Index: contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java
===================================================================
--- contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java (revision 797160)
+++ contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java (working copy)
@@ -36,10 +36,9 @@
*
* This analyzer implements light-stemming as specified by:
*
- * Improving Stemming for Arabic Information Retrieval:
- * Light Stemming and Co-occurrence Analysis
+ * Light Stemming for Arabic Information Retrieval
*
- * http://ciir.cs.umass.edu/pubfiles/ir-249.pdf
+ * http://www.mtholyoke.edu/~lballest/Pubs/arab_stem05.pdf
*
* The analysis package contains three primary components:
*
Index: contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicStemmer.java
===================================================================
--- contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicStemmer.java (revision 797160)
+++ contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicStemmer.java (working copy)
@@ -43,6 +43,7 @@
public static final char prefixes[][] = {
("" + ALEF + LAM).toCharArray(),
+ ("" + LAM + LAM).toCharArray(),
("" + WAW + ALEF + LAM).toCharArray(),
("" + BEH + ALEF + LAM).toCharArray(),
("" + KAF + ALEF + LAM).toCharArray(),
Index: contrib/analyzers/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java
===================================================================
--- contrib/analyzers/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java (revision 797160)
+++ contrib/analyzers/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java (working copy)
@@ -39,6 +39,9 @@
check("الحسن", "حسن");
}
+ public void testLlPrefix() throws IOException {
+ check("للاخر", "اخر");
+ }
public void testWalPrefix() throws IOException {
check("والحسن", "حسن");
}