我使用 intellij IDEA 12进行的测试。
建立java项目
建立项目HelloLucene，导入Lucene的几个库。“File”->“Project Structure”->
将IK Analyzer 2012FF_hf1.zip解压后的源码放入src目录，并将字典和配置文件放入src目录，最终如下：
一个示例：
IKAnalyzerDemo.java中是我在其他地方找的一个示例，和IK的官方示例很像。内容如下：
package org.apache.lucene.demo;
import java.io.IOException;
import java.io.StringReader;
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.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;
public class IKAnalyzerDemo {
/**
* @param args
* @throws IOException
*/
public static void main(String[] args) throws IOException {
// TODO Auto-generated method stub
//建立索引
String text1 = "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。";
String text2 = "中文分词工具包可以和lucene是一起使用的";
String text3 = "中文分词,你妹";
String fieldName = "contents";
Analyzer analyzer = new IKAnalyzer();
RAMDirectory directory = new RAMDirectory();
IndexWriterConfig writerConfig = new IndexWriterConfig(Version.LUCENE_34, analyzer);
IndexWriter indexWriter = new IndexWriter(directory, writerConfig);
Document document1 = new Document();
document1.add(new Field("ID", "1", Field.Store.YES, Field.Index.NOT_ANALYZED));
document1.add(new Field(fieldName, text1, Field.Store.YES, Field.Index.ANALYZED));
indexWriter.addDocument(document1);
Document document2 = new Document();
document2.add(new Field("ID", "2", Field.Store.YES, Field.Index.NOT_ANALYZED));
document2.add(new Field(fieldName, text2, Field.Store.YES, Field.Index.ANALYZED));
indexWriter.addDocument(document2);
Document document3 = new Document();
document3.add(new Field("ID", "2", Field.Store.YES, Field.Index.NOT_ANALYZED));
document3.add(new Field(fieldName, text3, Field.Store.YES, Field.Index.ANALYZED));
indexWriter.addDocument(document3);
indexWriter.close();
//搜索
IndexReader indexReader = IndexReader.open(directory);
IndexSearcher searcher = new IndexSearcher(indexReader);
String request = "中文分词工具包";
QueryParser parser = new QueryParser(Version.LUCENE_40, fieldName, analyzer);
parser.setDefaultOperator(QueryParser.AND_OPERATOR);
try {
Query query = parser.parse(request);
TopDocs topDocs = searcher.search(query, 5);
System.out.println("命中数:"+topDocs.totalHits);
ScoreDoc[] docs = topDocs.scoreDocs;
for(ScoreDoc doc : docs){
Document d = searcher.doc(doc.doc);
System.out.println("内容:"+d.get(fieldName));
}
} catch (ParseException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}finally{
if(indexReader != null){
try{
indexReader.close();
}catch (IOException e) {
e.printStackTrace();
}
}
if(directory != null){
try{
directory.close();
}catch (Exception e) {
e.printStackTrace();
}
}
}
}
}
加载扩展停止词典：stopword.dic
命中数:2
内容:中文分词工具包可以和lucene是一起使用的
内容: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。
1、Field()已经不推荐按使用。
2、QueryParser()的使用方式也改变了。
下面是更加符合要求的示例。
第二个示例：
MyIndex类用来创建索引：import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.*;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;
import java.io.File;
public class MyIndex {
public static void main(String[] args) {
String ID;
String content;
ID = "1231";
content = "BuzzFeed has compiled an amazing array of " +
"ridiculously strange bridesmaid snapshots, courtesy of Awkward Family Photos. ";
indexPost(ID, content);
ID = "1234";
content = "Lucene是apache软件基金会4 jakarta项目组的一个子项目，是一个开放源代码的全文检索引擎工具包";
indexPost(ID, content);
ID = "1235";
content = "Lucene不是一个完整的全文索引应用，而是是一个用Java写的全文索引引擎工具包，它可以方便的嵌入到各种应用中实现";
indexPost(ID, content);
}
public static void indexPost(String ID, String content) {
File indexDir = new File("/home/letian/lucene-test/index");
Analyzer analyzer = new IKAnalyzer();
TextField postIdField = new TextField("id", ID, Store.YES); // 不要用StringField
TextField postContentField = new TextField("content", content, Store.YES);
Document doc = new Document();
doc.add(postIdField);
doc.add(postContentField);
IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_4_10_1, analyzer);
iwConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
try {
Directory fsDirectory = FSDirectory.open(indexDir);
IndexWriter indexWriter = new IndexWriter(fsDirectory, iwConfig);
indexWriter.addDocument(doc);
indexWriter.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
运行上面的代码，创建索引的结果如下：
MySearch.java是一个搜索的示例：
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.index.DirectoryReader;
import org.wltea.analyzer.lucene.IKAnalyzer;
import java.io.File;
public class MySearch {
public static void main(String[] args) {
Analyzer analyzer = new IKAnalyzer();
File indexDir = new File("/home/letian/lucene-test/index");
try {
Directory fsDirectory = FSDirectory.open(indexDir);
DirectoryReader ireader = DirectoryReader.open(fsDirectory);
IndexSearcher isearcher = new IndexSearcher(ireader);
QueryParser qp = new QueryParser("content", analyzer); //使用QueryParser查询分析器构造Query对象
qp.setDefaultOperator(QueryParser.AND_OPERATOR);
Query query = qp.parse("Lucene"); // 搜索Lucene
TopDocs topDocs = isearcher.search(query , 5); //搜索相似度最高的5条记录
System.out.println("命中:" + topDocs.totalHits);
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for (int i = 0; i < topDocs.totalHits; i++){
Document targetDoc = isearcher.doc(scoreDocs[i].doc);
System.out.println("内容:" + targetDoc.toString());
}
} catch (Exception e) {
}
}
}
命中:2
内容:Document<stored,indexed,tokenized<id:1234> stored,indexed,tokenized<content:Lucene是apache软件基金会4 jakarta项目组的一个子项目，是一个开放源代码的全文检索引擎工具包>>
内容:Document<stored,indexed,tokenized<id:1235> stored,indexed,tokenized<content:Lucene不是一个完整的全文索引应用，而是是一个用Java写的全文索引引擎工具包，它可以方便的嵌入到各种应用中实现>>
参考：
http://lucene.apache.org/core/4_10_0/core/index.html
http://blog.csdn.net/tangpengtao/article/details/8670724
http://blog.csdn.net/enjoyinwind/article/details/8278250
http://blog.csdn.net/fyqcdbdx/article/details/17465929
更多资料：
初识 Lucene
http://www.ibm.com/developerworks/cn/java/j-lo-lucene1/
Lucene：基于Java的全文检索引擎简介
http://www.chedong.com/tech/lucene.html
使用 Apache Lucene 搜索文本
http://www.ibm.com/developerworks/cn/opensource/os-apache-lucenesearch/
深入 Lucene 索引机制
http://www.ibm.com/developerworks/cn/java/wa-lucene/
Lucene学习总结 系列文章
http://forfuture1978.iteye.com/category/89151
评论(2)
引用来自“fate-testarossa”的评论
Version.LUCENE_34 是被抛弃了吧，目前好像用Version.LATEST ？