ICU-22564 Java API for the host env to register a low level break eng…

…ine to break CJ + Southeastern Asia script

icu4j/main/core/src/main/java/com/ibm/icu/impl/breakiter/BurmeseBreakEngine.java

@@ -15,6 +15,7 @@
 import com.ibm.icu.lang.UProperty;
 import com.ibm.icu.lang.UScript;
 import com.ibm.icu.text.UnicodeSet;
+import com.ibm.icu.util.ULocale;
 
 
 public class BurmeseBreakEngine extends DictionaryBreakEngine {
@@ -70,7 +71,7 @@ public int hashCode() {
     }
 
     @Override
-    public boolean handles(int c) {
+    public boolean handles(int c, ULocale locale) {
         int script = UCharacter.getIntPropertyValue(c, UProperty.SCRIPT);
         return (script == UScript.MYANMAR);
     }

icu4j/main/core/src/main/java/com/ibm/icu/impl/breakiter/DictionaryBreakEngine.java

@@ -12,6 +12,7 @@
 
 import com.ibm.icu.impl.CharacterIteration;
 import com.ibm.icu.text.UnicodeSet;
+import com.ibm.icu.util.ULocale;
 
 public abstract class DictionaryBreakEngine implements LanguageBreakEngine {
 
@@ -177,7 +178,7 @@ public DictionaryBreakEngine() {
     }
 
     @Override
-    public boolean handles(int c) {
+    public boolean handles(int c, ULocale locale) {
         return fSet.contains(c);        // we recognize the character
     }
 

icu4j/main/core/src/main/java/com/ibm/icu/impl/breakiter/KhmerBreakEngine.java

@@ -15,6 +15,7 @@
 import com.ibm.icu.lang.UProperty;
 import com.ibm.icu.lang.UScript;
 import com.ibm.icu.text.UnicodeSet;
+import com.ibm.icu.util.ULocale;
 
 public class KhmerBreakEngine extends DictionaryBreakEngine {
 
@@ -78,7 +79,7 @@ public int hashCode() {
     }
 
     @Override
-    public boolean handles(int c) {
+    public boolean handles(int c, ULocale locale) {
         int script = UCharacter.getIntPropertyValue(c, UProperty.SCRIPT);
         return (script == UScript.KHMER);
     }

icu4j/main/core/src/main/java/com/ibm/icu/impl/breakiter/LSTMBreakEngine.java

@@ -22,6 +22,7 @@
 import com.ibm.icu.lang.UScript;
 import com.ibm.icu.text.BreakIterator;
 import com.ibm.icu.text.UnicodeSet;
+import com.ibm.icu.util.ULocale;
 import com.ibm.icu.util.UResourceBundle;
 
 /**
@@ -237,7 +238,7 @@ public int hashCode() {
     }
 
     @Override
-    public boolean handles(int c) {
+    public boolean handles(int c, ULocale locale) {
         return fScript == UCharacter.getIntPropertyValue(c, UProperty.SCRIPT);
     }
 

icu4j/main/core/src/main/java/com/ibm/icu/impl/breakiter/LanguageBreakEngine.java

@@ -9,6 +9,7 @@
 package com.ibm.icu.impl.breakiter;
 
 import java.text.CharacterIterator;
+import com.ibm.icu.util.ULocale;
 
 /**
  * The LanguageBreakEngine interface is to be used to implement any
@@ -17,9 +18,10 @@
 public interface LanguageBreakEngine {
     /**
      * @param c A Unicode codepoint value
+     * @param locale A locale
      * @return true if the engine can handle this character, false otherwise
      */
-    boolean handles(int c);
+    boolean handles(int c, ULocale locale);
 
     /**
      * Implements the actual breaking logic. Find any breaks within a run in the supplied text.

icu4j/main/core/src/main/java/com/ibm/icu/impl/breakiter/LaoBreakEngine.java

@@ -15,6 +15,7 @@
 import com.ibm.icu.lang.UProperty;
 import com.ibm.icu.lang.UScript;
 import com.ibm.icu.text.UnicodeSet;
+import com.ibm.icu.util.ULocale;
 
 public class LaoBreakEngine extends DictionaryBreakEngine {
 
@@ -78,7 +79,7 @@ public int hashCode() {
     }
 
     @Override
-    public boolean handles(int c) {
+    public boolean handles(int c, ULocale locale) {
         int script = UCharacter.getIntPropertyValue(c, UProperty.SCRIPT);
         return (script == UScript.LAO);
     }

icu4j/main/core/src/main/java/com/ibm/icu/impl/breakiter/ThaiBreakEngine.java

@@ -15,6 +15,7 @@
 import com.ibm.icu.lang.UProperty;
 import com.ibm.icu.lang.UScript;
 import com.ibm.icu.text.UnicodeSet;
+import com.ibm.icu.util.ULocale;
 
 public class ThaiBreakEngine extends DictionaryBreakEngine {
 
@@ -89,7 +90,7 @@ public int hashCode() {
     }
 
     @Override
-    public boolean handles(int c) {
+    public boolean handles(int c, ULocale locale) {
         int script = UCharacter.getIntPropertyValue(c, UProperty.SCRIPT);
         return (script == UScript.THAI);
     }

icu4j/main/core/src/main/java/com/ibm/icu/impl/breakiter/UnhandledBreakEngine.java

@@ -14,6 +14,7 @@
 import com.ibm.icu.lang.UCharacter;
 import com.ibm.icu.lang.UProperty;
 import com.ibm.icu.text.UnicodeSet;
+import com.ibm.icu.util.ULocale;
 
 public final class UnhandledBreakEngine implements LanguageBreakEngine {
     // TODO: Use two UnicodeSets, one with all frozen sets, one with unfrozen.
@@ -38,7 +39,7 @@ public UnhandledBreakEngine() {
     }
 
     @Override
-    public boolean handles(int c) {
+    public boolean handles(int c, ULocale locale) {
         return fHandled.contains(c);
     }
 

icu4j/main/core/src/main/java/com/ibm/icu/text/BreakIterator.java

@@ -1014,6 +1014,10 @@ public final ULocale getLocale(ULocale.Type type) {
             this.actualLocale : this.validLocale;
     }
 
+    protected final ULocale getRequestedLocale() {
+        return this.requestedLocale;
+    }
+
     /**
      * Set information about the locales that were used to create this
      * object.  If the object was not constructed from locale data,
@@ -1043,6 +1047,15 @@ final void setLocale(ULocale valid, ULocale actual) {
         this.actualLocale = actual;
     }
 
+    /**
+     * Set the requested locale.
+     * @param requested the locale requested to construct.
+     * @see com.ibm.icu.util.ULocale
+     */
+    final void setRequestedLocale(ULocale requested) {
+        this.requestedLocale = requested;
+    }
+
     /**
      * The most specific locale containing any resource data, or null.
      * @see com.ibm.icu.util.ULocale
@@ -1056,5 +1069,11 @@ final void setLocale(ULocale valid, ULocale actual) {
      */
     private ULocale actualLocale;
 
+    /**
+     * The locale requsted in the constructor.
+     * @see com.ibm.icu.util.ULocale
+     */
+    private ULocale requestedLocale;
+
     // -------- END ULocale boilerplate --------
 }

icu4j/main/core/src/main/java/com/ibm/icu/text/BreakIteratorFactory.java

@@ -171,6 +171,7 @@ private static BreakIterator createBreakInstance(ULocale locale, int kind) {
         // TODO: Determine valid and actual locale correctly.
         ULocale uloc = ULocale.forLocale(rb.getLocale());
         iter.setLocale(uloc, uloc);
+        iter.setRequestedLocale(locale);
 
         // filtered break
         if (kind == BreakIterator.KIND_SENTENCE) {

icu4j/main/core/src/main/java/com/ibm/icu/text/RuleBasedBreakIterator.java

@@ -40,6 +40,7 @@
 import com.ibm.icu.lang.UProperty;
 import com.ibm.icu.lang.UScript;
 import com.ibm.icu.util.CodePointTrie;
+import com.ibm.icu.util.ULocale;
 
 /**
  * Rule Based Break Iterator
@@ -727,7 +728,7 @@ private LanguageBreakEngine getLanguageBreakEngine(int c) {
         // We have a dictionary character.
         // Does an already instantiated break engine handle it?
         for (LanguageBreakEngine candidate : fBreakEngines) {
-            if (candidate.handles(c)) {
+            if (candidate.handles(c, getRequestedLocale())) {
                 return candidate;
             }
         }
@@ -737,7 +738,7 @@ private LanguageBreakEngine getLanguageBreakEngine(int c) {
             // Check the global list, another break iterator may have instantiated the
             // desired engine.
             for (LanguageBreakEngine candidate : gAllBreakEngines) {
-                if (candidate.handles(c)) {
+                if (candidate.handles(c, getRequestedLocale())) {
                     fBreakEngines.add(candidate);
                     return candidate;
                 }
@@ -1081,6 +1082,35 @@ private static int CISetIndex32(CharacterIterator ci, int index) {
         return ci.getIndex();
     }
 
+    /**
+     * Register a new external break engine. The external break engine will be adopted.
+     * Because ICU may choose to cache break engine internally, this must
+     * be called at application startup, prior to any calls to
+     * object methods of RuleBasedBreakIterator to avoid undefined behavior.
+     * @param engine the ExternalBreakEngine instance to be adopted
+     * @internal ICU 75 technology preview
+     */
+    public static void registerExternalBreakEngine(ExternalBreakEngine engine) {
+        synchronized(gAllBreakEngines) {
+            gAllBreakEngines.add(0, new LanguageBreakEngine() {
+                @Override
+                public boolean handles(int c, ULocale locale) {
+                   return engine.isFor(c, locale);
+                }
+                @Override
+                public int findBreaks(CharacterIterator text, int startPos, int endPos,
+                        DictionaryBreakEngine.DequeI foundBreaks, boolean isPhraseBreaking) {
+                    List<Integer> found = new ArrayList<Integer>();
+                    int result = engine.fillBreaks(text, startPos, endPos, found);
+                    for (Integer f : found) {
+                      foundBreaks.push(f);
+                    }
+                    return result;
+                }
+            });
+        }
+    }
+
     /** DictionaryCache  stores the boundaries obtained from a run of dictionary characters.
      *                 Dictionary boundaries are moved first to this cache, then from here
      *                 to the main BreakCache, where they may inter-leave with non-dictionary
@@ -1885,7 +1915,43 @@ void dumpCache() {
 };
 
 
+    public interface ExternalBreakEngine {
+        /**
+         * <p>Indicate whether this engine handles a particular character when
+         * the RuleBasedBreakIterator is used for a particular locale. This method is used
+         * by the RuleBasedBreakIterator to find a break engine.</p>
+         * @param c A character which begins a run that the engine might handle.
+         * @param locale    The locale.
+         * @return true if this engine handles the particular character for that locale.
+         * @internal ICU 75 technology preview
+         */
+        public boolean isFor(int c, ULocale locale);
+
+        /**
+         * <p>Indicate whether this engine handles a particular character.This method is
+         * used by the RuleBasedBreakIterator after it already find a break engine to see which
+         * characters after the first one can be handled by this break engine.</p>
+         * @param c A character that the engine might handle.
+         * @return true if this engine handles the particular character.
+         * @internal ICU 75 technology preview
+         */
+        public boolean handles(int c);
 
+        /**
+         * <p>Divide up a range of text handled by this break engine.</p>
+         *
+         * @param text A CharacterIterator representing the text
+         * @param rangeStart The start of the range of known characters
+         * @param rangeEnd The end of the range of known characters
+         * @param foundBreaks Output of a list of Integer to denote break positions.
+         * @return The number of breaks found
+         * @internal ICU 75 technology preview
+         */
+         public int fillBreaks(CharacterIterator text,
+                               int               rangeStart,
+                               int               rangeEnd,
+                               List<Integer>     foundBreaks);
+    }
 
 }