From 963fac4771477e0808ffff0e005fd0e9e767fb85 Mon Sep 17 00:00:00 2001
From: piaolingxue <piaolingxue305@gmail.com>
Date: Mon, 17 Jun 2013 11:45:39 +0800
Subject: [PATCH] add ik tokenizers and remove some useless class[IkAnalyzer].

---
 .../analysis/IkAnalysisBinderProcessor.java   |  7 ++++
 .../index/analysis/IkAnalyzer.java            | 33 -------------------
 .../index/analysis/IkTokenizerFactory.java    | 28 ++++++++++++++++
 3 files changed, 35 insertions(+), 33 deletions(-)
 delete mode 100644 src/main/java/org/elasticsearch/index/analysis/IkAnalyzer.java
 create mode 100644 src/main/java/org/elasticsearch/index/analysis/IkTokenizerFactory.java

diff --git a/src/main/java/org/elasticsearch/index/analysis/IkAnalysisBinderProcessor.java b/src/main/java/org/elasticsearch/index/analysis/IkAnalysisBinderProcessor.java
index 88661b3..a448c8a 100644
--- a/src/main/java/org/elasticsearch/index/analysis/IkAnalysisBinderProcessor.java
+++ b/src/main/java/org/elasticsearch/index/analysis/IkAnalysisBinderProcessor.java
@@ -12,4 +12,11 @@ public class IkAnalysisBinderProcessor extends AnalysisModule.AnalysisBinderProc
         analyzersBindings.processAnalyzer("ik", IkAnalyzerProvider.class);
         super.processAnalyzers(analyzersBindings);
     }
+
+
+    @Override
+    public void processTokenizers(TokenizersBindings tokenizersBindings) {
+      tokenizersBindings.processTokenizer("ik", IkTokenizerFactory.class);
+      super.processTokenizers(tokenizersBindings);
+    }
 }
diff --git a/src/main/java/org/elasticsearch/index/analysis/IkAnalyzer.java b/src/main/java/org/elasticsearch/index/analysis/IkAnalyzer.java
deleted file mode 100644
index ffdf0d6..0000000
--- a/src/main/java/org/elasticsearch/index/analysis/IkAnalyzer.java
+++ /dev/null
@@ -1,33 +0,0 @@
-package org.elasticsearch.index.analysis;
-
-import org.apache.lucene.analysis.Analyzer;
-import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.Tokenizer;
-import org.wltea.analyzer.lucene.IKTokenizer;
-//import org.wltea.lucene.IKTokenizer;
-
-import java.io.Reader;
-
-
-public class IkAnalyzer extends Analyzer {
-//    private boolean isMaxWordLength = false;
-//    @Override public TokenStream tokenStream(String fieldName, Reader reader) {
-//        return new IKTokenizer(reader,true);
-//    }
-    
-  
-    public IkAnalyzer() {
-        super(); 
-    }
-
-    @Override
-    protected TokenStreamComponents createComponents(String s, Reader reader) {
-//        new TokenStreamComponents
-        Tokenizer tokenizer = new IKTokenizer(reader, true);
-        return new TokenStreamComponents(tokenizer, null);  //To change body of implemented methods use File | Settings | File Templates.
-    }
-
-//    public boolean isMaxWordLength() {
-//        return isMaxWordLength;
-//    }
-}
diff --git a/src/main/java/org/elasticsearch/index/analysis/IkTokenizerFactory.java b/src/main/java/org/elasticsearch/index/analysis/IkTokenizerFactory.java
new file mode 100644
index 0000000..83d284c
--- /dev/null
+++ b/src/main/java/org/elasticsearch/index/analysis/IkTokenizerFactory.java
@@ -0,0 +1,28 @@
+package org.elasticsearch.index.analysis;
+
+import java.io.Reader;
+
+import org.apache.lucene.analysis.Tokenizer;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.index.Index;
+import org.wltea.analyzer.dic.Dictionary;
+import org.wltea.analyzer.lucene.IKTokenizer;
+
+public class IkTokenizerFactory extends AbstractTokenizerFactory {
+  private boolean useSmart = false;
+
+  public IkTokenizerFactory(Index index, Settings indexSettings, String name, Settings settings) {
+    super(index, indexSettings, name, settings);
+    Dictionary.getInstance().Init(indexSettings);
+
+    if (settings.get("use_smart", "true").equals("true")) {
+      useSmart = true;
+    }
+  }
+
+  @Override
+  public Tokenizer create(Reader reader) {
+    return new IKTokenizer(reader, useSmart);
+  }
+
+}