Some API change, go...

Author: glorieux-f

analysis/src/java/com/github/oeuvres/alix/ingest/AlixSaxHandler.java

@@ -265,10 +265,10 @@ public void endElement(String uri, String localName, String qName) throws SAXExc
     @Override
     public void characters(char[] ch, int start, int length) throws SAXException
     {
-        if (fieldMode == FieldMode.NONE)
-            return;
-        
         switch (fieldMode) {
+            case NONE -> {
+                return;
+            }
             case SCALAR, DERIVED -> {
                 if (!isAllWhitespace(ch, start, length)) {
                     throw new SAXException(

analysis/src/java/com/github/oeuvres/alix/lucene/analysis/FilterLocution.java

@@ -85,7 +85,6 @@ public final class MweFilter extends TokenFilter
 
     private final CharTermAttribute          termAtt     = addAttribute(CharTermAttribute.class);
     private final OffsetAttribute            offsetAtt   = addAttribute(OffsetAttribute.class);
-    private final PositionIncrementAttribute posIncrAtt  = addAttribute(PositionIncrementAttribute.class);
     private final TypeAttribute              typeAtt     = addAttribute(TypeAttribute.class);
 
     private boolean inputExhausted = false;

analysis/src/java/com/github/oeuvres/alix/lucene/analysis/MweFilter.java

@@ -41,6 +41,8 @@
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
 
+import com.github.oeuvres.alix.util.CharsMap;
+
 /**
  * Rewrite tokens by applying an exact, dictionary-based term mapping.
  *
@@ -75,7 +77,7 @@ public final class TermReplaceFilter extends TokenFilter {
      * Term rewrite table. Keys are matched against the current token term; values are copied
      * into the {@link CharTermAttribute} when a match is found.
      */
-    private final CharArrayMap<char[]> map;
+    private final CharsMap map;
 
     /** The current token term. */
     private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
@@ -86,7 +88,7 @@ public final class TermReplaceFilter extends TokenFilter {
      * @param input the upstream {@link TokenStream} (tokenizer or previous filter)
      * @param map the rewrite table mapping surface forms to replacement forms
      */
-    public TermReplaceFilter(final TokenStream input, final CharArrayMap<char[]> map) {
+    public TermReplaceFilter(final TokenStream input, final CharsMap map) {
         super(input);
         this.map = map;
     }
@@ -100,10 +102,13 @@ public TermReplaceFilter(final TokenStream input, final CharArrayMap<char[]> map
     @Override
     public boolean incrementToken() throws IOException {
         if (!input.incrementToken()) return false;
-
-        final char[] replacement = map.get(termAtt.buffer(), 0, termAtt.length());
-        if (replacement != null) {
-            termAtt.copyBuffer(replacement, 0, replacement.length);
+        
+        int vOrd = map.valueOrd(termAtt.buffer(), 0, termAtt.length());
+        if (vOrd >= 0) { 
+            int vLen = map.len(vOrd); 
+            char[] dst = termAtt.resizeBuffer(vLen);
+            map.copy(vOrd, dst, 0);
+            termAtt.setLength(vLen);
         }
         return true;
     }

analysis/src/java/com/github/oeuvres/alix/lucene/analysis/TermReplaceFilter.java

@@ -79,7 +79,7 @@ public class FrenchAnalyzer extends DelegatingAnalyzerWrapper
     /** Words with ending dots */
     public final CharArraySet brevidots;
     /** Term normalizer */
-    public final CharArrayMap<char[]> normalizer;
+    public final CharsMap normalizer;
     /** Multi-Word Expressions */
     public final MweLexicon expressions;
     /** Big dic */

analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/FrenchAnalyzer.java

@@ -40,6 +40,7 @@
 
 import com.github.oeuvres.alix.lucene.analysis.LexiconHelper;
 import com.github.oeuvres.alix.lucene.analysis.LexiconHelper.PosResolver;
+import com.github.oeuvres.alix.util.CharsMap;
 import com.github.oeuvres.alix.util.LemmaLexicon;
 import com.github.oeuvres.alix.util.MweLexicon;
 import com.github.oeuvres.alix.util.WordTokenizer;
@@ -135,9 +136,9 @@ public static MweLexicon buildMweLexicon()
     }
 
 
-    public static CharArrayMap<char[]> buildNormalizer()
+    public static CharsMap buildNormalizer()
     {
-        CharArrayMap<char[]> map = new CharArrayMap<char[]>(2000, false);
+        CharsMap map = new CharsMap(2000);
         LexiconHelper.loadMap(map, LexiconHelper.class, "/com/github/oeuvres/alix/fr/norm-1990-classical.csv", LexiconHelper.OnDuplicate.REPLACE);
         LexiconHelper.loadMap(map, LexiconHelper.class, "/com/github/oeuvres/alix/fr/norm-aeoe.csv", LexiconHelper.OnDuplicate.REPLACE);
         LexiconHelper.loadMap(map, LexiconHelper.class, "/com/github/oeuvres/alix/fr/norm-maj-noacc.csv", LexiconHelper.OnDuplicate.REPLACE);