OPENNLP-1869: Add emoji and emoticon normalizers to text normalization

opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/langdetect/LanguageDetectorFactory.java

@@ -45,8 +45,10 @@
 public class LanguageDetectorFactory extends BaseToolFactory {
 
   /**
-   * @return Retrieves a {@link LanguageDetectorContextGenerator}.
+   * @return Retrieves a {@link LanguageDetectorContextGenerator}. The deprecated emoji
+   *     normalizer stays in this chain because existing models were trained with it.
    */
+  @SuppressWarnings("deprecation")
   public LanguageDetectorContextGenerator getContextGenerator() {
     return new DefaultLanguageDetectorContextGenerator(1, 3,
         EmojiCharSequenceNormalizer.getInstance(),

opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/Dimension.java

@@ -60,6 +60,9 @@ public enum Dimension {
   /** Diacritic and accent folding; lossy, script gated, and language-wrong for some languages. */
   ACCENT_FOLD(AccentFoldCharSequenceNormalizer::getInstance),
 
+  /** Emoji folded to ASCII emoticons where a mapping exists; lossy, for matching only. */
+  EMOJI_FOLD(EmojiToEmoticonCharSequenceNormalizer::getInstance),
+
   /** Confusable (homoglyph) skeleton folding per UTS #39; lossy, for matching only. */
   CONFUSABLE_FOLD(ConfusableSkeletonCharSequenceNormalizer::getInstance),
 

opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/EmojiCharSequenceNormalizer.java

@@ -21,7 +21,11 @@
 /**
  * A {@link EmojiCharSequenceNormalizer} implementation that normalizes text
  * in terms of emojis. Every encounter will be replaced by a whitespace.
+ *
+ * @deprecated Replaces every supplementary-plane code point with a space, not only emoji. Use
+ *     {@link EmojiToEmoticonCharSequenceNormalizer} instead.
  */
+@Deprecated(since = "3.0.0")
 public class EmojiCharSequenceNormalizer implements CharSequenceNormalizer {
 
   private static final long serialVersionUID = 4553401197981667914L;