Author: gsingers
Date: Sat Dec 6 17:34:47 2008
New Revision: 724062
URL: http://svn.apache.org/viewvc?rev=724062&view=rev
Log:
SOLR-819: Added in factories for Arabic tokenizer/stemmer
Added:
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicLetterTokenizerFactory.java
(with props)
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicNormalizationFilterFactory.java
(with props)
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicStemFilterFactory.java
(with props)
Modified:
lucene/solr/trunk/CHANGES.txt
lucene/solr/trunk/lib/lucene-analyzers-2.9-dev.jar
lucene/solr/trunk/lib/lucene-core-2.9-dev.jar
lucene/solr/trunk/lib/lucene-highlighter-2.9-dev.jar
lucene/solr/trunk/lib/lucene-queries-2.9-dev.jar
lucene/solr/trunk/lib/lucene-snowball-2.9-dev.jar
lucene/solr/trunk/lib/lucene-spellchecker-2.9-dev.jar
Modified: lucene/solr/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/lucene/solr/trunk/CHANGES.txt?rev=724062&r1=724061&r2=724062&view=diff
==============================================================================
--- lucene/solr/trunk/CHANGES.txt (original)
+++ lucene/solr/trunk/CHANGES.txt Sat Dec 6 17:34:47 2008
@@ -101,6 +101,8 @@
20. SOLR-284: Added support for extracting content from binary documents like
MS Word and PDF using Apache Tika. See also contrib/extraction/CHANGES.txt
(Eric Pugh, Chris Harris, gsingers)
+21. SOLR-819: Added factories for Arabic support (gsingers)
+
Optimizations
----------------------
1. SOLR-374: Use IndexReader.reopen to save resources by re-using parts of the
@@ -175,6 +177,7 @@
8. SOLR-875: Upgraded to Lucene 2.9-dev (r723985) and consolidated the BitSet
implementations (Michael Busch, gsingers)
+ 9. SOLR-819: Upgraded to Lucene 2.9-dev (r724059) to get access to Arabic
public constructors (gsingers)
Build
----------------------
Modified: lucene/solr/trunk/lib/lucene-analyzers-2.9-dev.jar
URL:
http://svn.apache.org/viewvc/lucene/solr/trunk/lib/lucene-analyzers-2.9-dev.jar?rev=724062&r1=724061&r2=724062&view=diff
==============================================================================
Binary files - no diff available.
Modified: lucene/solr/trunk/lib/lucene-core-2.9-dev.jar
URL:
http://svn.apache.org/viewvc/lucene/solr/trunk/lib/lucene-core-2.9-dev.jar?rev=724062&r1=724061&r2=724062&view=diff
==============================================================================
Binary files - no diff available.
Modified: lucene/solr/trunk/lib/lucene-highlighter-2.9-dev.jar
URL:
http://svn.apache.org/viewvc/lucene/solr/trunk/lib/lucene-highlighter-2.9-dev.jar?rev=724062&r1=724061&r2=724062&view=diff
==============================================================================
Binary files - no diff available.
Modified: lucene/solr/trunk/lib/lucene-queries-2.9-dev.jar
URL:
http://svn.apache.org/viewvc/lucene/solr/trunk/lib/lucene-queries-2.9-dev.jar?rev=724062&r1=724061&r2=724062&view=diff
==============================================================================
Binary files - no diff available.
Modified: lucene/solr/trunk/lib/lucene-snowball-2.9-dev.jar
URL:
http://svn.apache.org/viewvc/lucene/solr/trunk/lib/lucene-snowball-2.9-dev.jar?rev=724062&r1=724061&r2=724062&view=diff
==============================================================================
Binary files - no diff available.
Modified: lucene/solr/trunk/lib/lucene-spellchecker-2.9-dev.jar
URL:
http://svn.apache.org/viewvc/lucene/solr/trunk/lib/lucene-spellchecker-2.9-dev.jar?rev=724062&r1=724061&r2=724062&view=diff
==============================================================================
Binary files - no diff available.
Added:
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicLetterTokenizerFactory.java
URL:
http://svn.apache.org/viewvc/lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicLetterTokenizerFactory.java?rev=724062&view=auto
==============================================================================
---
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicLetterTokenizerFactory.java
(added)
+++
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicLetterTokenizerFactory.java
Sat Dec 6 17:34:47 2008
@@ -0,0 +1,18 @@
+package org.apache.solr.analysis;
+
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.ar.ArabicLetterTokenizer;
+
+import java.io.Reader;
+
+
+/**
+ *
+ *
+ **/
+public class ArabicLetterTokenizerFactory extends BaseTokenizerFactory{
+
+ public TokenStream create(Reader input) {
+ return new ArabicLetterTokenizer(input);
+ }
+}
Propchange:
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicLetterTokenizerFactory.java
------------------------------------------------------------------------------
svn:eol-style = native
Added:
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicNormalizationFilterFactory.java
URL:
http://svn.apache.org/viewvc/lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicNormalizationFilterFactory.java?rev=724062&view=auto
==============================================================================
---
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicNormalizationFilterFactory.java
(added)
+++
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicNormalizationFilterFactory.java
Sat Dec 6 17:34:47 2008
@@ -0,0 +1,16 @@
+package org.apache.solr.analysis;
+
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.ar.ArabicNormalizationFilter;
+
+
+/**
+ *
+ *
+ **/
+public class ArabicNormalizationFilterFactory extends BaseTokenFilterFactory{
+
+ public TokenStream create(TokenStream input) {
+ return new ArabicNormalizationFilter(input);
+ }
+}
Propchange:
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicNormalizationFilterFactory.java
------------------------------------------------------------------------------
svn:eol-style = native
Added:
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicStemFilterFactory.java
URL:
http://svn.apache.org/viewvc/lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicStemFilterFactory.java?rev=724062&view=auto
==============================================================================
---
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicStemFilterFactory.java
(added)
+++
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicStemFilterFactory.java
Sat Dec 6 17:34:47 2008
@@ -0,0 +1,17 @@
+package org.apache.solr.analysis;
+
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.ar.ArabicStemFilter;
+
+
+/**
+ *
+ *
+ **/
+public class ArabicStemFilterFactory extends BaseTokenFilterFactory{
+
+
+ public TokenStream create(TokenStream input) {
+ return new ArabicStemFilter(input);
+ }
+}
Propchange:
lucene/solr/trunk/src/java/org/apache/solr/analysis/ArabicStemFilterFactory.java
------------------------------------------------------------------------------
svn:eol-style = native