IKAnalyzer中文分词

1. Project structure
   
   

2. IKAnalyzer.cfg.xml
   

   The configuration file of IKAnalyzer, a sentence separator supported Chinese. It must in the root of src.
   

   <?xml version="1.0" encoding="UTF-8"?>
   <!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">  
   <properties>  
   <comment>IK Analyzer extra configuration</comment>
   <!-- configure your own dic here -->
   <entry key="ext_dict">cn/com/tragicEnding/prov/util/ext.dic;</entry> 
   <!-- configure your own stop dic here -->
   <entry key="ext_stopwords">cn/com/tragicEnding/prov/util/stopword.dic</entry> 
   </properties>

3. ext.dic / stopword.dic
   

   View the spec of dic.
       
   

4. Keywords.java
   

   Function to separate sentence.
   

   public static List<String> splitToKeywords(String word)
   {
   	List<String> keywords = new ArrayList<String>();
   	try
   	{
   		Analyzer anal = new IKAnalyzer(true);
   		StringReader reader = new StringReader(word);
   		TokenStream ts = anal.tokenStream("", reader);
   		CharTermAttribute term = ts.getAttribute(CharTermAttribute.class);
   		while(ts.incrementToken())
   		{
   			keywords.add(term.toString());
   		}
   		reader.close();
   		anal.close();
   
   	}
   	catch(Exception e)
   	{
   		e.printStackTrace();
   	}
   
   	return keywords;
   }