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

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

@@ -17,6 +17,7 @@ public class Emoji {
   private final List<String> aliases;
   private final List<String> tags;
   private final String unicode;
+  private final String unicodeWithoutVariationSelectors;
   private final String htmlDec;
   private final String htmlHex;
 
@@ -44,6 +45,7 @@ protected Emoji(
     int count = 0;
     try {
       this.unicode = new String(bytes, "UTF-8");
+      this.unicodeWithoutVariationSelectors = this.unicode.replaceAll("\ufe0f", "");
       int stringLength = getUnicode().length();
       String[] pointCodes = new String[stringLength];
       String[] pointCodesHex = new String[stringLength];
@@ -144,6 +146,15 @@ public String getUnicode(Fitzpatrick fitzpatrick) {
     return this.getUnicode() + fitzpatrick.unicode;
   }
 
+  /**
+   * Returns the normalized unicode representation of the emoji
+   *
+   * @return the normalized unicode representation
+   */
+  public String getUnicodeWithoutVariationSelectors() {
+    return this.unicodeWithoutVariationSelectors;
+  }
+
   /**
    * Returns the HTML decimal representation of the emoji
    *

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

@@ -51,6 +51,7 @@ public static String parseToAliases(
     String input,
     final FitzpatrickAction fitzpatrickAction
   ) {
+    input = input.replaceAll("\ufe0f", "");
     EmojiTransformer emojiTransformer = new EmojiTransformer() {
       public String transform(UnicodeCandidate unicodeCandidate) {
         switch (fitzpatrickAction) {
@@ -87,6 +88,7 @@ public String transform(UnicodeCandidate unicodeCandidate) {
    * @return the string with replaced character
    */
   public static String replaceAllEmojis(String str, final String replacementString) {
+    str = str.replaceAll("\ufe0f", "");
     EmojiParser.EmojiTransformer emojiTransformer = new EmojiParser.EmojiTransformer() {
       public String transform(EmojiParser.UnicodeCandidate unicodeCandidate) {
         return replacementString;
@@ -111,6 +113,7 @@ public String transform(EmojiParser.UnicodeCandidate unicodeCandidate) {
    * their unicode.
    */
   public static String parseToUnicode(String input) {
+    input = input.replaceAll("\ufe0f", "");
     StringBuilder sb = new StringBuilder(input.length());
 
     for (int last = 0; last < input.length(); last++) {
@@ -229,6 +232,7 @@ public static String parseToHtmlDecimal(
     String input,
     final FitzpatrickAction fitzpatrickAction
   ) {
+    input = input.replaceAll("\ufe0f", "");
     EmojiTransformer emojiTransformer = new EmojiTransformer() {
       public String transform(UnicodeCandidate unicodeCandidate) {
         switch (fitzpatrickAction) {
@@ -284,6 +288,7 @@ public static String parseToHtmlHexadecimal(
     String input,
     final FitzpatrickAction fitzpatrickAction
   ) {
+    input = input.replaceAll("\ufe0f", "");
     EmojiTransformer emojiTransformer = new EmojiTransformer() {
       public String transform(UnicodeCandidate unicodeCandidate) {
         switch (fitzpatrickAction) {
@@ -309,6 +314,7 @@ public String transform(UnicodeCandidate unicodeCandidate) {
    * @return the string without any emoji
    */
   public static String removeAllEmojis(String str) {
+    str = str.replaceAll("\ufe0f", "");
     EmojiTransformer emojiTransformer = new EmojiTransformer() {
       public String transform(UnicodeCandidate unicodeCandidate) {
         return "";
@@ -331,6 +337,7 @@ public static String removeEmojis(
     String str,
     final Collection<Emoji> emojisToRemove
   ) {
+    str = str.replaceAll("\ufe0f", "");
     EmojiTransformer emojiTransformer = new EmojiTransformer() {
       public String transform(UnicodeCandidate unicodeCandidate) {
         if (!emojisToRemove.contains(unicodeCandidate.getEmoji())) {
@@ -356,6 +363,7 @@ public static String removeAllEmojisExcept(
     String str,
     final Collection<Emoji> emojisToKeep
   ) {
+    str = str.replaceAll("\ufe0f", "");
     EmojiTransformer emojiTransformer = new EmojiTransformer() {
       public String transform(UnicodeCandidate unicodeCandidate) {
         if (emojisToKeep.contains(unicodeCandidate.getEmoji())) {
@@ -383,6 +391,7 @@ public static String parseFromUnicode(
     String input,
     EmojiTransformer transformer
   ) {
+    input = input.replaceAll("\ufe0f", "");
     int prev = 0;
     StringBuilder sb = new StringBuilder(input.length());
     List<UnicodeCandidate> replacements = getUnicodeCandidates(input);
@@ -526,7 +535,7 @@ public int getEmojiStartIndex() {
     }
 
     public int getEmojiEndIndex() {
-      return startIndex + emoji.getUnicode().length();
+      return startIndex + emoji.getUnicodeWithoutVariationSelectors().length();
     }
 
     public int getFitzpatrickEndIndex() {

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

@@ -12,7 +12,7 @@ public EmojiTrie(Collection<Emoji> emojis) {
     int maxDepth = 0;
     for (Emoji emoji : emojis) {
       Node tree = root;
-      char[] chars = emoji.getUnicode().toCharArray();
+      char[] chars = emoji.getUnicodeWithoutVariationSelectors().toCharArray();
       maxDepth = Math.max(maxDepth, chars.length);
       for (char c: chars) {
         if (!tree.hasChild(c)) {