Better name for l’amer-tue

glorieux-f · glorieux-f · commit 127940ccdd01 · 2026-02-18T22:17:25.000+01:00
diff --git a/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/AnalyzerCloud.java b/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/AnalyzerCloud.java
@@ -36,7 +36,6 @@
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.Tokenizer;
 
-import com.github.oeuvres.alix.lucene.analysis.FilterAposHyphenFr;
 import com.github.oeuvres.alix.lucene.analysis.FilterCloud;
 import com.github.oeuvres.alix.lucene.analysis.FilterLemmatize;
 import com.github.oeuvres.alix.lucene.analysis.FilterLocution;
@@ -67,7 +66,7 @@ public TokenStreamComponents createComponents(String field)
         // interpret html tags as token events like para or section
         ts = new MLFilter(ts);
         // fr split on ’ and -
-        ts = new FilterAposHyphenFr(ts);
+        ts = new FrenchCliticSplitFilter(ts);
         // pos tagging before lemmatize
         ts = new PosTaggingFilter(ts);
         // provide lemma+pos
diff --git a/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/AnalyzerFind.java b/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/AnalyzerFind.java
@@ -37,7 +37,6 @@
 import org.apache.lucene.analysis.Tokenizer;
 import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter;
 
-import com.github.oeuvres.alix.lucene.analysis.FilterAposHyphenFr;
 import com.github.oeuvres.alix.lucene.analysis.FilterFind;
 import com.github.oeuvres.alix.lucene.analysis.FilterLemmatize;
 import com.github.oeuvres.alix.lucene.analysis.MLFilter;
@@ -64,7 +63,7 @@ public TokenStreamComponents createComponents(String field)
         final Tokenizer tokenizer = new MLTokenizer(); // segment words
         TokenStream ts = tokenizer;
         ts = new MLFilter(ts); // interpret tags
-        ts = new FilterAposHyphenFr(ts); // fr split on ’ and -
+        ts = new FrenchCliticSplitFilter(ts); // fr split on ’ and -
         ts = new FilterLemmatize(ts); // provide lemma+pos
         ts = new FilterFind(ts); // orthographic form and lemma as term to index
         ts = new ASCIIFoldingFilter(ts); // no accents
diff --git a/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/AnalyzerMeta.java b/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/AnalyzerMeta.java
@@ -37,7 +37,6 @@
 import org.apache.lucene.analysis.Tokenizer;
 import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter;
 
-import com.github.oeuvres.alix.lucene.analysis.FilterAposHyphenFr;
 import com.github.oeuvres.alix.lucene.analysis.MLFilter;
 import com.github.oeuvres.alix.lucene.analysis.MLTokenizer;
 
@@ -61,7 +60,7 @@ protected TokenStreamComponents createComponents(String fieldName)
         final Tokenizer tokenizer = new MLTokenizer(); // segment words
         TokenStream ts = tokenizer;
         ts = new MLFilter(ts); // strip tags
-        ts = new FilterAposHyphenFr(ts); // fr split on ’ and -
+        ts = new FrenchCliticSplitFilter(ts); // fr split on ’ and -
         ts = new ASCIIFoldingFilter(ts); // no accents
         return new TokenStreamComponents(tokenizer, ts);
     }
diff --git a/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/AnalyzerOrth.java b/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/AnalyzerOrth.java
@@ -36,7 +36,6 @@
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.Tokenizer;
 
-import com.github.oeuvres.alix.lucene.analysis.FilterAposHyphenFr;
 import com.github.oeuvres.alix.lucene.analysis.FilterLemmatize;
 import com.github.oeuvres.alix.lucene.analysis.FilterLocution;
 import com.github.oeuvres.alix.lucene.analysis.FilterOrth;
@@ -67,7 +66,7 @@ public TokenStreamComponents createComponents(String field)
         // interpret html tags as token events like para or section
         ts = new MLFilter(ts);
         // fr split on ’ and -
-        ts = new FilterAposHyphenFr(ts);
+        ts = new FrenchCliticSplitFilter(ts);
         // provide lemma+pos
         ts = new FilterLemmatize(ts);
         // group compounds after lemmatization for verbal compounds
diff --git a/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/AnalyzerPos.java b/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/AnalyzerPos.java
@@ -36,7 +36,6 @@
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.Tokenizer;
 
-import com.github.oeuvres.alix.lucene.analysis.FilterAposHyphenFr;
 import com.github.oeuvres.alix.lucene.analysis.MLFilter;
 import com.github.oeuvres.alix.lucene.analysis.MLTokenizer;
 import com.github.oeuvres.alix.lucene.analysis.PosTaggingFilter;
@@ -64,7 +63,7 @@ public TokenStreamComponents createComponents(String field)
         // interpret html tags as token events like para or section
         ts = new MLFilter(ts);
         // fr split on ’ and -
-        ts = new FilterAposHyphenFr(ts);
+        ts = new FrenchCliticSplitFilter(ts);
         // pos tagging before lemmatize
         ts = new PosTaggingFilter(ts);
         // provide lemma+pos
diff --git a/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/FrenchCliticSplitFilter.java b/analysis/src/java/com/github/oeuvres/alix/lucene/analysis/fr/FrenchCliticSplitFilter.java
@@ -30,7 +30,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package com.github.oeuvres.alix.lucene.analysis;
+package com.github.oeuvres.alix.lucene.analysis.fr;
 
 import java.io.IOException;
 
@@ -53,7 +53,7 @@
  * 
  * Known side effect : qu’en-dira-t-on, donne-m’en, emmène-m’y.
  */
-public class FilterAposHyphenFr extends TokenFilter
+public class FrenchCliticSplitFilter extends TokenFilter
 {
     private static final int MAX_STEPS = 16;
 
@@ -128,7 +128,7 @@ public class FilterAposHyphenFr extends TokenFilter
         SUFFIX.put("-y", "y".toCharArray()); // allons-y.
     }
 
-    public FilterAposHyphenFr(TokenStream input) {
+    public FrenchCliticSplitFilter(TokenStream input) {
         super(input);
     }
 
diff --git a/test/src/main/java/com/github/oeuvres/alix/lucene/analysis/TokenizerTest.java b/test/src/main/java/com/github/oeuvres/alix/lucene/analysis/TokenizerTest.java
@@ -18,6 +18,7 @@
 
 import static com.github.oeuvres.alix.common.Upos.*;
 
+import com.github.oeuvres.alix.lucene.analysis.fr.FrenchCliticSplitFilter;
 import com.github.oeuvres.alix.util.Char;
 import com.github.oeuvres.alix.util.Dir;
 
@@ -31,7 +32,7 @@ public TokenStreamComponents createComponents(String field)
         {
             final Tokenizer tokenizer = new MLTokenizer();
             TokenStream ts = tokenizer;
-            ts = new FilterAposHyphenFr(tokenizer);
+            ts = new FrenchCliticSplitFilter(tokenizer);
             return new TokenStreamComponents(tokenizer, ts);
         }
 
diff --git a/test/src/test/java/com/github/oeuvres/alix/lucene/analysis/FilterAposHyphenFrTest.java b/test/src/test/java/com/github/oeuvres/alix/lucene/analysis/FilterAposHyphenFrTest.java
@@ -12,6 +12,7 @@
 import org.junit.jupiter.api.Test;
 
 import com.github.oeuvres.alix.common.Upos;
+import com.github.oeuvres.alix.lucene.analysis.fr.FrenchCliticSplitFilter;
 
 
 public class FilterAposHyphenFrTest
@@ -52,7 +53,7 @@ public TokenStreamComponents createComponents(String field)
         {
             final Tokenizer tokenizer = new MLTokenizer();
             TokenStream ts = tokenizer;
-            ts = new FilterAposHyphenFr(tokenizer);
+            ts = new FrenchCliticSplitFilter(tokenizer);
             return new TokenStreamComponents(tokenizer, ts);
         }
 

Original file line number	Diff line number	Diff line change
`@@ -30,7 +30,7 @@`
`30`	`30`	`* See the License for the specific language governing permissions and`
`31`	`31`	`* limitations under the License.`
`32`	`32`	`*/`
`33`		`-package com.github.oeuvres.alix.lucene.analysis;`
	`33`	`+package com.github.oeuvres.alix.lucene.analysis.fr;`
`34`	`34`
`35`	`35`	`import java.io.IOException;`
`36`	`36`
`@@ -53,7 +53,7 @@`
`53`	`53`	`*`
`54`	`54`	`* Known side effect : qu’en-dira-t-on, donne-m’en, emmène-m’y.`
`55`	`55`	`*/`
`56`		`-public class FilterAposHyphenFr extends TokenFilter`
	`56`	`+public class FrenchCliticSplitFilter extends TokenFilter`
`57`	`57`	`{`
`58`	`58`	`private static final int MAX_STEPS = 16;`
`59`	`59`
`@@ -128,7 +128,7 @@ public class FilterAposHyphenFr extends TokenFilter`
`128`	`128`	`SUFFIX.put("-y", "y".toCharArray()); // allons-y.`
`129`	`129`	`}`
`130`	`130`
`131`		`- public FilterAposHyphenFr(TokenStream input) {`
	`131`	`+ public FrenchCliticSplitFilter(TokenStream input) {`
`132`	`132`	`super(input);`
`133`	`133`	`}`
`134`	`134`
Original file line number	Diff line number	Diff line change
`@@ -18,6 +18,7 @@`
`18`	`18`
`19`	`19`	`import static com.github.oeuvres.alix.common.Upos.*;`
`20`	`20`
	`21`	`+import com.github.oeuvres.alix.lucene.analysis.fr.FrenchCliticSplitFilter;`
`21`	`22`	`import com.github.oeuvres.alix.util.Char;`
`22`	`23`	`import com.github.oeuvres.alix.util.Dir;`
`23`	`24`
`@@ -31,7 +32,7 @@ public TokenStreamComponents createComponents(String field)`
`31`	`32`	`{`
`32`	`33`	`final Tokenizer tokenizer = new MLTokenizer();`
`33`	`34`	`TokenStream ts = tokenizer;`
`34`		`- ts = new FilterAposHyphenFr(tokenizer);`
	`35`	`+ ts = new FrenchCliticSplitFilter(tokenizer);`
`35`	`36`	`return new TokenStreamComponents(tokenizer, ts);`
`36`	`37`	`}`
`37`	`38`
Original file line number	Diff line number	Diff line change
`@@ -12,6 +12,7 @@`
`12`	`12`	`import org.junit.jupiter.api.Test;`
`13`	`13`
`14`	`14`	`import com.github.oeuvres.alix.common.Upos;`
	`15`	`+import com.github.oeuvres.alix.lucene.analysis.fr.FrenchCliticSplitFilter;`
`15`	`16`
`16`	`17`
`17`	`18`	`public class FilterAposHyphenFrTest`
`@@ -52,7 +53,7 @@ public TokenStreamComponents createComponents(String field)`
`52`	`53`	`{`
`53`	`54`	`final Tokenizer tokenizer = new MLTokenizer();`
`54`	`55`	`TokenStream ts = tokenizer;`
`55`		`- ts = new FilterAposHyphenFr(tokenizer);`
	`56`	`+ ts = new FrenchCliticSplitFilter(tokenizer);`
`56`	`57`	`return new TokenStreamComponents(tokenizer, ts);`
`57`	`58`	`}`
`58`	`59`