org.wltea.analyzer.sample.LuceneIndexAndSearchDemo Maven / Gradle / Ivy
/*
* IK 中文分词 版本 8.1.1
* IK Analyzer release 8.1.1
*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*
* 源代码由林良益([email protected])提供
* 版权声明 2012，乌龙茶工作室
* provided by Linliangyi and copyright 2012 by Oolong studio
*
* 8.1.1版本 由 Magese ([email protected]) 更新
* release 8.1.1 update by Magese([email protected])
*
*/
package org.wltea.analyzer.sample;
import org.apache.lucene.analysis.Analyzer;
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.IndexWriterConfig.OpenMode;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.wltea.analyzer.lucene.IKAnalyzer;
import java.io.IOException;
/**
* 使用IKAnalyzer进行Lucene索引和查询的演示
* 2012-3-2
*
* 以下是结合Lucene4.0 API的写法
*/
public class LuceneIndexAndSearchDemo {
/**
* 模拟：
* 创建一个单条记录的索引，并对其进行搜索
*
*/
public static void main(String[] args) {
//Lucene Document的域名
String fieldName = "text";
//检索内容
String text = "IK Analyzer是一个结合词典分词和文法分词的中文分词开源工具包。它使用了全新的正向迭代最细粒度切分算法。";
//实例化IKAnalyzer分词器
Analyzer analyzer = new IKAnalyzer(true);
Directory directory = null;
IndexWriter iwriter;
IndexReader ireader = null;
IndexSearcher isearcher;
try {
//建立内存索引对象
directory = new RAMDirectory();
//配置IndexWriterConfig
IndexWriterConfig iwConfig = new IndexWriterConfig(analyzer);
iwConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
iwriter = new IndexWriter(directory, iwConfig);
//写入索引
Document doc = new Document();
doc.add(new StringField("ID", "10000", Field.Store.YES));
doc.add(new TextField(fieldName, text, Field.Store.YES));
iwriter.addDocument(doc);
iwriter.close();
//搜索过程**********************************
//实例化搜索器
ireader = DirectoryReader.open(directory);
isearcher = new IndexSearcher(ireader);
String keyword = "中文分词工具包";
//使用QueryParser查询分析器构造Query对象
QueryParser qp = new QueryParser(fieldName, analyzer);
qp.setDefaultOperator(QueryParser.AND_OPERATOR);
Query query = qp.parse(keyword);
System.out.println("Query = " + query);
//搜索相似度最高的5条记录
TopDocs topDocs = isearcher.search(query, 5);
long totalHits = topDocs.totalHits.value;
System.out.println("命中：" + totalHits);
//输出结果
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for (int i = 0; i < totalHits; i++) {
Document targetDoc = isearcher.doc(scoreDocs[i].doc);
System.out.println("内容：" + targetDoc.toString());
}
} catch (ParseException | IOException e) {
e.printStackTrace();
} finally {
if (ireader != null) {
try {
ireader.close();
} catch (IOException e) {
e.printStackTrace();
}
}
if (directory != null) {
try {
directory.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
}