1.lucene创建索引和搜索,主要用到一下几个类,IndexWriter,Document,Analyzer;IndexSearcher,QueryParser,Query,TopDocs,
2.通过FSDirectory和RAMDirectory的并用,可以提高速度。先把磁盘上的索引文件载入内存,然后在内存操作,免去了IO操作,可以提高效率,最后退出时,要把内存操作的结果保存在磁盘上。
3.fsIndexWriter.optimize();优化索引文件,把多个cfs文件合并成一个
4.建立索引和进行搜索时应该使用同一个分词器。
ps:用到的jar包:/LuceneDemo/lib/je-analysis-1.5.3.jar(中文分词器)
/LuceneDemo/lib/lucene-analyzers-2.4.0.jar(lucenne自带的)
/LuceneDemo/lib/lucene-core-2.4.0.jar
/LuceneDemo/lib/lucene-highlighter-2.4.0.jar
package com.bjsxt.helloworld;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriter.MaxFieldLength;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Filter;
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.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.RAMDirectory;
import com.bjsxt.utils.File2DocumentUtil;
public class HelloWorld {
/**
* @param args
*/
String filePath = "D:\\flexWorkespace\\LuceneDemo\\luceneDataSource\\IndexWriter addDocument's a javadoc .txt";
String indexPath = "D:\\flexWorkespace\\LuceneDemo\\indexPath";
Analyzer analyzer = new StandardAnalyzer();
public static void main(String[] args) throws Exception {
new HelloWorld().createIndexByDir();
new HelloWorld().searchByDir("document");
}
public void createIndex() throws Exception {
// File file = new File(filePath);
Document doc = File2DocumentUtil.file2Document(filePath);
// IndexWriter 是用来操作(增删改)索引库的
IndexWriter iw = new IndexWriter(indexPath, analyzer, true,
MaxFieldLength.LIMITED);
iw.addDocument(doc);
iw.close();
}
public void createIndexByDir()throws Exception {
//1.创建时候载入文件系统里的索引
Directory fsDir = FSDirectory.getDirectory(indexPath);
Directory ramDir = new RAMDirectory(fsDir);
//new ramIndexWriter时不需要重新创建
IndexWriter ramIndexWriter = new IndexWriter(ramDir, analyzer, MaxFieldLength.LIMITED);
//添加document
Document doc = File2DocumentUtil.file2Document(filePath);
ramIndexWriter.addDocument(doc);
ramIndexWriter.close();
//2.退出时保存内存里的索引
//new fsIndexWriter时需要重新创建,即删除原来的索引文件
IndexWriter fsIndexWriter = new IndexWriter(fsDir, analyzer, true, MaxFieldLength.LIMITED);
// Directory[] dir = {ramDir};
fsIndexWriter.addIndexesNoOptimize(new Directory[]{ramDir});
//把内存里的东西提交后才优化
fsIndexWriter.commit();
// 优化索引文件,把多个cfs文件合并成一个
fsIndexWriter.optimize();
fsIndexWriter.close();
}
public void search(String queryStr) throws Exception {
String[] fields = { "name", "content" };
QueryParser queryParser = new MultiFieldQueryParser(fields, analyzer);
Query query = null;
Filter filter = null;
query = queryParser.parse(queryStr);
IndexSearcher indexSearcher = null;
indexSearcher = new IndexSearcher(indexPath);
TopDocs topDocs = indexSearcher.search(query, filter, 1000);
System.out.println("总共有" + topDocs.totalHits + "条记录:");
for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
int docNum = scoreDoc.doc;
Document doc = indexSearcher.doc(docNum);
File2DocumentUtil.printDocumentInfo(doc);
}
}
}
工具类:
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;
public class File2DocumentUtil {
public static Document file2Document(String filePath) throws Exception {
File file = new File(filePath);
Document doc = new Document();
doc.add(new Field("name", file.getName(), Store.YES, Index.ANALYZED));
doc.add(new Field("content", readFileContent(file), Store.YES,
Index.ANALYZED));
doc.add(new Field("size", String.valueOf(file.length()), Store.YES,
Index.NOT_ANALYZED));
doc.add(new Field("path", file.getAbsolutePath(), Store.YES, Index.NO));
return doc;
}
private static String readFileContent(File file) throws Exception {
// TODO Auto-generated method stub
StringBuffer content = new StringBuffer();
BufferedReader br = new BufferedReader(new FileReader(file));
for (String line = null; (line = br.readLine()) != null;) {
content.append(line).append("\n");
}
return content.toString();
}
public static void printDocumentInfo(Document doc) {
System.out.println("------------------------------");
System.out.println("name:" + doc.get("name"));
System.out.println("content:" + doc.get("content"));
System.out.println("path:" + doc.get("path"));
System.out.println("size:" + doc.get("size"));
}
}