -> void
-{
-	auto& p = program_name;
-	auto& o = cout;
-	o << "Usage:\n"
-	     "\n";
-	o << p << " [-s] [-d dict_NAME] [-i enc] [file_name]...\n";
-	o << p << " -l|-G [-L] [-s] [-d dict_NAME] [-i enc] [file_name]...\n";
-	o << p << " -D|-h|--help|-v|--version\n";
-	o << "\n"
-	     "Check spelling of each FILE. Without FILE, check standard "
-	     "input.\n"
-	     "\n"
-	     "  -d di_CT      use di_CT dictionary. Only one dictionary at a\n"
-	     "                time is currently supported\n"
-	     "  -D            print search paths and available dictionaries\n"
-	     "                and exit\n"
-	     "  -i enc        input/output encoding, default is active locale\n"
-	     "  -l            print only misspelled words or lines\n"
-	     "  -G            print only correct words or lines\n"
-	     "  -L            lines mode\n"
-	     "  -s            use simple whitespace text segmentation to\n"
-	     "                extract words instead of the default Unicode\n"
-	     "                text segmentation. It is not recommended to use\n"
-	     "                this.\n"
-	     "  -h, --help    print this help and exit\n"
-	     "  -v, --version print version number and exit\n"
-	     "\n";
-	o << "Example: " << p << " -d en_US file.txt\n";
-	o << "\n"
-	     "Bug reports: <https://github.com/nuspell/nuspell/issues>\n"
-	     "Full documentation: "
-	     "<https://github.com/nuspell/nuspell/wiki>\n"
-	     "Home page: <http://nuspell.github.io/>\n";
-}
-
-/**
- * @brief Prints the version number to standard output.
- */
-auto print_version() -> void
-{
-	cout << PACKAGE_STRING
-	    "\n"
-	    "Copyright (C) 2016-2021 Dimitrij Mijoski and Sander van Geloven\n"
-	    "License LGPLv3+: GNU LGPL version 3 or later "
-	    "<http://gnu.org/licenses/lgpl.html>.\n"
-	    "This is free software: you are free to change and "
-	    "redistribute it.\n"
-	    "There is NO WARRANTY, to the extent permitted by law.\n"
-	    "\n"
-	    "Written by Dimitrij Mijoski and Sander van Geloven.\n";
-}
-
-/**
- * @brief Lists dictionary paths and available dictionaries.
- *
- * @param f a finder for search paths and located dictionary.
- */
-auto list_dictionaries(const Dict_Finder_For_CLI_Tool& f) -> void
-{
-	if (f.get_dir_paths().empty()) {
-		cout << "No search paths available" << '\n';
-	}
-	else {
-		cout << "Search paths:" << '\n';
-		for (auto& p : f.get_dir_paths()) {
-			cout << p << '\n';
-		}
-	}
-
-	// Even if no search paths are available, still report on available
-	// dictionaries.
-	if (f.get_dictionaries().empty()) {
-		cout << "No dictionaries available\n";
-	}
-	else {
-		cout << "Available dictionaries:\n";
-		for (auto& d : f.get_dictionaries()) {
-			cout << left << setw(15) << d.first << ' ' << d.second
-			     << '\n';
-		}
-	}
-}
-
-auto to_utf8(string_view source, string& dest, UConverter* ucnv,
-             UErrorCode& uerr)
-{
-	dest.resize(dest.capacity());
-	auto len = ucnv_toAlgorithmic(UCNV_UTF8, ucnv, dest.data(), dest.size(),
-	                              source.data(), source.size(), &uerr);
-	dest.resize(len);
-	if (uerr == U_BUFFER_OVERFLOW_ERROR) {
-		uerr = U_ZERO_ERROR;
-		ucnv_toAlgorithmic(UCNV_UTF8, ucnv, dest.data(), dest.size(),
-		                   source.data(), source.size(), &uerr);
-	}
-}
-
-auto from_utf8(string_view source, string& dest, UConverter* ucnv,
-               UErrorCode& uerr)
-{
-	dest.resize(dest.capacity());
-	auto len =
-	    ucnv_fromAlgorithmic(ucnv, UCNV_UTF8, dest.data(), dest.size(),
-	                         source.data(), source.size(), &uerr);
-	dest.resize(len);
-	if (uerr == U_BUFFER_OVERFLOW_ERROR) {
-		uerr = U_ZERO_ERROR;
-		ucnv_fromAlgorithmic(ucnv, UCNV_UTF8, dest.data(), dest.size(),
-		                     source.data(), source.size(), &uerr);
-	}
-}
-
-auto to_unicode_string(string_view source, icu::UnicodeString& dest,
-                       UConverter* ucnv, UErrorCode& uerr)
-{
-	auto buf = dest.getBuffer(-1);
-	auto len = ucnv_toUChars(ucnv, buf, dest.getCapacity(), source.data(),
-	                         source.size(), &uerr);
-	if (uerr == U_BUFFER_OVERFLOW_ERROR) {
-		uerr = U_ZERO_ERROR;
-		dest.releaseBuffer(0);
-		buf = dest.getBuffer(len);
-		if (!buf)
-			throw bad_alloc();
-		len = ucnv_toUChars(ucnv, buf, dest.getCapacity(),
-		                    source.data(), source.size(), &uerr);
-	}
-	dest.releaseBuffer(len);
-}
-
-auto process_word(Mode mode, const Dictionary& dic, string_view word,
-                  size_t pos_word, vector<string_view>& wrong_words,
-                  vector<string>& suggestions, ostream& out)
-{
-	auto correct = dic.spell(word);
-	switch (mode) {
-	case DEFAULT_MODE: {
-		if (correct) {
-			out << "*\n";
-			break;
-		}
-		dic.suggest(word, suggestions);
-		if (suggestions.empty()) {
-			out << "# " << word << ' ' << pos_word << '\n';
-			break;
-		}
-		out << "& " << word << ' ' << suggestions.size() << ' '
-		    << pos_word << ": ";
-		out << suggestions[0];
-		for_each(begin(suggestions) + 1, end(suggestions),
-		         [&](auto& sug) { out << ", " << sug; });
-		out << '\n';
-		break;
-	}
-	case MISSPELLED_WORDS_MODE:
-		if (!correct)
-			out << word << '\n';
-		break;
-	case CORRECT_WORDS_MODE:
-		if (correct)
-			out << word << '\n';
-		break;
-	case MISSPELLED_LINES_MODE:
-	case CORRECT_LINES_MODE:
-		if (!correct)
-			wrong_words.push_back(word);
-		break;
-	default:
-		break;
-	}
-}
-
-auto process_word_other_encoding(Mode mode, const Dictionary& dic,
-                                 string_view word, string_view u8word,
-                                 size_t pos_word,
-                                 vector<string_view>& wrong_words,
-                                 vector<string>& suggestions, ostream& out,
-                                 UConverter* ucnv, UErrorCode& uerr)
-{
-	auto correct = dic.spell(u8word);
-	switch (mode) {
-	case DEFAULT_MODE: {
-		if (correct) {
-			out << "*\n";
-			break;
-		}
-		dic.suggest(u8word, suggestions);
-		if (suggestions.empty()) {
-			out << "# " << word << ' ' << pos_word << '\n';
-			break;
-		}
-		out << "& " << word << ' ' << suggestions.size() << ' '
-		    << pos_word << ": ";
-		auto sug_in_encoding = string();
-		from_utf8(suggestions[0], sug_in_encoding, ucnv, uerr);
-		out << sug_in_encoding;
-		for_each(begin(suggestions) + 1, end(suggestions),
-		         [&](const string& u8sug) {
-			         out << ", ";
-			         from_utf8(u8sug, sug_in_encoding, ucnv, uerr);
-			         out << sug_in_encoding;
-		         });
-		out << '\n';
-		break;
-	}
-	case MISSPELLED_WORDS_MODE:
-		if (!correct)
-			out << word << '\n';
-		break;
-	case CORRECT_WORDS_MODE:
-		if (correct)
-			out << word << '\n';
-		break;
-	case MISSPELLED_LINES_MODE:
-	case CORRECT_LINES_MODE:
-		if (!correct)
-			wrong_words.push_back(word);
-		break;
-	default:
-		break;
-	}
-}
-
-auto finish_line(Mode mode, const string& line,
-                 const vector<string_view>& wrong_words, ostream& out)
-{
-	switch (mode) {
-	case DEFAULT_MODE:
-		out << '\n';
-		break;
-	case MISSPELLED_LINES_MODE:
-		if (!wrong_words.empty())
-			out << line << '\n';
-		break;
-	case CORRECT_LINES_MODE:
-		if (wrong_words.empty())
-			out << line << '\n';
-		break;
-	default:
-		break;
-	}
-}
-
-auto whitespace_segmentation_loop(istream& in, ostream& out,
-                                  const Dictionary& dic, Mode mode,
-                                  UConverter* ucnv, UErrorCode& uerr)
-{
-	auto line = string();
-	auto suggestions = vector<string>();
-	auto wrong_words = vector<string_view>();
-	auto loc = in.getloc();
-	auto& facet = use_facet<ctype<char>>(loc);
-	auto isspace = [&](char c) { return facet.is(facet.space, c); };
-	auto u8word = string();
-	auto is_utf8 = ucnv_getType(ucnv) == UCNV_UTF8;
-
-	while (getline(in, line)) {
-		wrong_words.clear();
-		for (auto a = begin(line); a != end(line);) {
-			a = find_if_not(a, end(line), isspace);
-			if (a == end(line))
-				break;
-			auto b = find_if(a, end(line), isspace);
-			auto word = string_view(&*a, distance(a, b));
-			auto pos_word = distance(begin(line), a);
-			if (is_utf8) {
-				process_word(mode, dic, word, pos_word,
-				             wrong_words, suggestions, out);
-			}
-			else {
-				to_utf8(word, u8word, ucnv, uerr);
-				process_word_other_encoding(
-				    mode, dic, word, u8word, pos_word,
-				    wrong_words, suggestions, out, ucnv, uerr);
-			}
-			a = b;
-		}
-		finish_line(mode, line, wrong_words, out);
-	}
-}
-
-auto is_word_break(int32_t typ)
-{
-	return (UBRK_WORD_NUMBER <= typ && typ < UBRK_WORD_NUMBER_LIMIT) ||
-	       (UBRK_WORD_LETTER <= typ && typ < UBRK_WORD_LETTER_LIMIT) ||
-	       (UBRK_WORD_KANA <= typ && typ < UBRK_WORD_KANA_LIMIT) ||
-	       (UBRK_WORD_IDEO <= typ && typ < UBRK_WORD_IDEO_LIMIT);
-}
-
-auto segment_line_utf8(Mode mode, const Dictionary& dic, const string& line,
-                       UText* utext, icu::BreakIterator* ubrkiter,
-                       UErrorCode& uerr, vector<string>& suggestions,
-                       vector<string_view>& wrong_words, ostream& out)
-{
-	utext_openUTF8(utext, line.data(), line.size(), &uerr);
-	ubrkiter->setText(utext, uerr);
-	for (auto i = ubrkiter->first(), prev = 0; i != ubrkiter->DONE;
-	     prev = i, i = ubrkiter->next()) {
-		auto typ = ubrkiter->getRuleStatus();
-		if (is_word_break(typ)) {
-			auto word = string_view(line).substr(prev, i - prev);
-			process_word(mode, dic, word, prev, wrong_words,
-			             suggestions, out);
-		}
-	}
-	finish_line(mode, line, wrong_words, out);
-	assert(U_SUCCESS(uerr));
-}
-
-auto segment_line_generic(Mode mode, const Dictionary& dic, const string& line,
-                          icu::UnicodeString& uline, UConverter* ucnv,
-                          icu::BreakIterator* ubrkiter, UErrorCode& uerr,
-                          string& u8word, vector<string>& suggestions,
-                          vector<string_view>& wrong_words, ostream& out)
-{
-	to_unicode_string(line, uline, ucnv, uerr);
-	ubrkiter->setText(uline);
-	size_t orig_prev = 0, orig_i = 0;
-	auto src = line.c_str();
-	auto src_end = src + line.size();
-
-	ucnv_resetToUnicode(ucnv);
-	for (auto i = ubrkiter->first(), prev = 0; i != ubrkiter->DONE;
-	     prev = i, i = ubrkiter->next(), orig_prev = orig_i) {
-
-		for (auto j = prev; j != i; ++j) {
-			auto cp = ucnv_getNextUChar(ucnv, &src, src_end, &uerr);
-
-			// U_IS_SURROGATE(uline[j]) or
-			// U_IS_LEAD(uline[j]) can work too
-			j += !U_IS_BMP(cp);
-		}
-		orig_i = distance(line.c_str(), src);
-
-		auto typ = ubrkiter->getRuleStatus();
-		if (is_word_break(typ)) {
-			auto uword = uline.tempSubStringBetween(prev, i);
-			u8word.clear();
-			uword.toUTF8String(u8word);
-			auto word = string_view(line).substr(
-			    orig_prev, orig_i - orig_prev);
-			process_word_other_encoding(
-			    mode, dic, word, u8word, orig_prev, wrong_words,
-			    suggestions, out, ucnv, uerr);
-		}
-	}
-	finish_line(mode, line, wrong_words, out);
-	assert(U_SUCCESS(uerr));
-}
-
-auto unicode_segentation_loop(istream& in, ostream& out, const Dictionary& dic,
-                              Mode mode, UConverter* ucnv, UErrorCode& uerr)
-{
-	auto line = string();
-	auto suggestions = vector<string>();
-	auto wrong_words = vector<string_view>();
-
-	// TODO: try to use Locale constructed from dictionary name.
-	auto ubrkiter = unique_ptr<icu::BreakIterator>(
-	    icu::BreakIterator::createWordInstance(icu::Locale(), uerr));
-	auto utext = icu::LocalUTextPointer(
-	    utext_openUTF8(nullptr, line.data(), line.size(), &uerr));
-	auto uline = icu::UnicodeString();
-	auto u8word = string();
-	auto is_utf8 = ucnv_getType(ucnv) == UCNV_UTF8;
-
-	while (getline(in, line)) {
-		wrong_words.clear();
-		if (is_utf8)
-			segment_line_utf8(mode, dic, line, utext.getAlias(),
-			                  ubrkiter.get(), uerr, suggestions,
-			                  wrong_words, out);
-		else
-			segment_line_generic(mode, dic, line, uline, ucnv,
-			                     ubrkiter.get(), uerr, u8word,
-			                     suggestions, wrong_words, out);
-	}
-}
-
-int main(int argc, char* argv[])
-{
-	// May speed up I/O. After this, don't use C printf, scanf etc.
-	ios_base::sync_with_stdio(false);
-
-	auto args = Args_t(argc, argv);
-	switch (args.mode) {
-	case HELP_MODE:
-		print_help(args.program_name);
-		return 0;
-	case VERSION_MODE:
-		print_version();
-		return 0;
-	case ERROR_MODE:
-		cerr << "Invalid (combination of) arguments, try '"
-		     << args.program_name << " --help' for more information\n";
-		return 1;
-	default:
-		break;
-	}
-	auto f = Dict_Finder_For_CLI_Tool();
-	if (args.mode == LIST_DICTIONARIES_MODE) {
-		list_dictionaries(f);
-		return 0;
-	}
-	char* loc_str = nullptr;
-#ifdef _WIN32
-	loc_str = setlocale(LC_CTYPE, nullptr); // will return "C"
-
-	/* On Windows, the console is a buggy thing. If the default C locale is
-	active, then the encoding of the strings gotten from C or C++ stdio
-	(fgets, scanf, cin) is GetConsoleCP(). Stdout accessed via standard
-	functions (printf, cout) expects encoding of GetConsoleOutputCP() which
-	is the same as GetConsoleCP() unless manually changed. By default both
-	are the active OEM encoding, unless changed with the command chcp, or by
-	calling the Set functions.
-
-	If we call setlocale(LC_CTYPE, ""), or let's say setlocale(LC_CTYPE,
-	".1251"), then stdin will still return in the encoding GetConsoleCP(),
-	but stdout functions like printf now will expect a different encoding,
-	the one set via setlocale. Because of this mess don't change locale with
-	setlocale on Windows.
-
-	When stdin or stout are redirected from/to file or another terminal like
-	the one in MSYS2, they are read/written as-is. Then we will assume UTF-8
-	encoding. */
-#else
-	loc_str = setlocale(LC_CTYPE, "");
-	if (!loc_str) {
-		clog << "WARNING: Invalid locale string, fall back to \"C\".\n";
-		loc_str = setlocale(LC_CTYPE, nullptr); // will return "C"
-	}
-#endif
-	auto loc_str_sv = string_view(loc_str);
-	if (args.encoding.empty()) {
-#if _POSIX_VERSION
-		auto enc_str = nl_langinfo(CODESET);
-		args.encoding = enc_str;
-#elif _WIN32
-		if (_isatty(_fileno(stdin)) || _isatty(_fileno(stdout)))
-			args.encoding = "cp" + to_string(GetConsoleCP());
-		else
-			args.encoding = "UTF-8";
-#endif
-	}
-	clog << "INFO: Locale LC_CTYPE=" << loc_str_sv
-	     << ", Used encoding=" << args.encoding << '\n';
-	if (args.dictionary.empty()) {
-		// infer dictionary from locale
-		auto idx = min(loc_str_sv.find('.'), loc_str_sv.find('@'));
-		args.dictionary = loc_str_sv.substr(0, idx);
-	}
-	if (args.dictionary.empty()) {
-		cerr << "No dictionary provided and can not infer from OS "
-		        "locale\n";
-	}
-	auto filename = f.get_dictionary_path(args.dictionary);
-	if (filename.empty()) {
-		cerr << "Dictionary " << args.dictionary << " not found\n";
-		return 1;
-	}
-	clog << "INFO: Pointed dictionary " << filename << ".{dic,aff}\n";
-	auto dic = Dictionary();
-	try {
-		dic = Dictionary::load_from_path(filename);
-	}
-	catch (const Dictionary_Loading_Error& e) {
-		cerr << e.what() << '\n';
-		return 1;
-	}
-	// ICU reports all types of errors, logic errors and runtime errors
-	// using this enum. We should not check for logic errors, they should
-	// not happend. Optionally, only assert that they are not there can be
-	// used. We should check for runtime errors.
-	// The encoding conversion is a common case where runtime error can
-	// happen, but by default ICU uses Unicode replacement character on
-	// errors and reprots success. This can be changed, but there is no need
-	// for that.
-	auto uerr = U_ZERO_ERROR;
-	auto enc_cstr = args.encoding.c_str();
-	if (args.encoding.empty()) {
-		enc_cstr = nullptr;
-		clog << "WARNING: using default ICU encoding converter for IO"
-		     << endl;
-	}
-	auto ucnv = icu::LocalUConverterPointer(ucnv_open(enc_cstr, &uerr));
-	if (U_FAILURE(uerr)) {
-		cerr << "ERROR: Invalid encoding " << args.encoding << ".\n";
-		return 1;
-	}
-	auto loop_function = unicode_segentation_loop;
-	if (args.whitespace_segmentation)
-		loop_function = whitespace_segmentation_loop;
-	if (args.files.empty()) {
-		loop_function(cin, cout, dic, args.mode, ucnv.getAlias(), uerr);
-	}
-	else {
-		for (auto& file_name : args.files) {
-			ifstream in(file_name);
-			if (!in.is_open()) {
-				cerr << "Can't open " << file_name << '\n';
-				return 1;
-			}
-			loop_function(in, cout, dic, args.mode, ucnv.getAlias(),
-			              uerr);
-		}
-	}
-	return 0;
-}

app/src/main/java/dev/patrickgold/florisboard/FlorisApplication.kt

@@ -23,9 +23,13 @@ import android.content.Intent
 import android.content.IntentFilter
 import android.os.Build
 import androidx.core.os.UserManagerCompat
+import dev.patrickgold.florisboard.common.NativeStr
+import dev.patrickgold.florisboard.common.toNativeStr
 import dev.patrickgold.florisboard.crashutility.CrashUtility
 import dev.patrickgold.florisboard.debug.Flog
 import dev.patrickgold.florisboard.debug.LogTopic
+import dev.patrickgold.florisboard.debug.flogError
+import dev.patrickgold.florisboard.debug.flogInfo
 import dev.patrickgold.florisboard.ime.core.Preferences
 import dev.patrickgold.florisboard.ime.core.SubtypeManager
 import dev.patrickgold.florisboard.ime.dictionary.DictionaryManager
@@ -34,12 +38,16 @@ import dev.patrickgold.florisboard.ime.theme.ThemeManager
 import dev.patrickgold.florisboard.res.AssetManager
 import dev.patrickgold.florisboard.res.FlorisRef
 import timber.log.Timber
-import java.lang.Exception
-import java.lang.ref.WeakReference
+import java.io.File
+import kotlin.Exception
 
 @Suppress("unused")
 class FlorisApplication : Application() {
     companion object {
+        private const val ICU_DATA_ASSET_PATH = "icu/icudt69l.dat"
+
+        private external fun nativeInitICUData(path: NativeStr): Int
+
         init {
             try {
                 System.loadLibrary("florisboard-native")
@@ -61,6 +69,7 @@ class FlorisApplication : Application() {
                 flogLevels = Flog.LEVEL_ALL,
                 flogOutputs = Flog.OUTPUT_CONSOLE
             )
+            initICU()
             CrashUtility.install(this)
             val prefs = Preferences.initDefault(this)
             val assetManager = AssetManager.init(this)
@@ -80,6 +89,32 @@ class FlorisApplication : Application() {
         }
     }
 
+    fun initICU(): Boolean {
+        try {
+            val context = if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.N) {
+                createDeviceProtectedStorageContext()
+            } else {
+                this
+            }
+            val androidAssetManager = context.assets ?: return false
+            val dstDataFile = File(context.cacheDir, "icudt.dat")
+            dstDataFile.outputStream().use { os ->
+                androidAssetManager.open(ICU_DATA_ASSET_PATH).use { it.copyTo(os) }
+            }
+            val status = nativeInitICUData(dstDataFile.absolutePath.toNativeStr())
+            return if (status != 0) {
+                flogError { "Native ICU data initializing failed with error code $status!" }
+                false
+            } else {
+                flogInfo { "Successfully loaded ICU data!" }
+                true
+            }
+        } catch (e: Exception) {
+            flogError { e.toString() }
+            return false
+        }
+    }
+
     fun init() {
         CrashUtility.install(this)
         val prefs = Preferences.initDefault(this)

app/src/main/java/dev/patrickgold/florisboard/FlorisSpellCheckerService.kt

@@ -17,23 +17,26 @@
 package dev.patrickgold.florisboard
 
 import android.service.textservice.SpellCheckerService
-import android.util.LruCache
+import android.view.textservice.SentenceSuggestionsInfo
 import android.view.textservice.SuggestionsInfo
 import android.view.textservice.TextInfo
+import dev.patrickgold.florisboard.common.FlorisLocale
 import dev.patrickgold.florisboard.debug.LogTopic
 import dev.patrickgold.florisboard.debug.flogInfo
-import dev.patrickgold.florisboard.ime.core.Preferences
 import dev.patrickgold.florisboard.ime.core.Subtype
 import dev.patrickgold.florisboard.ime.core.SubtypeManager
 import dev.patrickgold.florisboard.ime.dictionary.DictionaryManager
-import dev.patrickgold.florisboard.ime.spelling.SpellingDict
-import dev.patrickgold.florisboard.ime.spelling.SpellingManager
-import java.util.*
-import kotlin.contracts.InvocationKind
-import kotlin.contracts.contract
+import dev.patrickgold.florisboard.ime.spelling.SpellingService
+import kotlinx.coroutines.runBlocking
 
 class FlorisSpellCheckerService : SpellCheckerService() {
+    companion object {
+        private const val USE_FLORIS_SUBTYPES_LOCALE: String = "zz"
+    }
+
     private val dictionaryManager get() = DictionaryManager.default()
+    private val spellingService: SpellingService = SpellingService.globalInstance()
+    private val subtypeManager get() = SubtypeManager.default()
 
     override fun onCreate() {
         flogInfo(LogTopic.SPELL_EVENTS)
@@ -54,75 +57,87 @@ class FlorisSpellCheckerService : SpellCheckerService() {
         super.onDestroy()
     }
 
-    private class SuggestionsCache(size: Int) {
-        val suggestionsInfoCache: LruCache<String, SuggestionsInfo> = LruCache(size)
-
-        inline fun getOrGenerate(word: String, generator: (w: String) -> SuggestionsInfo): SuggestionsInfo {
-            contract {
-                callsInPlace(generator, InvocationKind.AT_MOST_ONCE)
-            }
-            val cachedSuggestionsInfo = suggestionsInfoCache.get(word)
-            if (cachedSuggestionsInfo != null) {
-                return cachedSuggestionsInfo
-            }
-            val newSuggestionsInfo = generator(word)
-            suggestionsInfoCache.put(word, newSuggestionsInfo)
-            return newSuggestionsInfo
-        }
-    }
-
-    private class FlorisSpellCheckerSession : Session() {
-        companion object {
-            private const val USE_FLORIS_SUBTYPES_LOCALE: String = "zz"
-            private const val SUGGESTIONS_MAX_SIZE = 50
-
-            private val EMPTY_STRING_ARRAY: Array<out String> = arrayOf()
-        }
-
-        private val prefs get() = Preferences.default()
-        private val dictionaryManager get() = DictionaryManager.default()
-        private val spellingManager get() = SpellingManager.default()
-        private val subtypeManager get() = SubtypeManager.default()
-
-        private var spellingDict: SpellingDict? = null
-        private lateinit var spellingLocale: Locale
-        private val suggestionsCache = SuggestionsCache(SUGGESTIONS_MAX_SIZE)
+    private inner class FlorisSpellCheckerSession : Session() {
+        private var cachedSpellingLocale: FlorisLocale? = null
 
         override fun onCreate() {
             flogInfo(LogTopic.SPELL_EVENTS) { "Session locale: $locale" }
 
-            spellingLocale = when (locale) {
+            setupSpellingIfNecessary()
+        }
+
+        private fun setupSpellingIfNecessary() {
+            val evaluatedLocale = when (locale) {
                 null -> Subtype.DEFAULT.locale
                 USE_FLORIS_SUBTYPES_LOCALE -> (subtypeManager.getActiveSubtype() ?: Subtype.DEFAULT).locale
-                else -> Locale(locale)
+                else -> FlorisLocale.from(locale)
             }
 
-            spellingDict = spellingManager.getSpellingDict(spellingLocale)
+            if (evaluatedLocale != cachedSpellingLocale) {
+                cachedSpellingLocale = evaluatedLocale
+            }
+        }
+
+        private fun spellMultiple(
+            spellingLocale: FlorisLocale,
+            textInfos: Array<out TextInfo>,
+            suggestionsLimit: Int
+        ): Array<SuggestionsInfo> = runBlocking {
+            val retInfos = Array(textInfos.size) { n ->
+                val word = textInfos[n].text ?: ""
+                spellingService.spellAsync(spellingLocale, word, suggestionsLimit)
+            }
+            Array(textInfos.size) { n ->
+                retInfos[n].await().apply {
+                    setCookieAndSequence(textInfos[n].cookie, textInfos[n].sequence)
+                }
+            }
         }
 
         override fun onGetSuggestions(textInfo: TextInfo?, suggestionsLimit: Int): SuggestionsInfo {
-            flogInfo(LogTopic.SPELL_EVENTS) { "text=${textInfo?.text}, limit=$suggestionsLimit"}
+            flogInfo(LogTopic.SPELL_EVENTS) { "text=${textInfo?.text}, limit=$suggestionsLimit" }
 
-            val spellingDict = spellingDict ?: return SuggestionsInfo(0, EMPTY_STRING_ARRAY)
-            val word = textInfo?.text ?: return SuggestionsInfo(0, EMPTY_STRING_ARRAY)
+            textInfo?.text ?: return SpellingService.emptySuggestionsInfo()
+            setupSpellingIfNecessary()
+            val spellingLocale = cachedSpellingLocale ?: return SpellingService.emptySuggestionsInfo()
 
-            return suggestionsCache.getOrGenerate(word) {
-                var isWordOk = false
-                if (prefs.spelling.useUdmEntries) {
-                    isWordOk = dictionaryManager.spell(word, spellingLocale)
-                }
-                return@getOrGenerate if (isWordOk) {
-                    SuggestionsInfo(SuggestionsInfo.RESULT_ATTR_IN_THE_DICTIONARY, EMPTY_STRING_ARRAY)
-                } else {
-                    isWordOk = spellingDict.spell(word)
-                    if (isWordOk) {
-                        SuggestionsInfo(SuggestionsInfo.RESULT_ATTR_IN_THE_DICTIONARY, EMPTY_STRING_ARRAY)
-                    } else {
-                        val suggestions = spellingDict.suggest(word, suggestionsLimit)
-                        SuggestionsInfo(SuggestionsInfo.RESULT_ATTR_LOOKS_LIKE_TYPO, suggestions)
-                    }
-                }
-            }
+            return spellingService.spell(spellingLocale, textInfo.text, suggestionsLimit)
+        }
+
+        override fun onGetSuggestionsMultiple(
+            textInfos: Array<out TextInfo>?,
+            suggestionsLimit: Int,
+            sequentialWords: Boolean
+        ): Array<SuggestionsInfo> {
+            flogInfo(LogTopic.SPELL_EVENTS)
+
+            textInfos ?: return emptyArray()
+            setupSpellingIfNecessary()
+            val spellingLocale = cachedSpellingLocale ?: return emptyArray()
+
+            return spellMultiple(spellingLocale, textInfos, suggestionsLimit)
+        }
+
+        override fun onGetSentenceSuggestionsMultiple(
+            textInfos: Array<out TextInfo>?,
+            suggestionsLimit: Int
+        ): Array<SentenceSuggestionsInfo> {
+            flogInfo(LogTopic.SPELL_EVENTS)
+
+            // TODO: implement custom solution here instead of calling the default implementation
+            return super.onGetSentenceSuggestionsMultiple(textInfos, suggestionsLimit)
+        }
+
+        override fun onCancel() {
+            flogInfo(LogTopic.SPELL_EVENTS)
+
+            super.onCancel()
+        }
+
+        override fun onClose() {
+            flogInfo(LogTopic.SPELL_EVENTS)
+
+            super.onClose()
         }
     }
 }

app/src/main/java/dev/patrickgold/florisboard/common/FlorisLocale.kt

@@ -0,0 +1,306 @@
+/*
+ * Copyright (C) 2021 Patrick Goldinger
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package dev.patrickgold.florisboard.common
+
+import kotlinx.serialization.KSerializer
+import kotlinx.serialization.Serializable
+import kotlinx.serialization.descriptors.PrimitiveKind
+import kotlinx.serialization.descriptors.PrimitiveSerialDescriptor
+import kotlinx.serialization.descriptors.SerialDescriptor
+import kotlinx.serialization.encoding.Decoder
+import kotlinx.serialization.encoding.Encoder
+import java.util.*
+
+/**
+ * Project-specific locale class wrapping [java.util.Locale]. The wrapping is
+ * necessary to provide consistent language display names and tags across the
+ * whole code base.
+ *
+ * This class would be ideal for Kotlin's value classes, though AndroidX.Room
+ * does not like this at all, so this is a "normal" class.
+ *
+ * To construct a FlorisLocale, use one of the many from() methods provided.
+ *
+ * @see java.util.Locale
+ */
+@Serializable(with = FlorisLocale.Serializer::class)
+class FlorisLocale private constructor(val base: Locale) {
+    companion object {
+        /** Delimiter for a language tag. */
+        private const val DELIMITER_LANGUAGE_TAG = '-'
+        /** Delimiter for a locale tag. */
+        private const val DELIMITER_LOCALE_TAG = '_'
+
+        /** Delimiter regex to split language/locale tags. */
+        private val DELIMITER_SPLITTER = """[${DELIMITER_LANGUAGE_TAG}${DELIMITER_LOCALE_TAG}]""".toRegex()
+
+        /** Constant locale for ROOT */
+        val ROOT = from("", "", "")
+
+        /** Constant locale for ENGLISH */
+        val ENGLISH = from("en", "", "")
+
+        /**
+         * Wraps a [java.util.Locale] and returns the [FlorisLocale].
+         *
+         * @return The wrapped locale.
+         */
+        fun from(javaLocale: Locale) = FlorisLocale(javaLocale)
+
+        /**
+         * Constructs a new [FlorisLocale] with given [language].
+         *
+         * @param language A two-letter language code.
+         *
+         * @return A new [FlorisLocale].
+         */
+        fun from(language: String) = from(Locale(language))
+
+        /**
+         * Constructs a new [FlorisLocale] with given [language] and [country].
+         *
+         * @param language A two-letter language code.
+         * @param country A two-letter country code.
+         *
+         * @return A new [FlorisLocale].
+         */
+        fun from(language: String, country: String) = from(Locale(language, country))
+
+        /**
+         * Constructs a new [FlorisLocale] with given [language], [country] and [variant].
+         *
+         * @param language A two-letter language code.
+         * @param country A two-letter country code.
+         * @param variant A two-letter variant code.
+         *
+         * @return A new [FlorisLocale].
+         */
+        fun from(language: String, country: String, variant: String) = from(Locale(language, country, variant))
+
+        /**
+         * Constructs a new [FlorisLocale] from given [str].
+         *
+         * @param str Either a language or locale tag in string form.
+         *
+         * @return A new [FlorisLocale].
+         */
+        fun fromTag(str: String) = when {
+            str.contains(DELIMITER_SPLITTER) -> {
+                val lc = str.split(DELIMITER_SPLITTER)
+                if (lc.size >= 3) {
+                    from(lc[0], lc[1], lc[2])
+                } else {
+                    from(lc[0], lc[1])
+                }
+            }
+            else -> from(str)
+        }
+
+        /**
+         * Gets the current value of the default locale for this instance of
+         * the Java Virtual Machine.
+         *
+         * @see java.util.Locale.getDefault
+         */
+        fun default() = FlorisLocale(Locale.getDefault())
+    }
+
+    /**
+     * Builds a locale or language tag for this locale by using [delimiter].
+     *
+     * @param delimiter The delimiter to use between the components.
+     *
+     * @return The generated tag for this locale. May be an empty string if
+     *  [language], [country] and [variant] are not specified.
+     */
+    private fun buildLocaleString(delimiter: Char) = stringBuilder {
+        val language = base.language
+        val country = base.country
+        val variant = base.variant
+        append(language)
+        if (language.isNotBlank() && country.isNotBlank()) {
+            append(delimiter)
+        }
+        append(country)
+        if (country.isNotBlank() && variant.isNotBlank()) {
+            append(delimiter)
+        }
+        append(variant)
+    }
+
+    /**
+     * Returns the language code of this locale.
+     *
+     * @see java.util.Locale.getLanguage
+     */
+    val language: String get() = base.language
+
+    /**
+     * Returns the country/region code for this locale.
+     *
+     * @see java.util.Locale.getCountry
+     */
+    val country: String get() = base.country
+
+    /**
+     * Returns the variant code for this locale.
+     *
+     * @see java.util.Locale.getVariant
+     */
+    val variant: String get() = base.variant
+
+    /**
+     * Returns a three-letter abbreviation of this locale's language.
+     *
+     * @see java.util.Locale.getISO3Language
+     */
+    val iso3Language: String get() = base.isO3Language
+
+    /**
+     * Returns a three-letter abbreviation of this locale's country.
+     *
+     * @see java.util.Locale.getISO3Country
+     */
+    val iso3Country: String get() = base.isO3Country
+
+    /**
+     * Generates the language tag for this locale in the format `xx`,
+     * `xx-YY` or `xx-YY-zzz` and returns it as a string.
+     *
+     * xx: Two-letter language code
+     * YY: Two-letter country code
+     * zzz: Three letter variant
+     *
+     * @return The language tag for this locale. May be an empty string if
+     *  [language], [country] and [variant] are not specified.
+     */
+    fun languageTag(): String = buildLocaleString(DELIMITER_LANGUAGE_TAG)
+
+    /**
+     * Generates the locale tag for this locale in the format `xx`,
+     * `xx_YY` or `xx_YY_zzz` and returns it as a string.
+     *
+     * xx: Two-letter language code
+     * YY: Two-letter country code
+     * zzz: Three letter variant
+     *
+     * @return The locale tag for this locale. May be an empty string if
+     *  [language], [country] and [variant] are not specified.
+     */
+    fun localeTag(): String = buildLocaleString(DELIMITER_LOCALE_TAG)
+
+    /**
+     * Returns the name of this locale's language, localized to [locale].
+     *
+     * @see java.util.Locale.getDisplayLanguage
+     */
+    fun displayLanguage(locale: FlorisLocale = default()): String = base.getDisplayLanguage(locale.base)
+
+    /**
+     * Returns the name of this locale's country, localized to [locale].
+     *
+     * @see java.util.Locale.getDisplayCountry
+     */
+    fun displayCountry(locale: FlorisLocale = default()): String = base.getDisplayCountry(locale.base)
+
+    /**
+     * Returns a name for the locale's variant code that is appropriate for
+     * display to the user.
+     *
+     * @see java.util.Locale.getDisplayVariant
+     */
+    fun displayVariant(locale: FlorisLocale = default()): String = base.getDisplayVariant(locale.base)
+
+    /**
+     * Returns the display name for this locale, localized to [locale] in
+     * the format `Language`, `Language (Country)` or `Language (Country) \[VARIANT]`.
+     *
+     * @param locale The locale to use for generating the display name for
+     *  this locale, or [default] if otherwise.
+     *
+     * @return The display name for this locale. May be an empty string if
+     *  [language], [country] and [variant] are not specified.
+     */
+    fun displayName(locale: FlorisLocale = default()) = stringBuilder {
+        val languageName = displayLanguage(locale).ifBlank { base.language }
+        val countryName = displayCountry(locale).ifBlank { base.country }
+        val variantName = displayVariant(locale).ifBlank { base.variant }
+        append(languageName)
+        if (countryName.isNotBlank()) {
+            if (languageName.isNotBlank()) {
+                append(' ')
+            }
+            append('(')
+            append(countryName)
+            append(')')
+        }
+        if (variantName.isNotBlank()) {
+            if (languageName.isNotBlank() || countryName.isNotBlank()) {
+                append(' ')
+            }
+            append('[')
+            append(variantName.uppercase())
+            append(']')
+        }
+    }
+
+    /**
+     * Generate a debug string representing this locale. Not to be confused
+     * with [java.util.Locale.toString], which produces a locale tag. If such
+     * tag is needed, use [localeTag].
+     *
+     * @return The debug representation of this locale.
+     */
+    override fun toString() = "FlorisLocale { l=${base.language} c=${base.country} v=${base.variant} }"
+
+    /**
+     * Equality check for this locale.
+     */
+    override fun equals(other: Any?): Boolean {
+        if (this === other) return true
+        if (javaClass != other?.javaClass) return false
+
+        other as FlorisLocale
+
+        if (base != other.base) return false
+
+        return true
+    }
+
+    /**
+     * Returns the hash code for this locale.
+     */
+    override fun hashCode(): Int {
+        return base.hashCode()
+    }
+
+    /**
+     * The JSON (de)serializer for FlorisLocale.
+     */
+    class Serializer : KSerializer<FlorisLocale> {
+        override val descriptor: SerialDescriptor =
+            PrimitiveSerialDescriptor("FlorisLocale", PrimitiveKind.STRING)
+
+        override fun serialize(encoder: Encoder, value: FlorisLocale) {
+            encoder.encodeString(value.languageTag())
+        }
+
+        override fun deserialize(decoder: Decoder): FlorisLocale {
+            return fromTag(decoder.decodeString())
+        }
+    }
+}

app/src/main/java/dev/patrickgold/florisboard/common/Result.kt

@@ -0,0 +1,41 @@
+/*
+ * Copyright (C) 2021 Patrick Goldinger
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package dev.patrickgold.florisboard.common
+
+import kotlin.contracts.InvocationKind
+import kotlin.contracts.contract
+
+inline fun <T> resultOk(value: () -> T): Result<T> {
+    contract {
+        callsInPlace(value, InvocationKind.EXACTLY_ONCE)
+    }
+    return Result.success(value())
+}
+
+inline fun <T> resultErr(error: () -> Throwable): Result<T> {
+    contract {
+        callsInPlace(error, InvocationKind.EXACTLY_ONCE)
+    }
+    return Result.failure(error())
+}
+
+inline fun <T> resultErrStr(error: () -> String): Result<T> {
+    contract {
+        callsInPlace(error, InvocationKind.EXACTLY_ONCE)
+    }
+    return Result.failure(Exception(error()))
+}

app/src/main/java/dev/patrickgold/florisboard/common/Strings.kt

@@ -0,0 +1,35 @@
+/*
+ * Copyright (C) 2021 Patrick Goldinger
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+@file:Suppress("NOTHING_TO_INLINE")
+
+package dev.patrickgold.florisboard.common
+
+import kotlin.contracts.InvocationKind
+import kotlin.contracts.contract
+
+inline fun <R> stringBuilder(builder: StringBuilder.() -> R): String {
+    contract {
+        callsInPlace(builder, InvocationKind.EXACTLY_ONCE)
+    }
+    val sb = StringBuilder()
+    builder(sb)
+    return sb.toString()
+}
+
+inline fun String.lowercase(locale: FlorisLocale): String = this.lowercase(locale.base)
+
+inline fun String.uppercase(locale: FlorisLocale): String = this.uppercase(locale.base)

app/src/main/java/dev/patrickgold/florisboard/debug/LogTopic.kt

@@ -37,10 +37,13 @@ object LogTopic {
     const val TEXT_KEYBOARD_VIEW: FlogTopic =   16u
     const val GESTURES: FlogTopic =             32u
     const val SMARTBAR: FlogTopic =             64u
+    const val THEME_MANAGER: FlogTopic =        128u
+    const val ASSET_MANAGER: FlogTopic =        256u
 
     const val GLIDE: FlogTopic =                512u
     const val CLIPBOARD: FlogTopic =            1024u
     const val CRASH_UTILITY: FlogTopic =        2048u
 
     const val SPELL_EVENTS: FlogTopic =         4096u
+    const val EDITOR_INSTANCE: FlogTopic =      0x00_00_20_00u
 }

app/src/main/java/dev/patrickgold/florisboard/ime/clip/ClipboardInputManager.kt

@@ -12,7 +12,7 @@ import dev.patrickgold.florisboard.ime.clip.provider.ClipboardItem
 import dev.patrickgold.florisboard.ime.core.FlorisBoard
 import dev.patrickgold.florisboard.ime.core.InputKeyEvent
 import dev.patrickgold.florisboard.ime.text.key.KeyCode
-import dev.patrickgold.florisboard.ime.text.keyboard.BasicTextKeyData
+import dev.patrickgold.florisboard.ime.text.keyboard.TextKeyData
 import kotlinx.coroutines.*
 import kotlin.math.pow
 
@@ -128,15 +128,14 @@ class ClipboardInputManager private constructor() : CoroutineScope by MainScope(
         event ?: return false
 
         val data = when (view.id) {
-            R.id.back_to_keyboard_button -> BasicTextKeyData(code = KeyCode.SWITCH_TO_TEXT_CONTEXT)
-            R.id.clear_clipboard_history -> BasicTextKeyData(code = KeyCode.CLEAR_CLIPBOARD_HISTORY)
+            R.id.back_to_keyboard_button -> TextKeyData(code = KeyCode.SWITCH_TO_TEXT_CONTEXT)
+            R.id.clear_clipboard_history -> TextKeyData(code = KeyCode.CLEAR_CLIPBOARD_HISTORY)
             else -> null
         } ?: return false
 
         when (event.actionMasked) {
             MotionEvent.ACTION_DOWN -> {
-                florisboard.keyPressVibrate()
-                florisboard.keyPressSound(data)
+                florisboard.inputFeedbackManager.keyPress(data)
                 florisboard.textInputManager.inputEventDispatcher.send(InputKeyEvent.down(data))
             }
             MotionEvent.ACTION_UP -> {

app/src/main/java/dev/patrickgold/florisboard/ime/clip/FlorisClipboardManager.kt

@@ -3,6 +3,7 @@ package dev.patrickgold.florisboard.ime.clip
 import android.content.ClipboardManager
 import android.content.Context
 import android.content.Context.CLIPBOARD_SERVICE
+import dev.patrickgold.florisboard.debug.flogDebug
 import dev.patrickgold.florisboard.ime.clip.provider.*
 import dev.patrickgold.florisboard.ime.core.FlorisBoard
 import dev.patrickgold.florisboard.ime.core.Preferences
@@ -13,7 +14,6 @@ import kotlinx.coroutines.MainScope
 import kotlinx.coroutines.delay
 import kotlinx.coroutines.launch
 import java.io.Closeable
-import java.util.*
 import kotlin.collections.ArrayDeque
 
 /**
@@ -237,7 +237,7 @@ class FlorisClipboardManager private constructor() : ClipboardManager.OnPrimaryC
         } else if (prefs.clipboard.enableHistory) {
             // in the event history is enabled, and it should be updated it is updated
             if (shouldUpdateHistory) {
-                updateHistory(ClipboardItem.fromClipData(systemPrimaryClip, false))
+                updateHistory(ClipboardItem.fromClipData(systemPrimaryClip, true))
             } else {
                 shouldUpdateHistory = true
             }
@@ -293,9 +293,7 @@ class FlorisClipboardManager private constructor() : ClipboardManager.OnPrimaryC
                 ClipboardInputManager.getInstance().notifyItemRangeRemoved(pins.size + history.size, numToPop)
             }
             FlorisBoard.getInstance().clipInputManager.initClipboard(this.history, this.pins)
-            prefs
             cleanUpJob = launch(Dispatchers.Main) {
-
                 while (true) {
                     cleanUpClipboard.run()
                     delay(INTERVAL)
@@ -304,7 +302,11 @@ class FlorisClipboardManager private constructor() : ClipboardManager.OnPrimaryC
             launch(Dispatchers.IO) {
                 pinsDao = PinnedItemsDatabase.getInstance().clipboardItemDao()
                 pinsDao.getAll().toCollection(pins)
-                FlorisContentProvider.getInstance().initIfNotAlready()
+                try {
+                    FlorisContentProvider.getInstance().initIfNotAlready()
+                } catch (e: Exception) {
+                    e.fillInStackTrace()
+                }
             }
         } catch (e : Exception) {
             e.fillInStackTrace()

app/src/main/java/dev/patrickgold/florisboard/ime/clip/provider/FlorisDatabase.kt

@@ -22,7 +22,6 @@ enum class ItemType(val value: Int) {
 
 /**
  * Represents an item on the clipboard.
- * The URI stored belongs to FlorisContentProvider, not whatever app copied the image
  *
  * If type == ItemType.IMAGE there must be a uri set
  * if type == ItemType.TEXT there must be a text set

app/src/main/java/dev/patrickgold/florisboard/ime/core/FlorisBoard.kt

@@ -23,26 +23,22 @@ import android.content.res.Configuration
 import android.graphics.Color
 import android.inputmethodservice.ExtractEditText
 import android.inputmethodservice.InputMethodService
-import android.media.AudioManager
 import android.os.Build
 import android.os.Bundle
 import android.os.Handler
 import android.os.Looper
-import android.os.VibrationEffect
-import android.os.Vibrator
 import android.util.Size
 import android.view.ContextThemeWrapper
 import android.view.Gravity
-import android.view.HapticFeedbackConstants
 import android.view.LayoutInflater
 import android.view.View
 import android.view.ViewGroup
 import android.view.ViewTreeObserver
 import android.view.WindowManager
 import android.view.inputmethod.EditorInfo
+import android.view.inputmethod.ExtractedText
 import android.view.inputmethod.InlineSuggestionsRequest
 import android.view.inputmethod.InlineSuggestionsResponse
-import android.view.inputmethod.InputConnection
 import android.view.inputmethod.InputMethodManager
 import android.widget.Button
 import android.widget.FrameLayout
@@ -57,7 +53,6 @@ import dev.patrickgold.florisboard.crashutility.CrashUtility
 import dev.patrickgold.florisboard.debug.*
 import dev.patrickgold.florisboard.ime.clip.ClipboardInputManager
 import dev.patrickgold.florisboard.ime.clip.FlorisClipboardManager
-import dev.patrickgold.florisboard.ime.keyboard.KeyData
 import dev.patrickgold.florisboard.ime.landscapeinput.LandscapeInputUiMode
 import dev.patrickgold.florisboard.ime.media.MediaInputManager
 import dev.patrickgold.florisboard.ime.onehanded.OneHandedMode
@@ -67,7 +62,6 @@ import dev.patrickgold.florisboard.ime.text.composing.Appender
 import dev.patrickgold.florisboard.ime.text.composing.Composer
 import dev.patrickgold.florisboard.ime.text.gestures.SwipeAction
 import dev.patrickgold.florisboard.ime.text.key.CurrencySet
-import dev.patrickgold.florisboard.ime.text.key.KeyCode
 import dev.patrickgold.florisboard.ime.text.keyboard.TextKeyData
 import dev.patrickgold.florisboard.ime.theme.Theme
 import dev.patrickgold.florisboard.ime.theme.ThemeManager
@@ -75,6 +69,7 @@ import dev.patrickgold.florisboard.setup.SetupActivity
 import dev.patrickgold.florisboard.util.AppVersionUtils
 import dev.patrickgold.florisboard.common.ViewUtils
 import dev.patrickgold.florisboard.databinding.FlorisboardBinding
+import dev.patrickgold.florisboard.ime.keyboard.InputFeedbackManager
 import dev.patrickgold.florisboard.ime.keyboard.KeyboardState
 import dev.patrickgold.florisboard.ime.keyboard.updateKeyboardState
 import dev.patrickgold.florisboard.util.debugSummarize
@@ -133,11 +128,10 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
         private set
     private var eventListeners: CopyOnWriteArrayList<EventListener> = CopyOnWriteArrayList()
 
-    private var audioManager: AudioManager? = null
     var imeManager: InputMethodManager? = null
+    lateinit var inputFeedbackManager: InputFeedbackManager
     var florisClipboardManager: FlorisClipboardManager? = null
     private val themeManager: ThemeManager = ThemeManager.default()
-    private var vibrator: Vibrator? = null
 
     private var internalBatchNestingLevel: Int = 0
     private val internalSelectionCache = object {
@@ -150,7 +144,7 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
         var candidatesEnd: Int = -1
     }
 
-    var activeEditorInstance: EditorInstance = EditorInstance.default()
+    lateinit var activeEditorInstance: EditorInstance
 
     val subtypeManager: SubtypeManager get() = SubtypeManager.default()
     val composer: Composer get() = subtypeManager.imeConfig.composerFromName.getValue(activeSubtype.composerName)
@@ -219,10 +213,10 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
                 flogInfo(LogTopic.IMS_EVENTS)
                 serviceLifecycleDispatcher.onServicePreSuperOnCreate()
 
+                activeEditorInstance = EditorInstance(this, activeState)
+
                 imeManager = getSystemService(Context.INPUT_METHOD_SERVICE) as? InputMethodManager
-                audioManager = getSystemService(Context.AUDIO_SERVICE) as? AudioManager
-                vibrator = getSystemService(Context.VIBRATOR_SERVICE) as? Vibrator
-                prefs.syncSystemSettings()
+                inputFeedbackManager = InputFeedbackManager.new(this)
                 activeSubtype = subtypeManager.getActiveSubtype() ?: Subtype.DEFAULT
 
                 currentThemeIsNight = themeManager.activeTheme.isNightTheme
@@ -320,16 +314,15 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
             it.close()
             florisClipboardManager = null
         }
-        audioManager = null
         imeManager = null
-        vibrator = null
         popupLayerView = null
         uiBinding = null
-        florisboardInstance = null
 
         eventListeners.toList().forEach { it?.onDestroy() }
         eventListeners.clear()
         super.onDestroy()
+
+        florisboardInstance = null
     }
 
     override fun onEvaluateFullscreenMode(): Boolean {
@@ -351,6 +344,15 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
         updateSoftInputWindowLayoutParameters()
     }
 
+    override fun onUpdateExtractedText(token: Int, text: ExtractedText?) {
+        super.onUpdateExtractedText(token, text)
+        activeEditorInstance.updateText(token, text)
+    }
+
+    override fun onUpdateExtractingViews(ei: EditorInfo?) {
+        super.onUpdateExtractingViews(ei)
+    }
+
     override fun onUpdateExtractingVisibility(ei: EditorInfo?) {
         isExtractViewShown = activeState.isRichInputEditor && when (prefs.keyboard.landscapeInputUiMode) {
             LandscapeInputUiMode.DYNAMICALLY_SHOW -> !activeState.imeOptions.flagNoExtractUi
@@ -359,6 +361,10 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
         }
     }
 
+    override fun onBindInput() {
+        activeEditorInstance.bindInput()
+    }
+
     override fun onStartInput(attribute: EditorInfo?, restarting: Boolean) {
         flogInfo(LogTopic.IMS_EVENTS)
 
@@ -368,7 +374,7 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
         } else {
             ResponseState.RESET
         }
-        currentInputConnection?.requestCursorUpdates(InputConnection.CURSOR_UPDATE_MONITOR)
+        activeEditorInstance.startInput(attribute)
     }
 
     override fun onStartInputView(info: EditorInfo?, restarting: Boolean) {
@@ -380,8 +386,8 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
             activeState.update(info)
             activeState.isSelectionMode = (info.initialSelEnd - info.initialSelStart) != 0
         }
-        activeEditorInstance = EditorInstance.from(info, this, activeState)
-        themeManager.updateRemoteColorValues(activeEditorInstance.packageName)
+        activeEditorInstance.startInputView(info)
+        themeManager.updateRemoteColorValues(activeEditorInstance.packageName ?: "")
         eventListeners.toList().forEach {
             it?.onStartInputView(activeEditorInstance, restarting)
         }
@@ -391,13 +397,12 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
     override fun onFinishInputView(finishingInput: Boolean) {
         flogInfo(LogTopic.IMS_EVENTS) { "finishingInput=$finishingInput" }
 
-        if (finishingInput) {
-            activeEditorInstance = EditorInstance.default()
-        } else {
+        if (!finishingInput) {
             if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.R) {
                 textInputManager.smartbarView?.clearInlineSuggestions()
             }
         }
+        activeEditorInstance.finishInputView()
 
         super.onFinishInputView(finishingInput)
         eventListeners.toList().forEach { it?.onFinishInputView(finishingInput) }
@@ -407,10 +412,14 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
     override fun onFinishInput() {
         flogInfo(LogTopic.IMS_EVENTS)
 
-        currentInputConnection?.requestCursorUpdates(0)
+        activeEditorInstance.finishInput()
         super.onFinishInput()
     }
 
+    override fun onUnbindInput() {
+        activeEditorInstance.unbindInput()
+    }
+
     @RequiresApi(Build.VERSION_CODES.R)
     override fun onCreateInlineSuggestionsRequest(uiExtras: Bundle): InlineSuggestionsRequest? {
         return if (prefs.smartbar.enabled && prefs.suggestion.api30InlineSuggestionsEnabled) {
@@ -490,7 +499,6 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
         }
         isWindowShown = true
 
-        prefs.syncSystemSettings()
         val newActiveSubtype = subtypeManager.getActiveSubtype() ?: Subtype.DEFAULT
         if (newActiveSubtype != activeSubtype) {
             activeSubtype = newActiveSubtype
@@ -593,7 +601,7 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
         activeState.isSelectionMode = (newSelEnd - newSelStart) != 0
         if (internalBatchNestingLevel == 0) {
             flogInfo(LogTopic.IMS_EVENTS) { "onUpdateSelection($oldSelStart, $oldSelEnd, $newSelStart, $newSelEnd, $candidatesStart, $candidatesEnd)" }
-            activeEditorInstance.onUpdateSelection(
+            activeEditorInstance.updateSelection(
                 oldSelStart, oldSelEnd,
                 newSelStart, newSelEnd,
                 candidatesStart, candidatesEnd
@@ -725,84 +733,6 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
         }
     }
 
-    /**
-     * Makes a key press vibration if the user has this feature enabled in the preferences.
-     */
-    fun keyPressVibrate(isMovingGestureEffect: Boolean = false) {
-        if (prefs.keyboard.vibrationEnabled) {
-            var vibrationDuration = prefs.keyboard.vibrationDuration.toLong()
-            var vibrationStrength = prefs.keyboard.vibrationStrength
-
-            if (!prefs.keyboard.vibrationEnabledSystem && vibrationDuration < 0 && vibrationStrength < 0) {
-                return
-            }
-
-            val hapticsPerformed = if (vibrationDuration < 0 && vibrationStrength < 0) {
-                if (isMovingGestureEffect && Build.VERSION.SDK_INT >= Build.VERSION_CODES.O_MR1) {
-                    uiBinding?.inputWindowView?.performHapticFeedback(HapticFeedbackConstants.TEXT_HANDLE_MOVE)
-                } else {
-                    uiBinding?.inputWindowView?.performHapticFeedback(HapticFeedbackConstants.KEYBOARD_TAP)
-                }
-            } else {
-                false
-            }
-
-            if (hapticsPerformed == true) {
-                return
-            }
-
-            if (vibrationDuration == -1L) {
-                vibrationDuration = 36
-            }
-            if (isMovingGestureEffect) {
-                vibrationDuration = (vibrationDuration / 8.0).toLong().coerceAtLeast(1)
-            }
-            if (vibrationStrength == -1 && Build.VERSION.SDK_INT >= Build.VERSION_CODES.O) {
-                vibrationStrength = VibrationEffect.DEFAULT_AMPLITUDE
-            } else if (vibrationStrength == -1) {
-                vibrationStrength = 36
-            }
-            if (isMovingGestureEffect && vibrationStrength > 0) {
-                vibrationStrength = (vibrationStrength / 2.0).toInt().coerceAtLeast(1)
-            } else if (isMovingGestureEffect) {
-                vibrationStrength = 8
-            }
-            if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.O) {
-                vibrator?.vibrate(
-                    VibrationEffect.createOneShot(
-                        vibrationDuration, vibrationStrength
-                    )
-                )
-            } else {
-                @Suppress("DEPRECATION")
-                vibrator?.vibrate(vibrationDuration)
-            }
-        }
-    }
-
-    /**
-     * Makes a key press sound if the user has this feature enabled in the preferences.
-     */
-    fun keyPressSound(keyData: KeyData? = null) {
-        if (prefs.keyboard.soundEnabled) {
-            val soundVolume = prefs.keyboard.soundVolume
-            val effect = when (keyData) {
-                is TextKeyData -> when (keyData.code) {
-                    KeyCode.SPACE -> AudioManager.FX_KEYPRESS_SPACEBAR
-                    KeyCode.DELETE -> AudioManager.FX_KEYPRESS_DELETE
-                    KeyCode.ENTER -> AudioManager.FX_KEYPRESS_RETURN
-                    else -> AudioManager.FX_KEYPRESS_STANDARD
-                }
-                else -> AudioManager.FX_KEYPRESS_STANDARD
-            }
-            if (soundVolume == -1 && prefs.keyboard.soundEnabledSystem) {
-                audioManager!!.playSoundEffect(effect)
-            } else if (soundVolume > 0) {
-                audioManager!!.playSoundEffect(effect, soundVolume / 100f)
-            }
-        }
-    }
-
     /**
      * Executes a given [SwipeAction]. Ignores any [SwipeAction] but the ones relevant for this
      * class.
@@ -1053,7 +983,7 @@ open class FlorisBoard : InputMethodService(), LifecycleOwner, FlorisClipboardMa
 
             val tmpSubtypeList = mutableListOf<Pair<String, String>>()
             for (defaultSubtype in defaultSubtypes) {
-                tmpSubtypeList.add(Pair(defaultSubtype.locale.toString(), defaultSubtype.locale.displayName))
+                tmpSubtypeList.add(Pair(defaultSubtype.locale.localeTag(), defaultSubtype.locale.displayName()))
             }
             // Sort language list alphabetically by the display name of a language
             tmpSubtypeList.sortBy { it.second }

app/src/main/java/dev/patrickgold/florisboard/ime/core/InputEventDispatcher.kt

@@ -20,12 +20,12 @@ import android.os.SystemClock
 import android.util.SparseArray
 import androidx.core.util.forEach
 import androidx.core.util.set
-import dev.patrickgold.florisboard.BuildConfig
+import dev.patrickgold.florisboard.debug.LogTopic
+import dev.patrickgold.florisboard.debug.flogDebug
+import dev.patrickgold.florisboard.ime.keyboard.KeyData
 import dev.patrickgold.florisboard.ime.text.key.KeyCode
-import dev.patrickgold.florisboard.ime.text.keyboard.TextKeyData
 import kotlinx.coroutines.*
 import kotlinx.coroutines.channels.Channel
-import timber.log.Timber
 
 /**
  * The main logic point of processing input events and delegating them to the registered event receivers. Currently,
@@ -96,9 +96,7 @@ class InputEventDispatcher private constructor(
             for (ev in channel) {
                 if (!isActive) break
                 val startTime = System.nanoTime()
-                if (BuildConfig.DEBUG) {
-                    Timber.d(ev.toString())
-                }
+                flogDebug(LogTopic.KEY_EVENTS) { ev.toString() }
                 when (ev.action) {
                     InputKeyEvent.Action.DOWN -> {
                         if (pressedKeys.indexOfKey(ev.data.code) >= 0) continue
@@ -155,9 +153,7 @@ class InputEventDispatcher private constructor(
                         }
                     }
                 }
-                if (BuildConfig.DEBUG) {
-                    Timber.d("Time elapsed: ${(System.nanoTime() - startTime) / 1_000_000}")
-                }
+                flogDebug(LogTopic.KEY_EVENTS) { "Time elapsed: ${(System.nanoTime() - startTime) / 1_000_000}" }
             }
             pressedKeys.forEach { _, value -> value.repeatKeyPressJob?.cancel() }
             pressedKeys.clear()
@@ -210,7 +206,7 @@ class InputEventDispatcher private constructor(
 data class InputKeyEvent(
     val eventTime: Long,
     val action: Action,
-    val data: TextKeyData,
+    val data: KeyData,
     val count: Int
 ) {
     companion object {
@@ -221,7 +217,7 @@ data class InputKeyEvent(
          *
          * @return The created input key event.
          */
-        fun down(keyData: TextKeyData): InputKeyEvent {
+        fun down(keyData: KeyData): InputKeyEvent {
             return InputKeyEvent(
                 eventTime = SystemClock.uptimeMillis(),
                 action = Action.DOWN,
@@ -238,7 +234,7 @@ data class InputKeyEvent(
          *
          * @return The created input key event.
          */
-        fun downUp(keyData: TextKeyData, count: Int = 1): InputKeyEvent {
+        fun downUp(keyData: KeyData, count: Int = 1): InputKeyEvent {
             return InputKeyEvent(
                 eventTime = SystemClock.uptimeMillis(),
                 action = Action.DOWN_UP,
@@ -254,7 +250,7 @@ data class InputKeyEvent(
          *
          * @return The created input key event.
          */
-        fun up(keyData: TextKeyData): InputKeyEvent {
+        fun up(keyData: KeyData): InputKeyEvent {
             return InputKeyEvent(
                 eventTime = SystemClock.uptimeMillis(),
                 action = Action.UP,
@@ -271,7 +267,7 @@ data class InputKeyEvent(
          *
          * @return The created input key event.
          */
-        fun repeat(keyData: TextKeyData, count: Int = 1): InputKeyEvent {
+        fun repeat(keyData: KeyData, count: Int = 1): InputKeyEvent {
             return InputKeyEvent(
                 eventTime = SystemClock.uptimeMillis(),
                 action = Action.REPEAT,
@@ -287,7 +283,7 @@ data class InputKeyEvent(
          *
          * @return The created input key event.
          */
-        fun cancel(keyData: TextKeyData): InputKeyEvent {
+        fun cancel(keyData: KeyData): InputKeyEvent {
             return InputKeyEvent(
                 eventTime = SystemClock.uptimeMillis(),
                 action = Action.CANCEL,

app/src/main/java/dev/patrickgold/florisboard/ime/core/Preferences.kt

@@ -19,7 +19,6 @@ package dev.patrickgold.florisboard.ime.core
 import android.content.Context
 import android.content.SharedPreferences
 import android.os.Build
-import android.provider.Settings
 import androidx.core.os.UserManagerCompat
 import androidx.preference.PreferenceManager
 import dev.patrickgold.florisboard.R
@@ -57,6 +56,7 @@ class Preferences(
     val dictionary = Dictionary(this)
     val gestures = Gestures(this)
     val glide = Glide(this)
+    val inputFeedback = InputFeedback(this)
     val internal = Internal(this)
     val keyboard = Keyboard(this)
     val localization = Localization(this)
@@ -152,21 +152,6 @@ class Preferences(
         }
     }
 
-    /**
-     * Syncs the system preference values and clears the cache.
-     */
-    fun syncSystemSettings() {
-        applicationContext.get()?.let { context ->
-            val contentResolver = context.contentResolver
-            keyboard.soundEnabledSystem = Settings.System.getInt(
-                contentResolver, Settings.System.SOUND_EFFECTS_ENABLED, 0
-            ) != 0
-            keyboard.vibrationEnabledSystem = Settings.System.getInt(
-                contentResolver, Settings.System.HAPTIC_FEEDBACK_ENABLED, 0
-            ) != 0
-        }
-    }
-
     /**
      * Wrapper class for advanced preferences.
      */
@@ -217,6 +202,7 @@ class Preferences(
         companion object {
             const val ENABLED =                     "devtools__enabled"
             const val SHOW_HEAP_MEMORY_STATS =      "devtools__show_heap_memory_stats"
+            const val OVERRIDE_WS_MIN_HEAP_RES =    "devtools__override_word_suggestions_min_heap_restriction"
             const val CLEAR_UDM_INTERNAL_DATABASE = "devtools__clear_udm_internal_database"
         }
 
@@ -226,6 +212,9 @@ class Preferences(
         var showHeapMemoryStats: Boolean
             get() =  prefs.getPref(SHOW_HEAP_MEMORY_STATS, false)
             set(v) = prefs.setPref(SHOW_HEAP_MEMORY_STATS, v)
+        var overrideWordSuggestionsMinHeapRestriction: Boolean
+            get() =  prefs.getPref(OVERRIDE_WS_MIN_HEAP_RES, false)
+            set(v) = prefs.setPref(OVERRIDE_WS_MIN_HEAP_RES, v)
     }
 
     /**
@@ -329,6 +318,90 @@ class Preferences(
             set(v) = prefs.setPref(PREVIEW_REFRESH_DELAY, v)
     }
 
+    /**
+     * Wrapper class for internal preferences. A preference qualifies as an internal pref if the
+     * user has no ability to control this preference's value directly (via a UI pref view).
+     */
+    class InputFeedback(private val prefs: Preferences) {
+        companion object {
+            const val AUDIO_ENABLED =                       "input_feedback__audio_enabled"
+            const val AUDIO_IGNORE_SYSTEM_SETTINGS =        "input_feedback__audio_ignore_system_settings"
+            const val AUDIO_VOLUME =                        "input_feedback__audio_volume"
+            const val AUDIO_FEAT_KEY_PRESS =                "input_feedback__audio_feat_key_press"
+            const val AUDIO_FEAT_KEY_LONG_PRESS =           "input_feedback__audio_feat_key_long_press"
+            const val AUDIO_FEAT_KEY_REPEATED_ACTION =      "input_feedback__audio_feat_key_repeated_action"
+            const val AUDIO_FEAT_GESTURE_SWIPE =            "input_feedback__audio_feat_gesture_swipe"
+            const val AUDIO_FEAT_GESTURE_MOVING_SWIPE =     "input_feedback__audio_feat_gesture_moving_swipe"
+
+            const val HAPTIC_ENABLED =                      "input_feedback__haptic_enabled"
+            const val HAPTIC_IGNORE_SYSTEM_SETTINGS =       "input_feedback__haptic_ignore_system_settings"
+            const val HAPTIC_USE_VIBRATOR =                 "input_feedback__haptic_use_vibrator"
+            const val HAPTIC_VIBRATION_DURATION =           "input_feedback__haptic_vibration_duration"
+            const val HAPTIC_VIBRATION_STRENGTH =           "input_feedback__haptic_vibration_strength"
+            const val HAPTIC_FEAT_KEY_PRESS =               "input_feedback__haptic_feat_key_press"
+            const val HAPTIC_FEAT_KEY_LONG_PRESS =          "input_feedback__haptic_feat_key_long_press"
+            const val HAPTIC_FEAT_KEY_REPEATED_ACTION =     "input_feedback__haptic_feat_key_repeated_action"
+            const val HAPTIC_FEAT_GESTURE_SWIPE =           "input_feedback__haptic_feat_gesture_swipe"
+            const val HAPTIC_FEAT_GESTURE_MOVING_SWIPE =    "input_feedback__haptic_feat_gesture_moving_swipe"
+        }
+
+        var audioEnabled: Boolean
+            get() =  prefs.getPref(AUDIO_ENABLED, true)
+            set(v) = prefs.setPref(AUDIO_ENABLED, v)
+        var audioIgnoreSystemSettings: Boolean
+            get() =  prefs.getPref(AUDIO_IGNORE_SYSTEM_SETTINGS, false)
+            set(v) = prefs.setPref(AUDIO_IGNORE_SYSTEM_SETTINGS, v)
+        var audioVolume: Int
+            get() =  prefs.getPref(AUDIO_VOLUME, 50)
+            set(v) = prefs.setPref(AUDIO_VOLUME, v)
+        var audioFeatKeyPress: Boolean
+            get() =  prefs.getPref(AUDIO_FEAT_KEY_PRESS, true)
+            set(v) = prefs.setPref(AUDIO_FEAT_KEY_PRESS, v)
+        var audioFeatKeyLongPress: Boolean
+            get() =  prefs.getPref(AUDIO_FEAT_KEY_LONG_PRESS, false)
+            set(v) = prefs.setPref(AUDIO_FEAT_KEY_LONG_PRESS, v)
+        var audioFeatKeyRepeatedAction: Boolean
+            get() =  prefs.getPref(AUDIO_FEAT_KEY_REPEATED_ACTION, false)
+            set(v) = prefs.setPref(AUDIO_FEAT_KEY_REPEATED_ACTION, v)
+        var audioFeatGestureSwipe: Boolean
+            get() =  prefs.getPref(AUDIO_FEAT_GESTURE_SWIPE, false)
+            set(v) = prefs.setPref(AUDIO_FEAT_GESTURE_SWIPE, v)
+        var audioFeatGestureMovingSwipe: Boolean
+            get() =  prefs.getPref(AUDIO_FEAT_GESTURE_MOVING_SWIPE, false)
+            set(v) = prefs.setPref(AUDIO_FEAT_GESTURE_MOVING_SWIPE, v)
+
+        var hapticEnabled: Boolean
+            get() =  prefs.getPref(HAPTIC_ENABLED, true)
+            set(v) = prefs.setPref(HAPTIC_ENABLED, v)
+        var hapticIgnoreSystemSettings: Boolean
+            get() =  prefs.getPref(HAPTIC_IGNORE_SYSTEM_SETTINGS, false)
+            set(v) = prefs.setPref(HAPTIC_IGNORE_SYSTEM_SETTINGS, v)
+        var hapticUseVibrator: Boolean
+            get() =  prefs.getPref(HAPTIC_USE_VIBRATOR, true)
+            set(v) = prefs.setPref(HAPTIC_USE_VIBRATOR, v)
+        var hapticVibrationDuration: Int
+            get() =  prefs.getPref(HAPTIC_VIBRATION_DURATION, 50)
+            set(v) = prefs.setPref(HAPTIC_VIBRATION_DURATION, v)
+        var hapticVibrationStrength: Int
+            get() =  prefs.getPref(HAPTIC_VIBRATION_STRENGTH, 50)
+            set(v) = prefs.setPref(HAPTIC_VIBRATION_STRENGTH, v)
+        var hapticFeatKeyPress: Boolean
+            get() =  prefs.getPref(HAPTIC_FEAT_KEY_PRESS, true)
+            set(v) = prefs.setPref(HAPTIC_FEAT_KEY_PRESS, v)
+        var hapticFeatKeyLongPress: Boolean
+            get() =  prefs.getPref(HAPTIC_FEAT_KEY_LONG_PRESS, false)
+            set(v) = prefs.setPref(HAPTIC_FEAT_KEY_LONG_PRESS, v)
+        var hapticFeatKeyRepeatedAction: Boolean
+            get() =  prefs.getPref(HAPTIC_FEAT_KEY_REPEATED_ACTION, true)
+            set(v) = prefs.setPref(HAPTIC_FEAT_KEY_REPEATED_ACTION, v)
+        var hapticFeatGestureSwipe: Boolean
+            get() =  prefs.getPref(HAPTIC_FEAT_GESTURE_SWIPE, false)
+            set(v) = prefs.setPref(HAPTIC_FEAT_GESTURE_SWIPE, v)
+        var hapticFeatGestureMovingSwipe: Boolean
+            get() =  prefs.getPref(HAPTIC_FEAT_GESTURE_MOVING_SWIPE, true)
+            set(v) = prefs.setPref(HAPTIC_FEAT_GESTURE_MOVING_SWIPE, v)
+    }
+
     /**
      * Wrapper class for internal preferences. A preference qualifies as an internal pref if the
      * user has no ability to control this preference's value directly (via a UI pref view).
@@ -377,14 +450,9 @@ class Preferences(
             const val ONE_HANDED_MODE =                     "keyboard__one_handed_mode"
             const val ONE_HANDED_MODE_SCALE_FACTOR =        "keyboard__one_handed_mode_scale_factor"
             const val POPUP_ENABLED =                       "keyboard__popup_enabled"
-            const val SOUND_ENABLED =                       "keyboard__sound_enabled"
-            const val SOUND_VOLUME =                        "keyboard__sound_volume"
             const val SPACE_BAR_SWITCHES_TO_CHARACTERS =    "keyboard__space_bar_switches_to_characters"
             const val UTILITY_KEY_ACTION =                  "keyboard__utility_key_action"
             const val UTILITY_KEY_ENABLED =                 "keyboard__utility_key_enabled"
-            const val VIBRATION_ENABLED =                   "keyboard__vibration_enabled"
-            const val VIBRATION_DURATION =                  "keyboard__vibration_duration"
-            const val VIBRATION_STRENGTH =                  "keyboard__vibration_strength"
         }
 
         var bottomOffsetPortrait: Int = 0
@@ -438,13 +506,6 @@ class Preferences(
         var popupEnabled: Boolean = false
             get() = prefs.getPref(POPUP_ENABLED, true)
             private set
-        var soundEnabled: Boolean = false
-            get() = prefs.getPref(SOUND_ENABLED, true)
-            private set
-        var soundEnabledSystem: Boolean = false
-        var soundVolume: Int = 0
-            get() = prefs.getPref(SOUND_VOLUME, -1)
-            private set
         var spaceBarSwitchesToCharacters: Boolean
             get() =  prefs.getPref(SPACE_BAR_SWITCHES_TO_CHARACTERS, true)
             set(v) = prefs.setPref(SPACE_BAR_SWITCHES_TO_CHARACTERS, v)
@@ -454,16 +515,6 @@ class Preferences(
         var utilityKeyEnabled: Boolean
             get() =  prefs.getPref(UTILITY_KEY_ENABLED, true)
             set(v) = prefs.setPref(UTILITY_KEY_ENABLED, v)
-        var vibrationEnabled: Boolean = false
-            get() = prefs.getPref(VIBRATION_ENABLED, true)
-            private set
-        var vibrationEnabledSystem: Boolean = false
-        var vibrationDuration: Int = 0
-            get() = prefs.getPref(VIBRATION_DURATION, -1)
-            private set
-        var vibrationStrength: Int = 0
-            get() = prefs.getPref(VIBRATION_STRENGTH, -1)
-            private set
 
         fun keyHintConfiguration(): KeyHintConfiguration {
             return KeyHintConfiguration(hintedSymbolsMode, hintedNumberRowMode, mergeHintPopupsEnabled)

app/src/main/java/dev/patrickgold/florisboard/ime/core/Subtype.kt

@@ -16,16 +16,10 @@
 
 package dev.patrickgold.florisboard.ime.core
 
+import dev.patrickgold.florisboard.common.FlorisLocale
 import dev.patrickgold.florisboard.ime.text.composing.Appender
-import dev.patrickgold.florisboard.ime.text.composing.Composer
 import dev.patrickgold.florisboard.ime.text.layout.LayoutType
-import dev.patrickgold.florisboard.util.LocaleUtils
 import kotlinx.serialization.*
-import kotlinx.serialization.descriptors.PrimitiveKind
-import kotlinx.serialization.descriptors.PrimitiveSerialDescriptor
-import kotlinx.serialization.descriptors.SerialDescriptor
-import kotlinx.serialization.encoding.Decoder
-import kotlinx.serialization.encoding.Encoder
 import java.util.*
 
 /**
@@ -40,7 +34,7 @@ import java.util.*
  */
 data class Subtype(
     val id: Int,
-    val locale: Locale,
+    val locale: FlorisLocale,
     val composerName: String,
     val currencySetName: String,
     val layoutMap: SubtypeLayoutMap,
@@ -53,7 +47,7 @@ data class Subtype(
          */
         val DEFAULT = Subtype(
             id = -1,
-            locale = Locale.ENGLISH,
+            locale = FlorisLocale.ENGLISH,
             composerName = Appender.name,
             currencySetName = "\$default",
             layoutMap = SubtypeLayoutMap(characters = "qwerty")
@@ -74,7 +68,7 @@ data class Subtype(
             val data = str.split("/")
             when (data.size) {
                 4 -> {
-                    val locale = LocaleUtils.stringToLocale(data[1])
+                    val locale = FlorisLocale.fromTag(data[1])
                     return Subtype(
                         data[0].toInt(),
                         locale,
@@ -84,7 +78,7 @@ data class Subtype(
                     )
                 }
                 5 -> {
-                    val locale = LocaleUtils.stringToLocale(data[1])
+                    val locale = FlorisLocale.fromTag(data[1])
                     return Subtype(
                         data[0].toInt(),
                         locale,
@@ -114,7 +108,7 @@ data class Subtype(
      *  <id>/<language_tag>/<composer_name>/<currency_set_name>/<layout_map>
      */
     override fun toString(): String {
-        val languageTag = locale.toLanguageTag()
+        val languageTag = locale.languageTag()
         return "$id/$languageTag/$composerName/$currencySetName/$layoutMap"
     }
 
@@ -123,7 +117,7 @@ data class Subtype(
      *  <id>/<language_tag>/<currency_set_name>
      */
     fun toShortString(): String {
-        val languageTag = locale.toLanguageTag()
+        val languageTag = locale.languageTag()
         return "$id/$languageTag/$currencySetName"
     }
 
@@ -326,24 +320,12 @@ data class SubtypeLayoutMap(
 @Serializable
 data class DefaultSubtype(
     var id: Int,
-    @Serializable(with = LocaleSerializer::class)
+    @Serializable(with = FlorisLocale.Serializer::class)
     @SerialName("languageTag")
-    var locale: Locale,
+    var locale: FlorisLocale,
     @SerialName("composer")
     var composerName: String,
     @SerialName("currencySet")
     var currencySetName: String,
     var preferred: SubtypeLayoutMap
 )
-
-class LocaleSerializer : KSerializer<Locale> {
-    override val descriptor: SerialDescriptor = PrimitiveSerialDescriptor("Locale", PrimitiveKind.STRING)
-
-    override fun serialize(encoder: Encoder, value: Locale) {
-        encoder.encodeString(value.toString())
-    }
-
-    override fun deserialize(decoder: Decoder): Locale {
-        return LocaleUtils.stringToLocale(decoder.decodeString())
-    }
-}

app/src/main/java/dev/patrickgold/florisboard/ime/core/SubtypeManager.kt

@@ -17,14 +17,13 @@
 package dev.patrickgold.florisboard.ime.core
 
 import android.content.Context
+import dev.patrickgold.florisboard.common.FlorisLocale
 import dev.patrickgold.florisboard.debug.*
 import dev.patrickgold.florisboard.res.AssetManager
-import dev.patrickgold.florisboard.res.AssetRef
-import dev.patrickgold.florisboard.res.AssetSource
 import dev.patrickgold.florisboard.ime.text.key.CurrencySet
+import dev.patrickgold.florisboard.res.FlorisRef
 import kotlinx.coroutines.CoroutineScope
 import kotlinx.coroutines.MainScope
-import java.util.*
 import kotlin.collections.ArrayList
 
 /**
@@ -85,7 +84,7 @@ class SubtypeManager(
      * @return The [FlorisBoard.ImeConfig] or a default config.
      */
     private fun loadImeConfig(path: String): FlorisBoard.ImeConfig {
-        return assetManager.loadJsonAsset<FlorisBoard.ImeConfig>(AssetRef(AssetSource.Assets, path)).getOrElse {
+        return assetManager.loadJsonAsset<FlorisBoard.ImeConfig>(FlorisRef.assets(path)).getOrElse {
             flogError(LogTopic.SUBTYPE_MANAGER) { "Failed to retrieve IME config: $it" }
             FlorisBoard.ImeConfig(packageName)
         }
@@ -118,7 +117,7 @@ class SubtypeManager(
      * @return True if the subtype was added, false otherwise. A return value of false indicates
      *  that the subtype already exists.
      */
-    fun addSubtype(locale: Locale, composerName: String, currencySetName: String, layoutMap: SubtypeLayoutMap): Boolean {
+    fun addSubtype(locale: FlorisLocale, composerName: String, currencySetName: String, layoutMap: SubtypeLayoutMap): Boolean {
         return addSubtype(
             Subtype(
                 (locale.hashCode() + 31 * layoutMap.hashCode() + 31 * currencySetName.hashCode()),
@@ -186,7 +185,7 @@ class SubtypeManager(
      * @return The default system locale or null, if no matching default system subtype could be
      *  found.
      */
-    fun getDefaultSubtypeForLocale(locale: Locale): DefaultSubtype? {
+    fun getDefaultSubtypeForLocale(locale: FlorisLocale): DefaultSubtype? {
         for (defaultSubtype in imeConfig.defaultSubtypes) {
             if (defaultSubtype.locale == locale) {
                 return defaultSubtype

app/src/main/java/dev/patrickgold/florisboard/ime/core/TextProcessor.kt

@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) 2021 Patrick Goldinger
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package dev.patrickgold.florisboard.ime.core
+
+import dev.patrickgold.florisboard.common.FlorisLocale
+
+@Suppress("RegExpRedundantEscape")
+object TextProcessor {
+    private val LATIN_BASIC_WORD_REGEX = """[_]*(([\p{L}\d\']+[_-]*[\p{L}\d\']+)|[\p{L}\d\']+)[_]*""".toRegex()
+
+    private fun wordRegexFor(locale: FlorisLocale): Regex {
+        return when (locale) {
+            else -> LATIN_BASIC_WORD_REGEX
+        }
+    }
+
+    fun detectWords(text: CharSequence, locale: FlorisLocale): Sequence<IntRange> {
+        val regex = wordRegexFor(locale)
+        return regex.findAll(text).map { it.range }
+    }
+
+    fun detectWords(text: CharSequence, start: Int, end: Int, locale: FlorisLocale): Sequence<IntRange> {
+        val regex = wordRegexFor(locale)
+        val tStart = start.coerceAtLeast(0)
+        val tEnd = end.coerceAtMost(text.length)
+        return regex.findAll(text.slice(tStart..tEnd)).map { it.range }
+    }
+
+    fun isWord(text: CharSequence, locale: FlorisLocale): Boolean {
+        val regex = wordRegexFor(locale)
+        return regex.matches(text)
+    }
+}

app/src/main/java/dev/patrickgold/florisboard/ime/dictionary/DictionaryManager.kt

@@ -18,15 +18,16 @@ package dev.patrickgold.florisboard.ime.dictionary
 
 import android.content.Context
 import androidx.room.Room
-import dev.patrickgold.florisboard.ime.core.FlorisBoard
+import dev.patrickgold.florisboard.common.FlorisLocale
+import dev.patrickgold.florisboard.debug.flogError
 import dev.patrickgold.florisboard.ime.core.Preferences
 import dev.patrickgold.florisboard.ime.core.Subtype
 import dev.patrickgold.florisboard.ime.nlp.SuggestionList
 import dev.patrickgold.florisboard.ime.nlp.Word
+import dev.patrickgold.florisboard.res.FlorisRef
 import kotlinx.coroutines.CoroutineDispatcher
 import kotlinx.coroutines.Dispatchers
 import java.lang.ref.WeakReference
-import java.util.*
 
 /**
  * TODO: document
@@ -44,6 +45,8 @@ class DictionaryManager private constructor(
     private var systemUserDictionaryDatabase: SystemUserDictionaryDatabase? = null
 
     companion object {
+        val FLORIS_EN_REF = FlorisRef.assets("ime/dict/en.flict")
+
         private var defaultInstance: DictionaryManager? = null
 
         fun init(applicationContext: Context): DictionaryManager {
@@ -74,15 +77,39 @@ class DictionaryManager private constructor(
     ) {
         val suggestions = SuggestionList.new(maxSuggestionCount)
         queryUserDictionary(currentWord, subtype.locale, suggestions)
+        loadDictionary(FLORIS_EN_REF).onSuccess {
+            it.getTokenPredictions(preceidingWords, currentWord, maxSuggestionCount, allowPossiblyOffensive, suggestions)
+        }
         block(suggestions)
         suggestions.dispose()
     }
 
-    fun prepareDictionaries(subtype: Subtype) {
-        // TODO: Implement this
+    fun loadDictionary(ref: FlorisRef): Result<Dictionary> {
+        dictionaryCache[ref.toString()]?.let {
+            return Result.success(it)
+        }
+        if (ref.relativePath.endsWith(".flict")) {
+            // Assume this is a Flictionary
+            applicationContext.get()?.let {
+                Flictionary.load(it, ref).onSuccess { flict ->
+                    dictionaryCache[ref.toString()] = flict
+                    return Result.success(flict)
+                }.onFailure { err ->
+                    flogError { err.toString() }
+                    return Result.failure(err)
+                }
+            }
+        } else {
+            return Result.failure(Exception("Unable to determine supported type for given AssetRef!"))
+        }
+        return Result.failure(Exception("If this message is ever thrown, something is completely broken..."))
     }
 
-    fun queryUserDictionary(word: Word, locale: Locale, destSuggestionList: SuggestionList) {
+    fun prepareDictionaries(subtype: Subtype) {
+        loadDictionary(FLORIS_EN_REF)
+    }
+
+    fun queryUserDictionary(word: Word, locale: FlorisLocale, destSuggestionList: SuggestionList) {
         val florisDao = florisUserDictionaryDao()
         val systemDao = systemUserDictionaryDao()
         if (florisDao == null && systemDao == null) {
@@ -114,7 +141,7 @@ class DictionaryManager private constructor(
         }
     }
 
-    fun spell(word: Word, locale: Locale): Boolean {
+    fun spell(word: Word, locale: FlorisLocale): Boolean {
         val florisDao = florisUserDictionaryDao()
         val systemDao = systemUserDictionaryDao()
         if (florisDao == null && systemDao == null) {

app/src/main/java/dev/patrickgold/florisboard/ime/dictionary/Flictionary.kt

@@ -16,7 +16,10 @@
 
 package dev.patrickgold.florisboard.ime.dictionary
 
+import android.content.Context
 import dev.patrickgold.florisboard.ime.nlp.*
+import dev.patrickgold.florisboard.res.FlorisRef
+import java.io.InputStream
 
 /**
  * Class Flictionary which takes care of loading the binary asset as well as providing words for
@@ -25,14 +28,14 @@ import dev.patrickgold.florisboard.ime.nlp.*
  * This class accepts binary dictionary files of the type "flict" as defined in here:
  * https://github.com/florisboard/dictionary-tools/blob/main/flictionary.md
  */
-/**
 class Flictionary private constructor(
     override val name: String,
     override val label: String,
     override val authors: List<String>,
     private val date: Long,
     private val version: Int,
-    private val headerStr: String
+    private val headerStr: String,
+    private val languageModel: FlorisLanguageModel
 ) : Dictionary {
     companion object {
         private const val VERSION_0 =                           0x0
@@ -63,11 +66,11 @@ class Flictionary private constructor(
          * either the parsed dictionary or an exception giving information about the error which
          * occurred.
          */
-        fun load(context: Context, assetRef: AssetRef): Result<Flictionary> {
+        fun load(context: Context, assetRef: FlorisRef): Result<Flictionary> {
             val buffer = ByteArray(5000) { 0 }
             val inputStream: InputStream
-            if (assetRef.source == AssetSource.Assets) {
-                inputStream = context.assets.open(assetRef.path)
+            if (assetRef.isAssets) {
+                inputStream = context.assets.open(assetRef.relativePath)
             } else {
                 return Result.failure(Exception("Only AssetSource.Assets is currently supported!"))
             }
@@ -291,26 +294,25 @@ class Flictionary private constructor(
 
     // TODO: preceding tokens are currently ignored
     override fun getTokenPredictions(
-        precedingTokens: List<Token<String>>,
-        currentToken: Token<String>?,
+        precedingTokens: List<Word>,
+        currentToken: Word?,
         maxSuggestionCount: Int,
-        allowPossiblyOffensive: Boolean
-    ): List<WeightedToken<String, Int>> {
-        currentToken ?: return listOf()
+        allowPossiblyOffensive: Boolean,
+        destSuggestionList: SuggestionList
+    ) {
+        currentToken ?: return
 
-        return if (currentToken.data.isNotEmpty()) {
+        if (currentToken.isNotBlank()) {
             val retList = languageModel.matchAllNgrams(
                 ngram = Ngram(
-                    _tokens = listOf(Token(currentToken.data.lowercase())),
+                    _tokens = listOf(Token(currentToken.lowercase())),
                     _freq = -1
                 ),
                 maxEditDistance = 2,
                 maxTokenCount = maxSuggestionCount,
                 allowPossiblyOffensive = allowPossiblyOffensive
             )
-            retList
-        } else {
-            listOf()
+            retList.forEach { destSuggestionList.add(it.data, 128) }
         }
     }
 
@@ -422,4 +424,3 @@ fun InputStream.readNext(b: ByteArray, off: Int, len: Int): Int {
     }
     return lenRead
 }
-*/

app/src/main/java/dev/patrickgold/florisboard/ime/dictionary/UserDictionary.kt

@@ -33,10 +33,9 @@ import androidx.room.RoomDatabase
 import androidx.room.TypeConverter
 import androidx.room.TypeConverters
 import androidx.room.Update
+import dev.patrickgold.florisboard.common.FlorisLocale
 import dev.patrickgold.florisboard.res.ExternalContentUtils
-import dev.patrickgold.florisboard.util.LocaleUtils
 import java.lang.ref.WeakReference
-import java.util.*
 
 private const val WORDS_TABLE = "words"
 
@@ -89,31 +88,31 @@ interface UserDictionaryDao {
     fun query(word: String): List<UserDictionaryEntry>
 
     @Query("$SELECT_ALL_FROM_WORDS WHERE ${UserDictionary.Words.WORD} LIKE '%' || :word || '%' AND $LOCALE_MATCHES")
-    fun query(word: String, locale: Locale?): List<UserDictionaryEntry>
+    fun query(word: String, locale: FlorisLocale?): List<UserDictionaryEntry>
 
     @Query("$SELECT_ALL_FROM_WORDS WHERE ${UserDictionary.Words.SHORTCUT} = :shortcut")
     fun queryShortcut(shortcut: String): List<UserDictionaryEntry>
 
     @Query("$SELECT_ALL_FROM_WORDS WHERE ${UserDictionary.Words.SHORTCUT} = :shortcut AND $LOCALE_MATCHES")
-    fun queryShortcut(shortcut: String, locale: Locale?): List<UserDictionaryEntry>
+    fun queryShortcut(shortcut: String, locale: FlorisLocale?): List<UserDictionaryEntry>
 
     @Query(SELECT_ALL_FROM_WORDS)
     fun queryAll(): List<UserDictionaryEntry>
 
     @Query("$SELECT_ALL_FROM_WORDS WHERE (${UserDictionary.Words.LOCALE} = :locale AND :locale IS NOT NULL) OR (${UserDictionary.Words.LOCALE} IS NULL AND :locale IS NULL)")
-    fun queryAll(locale: Locale?): List<UserDictionaryEntry>
+    fun queryAll(locale: FlorisLocale?): List<UserDictionaryEntry>
 
     @Query("$SELECT_ALL_FROM_WORDS WHERE ${UserDictionary.Words.WORD} = :word")
     fun queryExact(word: String): List<UserDictionaryEntry>
 
     @Query("$SELECT_ALL_FROM_WORDS WHERE ${UserDictionary.Words.WORD} = :word AND (${UserDictionary.Words.LOCALE} = :locale OR (${UserDictionary.Words.LOCALE} IS NULL AND :locale IS NULL))")
-    fun queryExact(word: String, locale: Locale?): List<UserDictionaryEntry>
+    fun queryExact(word: String, locale: FlorisLocale?): List<UserDictionaryEntry>
 
     @Query("$SELECT_ALL_FROM_WORDS WHERE ${UserDictionary.Words.WORD} = :word AND $LOCALE_MATCHES")
-    fun queryExactFuzzyLocale(word: String, locale: Locale?): List<UserDictionaryEntry>
+    fun queryExactFuzzyLocale(word: String, locale: FlorisLocale?): List<UserDictionaryEntry>
 
     @Query("SELECT DISTINCT ${UserDictionary.Words.LOCALE} FROM $WORDS_TABLE")
-    fun queryLanguageList(): List<Locale?>
+    fun queryLanguageList(): List<FlorisLocale?>
 
     @Insert
     fun insert(entry: UserDictionaryEntry)
@@ -165,7 +164,7 @@ interface UserDictionaryDatabase {
                     }
                     if (word != null && freq != null) {
                         val alreadyExistingEntries = userDictionaryDao().queryExact(
-                            word!!, locale?.let { LocaleUtils.stringToLocale(it) }
+                            word!!, locale?.let { FlorisLocale.fromTag(it) }
                         )
                         if (alreadyExistingEntries.isNotEmpty()) {
                             userDictionaryDao().update(UserDictionaryEntry(alreadyExistingEntries[0].id, word!!, freq!!, locale, shortcut))
@@ -226,18 +225,18 @@ abstract class FlorisUserDictionaryDatabase : RoomDatabase(), UserDictionaryData
 
     class Converters {
         @TypeConverter
-        fun localeToString(locale: Locale?): String? {
+        fun localeToString(locale: FlorisLocale?): String? {
             return when (locale) {
                 null -> null
-                else -> locale.toString()
+                else -> locale.localeTag()
             }
         }
 
         @TypeConverter
-        fun stringToLocale(string: String?): Locale? {
+        fun stringToLocale(string: String?): FlorisLocale? {
             return when (string) {
                 null, "all", "null", "" -> null
-                else -> LocaleUtils.stringToLocale(string)
+                else -> FlorisLocale.fromTag(string)
             }
         }
     }
@@ -255,7 +254,7 @@ class SystemUserDictionaryDatabase(context: Context) : UserDictionaryDatabase {
             )
         }
 
-        override fun query(word: String, locale: Locale?): List<UserDictionaryEntry> {
+        override fun query(word: String, locale: FlorisLocale?): List<UserDictionaryEntry> {
             return if (locale == null) {
                 queryResolver(
                     selection = "${UserDictionary.Words.WORD} LIKE ? AND ${UserDictionary.Words.LOCALE} IS NULL",
@@ -265,7 +264,7 @@ class SystemUserDictionaryDatabase(context: Context) : UserDictionaryDatabase {
             } else {
                 queryResolver(
                     selection = "${UserDictionary.Words.WORD} LIKE ? AND (${UserDictionary.Words.LOCALE} = ? OR ${UserDictionary.Words.LOCALE} = ? OR ${UserDictionary.Words.LOCALE} IS NULL)",
-                    selectionArgs = arrayOf("%$word%", locale.toString(), locale.language.toString()),
+                    selectionArgs = arrayOf("%$word%", locale.localeTag(), locale.language),
                     sortOrder = SORT_BY_FREQ_DESC,
                 )
             }
@@ -279,7 +278,7 @@ class SystemUserDictionaryDatabase(context: Context) : UserDictionaryDatabase {
             )
         }
 
-        override fun queryShortcut(shortcut: String, locale: Locale?): List<UserDictionaryEntry> {
+        override fun queryShortcut(shortcut: String, locale: FlorisLocale?): List<UserDictionaryEntry> {
             return if (locale == null) {
                 queryResolver(
                     selection = "${UserDictionary.Words.SHORTCUT} = ? AND ${UserDictionary.Words.LOCALE} IS NULL",
@@ -289,7 +288,7 @@ class SystemUserDictionaryDatabase(context: Context) : UserDictionaryDatabase {
             } else {
                 queryResolver(
                     selection = "${UserDictionary.Words.SHORTCUT} = ? AND (${UserDictionary.Words.LOCALE} = ? OR ${UserDictionary.Words.LOCALE} = ? OR ${UserDictionary.Words.LOCALE} IS NULL)",
-                    selectionArgs = arrayOf(shortcut, locale.toString(), locale.language.toString()),
+                    selectionArgs = arrayOf(shortcut, locale.localeTag(), locale.language),
                     sortOrder = SORT_BY_FREQ_DESC,
                 )
             }
@@ -303,7 +302,7 @@ class SystemUserDictionaryDatabase(context: Context) : UserDictionaryDatabase {
             )
         }
 
-        override fun queryAll(locale: Locale?): List<UserDictionaryEntry> {
+        override fun queryAll(locale: FlorisLocale?): List<UserDictionaryEntry> {
             return if (locale == null) {
                 queryResolver(
                     selection = "${UserDictionary.Words.LOCALE} IS NULL",
@@ -313,7 +312,7 @@ class SystemUserDictionaryDatabase(context: Context) : UserDictionaryDatabase {
             } else {
                 queryResolver(
                     selection = "${UserDictionary.Words.LOCALE} = ?",
-                    selectionArgs = arrayOf(locale.toString()),
+                    selectionArgs = arrayOf(locale.localeTag()),
                     sortOrder = SORT_BY_FREQ_DESC,
                 )
             }
@@ -327,7 +326,7 @@ class SystemUserDictionaryDatabase(context: Context) : UserDictionaryDatabase {
             )
         }
 
-        override fun queryExact(word: String, locale: Locale?): List<UserDictionaryEntry> {
+        override fun queryExact(word: String, locale: FlorisLocale?): List<UserDictionaryEntry> {
             return if (locale == null) {
                 queryResolver(
                     selection = "${UserDictionary.Words.WORD} = ? AND ${UserDictionary.Words.LOCALE} IS NULL",
@@ -337,13 +336,13 @@ class SystemUserDictionaryDatabase(context: Context) : UserDictionaryDatabase {
             } else {
                 queryResolver(
                     selection = "${UserDictionary.Words.WORD} = ? AND ${UserDictionary.Words.LOCALE} = ?",
-                    selectionArgs = arrayOf(word, locale.toString()),
+                    selectionArgs = arrayOf(word, locale.localeTag()),
                     sortOrder = SORT_BY_FREQ_DESC,
                 )
             }
         }
 
-        override fun queryExactFuzzyLocale(word: String, locale: Locale?): List<UserDictionaryEntry> {
+        override fun queryExactFuzzyLocale(word: String, locale: FlorisLocale?): List<UserDictionaryEntry> {
             return if (locale == null) {
                 queryResolver(
                     selection = "${UserDictionary.Words.WORD} = ? AND ${UserDictionary.Words.LOCALE} IS NULL",
@@ -353,13 +352,13 @@ class SystemUserDictionaryDatabase(context: Context) : UserDictionaryDatabase {
             } else {
                 queryResolver(
                     selection = "${UserDictionary.Words.WORD} = ? AND (${UserDictionary.Words.LOCALE} = ? OR ${UserDictionary.Words.LOCALE} IS NULL)",
-                    selectionArgs = arrayOf(word, locale.toString()),
+                    selectionArgs = arrayOf(word, locale.localeTag()),
                     sortOrder = SORT_BY_FREQ_DESC,
                 )
             }
         }
 
-        override fun queryLanguageList(): List<Locale?> {
+        override fun queryLanguageList(): List<FlorisLocale?> {
             val resolver = applicationContext.get()?.contentResolver ?: return listOf()
             val cursor = resolver.query(
                 UserDictionary.Words.CONTENT_URI,
@@ -372,13 +371,13 @@ class SystemUserDictionaryDatabase(context: Context) : UserDictionaryDatabase {
                 return listOf()
             }
             val localeIndex = cursor.getColumnIndex(UserDictionary.Words.LOCALE)
-            val retList = mutableSetOf<Locale?>()
+            val retList = mutableSetOf<FlorisLocale?>()
             while (cursor.moveToNext()) {
                 val localeStr = cursor.getString(localeIndex)
                 if (localeStr == null) {
                     retList.add(null)
                 } else {
-                    retList.add(LocaleUtils.stringToLocale(localeStr))
+                    retList.add(FlorisLocale.fromTag(localeStr))
                 }
             }
             cursor.close()

app/src/main/java/dev/patrickgold/florisboard/ime/dictionary/temp_suggestion_code.kt

@@ -0,0 +1,441 @@
+/*
+ * Copyright (C) 2021 Patrick Goldinger
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package dev.patrickgold.florisboard.ime.dictionary
+
+import dev.patrickgold.florisboard.ime.nlp.SuggestionList
+
+/*
+ * ====================== IMPORTANT ========================
+ *
+ * All code in this file is only temporary added back in so the stable track has suggestions again.
+ * In 0.3.15 a renewed suggestion algorithm will be built and this mess will be removed!
+ *
+ * ==========================================================
+ */
+
+/**
+ * Abstract interface representing a n-gram of tokens. Each n-gram instance can be assigned a
+ * unique frequency [freq].
+ */
+open class Ngram<T : Any, F : Comparable<F>>(_tokens: List<Token<T>>, _freq: F) {
+    companion object {
+        /** Constant order value for unigrams. */
+        const val ORDER_UNIGRAM: Int = 1
+
+        /** Constant order value for bigrams. */
+        const val ORDER_BIGRAM: Int = 2
+
+        /** Constant order value for trigrams. */
+        const val ORDER_TRIGRAM: Int = 3
+    }
+
+    init {
+        if (_tokens.size < ORDER_UNIGRAM) {
+            throw Exception("A n-gram must contain at least 1 token!")
+        }
+    }
+
+    /**
+     * A list of tokens for this n-gram. The length of this list is guaranteed to be matching
+     * [order].
+     */
+    val tokens: List<Token<T>> = _tokens
+
+    /**
+     * The frequency value of this n-gram.
+     */
+    val freq: F = _freq
+
+    /**
+     * The order of this n-gram (1, 2, 3, ...).
+     */
+    val order: Int
+        get() = tokens.size
+}
+
+/**
+ * Abstract interface representing a token used in [Ngram].
+ */
+open class Token<T : Any>(_data: T) {
+    /**
+     * The data of this token.
+     */
+    val data: T = _data
+
+    override fun toString(): String {
+        return "Token(\"$data\")"
+    }
+
+    override fun hashCode(): Int {
+        return data.hashCode()
+    }
+
+    override fun equals(other: Any?): Boolean {
+        if (this === other) return true
+        if (javaClass != other?.javaClass) return false
+
+        other as Token<*>
+
+        if (data != other.data) return false
+
+        return true
+    }
+}
+
+/**
+ * Converts a list of tokens carrying [CharSequence] data to a list of [CharSequence].
+ */
+fun List<Token<CharSequence>>.toCharSequenceList(): List<CharSequence> {
+    return this.map { it.data }
+}
+
+/**
+ * Converts a list of tokens carrying [String] data to a list of [String].
+ */
+fun List<Token<String>>.toStringList(): List<String> {
+    return this.map { it.data }
+}
+
+/**
+ * Abstract interface for a language model. Can house any n-grams with a minimum order of one.
+ */
+interface LanguageModel<T : Any, F : Comparable<F>> {
+    /**
+     * Tries to get the n-gram for the passed [tokens]. Throws a NPE if no match could be found.
+     */
+    @Throws(NullPointerException::class)
+    fun getNgram(vararg tokens: T): Ngram<T, F>
+
+    /**
+     * Tries to get the n-gram for the passed [ngram], whereas the frequency is ignored while
+     * searching. Throws a NPE if no match could be found.
+     */
+    @Throws(NullPointerException::class)
+    fun getNgram(ngram: Ngram<T, F>): Ngram<T, F>
+
+    /**
+     * Tries to get the n-gram for the passed [tokens]. Returns null if no match could be found.
+     */
+    fun getNgramOrNull(vararg tokens: T): Ngram<T, F>?
+
+    /**
+     * Tries to get the n-gram for the passed [ngram], whereas the frequency is ignored while
+     * searching. Returns null if no match could be found.
+     */
+    fun getNgramOrNull(ngram: Ngram<T, F>): Ngram<T, F>?
+
+    /**
+     * Checks if a given [ngram] exists within this model. If [doMatchFreq] is set to true, the
+     * frequency is also matched.
+     */
+    fun hasNgram(ngram: Ngram<T, F>, doMatchFreq: Boolean = false): Boolean
+
+    /**
+     * Matches all n-grams which match the given [ngram], whereas the last item in the n-gram is
+     * is used to search for predictions.
+     */
+    fun matchAllNgrams(
+        ngram: Ngram<T, F>,
+        maxEditDistance: Int,
+        maxTokenCount: Int,
+        allowPossiblyOffensive: Boolean
+    ): List<Token<T>>
+}
+
+/**
+ * Mutable version of [LanguageModel].
+ */
+interface MutableLanguageModel<T : Any, F : Comparable<F>> : LanguageModel<T, F> {
+    fun deleteNgram(ngram: Ngram<T, F>)
+
+    fun insertNgram(ngram: Ngram<T, F>)
+
+    fun updateNgram(ngram: Ngram<T, F>)
+}
+
+/**
+ * Represents the root node to a n-gram tree.
+ */
+open class NgramTree(
+    sameOrderChildren: MutableList<NgramNode> = mutableListOf(),
+    higherOrderChildren: MutableList<NgramNode> = mutableListOf()
+) : NgramNode(0, '?', -1, sameOrderChildren, higherOrderChildren)
+
+/**
+ * A node of a n-gram tree, which holds the character it represents, the corresponding frequency,
+ * a pre-computed string representing all parent characters and the current one as well as child
+ * nodes, one for the same order n-gram nodes and one for the higher order n-gram nodes.
+ */
+open class NgramNode(
+    val order: Int,
+    val char: Char,
+    val freq: Int,
+    val sameOrderChildren: MutableList<NgramNode> = mutableListOf(),
+    val higherOrderChildren: MutableList<NgramNode> = mutableListOf()
+) {
+    companion object {
+        const val FREQ_CHARACTER = -1
+        const val FREQ_WORD_MIN = 0
+        const val FREQ_WORD_MAX = 255
+        const val FREQ_WORD_FILLER = -2
+        const val FREQ_IS_POSSIBLY_OFFENSIVE = 0
+    }
+
+    val isCharacter: Boolean
+        get() = freq == FREQ_CHARACTER
+
+    val isWord: Boolean
+        get() = freq in FREQ_WORD_MIN..FREQ_WORD_MAX
+
+    val isWordFiller: Boolean
+        get() = freq == FREQ_WORD_FILLER
+
+    val isPossiblyOffensive: Boolean
+        get() = freq == FREQ_IS_POSSIBLY_OFFENSIVE
+
+    fun findWord(word: String): NgramNode? {
+        var currentNode = this
+        for ((pos, char) in word.withIndex()) {
+            val childNode = if (pos == 0) {
+                currentNode.higherOrderChildren.find { it.char == char }
+            } else {
+                currentNode.sameOrderChildren.find { it.char == char }
+            }
+            if (childNode != null) {
+                currentNode = childNode
+            } else {
+                return null
+            }
+        }
+        return if (currentNode.isWord || currentNode.isWordFiller) {
+            currentNode
+        } else {
+            null
+        }
+    }
+
+    /**
+     * This function allows to search for a given [input] word with a given [maxEditDistance] and
+     * adds all matches in the trie to the [list].
+     */
+    fun listSimilarWords(
+        input: String,
+        list: SuggestionList,
+        word: StringBuilder,
+        allowPossiblyOffensive: Boolean,
+        maxEditDistance: Int,
+        deletionCost: Int = 0,
+        insertionCost: Int = 0,
+        substitutionCost: Int = 0,
+        pos: Int = -1
+    ) {
+        if (pos > -1) {
+            word.append(char)
+        }
+        val costSum = deletionCost + insertionCost + substitutionCost
+        if (pos > -1 && (pos + 1 == input.length) && isWord && ((isPossiblyOffensive && allowPossiblyOffensive)
+                || !isPossiblyOffensive)) {
+            // Using shift right instead of divide by 2^(costSum) as it is mathematically the
+            // same but faster.
+            list.add(word.toString(), freq shr costSum)
+        }
+        if (pos <= -1) {
+            for (childNode in higherOrderChildren) {
+                childNode.listSimilarWords(
+                    input, list, word, allowPossiblyOffensive, maxEditDistance, 0, 0, 0, 0
+                )
+            }
+        } else if (maxEditDistance == costSum) {
+            if (pos + 1 < input.length) {
+                sameOrderChildren.find { it.char == input[pos + 1] }?.listSimilarWords(
+                    input, list, word, allowPossiblyOffensive, maxEditDistance,
+                    deletionCost, insertionCost, substitutionCost, pos + 1
+                )
+            }
+        } else {
+            // Delete
+            if (pos + 2 < input.length) {
+                sameOrderChildren.find { it.char == input[pos + 2] }?.listSimilarWords(
+                    input, list, word, allowPossiblyOffensive, maxEditDistance,
+                    deletionCost + 1, insertionCost, substitutionCost, pos + 2
+                )
+            }
+            for (childNode in sameOrderChildren) {
+                if (pos + 1 < input.length && childNode.char == input[pos + 1]) {
+                    childNode.listSimilarWords(
+                        input, list, word, allowPossiblyOffensive, maxEditDistance,
+                        deletionCost, insertionCost, substitutionCost, pos + 1
+                    )
+                } else  {
+                    // Insert
+                    childNode.listSimilarWords(
+                        input, list, word, allowPossiblyOffensive, maxEditDistance,
+                        deletionCost, insertionCost + 1, substitutionCost, pos
+                    )
+                    if (pos + 1 < input.length) {
+                        // Substitute
+                        childNode.listSimilarWords(
+                            input, list, word, allowPossiblyOffensive, maxEditDistance,
+                            deletionCost, insertionCost, substitutionCost + 1, pos + 1
+                        )
+                    }
+                }
+            }
+        }
+        if (pos > -1) {
+            word.deleteAt(word.lastIndex)
+        }
+    }
+
+    fun listAllSameOrderWords(list: SuggestionList, word: StringBuilder, allowPossiblyOffensive: Boolean) {
+        word.append(char)
+        if (isWord && ((isPossiblyOffensive && allowPossiblyOffensive) || !isPossiblyOffensive)) {
+            list.add(word.toString(), freq)
+        }
+        for (childNode in sameOrderChildren) {
+            childNode.listAllSameOrderWords(list, word, allowPossiblyOffensive)
+        }
+        word.deleteAt(word.lastIndex)
+    }
+}
+
+open class FlorisLanguageModel(
+    initTreeObj: NgramTree? = null
+) : LanguageModel<String, Int> {
+    protected val ngramTree: NgramTree = initTreeObj ?: NgramTree()
+
+    override fun getNgram(vararg tokens: String): Ngram<String, Int> {
+        val ngramOut = getNgramOrNull(*tokens)
+        if (ngramOut != null) {
+            return ngramOut
+        } else {
+            throw NullPointerException("No n-gram found matching the given tokens: $tokens")
+        }
+    }
+
+    override fun getNgram(ngram: Ngram<String, Int>): Ngram<String, Int> {
+        val ngramOut = getNgramOrNull(ngram)
+        if (ngramOut != null) {
+            return ngramOut
+        } else {
+            throw NullPointerException("No n-gram found matching the given ngram: $ngram")
+        }
+    }
+
+    override fun getNgramOrNull(vararg tokens: String): Ngram<String, Int>? {
+        var currentNode: NgramNode = ngramTree
+        for (token in tokens) {
+            val childNode = currentNode.findWord(token)
+            if (childNode != null) {
+                currentNode = childNode
+            } else {
+                return null
+            }
+        }
+        return Ngram(tokens.toList().map { Token(it) }, currentNode.freq)
+    }
+
+    override fun getNgramOrNull(ngram: Ngram<String, Int>): Ngram<String, Int>? {
+        return getNgramOrNull(*ngram.tokens.toStringList().toTypedArray())
+    }
+
+    override fun hasNgram(ngram: Ngram<String, Int>, doMatchFreq: Boolean): Boolean {
+        val result = getNgramOrNull(ngram)
+        return if (result != null) {
+            if (doMatchFreq) {
+                ngram.freq == result.freq
+            } else {
+                true
+            }
+        } else {
+            false
+        }
+    }
+
+    override fun matchAllNgrams(
+        ngram: Ngram<String, Int>,
+        maxEditDistance: Int,
+        maxTokenCount: Int,
+        allowPossiblyOffensive: Boolean
+    ): List<Token<String>> {
+        val ngramList = mutableListOf<Token<String>>()
+        var currentNode: NgramNode = ngramTree
+        for ((t, token) in ngram.tokens.withIndex()) {
+            val word = token.data
+            if (t + 1 >= ngram.tokens.size) {
+                if (word.isNotEmpty()) {
+                    // The last word is not complete, so find all possible words and sort
+                    val splitWord = mutableListOf<Char>()
+                    var splitNode: NgramNode? = currentNode
+                    for ((pos, char) in word.withIndex()) {
+                        val node = if (pos == 0) {
+                            splitNode?.higherOrderChildren?.find { it.char == char }
+                        } else {
+                            splitNode?.sameOrderChildren?.find { it.char == char }
+                        }
+                        splitWord.add(char)
+                        splitNode = node
+                        if (node == null) {
+                            break
+                        }
+                    }
+                    if (splitNode != null) {
+                        // Input thus far is valid
+                        val wordNodes = SuggestionList.new(maxTokenCount)
+                        val strBuilder = StringBuilder().append(word.substring(0, word.length - 1))
+                        splitNode.listAllSameOrderWords(wordNodes, strBuilder, allowPossiblyOffensive)
+                        ngramList.addAll(wordNodes.map { Token(it) })
+                    }
+                    if (ngramList.size < maxTokenCount) {
+                        val wordNodes = SuggestionList.new(maxTokenCount)
+                        val strBuilder = StringBuilder()
+                        currentNode.listSimilarWords(word, wordNodes, strBuilder, allowPossiblyOffensive, maxEditDistance)
+                        ngramList.addAll(wordNodes.map { Token(it) })
+                    }
+                }
+            } else {
+                val node = currentNode.findWord(word)
+                if (node == null) {
+                    return ngramList
+                } else {
+                    currentNode = node
+                }
+            }
+        }
+        return ngramList
+    }
+
+    fun toFlorisMutableLanguageModel(): FlorisMutableLanguageModel = FlorisMutableLanguageModel(ngramTree)
+}
+
+open class FlorisMutableLanguageModel(
+    initTreeObj: NgramTree? = null
+) : MutableLanguageModel<String, Int>, FlorisLanguageModel(initTreeObj) {
+    override fun deleteNgram(ngram: Ngram<String, Int>) {
+        TODO("Not yet implemented")
+    }
+
+    override fun insertNgram(ngram: Ngram<String, Int>) {
+        TODO("Not yet implemented")
+    }
+
+    override fun updateNgram(ngram: Ngram<String, Int>) {
+        TODO("Not yet implemented")
+    }
+
+    fun toFlorisLanguageModel(): FlorisLanguageModel = FlorisLanguageModel(ngramTree)
+}

app/src/main/java/dev/patrickgold/florisboard/ime/keyboard/ComputingEvaluator.kt

@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2021 Patrick Goldinger
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package dev.patrickgold.florisboard.ime.keyboard
+
+import dev.patrickgold.florisboard.ime.core.Subtype
+import dev.patrickgold.florisboard.ime.text.key.*
+
+interface ComputingEvaluator {
+    fun evaluateCaps(): Boolean
+
+    fun evaluateCaps(data: KeyData): Boolean
+
+    fun evaluateCharHalfWidth(): Boolean = false
+
+    fun evaluateKanaKata(): Boolean = false
+
+    fun evaluateKanaSmall(): Boolean = false
+
+    fun evaluateEnabled(data: KeyData): Boolean
+
+    fun evaluateVisible(data: KeyData): Boolean
+
+    fun getActiveSubtype(): Subtype
+
+    fun getKeyVariation(): KeyVariation
+
+    fun getKeyboard(): Keyboard
+
+    fun isSlot(data: KeyData): Boolean
+
+    fun getSlotData(data: KeyData): KeyData?
+}
+
+object DefaultComputingEvaluator : ComputingEvaluator {
+    override fun evaluateCaps(): Boolean = false
+
+    override fun evaluateCaps(data: KeyData): Boolean = false
+
+    override fun evaluateCharHalfWidth(): Boolean = false
+
+    override fun evaluateKanaKata(): Boolean = false
+
+    override fun evaluateKanaSmall(): Boolean = false
+
+    override fun evaluateEnabled(data: KeyData): Boolean = true
+
+    override fun evaluateVisible(data: KeyData): Boolean = true
+
+    override fun getActiveSubtype(): Subtype = Subtype.DEFAULT
+
+    override fun getKeyVariation(): KeyVariation = KeyVariation.NORMAL
+
+    override fun getKeyboard(): Keyboard = throw NotImplementedError()
+
+    override fun isSlot(data: KeyData): Boolean = false
+
+    override fun getSlotData(data: KeyData): KeyData? = null
+}

app/src/main/java/dev/patrickgold/florisboard/ime/keyboard/InputFeedbackManager.kt

@@ -0,0 +1,145 @@
+/*
+ * Copyright (C) 2021 Patrick Goldinger
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package dev.patrickgold.florisboard.ime.keyboard
+
+import android.content.Context
+import android.inputmethodservice.InputMethodService
+import android.media.AudioManager
+import android.os.Build
+import android.os.VibrationEffect
+import android.os.Vibrator
+import android.provider.Settings
+import android.view.HapticFeedbackConstants
+import dev.patrickgold.florisboard.debug.flogDebug
+import dev.patrickgold.florisboard.ime.core.Preferences
+import dev.patrickgold.florisboard.ime.text.key.KeyCode
+import dev.patrickgold.florisboard.ime.text.keyboard.TextKeyData
+
+/**
+ * Input feedback manager responsible to process and perform audio and haptic
+ * feedback for user interactions based on the system and floris preferences.
+ */
+class InputFeedbackManager private constructor(private val ims: InputMethodService) {
+    companion object {
+        fun new(ims: InputMethodService) = InputFeedbackManager(ims)
+    }
+
+    private val prefs get() = Preferences.default()
+
+    private val audioManager = ims.getSystemService(Context.AUDIO_SERVICE) as? AudioManager
+    private val vibrator = ims.getSystemService(Context.VIBRATOR_SERVICE) as? Vibrator
+    private val contentResolver = ims.contentResolver
+
+    fun keyPress(data: KeyData = TextKeyData.UNSPECIFIED) {
+        if (prefs.inputFeedback.audioFeatKeyPress) performAudioFeedback(data, 1.0)
+        if (prefs.inputFeedback.hapticFeatKeyPress) performHapticFeedback(data, 1.0)
+    }
+
+    fun keyLongPress(data: KeyData = TextKeyData.UNSPECIFIED) {
+        if (prefs.inputFeedback.audioFeatKeyLongPress) performAudioFeedback(data, 0.7)
+        if (prefs.inputFeedback.hapticFeatKeyLongPress) performHapticFeedback(data, 0.4)
+    }
+
+    fun keyRepeatedAction(data: KeyData = TextKeyData.UNSPECIFIED) {
+        if (prefs.inputFeedback.audioFeatKeyRepeatedAction) performAudioFeedback(data, 0.4)
+        if (prefs.inputFeedback.hapticFeatKeyRepeatedAction) performHapticFeedback(data, 0.05)
+    }
+
+    fun gestureSwipe(data: KeyData = TextKeyData.UNSPECIFIED) {
+        if (prefs.inputFeedback.audioFeatGestureSwipe) performAudioFeedback(data, 0.7)
+        if (prefs.inputFeedback.hapticFeatGestureSwipe) performHapticFeedback(data, 0.4)
+    }
+
+    fun gestureMovingSwipe(data: KeyData = TextKeyData.UNSPECIFIED) {
+        if (prefs.inputFeedback.audioFeatGestureMovingSwipe) performAudioFeedback(data, 0.4)
+        if (prefs.inputFeedback.hapticFeatGestureMovingSwipe) performHapticFeedback(data, 0.05)
+    }
+
+    private fun systemPref(id: String): Boolean {
+        if (contentResolver == null) return false
+        return Settings.System.getInt(contentResolver, id, 0) != 0
+    }
+
+    private fun performAudioFeedback(data: KeyData, factor: Double) {
+        if (audioManager == null) return
+        if (!prefs.inputFeedback.audioEnabled) return
+
+        if (!prefs.inputFeedback.audioIgnoreSystemSettings) {
+            if (!systemPref(Settings.System.SOUND_EFFECTS_ENABLED)) return
+        }
+
+        val volume = (prefs.inputFeedback.audioVolume * factor) / 100.0
+        val effect = when (data.code) {
+            KeyCode.DELETE -> AudioManager.FX_KEYPRESS_DELETE
+            KeyCode.ENTER -> AudioManager.FX_KEYPRESS_RETURN
+            KeyCode.SPACE -> AudioManager.FX_KEYPRESS_SPACEBAR
+            else -> AudioManager.FX_KEYPRESS_STANDARD
+        }
+        if (volume in 0.01..1.00) {
+            flogDebug { "Perform audio with volume=$volume and effect=$effect" }
+            audioManager.playSoundEffect(effect, volume.toFloat())
+        }
+    }
+
+    private fun performHapticFeedback(data: KeyData, factor: Double) {
+        if (vibrator == null || !vibrator.hasVibrator()) return
+        if (!prefs.inputFeedback.hapticEnabled) return
+
+        if (!prefs.inputFeedback.hapticIgnoreSystemSettings) {
+            if (!systemPref(Settings.System.HAPTIC_FEEDBACK_ENABLED)) return
+        }
+
+        if (!prefs.inputFeedback.hapticUseVibrator) {
+            val view = ims.window?.window?.decorView ?: return
+            val hfc = if (factor < 1.0 && Build.VERSION.SDK_INT >= Build.VERSION_CODES.O_MR1) {
+                HapticFeedbackConstants.TEXT_HANDLE_MOVE
+            } else {
+                HapticFeedbackConstants.KEYBOARD_TAP
+            }
+            val didPerform = view.performHapticFeedback(hfc,
+                HapticFeedbackConstants.FLAG_IGNORE_VIEW_SETTING or
+                    HapticFeedbackConstants.FLAG_IGNORE_GLOBAL_SETTING
+            )
+            if (didPerform) return
+            // If not performed fall back to using the vibrator directly
+        }
+
+        val duration = prefs.inputFeedback.hapticVibrationDuration
+        if (duration != 0) {
+            val effectiveDuration = (duration * factor).toLong().coerceAtLeast(1L)
+            if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.O) {
+                val strength = when {
+                    vibrator.hasAmplitudeControl() -> prefs.inputFeedback.hapticVibrationStrength
+                    else -> VibrationEffect.DEFAULT_AMPLITUDE
+                }
+                if (strength != 0) {
+                    val effectiveStrength = when {
+                        vibrator.hasAmplitudeControl() -> (255.0 * ((strength * factor) / 100.0)).toInt().coerceIn(1, 255)
+                        else -> strength
+                    }
+                    flogDebug { "Perform haptic with duration=$effectiveDuration and strength=$effectiveStrength" }
+                    val effect = VibrationEffect.createOneShot(effectiveDuration, effectiveStrength)
+                    vibrator.vibrate(effect)
+                }
+            } else {
+                flogDebug { "Perform haptic with duration=$effectiveDuration" }
+                @Suppress("DEPRECATION")
+                vibrator.vibrate(effectiveDuration)
+            }
+        }
+    }
+}