Upgrade to Unicode 16.0 and add support for almost all gemoji aliases

CHANGELOG.md

@@ -1,5 +1,14 @@
 # Changelog
 
+## v5.1.2
+
+- Upgrade emoji database to Unicode 16.0 (+330 emojis)
+- Add support for almost all gemoji aliases (+742 aliases, 2711 total)
+- FE0F handled transparently: `getUnicode()` return values for existing emojis unchanged
+- `:bride_with_veil:`, `:guardsman:`, `:man_in_tuxedo:`, `:man_with_turban:`,
+  `:ok_woman:` now map to their gender-explicit ZWJ variants
+- `:jolly_roger:` / `:pirate_flag:` had an erroneous leading ♾ removed (bugfix)
+
 ## v5.1.1
 
 - Bugfix: respect fitzpatrick modifier when extracting emojis (thanks @sullis)

README.md

@@ -16,7 +16,7 @@ _The missing emoji library for java._
 <dependency>
   <groupId>com.vdurmont</groupId>
   <artifactId>emoji-java</artifactId>
-  <version>5.1.1</version>
+  <version>5.1.2</version>
 </dependency>
 ```
 
@@ -25,7 +25,7 @@ You can also download the project, build it with `mvn clean install` and add the
 ##### Via Gradle:
 
 ```gradle
-compile 'com.vdurmont:emoji-java:5.1.1'
+compile 'com.vdurmont:emoji-java:5.1.2'
 ```
 
 ##### Via Direct Download:

pom.xml

@@ -4,7 +4,7 @@
 
     <groupId>com.vdurmont</groupId>
     <artifactId>emoji-java</artifactId>
-    <version>5.1.1</version>
+    <version>5.1.2</version>
     <packaging>jar</packaging>
 
     <name>emoji-java</name>

src/main/java/com/vdurmont/emoji/EmojiParser.java

@@ -451,7 +451,8 @@ protected static UnicodeCandidate getNextUnicodeCandidate(char[] chars, int star
         return new UnicodeCandidate(
                 emoji,
                 fitzpatrickString,
-                i
+                i,
+                emojiEnd
         );
       }
     }
@@ -494,11 +495,13 @@ public static class UnicodeCandidate {
     private final Emoji emoji;
     private final Fitzpatrick fitzpatrick;
     private final int startIndex;
+    private final int emojiEndIndex;
 
-    private UnicodeCandidate(Emoji emoji, String fitzpatrick, int startIndex) {
+    private UnicodeCandidate(Emoji emoji, String fitzpatrick, int startIndex, int emojiEndIndex) {
       this.emoji = emoji;
       this.fitzpatrick = Fitzpatrick.fitzpatrickFromUnicode(fitzpatrick);
       this.startIndex = startIndex;
+      this.emojiEndIndex = emojiEndIndex;
     }
 
     public Emoji getEmoji() {
@@ -526,7 +529,7 @@ public int getEmojiStartIndex() {
     }
 
     public int getEmojiEndIndex() {
-      return startIndex + emoji.getUnicode().length();
+      return emojiEndIndex;
     }
 
     public int getFitzpatrickEndIndex() {

src/main/java/com/vdurmont/emoji/EmojiTrie.java

@@ -12,8 +12,10 @@ public EmojiTrie(Collection<Emoji> emojis) {
     int maxDepth = 0;
     for (Emoji emoji : emojis) {
       Node tree = root;
-      char[] chars = emoji.getUnicode().toCharArray();
-      maxDepth = Math.max(maxDepth, chars.length);
+      // Build trie keys without variation selectors; use full unicode length for
+      // buffer sizing in getHtmlEncodedEmojiAt (which may decode FE0F entities).
+      char[] chars = emoji.getUnicode().replace("\ufe0f", "").toCharArray();
+      maxDepth = Math.max(maxDepth, emoji.getUnicode().length());
       for (char c: chars) {
         if (!tree.hasChild(c)) {
           tree.addChild(c);
@@ -64,6 +66,7 @@ public Matches isEmoji(char[] sequence, int start, int end) {
 
     Node tree = root;
     for (int i = start; i < end; i++) {
+      if (sequence[i] == '\ufe0f') continue;
       if (!tree.hasChild(sequence[i])) {
         return Matches.IMPOSSIBLE;
       }
@@ -91,6 +94,7 @@ Emoji getEmoji(char[] sequence, int start, int end) {
 
     Node tree = root;
     for (int i = 0; i < end; i++) {
+      if (sequence[i] == '\ufe0f') continue;
       if (!tree.hasChild(sequence[i])) {
         return null;
       }