lucene的使用

2019独角兽企业重金招聘Python工程师标准>>>

使用luncene3.6

下载地址   http://www.apache.org/dyn/closer.cgi/lucene/java/3.6.1

分词器使用 mmseg4j

下载地址  http://code.google.com/p/mmseg4j/downloads/list

项目中使用到的jar包有  :

lucene-3.6.1/lucene-core-3.6.1.jar(核心包)

lucene-3.6.1/contrib/lucene-analyzers-3.6.1.jar(分词包)

lucene-3.6.1/contrib/lucene-highlighter-3.6.1.jar(高亮包)

mmseg4j-1.8.3/mmseg4j-all-1.8.3.jar(第三方分词器，因为luncene自带的分词器没有词库，汉字都是一个一个拆开的)

使用时记得设置词库的路径

mmseg4j-1.8.3/data

package lucene;

import java.io.File;
import java.io.StringReader;
import java.util.List;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.Fieldable;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.search.highlight.Formatter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
import com.chenlb.mmseg4j.analysis.MaxWordAnalyzer;

public class LuceneSearch {
	
	//mmseg4j词库路径
	private static final String DISC_URL = "D:/My Documents/Downloads/mmseg4j-1.8.3/data";
	//指定分词器 StandardAnalyzer、MaxWordAnalyzer、SimpleAnalyzer、ComplexAnalyzer
	private static Analyzer analyzer = new MaxWordAnalyzer(new File(DISC_URL));
	//lucene版本
	private static Version version = Version.LUCENE_36;
	//指定索引位置   RAMDirectory(内存)、FSDirectory(文件)
	private static Directory directory = new RAMDirectory();
	//配置
	private static IndexWriterConfig conf = new IndexWriterConfig(version,analyzer);
	//配置IndexWriter
	private static IndexWriter writer;
	static{
		try {
			writer = new IndexWriter(directory, conf);
		} catch (Exception e) {
		}
	}

	/**
	 * 全量索引
	 * @Author TangJiaZhi
	 */
	public void fullIndex(Document[] documentes) throws Exception {
		
		writer.deleteAll();
		for (Document document : documentes) {
			writer.addDocument(document);
		}
		writer.commit();
//		writer.close();
	}
	
	
	/**
	 * 根据id删除索引
	 * @Author TangJiaZhi
	 */
	public void deleteIndex(Document document)throws Exception{
		Term term = new Term("id", document.get("id"));
		writer.deleteDocuments(term);
		writer.commit();
	}
	
	/**
	 * 根据id增量索引
	 * @Author TangJiaZhi
	 */
	public void updateIndex(Document[] documentes) throws Exception{
		for (Document document : documentes) {
			Term term = new Term("id", document.get("id"));
			writer.updateDocument(term, document);
		}
		writer.commit();
//		writer.close();
	}
	
	/**
	 * 直接查询
	 * @Author TangJiaZhi
	 */
	public void simpleSearch(String filedStr,String queryStr,int page, int pageSize) throws Exception{
		IndexReader reader = IndexReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		TopScoreDocCollector topCollector = TopScoreDocCollector.create(searcher.maxDoc(), false);
		
		Term term = new Term(filedStr, queryStr);
		Query query = new TermQuery(term);
		searcher.search(query, topCollector);
		ScoreDoc[] docs = topCollector.topDocs((page-1)*pageSize, pageSize).scoreDocs;
		
		printScoreDoc(docs, searcher);
	}
	
	/**
	 * 高亮查询
	 * @Author TangJiaZhi
	 */
	public void highLightSearch(String filedStr,String queryStr,int page, int pageSize) throws Exception{
		IndexReader reader = IndexReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		TopScoreDocCollector topCollector = TopScoreDocCollector.create(searcher.maxDoc(), false);
		
		Term term = new Term(filedStr, queryStr);
		Query query = new TermQuery(term);
		searcher.search(query, topCollector);
		ScoreDoc[] docs = topCollector.topDocs((page-1)*pageSize, pageSize).scoreDocs;
		
		
		Formatter formatter = new SimpleHTMLFormatter("<span>","</span>");
		Highlighter highlighter = new Highlighter(formatter, new QueryScorer(query));
		for (int i = 0; i < docs.length; i++) {
			List<Fieldable> list = searcher.doc(docs[i].doc).getFields();
			for (Fieldable fieldable : list) {
				String fieldName = fieldable.name();
				String fieldValue = fieldable.stringValue();
				TokenStream ts = analyzer.tokenStream(fieldName, new StringReader(fieldValue));
				String frament = highlighter.getBestFragment(ts, fieldValue); 
				System.out.println(fieldName+" : "+frament);
			}
		}
	}
	
	/**
	 * 根据前缀查询
	 * @Author TangJiaZhi
	 */
	public void prefixSearch(String filedStr,String queryStr) throws Exception{
		IndexReader reader = IndexReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		
		Term term = new Term(filedStr, queryStr);
		Query query = new PrefixQuery(term);
		
		ScoreDoc[] docs = searcher.search(query, 3).scoreDocs;
		printScoreDoc(docs, searcher);
	}
	
	/**
	 * 通配符查询
	 * @Author TangJiaZhi
	 */
	public void wildcardSearch(String filedStr,String queryStr) throws Exception{
		IndexReader reader = IndexReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		
		Term term = new Term(filedStr, queryStr);
		Query query = new WildcardQuery(term);
		
		
		
		ScoreDoc[] docs = searcher.search(query, 3).scoreDocs;
		printScoreDoc(docs, searcher);
	}
	
	/**
	 * 分词查询
	 * @Author TangJiaZhi
	 */
	public void analyzerSearch(String filedStr,String queryStr) throws Exception{
		IndexReader reader = IndexReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		
		QueryParser queryParser = new QueryParser(version, filedStr, analyzer);
		Query query = queryParser.parse(queryStr);
		
		ScoreDoc[] docs = searcher.search(query, 3).scoreDocs;
		printScoreDoc(docs, searcher);
	}
	
	/**
	 * 多属性分词查询
	 * @Author TangJiaZhi
	 */
	public void multiAnalyzerSearch(String[] filedStr,String queryStr) throws Exception{
		IndexReader reader = IndexReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		QueryParser queryParser = new MultiFieldQueryParser(version, filedStr, analyzer);
		Query query = queryParser.parse(queryStr);
		
		ScoreDoc[] docs = searcher.search(query, 3).scoreDocs;
		printScoreDoc(docs, searcher);
	}
	
	public void printScoreDoc(ScoreDoc[] docs,IndexSearcher searcher)throws Exception{
		for (int i = 0; i < docs.length; i++) {
			List<Fieldable> list = searcher.doc(docs[i].doc).getFields();
			for (Fieldable fieldable : list) {
				String fieldName = fieldable.name();
				String fieldValue = fieldable.stringValue();
				System.out.println(fieldName+" : "+fieldValue);
			}
		}
	}

	public static void main(String[] args) throws Exception {
		LuceneSearch t = new LuceneSearch();
		Document d1 = new Document();
		d1.add(new Field("id", "1", Store.YES, Index.ANALYZED));
		d1.add(new Field("name", "苦逼的程序员", Store.YES, Index.ANALYZED));
		Document d2 = new Document();
		d2.add(new Field("id", "2", Store.YES, Index.ANALYZED));
		d2.add(new Field("name", "2b的程序员", Store.YES, Index.ANALYZED));
		Document[] documentes = {d1,d2};
		
		System.out.println("--------------------------全量索引--------------------------");
		t.fullIndex(documentes);
		t.simpleSearch("name", "程序", 1, 10);
		t.highLightSearch("name", "程序", 1, 10);
		
		System.out.println("--------------------------增量索引--------------------------");
		d1.removeField("name");
		d1.add(new Field("name", "程序", Store.YES, Index.ANALYZED));
		t.updateIndex(documentes);
		t.simpleSearch("name", "程序", 1, 10);
		
		System.out.println("--------------------------删除索引--------------------------");
		t.deleteIndex(d1);
		t.simpleSearch("name", "2b", 1, 10);
		
		System.out.println("--------------------------分词查询--------------------------");
		t.multiAnalyzerSearch(new String[]{"id","name"}, "苦逼的程序员");
		
	}

}

使用QueryParser接口查询时，会根据指定的分词器对查询条件先分词再搜索

这就是为什么

t.multiAnalyzerSearch(new String[]{"id","name"}, "苦逼的程序员");

能搜索出结果的原因

不过实际项目中所要求的站内搜索直接使用lucene的子项目solr就可以轻松的实现了。

转载于:https://my.oschina.net/eatsuger/blog/87119