mirror of https://github.com/apache/lucene.git
SOLR-819: Added in factories for Arabic tokenizer/stemmer
git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/trunk@724062 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
parent
246a83f0d4
commit
4111e3b758
|
@ -101,6 +101,8 @@ New Features
|
|||
|
||||
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 @@ Other Changes
|
|||
|
||||
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
|
||||
----------------------
|
||||
|
|
|
@ -1,2 +1,2 @@
|
|||
AnyObjectId[bd68f2e2af1f4c65f2857a0c5fb2d39b910e122d] was removed in git history.
|
||||
AnyObjectId[44288d7bcfdc6e8ffa2cad2e63e5501b79a7adc4] was removed in git history.
|
||||
Apache SVN contains full history.
|
|
@ -1,2 +1,2 @@
|
|||
AnyObjectId[392f97ca7b216bcb772746bc4106154c96f2c4f6] was removed in git history.
|
||||
AnyObjectId[611288f868c675bcb3035a37f24241dc2467b070] was removed in git history.
|
||||
Apache SVN contains full history.
|
|
@ -1,2 +1,2 @@
|
|||
AnyObjectId[76fe36d5a34fea911866a623f2b81a99b5d51462] was removed in git history.
|
||||
AnyObjectId[b81869d9d757536394778e3fa1745cafbe0de9be] was removed in git history.
|
||||
Apache SVN contains full history.
|
|
@ -1,2 +1,2 @@
|
|||
AnyObjectId[734a27bf9d7d0e1af60c959f3ac94fa396faf78f] was removed in git history.
|
||||
AnyObjectId[646dc4e52ca42021cb57206ff3fde0640207711c] was removed in git history.
|
||||
Apache SVN contains full history.
|
|
@ -1,2 +1,2 @@
|
|||
AnyObjectId[54d7e351cf51f25642359e551e2df1765f9b5a3c] was removed in git history.
|
||||
AnyObjectId[fad9361f68e6eda6db82653420ae20497d1b9675] was removed in git history.
|
||||
Apache SVN contains full history.
|
|
@ -1,2 +1,2 @@
|
|||
AnyObjectId[b1ad8fbea0c97811807841055b053aa535170386] was removed in git history.
|
||||
AnyObjectId[b5bc8abac7c1645b58a12bc6942d00aca0a3afe5] was removed in git history.
|
||||
Apache SVN contains full history.
|
|
@ -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);
|
||||
}
|
||||
}
|
|
@ -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);
|
||||
}
|
||||
}
|
|
@ -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);
|
||||
}
|
||||
}
|
Loading…
Reference in New Issue