From 96e38eca6183646c77d4fde99eec457b22e5df4b Mon Sep 17 00:00:00 2001
From: barsk <krjg@devo.se>
Date: Tue, 28 Feb 2012 13:57:54 +0100
Subject: [PATCH] Exposing filtering capabilities via the unicodeSetFilter
 attribute

---
 .../IcuFoldingTokenFilterFactory.java         | 41 +++++++++++++++----
 1 file changed, 34 insertions(+), 7 deletions(-)

diff --git a/src/main/java/org/elasticsearch/index/analysis/IcuFoldingTokenFilterFactory.java b/src/main/java/org/elasticsearch/index/analysis/IcuFoldingTokenFilterFactory.java
index ed11a227dcf..f543654dbc3 100644
--- a/src/main/java/org/elasticsearch/index/analysis/IcuFoldingTokenFilterFactory.java
+++ b/src/main/java/org/elasticsearch/index/analysis/IcuFoldingTokenFilterFactory.java
@@ -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
  * 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
  * "License"); you may not use this file except in compliance
  * 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.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 {
+    private final String unicodeSetFilter;
 
-    @Inject
-    public IcuFoldingTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, @Assisted String name, @Assisted Settings settings) {
+    @Inject public IcuFoldingTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, @Assisted String name, @Assisted Settings settings) {
         super(index, indexSettings, name, settings);
+        this.unicodeSetFilter = settings.get("unicodeSetFilter");
     }
 
-    @Override
-    public TokenStream create(TokenStream tokenStream) {
-        return new ICUFoldingFilter(tokenStream);
+    @Override public TokenStream create(TokenStream 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);
+    	}
     }
 }
\ No newline at end of file