lucene 4.0 小示例

package test;

import java.io.File;
import java.io.StringReader;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.MultiReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;

public class Test {
	private static Log logger = LogFactory.getLog(Test.class);

	public static void main(String[] args) throws Exception {
		//write();
		//read();
		analyKeyWord("北京 全文索引");
	}
	
	public static void write() throws Exception {
		File dir = new File("d:/indexdata2/");
		Analyzer analyzer = new IKAnalyzer();
		FSDirectory directory = FSDirectory.open(dir);
	    IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_40, analyzer);  
		IndexWriter writer = new IndexWriter(directory, iwc);
		try{
			Document doc = new Document();
			doc.add(new StringField("id", "1", Field.Store.YES));
			doc.add(new TextField("title", "用lucene实现在一个上海", Field.Store.YES));
			doc.add(new TextField("content","用lucene实现在一个(或者多个)字段中查找多个关键字", Field.Store.YES));
			doc.add(new StringField("cityCode", "32057",Field.Store.YES));
			writer.addDocument(doc);
			//writer.deleteDocuments(new Term("title", "用lucene实现在一个上海"+i));
			//writer.updateDocument(new Term("title", "用lucene实现在一个上海"+i), doc);
			
			Document doc1 = new Document();
			doc1.add(new StringField("id", "1", Field.Store.YES));
			doc1.add(new TextField("title", "开源的免费北京", Field.Store.YES));
			doc1.add(new TextField("content","Lucene是非常优秀的成熟的开源的的纯java语言的全文索引检索工具包", Field.Store.YES));
			doc1.add(new StringField("cityCode", "32057",Field.Store.YES));
			writer.addDocument(doc1);
			//writer.forceMerge(1);
		} catch(Exception ex) {
			logger.error(ex.getMessage(),ex);
		} finally{
			writer.close();
		}
	}
	
	public static void read() throws Exception {
		File dir = new File("d:/indexdata2/");
		FSDirectory directory = FSDirectory.open(dir);
		IndexReader reader  = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		
		//MultiReader
		/*File dir2 = new File("d:/indexdata2/");
		FSDirectory directory2 = FSDirectory.open(dir2);
		IndexReader reader2  = DirectoryReader.open(directory2);
		MultiReader mr = new MultiReader(reader,reader2);
		IndexSearcher searcher = new IndexSearcher(mr);
		mr.close();*/
		
		//对要查询的关键字进行分词
		Analyzer analyzer = new IKAnalyzer();	
		String[] fields = {"title", "content"};
		
		BooleanQuery query = new BooleanQuery();
		TermQuery cityQuery = new TermQuery(new Term("cityCode", "32057"));
		MultiFieldQueryParser parser = new MultiFieldQueryParser(Version.LUCENE_40, fields, analyzer);
		parser.setDefaultOperator(QueryParser.AND_OPERATOR);
		Query keyQuery = parser.parse("北京 全文索引");
		//BooleanClause.Occur[] flags = new BooleanClause.Occur[] {BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD};
		//Query keyQuery = MultiFieldQueryParser.parse(Version.LUCENE_40, keyword, fields, flags, analyzer);
		
		query.add(cityQuery, BooleanClause.Occur.MUST);
		query.add(keyQuery, BooleanClause.Occur.MUST);
		
		
		//BooleanQuery
		/*BooleanQuery boolquery = new BooleanQuery();
		QueryParser parser = new QueryParser(Version.LUCENE_40, "title",analyzer);
		parser.setDefaultOperator(QueryParser.AND_OPERATOR);
		boolquery.add(parser.parse("北京 全文检索"),BooleanClause.Occur.SHOULD);
		
		QueryParser parser2 = new QueryParser(Version.LUCENE_40, "content",analyzer);
		parser2.setDefaultOperator(QueryParser.AND_OPERATOR);
		boolquery.add(parser2.parse("北京 全文检索"),BooleanClause.Occur.SHOULD);
		
		BooleanQuery query2 = new BooleanQuery();
		query2.add(cityQuery, BooleanClause.Occur.MUST);
		query.add(boolquery, BooleanClause.Occur.MUST);*/
		
		//排序
		//Sort sort = new Sort(new SortField[]{SortField.FIELD_SCORE, new SortField("pubDate", SortField.Type.STRING, true)});

		TopDocs results = searcher.search(query, 10);
	    ScoreDoc[] hits = results.scoreDocs;
		for (int i = 0; i < hits.length; i++) {
			Document doc = searcher.doc(hits[i].doc);
			String title = doc.get("title");
			
			//高亮
			SimpleHTMLFormatter format = new SimpleHTMLFormatter("<font color=red>", "</font>");
			Highlighter highlighter = new Highlighter(format, new QueryScorer(query));					

			//关键字附近字符串的截取，截取150个字符
			Fragmenter fragmenter = new SimpleFragmenter(150);				
			highlighter.setTextFragmenter(fragmenter);	
			TokenStream title_tokenStream = analyzer.tokenStream("title", new StringReader(title));
			title = highlighter.getBestFragment(title_tokenStream, title);
			if(title == null) {
				title = doc.get("title");
			}
				
			System.out.println(title);
		}
		System.out.println("共检索出符合条件的Document "+hits.length+" 个。");
		reader.close();

	}
	
	/**
	 * 分词
	 */
	public static void analyKeyWord(String keyWord) throws Exception	 {
		Analyzer analyzer = new IKAnalyzer();
		StringReader strReader = new StringReader(keyWord);
		TokenStream ts = analyzer.tokenStream(keyWord, strReader);
		StringBuilder builder = new StringBuilder();
		while (ts.incrementToken()) {
			CharTermAttribute ta = ts.getAttribute(CharTermAttribute.class);
			builder.append(ta.toString() + " ");
		}
		System.out.println(builder.toString());
	}
	

}