From 5913e742864637e8aa6fb7e80babf9e409ed3c89 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Luk=C3=A1=C5=A1=20Vl=C4=8Dek?= <lukas.vlcek@gmail.com>
Date: Tue, 21 Jun 2011 14:57:04 +0200
Subject: [PATCH] Analysis: expose Lucene KeywordMarkerFilter. Closes #1052

---
 .../index/analysis/AnalysisModule.java        |  2 +
 .../KeywordMarkerTokenFilterFactory.java      | 55 +++++++++++++++++++
 2 files changed, 57 insertions(+)
 create mode 100644 modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/KeywordMarkerTokenFilterFactory.java

diff --git a/modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/AnalysisModule.java b/modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/AnalysisModule.java
index 121ac0414eb..61a712d9508 100644
--- a/modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/AnalysisModule.java
+++ b/modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/AnalysisModule.java
@@ -384,6 +384,8 @@ public class AnalysisModule extends AbstractModule {
             tokenFiltersBindings.processTokenFilter("french_stem", FrenchStemTokenFilterFactory.class);
             tokenFiltersBindings.processTokenFilter("german_stem", GermanStemTokenFilterFactory.class);
             tokenFiltersBindings.processTokenFilter("russian_stem", RussianStemTokenFilterFactory.class);
+
+            tokenFiltersBindings.processTokenFilter("keyword_marker", KeywordMarkerTokenFilterFactory.class);
         }
 
         @Override public void processTokenizers(TokenizersBindings tokenizersBindings) {
diff --git a/modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/KeywordMarkerTokenFilterFactory.java b/modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/KeywordMarkerTokenFilterFactory.java
new file mode 100644
index 00000000000..996fb3af7e3
--- /dev/null
+++ b/modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/KeywordMarkerTokenFilterFactory.java
@@ -0,0 +1,55 @@
+/*
+ * 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. 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
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.elasticsearch.index.analysis;
+
+import org.apache.lucene.analysis.CharArraySet;
+import org.apache.lucene.analysis.KeywordMarkerFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.elasticsearch.ElasticSearchIllegalArgumentException;
+import org.elasticsearch.common.inject.Inject;
+import org.elasticsearch.common.inject.assistedinject.Assisted;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.env.Environment;
+import org.elasticsearch.index.Index;
+import org.elasticsearch.index.settings.IndexSettings;
+import org.apache.lucene.util.Version;
+
+import java.util.Set;
+
+@AnalysisSettingsRequired
+public class KeywordMarkerTokenFilterFactory extends AbstractTokenFilterFactory {
+
+    private final CharArraySet keywordLookup;
+
+    @Inject public KeywordMarkerTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
+        super(index, indexSettings, name, settings);
+
+        boolean ignoreCase = settings.getAsBoolean("ignore_case", false);
+        Set<String> rules = Analysis.getWordSet(env, settings, "keywords");
+        if (rules == null) {
+            throw new ElasticSearchIllegalArgumentException("keyword filter requires either `keywords` or `keywords_path` to be configured");
+        }
+        keywordLookup = new CharArraySet(Version.LUCENE_32, rules, ignoreCase);
+    }
+
+    @Override public TokenStream create(TokenStream tokenStream) {
+        return new KeywordMarkerFilter(tokenStream, keywordLookup);
+    }
+}