MMSegAnalyzer 自定义 同义词分词器

package synonym;

import java.io.File;
import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.en.PorterStemFilter;
import org.apache.lucene.analysis.synonym.SynonymFilter;
import org.apache.lucene.analysis.synonym.SynonymMap;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.util.CharsRef;
import org.apache.lucene.util.Version;

import com.chenlb.mmseg4j.Dictionary;
import com.chenlb.mmseg4j.MaxWordSeg;
import com.chenlb.mmseg4j.Seg;
import com.chenlb.mmseg4j.analysis.MMSegTokenizer;

public class MMSegAnalyzer extends Analyzer {
	
	protected Dictionary dic;

	/**
	 * @see Dictionary#getInstance()
	 */
	public MMSegAnalyzer() {
		dic = Dictionary.getInstance();
	}

	/**
	 * @param path 词库路径
	 * @see Dictionary#getInstance(String)
	 */
	public MMSegAnalyzer(String path) {
		dic = Dictionary.getInstance(path);
	}

	/**
	 * @param path 词库目录
	 * @see Dictionary#getInstance(File)
	 */
	public MMSegAnalyzer(File path) {
		dic = Dictionary.getInstance(path);
	}

	public MMSegAnalyzer(Dictionary dic) {
		super();
		this.dic = dic;
	}

	protected Seg newSeg() {
		return new MaxWordSeg(dic);
	}

	public Dictionary getDict() {
		return dic;
	}

	// 自定义停用词
	private static final String[] stopWords = {"and", "of", "the", "to", "is", "their", "can", "all"};

	@Override
	protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
		// 创建一个分词器
		//Tokenizer tokenizer = new StandardTokenizer(Version.LUCENE_47, reader);
		
		Tokenizer tokenizer = new MMSegTokenizer(newSeg(), reader);
		
		
		// 创建一系列的分词过滤器
		TokenFilter lowerCaseFilter = new LowerCaseFilter(Version.LUCENE_47, tokenizer);
		TokenFilter synonymFilter = new SynonymFilter(lowerCaseFilter, getSynonymMap(), true);
		TokenFilter stopFilter = new StopFilter(Version.LUCENE_47, synonymFilter, buildCharArraySetFromArry(stopWords));
		TokenFilter stemFilter = new PorterStemFilter(stopFilter);
		
		// TokenStream的包装类 在2.2之中 是TokenStream
		return new TokenStreamComponents(tokenizer, stemFilter);
	}
	
	// 将数组转成lucene可识别的CharArraySet对象 CharArraySet类似java.util.set
	private CharArraySet buildCharArraySetFromArry(String[] array) {
		CharArraySet set = new CharArraySet(Version.LUCENE_47, array.length, true);
		for(String value : array) {
			set.add(value);
		}
		return set;
	}
	
	// 创建一个同义词表
	private SynonymMap getSynonymMap() {
		String base1 = "fast";
		String syn1 = "rapid";
		
		String base2 = "slow";
		String syn2 = "sluggish";
		
		String base3 = "中国";
		String syn3 = "天朝";
		
		SynonymMap.Builder sb = new SynonymMap.Builder(true);
		sb.add(new CharsRef(base1), new CharsRef(syn1), true);
		sb.add(new CharsRef(base2), new CharsRef(syn2), true);
		sb.add(new CharsRef(base3), new CharsRef(syn3), true);
		
		sb.add(new CharsRef(syn3), new CharsRef(base3), true);
		
		SynonymMap smap = null;
		try {
			smap = sb.build();
		} catch (IOException e) {
			e.printStackTrace();
		}
		return smap;
	}
	
	// 测试方法
	public static void testPorterStemmingAnalyzer() throws IOException {
		Analyzer analyzer = new MMSegAnalyzer();
		String text = "Collective slow intelligence and Web2.0, fast and rapid2  天朝";
		Reader reader = new StringReader(text);
		TokenStream ts = null;
		try {
			ts = analyzer.tokenStream(null, reader);
			//ts.reset();
			while(ts.incrementToken()) {
				CharTermAttribute ta = ts.getAttribute(CharTermAttribute.class);  
				System.out.println(ta.toString());
			}
		} catch (IOException e) {
			e.printStackTrace();
		} 
		
	}
	
	public static void main(String[] args) throws IOException {
		testPorterStemmingAnalyzer();
	}

}

package luncen;
 
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.analysis.synonym.SynonymFilterFactory;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.util.FilesystemResourceLoader;
import org.apache.lucene.util.Version;
 
/**
 * @author hankcs
 */
public class TestSynonyms
{
    private static void displayTokens(TokenStream ts) throws IOException
    {
        CharTermAttribute termAttr = ts.addAttribute(CharTermAttribute.class);
        OffsetAttribute offsetAttribute = ts.addAttribute(OffsetAttribute.class);
        ts.reset();
        while (ts.incrementToken())
        {
            String token = termAttr.toString();
            System.out.print(offsetAttribute.startOffset() + "-" + offsetAttribute.endOffset() + "[" + token + "] ");
        }
        System.out.println();
        ts.end();
        ts.close();
    }
 
    public static void main(String[] args) throws Exception
    {
        String testInput = "其实 hankcs 似 好人 luncen";
        Version ver = Version.LUCENE_47;
        Map<String, String> filterArgs = new HashMap<String, String>();
        filterArgs.put("luceneMatchVersion", ver.toString());
        filterArgs.put("synonyms", "f:\\synonym.txt");
        filterArgs.put("expand", "true");
        SynonymFilterFactory factory = new SynonymFilterFactory(filterArgs);
        factory.inform(new FilesystemResourceLoader());
        WhitespaceAnalyzer whitespaceAnalyzer = new WhitespaceAnalyzer(ver);
        TokenStream ts = factory.create(whitespaceAnalyzer.tokenStream("someField", testInput));
        displayTokens(ts);
    }
}