Skip to content

Apache Lucene open-source search software

LUCENE-10312: MIGRATE entry and small follow-ups (#908)

Tomoko Uchida71a9acb2e2aa
diff --git a/lucene/MIGRATE.md b/lucene/MIGRATE.md
index a6836166046..8a1c5c535bb 100644
--- a/lucene/MIGRATE.md
+++ b/lucene/MIGRATE.md
@@ -19,6 +19,11 @@
## Migration from Lucene 9.x to Lucene 10.0
+### PersianStemFilter is added to PersianAnalyzer (LUCENE-10312)
+
+PersianAnalyzer now includes PersianStemFilter, that would change analysis results. If you need the exactly same analysis
+behaviour as 9.x, clone `PersianAnalyzer` in 9.x or create custom analyzer by using `CustomAnalyzer` on your own.
+
### AutomatonQuery/CompiledAutomaton/RunAutomaton/RegExp no longer determinize (LUCENE-10010)
These classes no longer take a `determinizeWorkLimit` and no longer determinize
diff --git a/lucene/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianAnalyzer.java b/lucene/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianAnalyzer.java
index afc41233906..2da9df1f3cc 100644
--- a/lucene/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianAnalyzer.java
+++ b/lucene/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianAnalyzer.java
@@ -121,8 +121,8 @@ public final class PersianAnalyzer extends StopwordAnalyzerBase {
*
* @return {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents} built from a {@link
* StandardTokenizer} filtered with {@link LowerCaseFilter}, {@link DecimalDigitFilter},
- * {@link ArabicNormalizationFilter}, {@link PersianNormalizationFilter} and Persian Stop
- * words
+ * {@link ArabicNormalizationFilter}, {@link PersianNormalizationFilter}, Persian Stop words,
+ * and {@link PersianStemFilter}.
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
diff --git a/lucene/analysis/common/src/test/org/apache/lucene/analysis/fa/TestPersianStemFilter.java b/lucene/analysis/common/src/test/org/apache/lucene/analysis/fa/TestPersianStemFilter.java
index 983dd077347..5b7716cf124 100644
--- a/lucene/analysis/common/src/test/org/apache/lucene/analysis/fa/TestPersianStemFilter.java
+++ b/lucene/analysis/common/src/test/org/apache/lucene/analysis/fa/TestPersianStemFilter.java
@@ -32,7 +32,14 @@ public class TestPersianStemFilter extends BaseTokenStreamTestCase {
@Override
public void setUp() throws Exception {
super.setUp();
- a = new PersianAnalyzer();
+ a =
+ new Analyzer() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName) {
+ final Tokenizer source = new MockTokenizer();
+ return new TokenStreamComponents(source, new PersianStemFilter(source));
+ }
+ };
}
@Override