honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Exposing filtering capabilities via the unicodeSetFilter attribute

This commit is contained in:
barsk 2012-02-28 13:57:54 +01:00
parent 7c87f2aa50
commit 96e38eca61
1 changed files with 34 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
src/main/java/org/elasticsearch/index/analysis/IcuFoldingTokenFilterFactory.java
View File

@ -1,8 +1,8 @@
/* /*
* Licensed to ElasticSearch and Shay Banon under one * Licensed to Elastic Search and Shay Banon under one
* or more contributor license agreements. See the NOTICE file * or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information * distributed with this work for additional information
* regarding copyright ownership. ElasticSearch licenses this * regarding copyright ownership. Elastic Search licenses this
* file to you under the Apache License, Version 2.0 (the * file to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance * "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at * with the License. You may obtain a copy of the License at
@ -27,19 +27,46 @@ import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.index.Index; import org.elasticsearch.index.Index;
import org.elasticsearch.index.settings.IndexSettings; import org.elasticsearch.index.settings.IndexSettings;
import com.ibm.icu.text.FilteredNormalizer2;
import com.ibm.icu.text.Normalizer2;
import com.ibm.icu.text.UnicodeSet;
/** /**
* Uses the {@link org.apache.lucene.analysis.icu.ICUFoldingFilter}.
* Applies foldings from UTR#30 Character Foldings.
* <p>
* Can be filtered to handle certain characters in a specified way (see http://icu-project.org/apiref/icu4j/com/ibm/icu/text/UnicodeSet.html)
* E.g national chars that should be retained (filter : "[^åäöÅÄÖ]").
* *
* <p>The <tt>unicodeSetFilter</tt> attribute can be used to provide the UniCodeSet for filtering.
*
* @author kimchy (shay.banon)
*/ */
public class IcuFoldingTokenFilterFactory extends AbstractTokenFilterFactory { public class IcuFoldingTokenFilterFactory extends AbstractTokenFilterFactory {
private final String unicodeSetFilter;
@Inject @Inject public IcuFoldingTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, @Assisted String name, @Assisted Settings settings) {
public IcuFoldingTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, @Assisted String name, @Assisted Settings settings) {
super(index, indexSettings, name, settings); super(index, indexSettings, name, settings);
this.unicodeSetFilter = settings.get("unicodeSetFilter");
} }
@Override @Override public TokenStream create(TokenStream tokenStream) {
public TokenStream create(TokenStream tokenStream) {
return new ICUFoldingFilter(tokenStream); // The ICUFoldingFilter is in fact implemented as a ICUNormalizer2Filter.
// ICUFoldingFilter lacks a constructor for adding filtering so we implemement it here
if (unicodeSetFilter != null) {
Normalizer2 base = Normalizer2.getInstance(
ICUFoldingFilter.class.getResourceAsStream("utr30.nrm"),
"utr30", Normalizer2.Mode.COMPOSE);
UnicodeSet unicodeSet = new UnicodeSet(unicodeSetFilter);
unicodeSet.freeze();
Normalizer2 filtered = new FilteredNormalizer2(base, unicodeSet);
return new org.apache.lucene.analysis.icu.ICUNormalizer2Filter(tokenStream, filtered);
}
else {
return new ICUFoldingFilter(tokenStream);
}
} }
} }