Lucene:为文本文件创建索引

需求描述:为某个文件夹A下的所有后缀名为.txt的文件创建索引,索引文件存放于文件夹B下

开发环境:Lucene 3.4.0 + eclipse indigo + jdk1.7.0,配置如下

为文件创建索引的是mytest包下的indexer类,具体代码如下:

 

View Code
package mytest;

import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.Version;

import java.io.File;
import java.io.FileFilter;
import java.io.IOException;
import java.io.FileReader;

// From chapter 1

public class Indexer {

public static void main(String[] args) throws Exception {
String indexDir = "E://eclipse//javaProject//lucene-3.4.0//indexDir"; //1
String dataDir = "E://eclipse//javaProject//lucene-3.4.0//dataDir"; //2

long start = System.currentTimeMillis();
Indexer indexer = new Indexer(indexDir);
int numIndexed;
try {
numIndexed = indexer.index(dataDir, new TextFilesFilter());
} finally {
indexer.close();
}
long end = System.currentTimeMillis();

System.out.println("Indexing " + numIndexed + " files took "
+ (end - start) + " milliseconds");
}

private IndexWriter writer;

public Indexer(String indexDir) throws IOException {
Directory dir = FSDirectory.open(new File(indexDir));
writer = new IndexWriter(dir, //3
new StandardAnalyzer( //3
Version.LUCENE_34),//3
true, //3
IndexWriter.MaxFieldLength.UNLIMITED); //3
}

public void close() throws IOException {
writer.close(); //4
}

public int index(String dataDir, FileFilter filter)
throws Exception {

File[] files = new File(dataDir).listFiles();

for (File f: files) {
if (!f.isDirectory() &&
!f.isHidden() &&
f.exists() &&
f.canRead() &&
(filter == null || filter.accept(f))) {
indexFile(f);
}
}

return writer.numDocs(); //5
}

private static class TextFilesFilter implements FileFilter {
public boolean accept(File path) {
return path.getName().toLowerCase() //6
.endsWith(".txt"); //6
}
}

protected Document getDocument(File f) throws Exception {
Document doc = new Document();
doc.add(new Field("contents", new FileReader(f))); //7
doc.add(new Field("filename", f.getName(), //8
Field.Store.YES, Field.Index.NOT_ANALYZED));//8
doc.add(new Field("fullpath", f.getCanonicalPath(), //9
Field.Store.YES, Field.Index.NOT_ANALYZED));//9
return doc;
}

private void indexFile(File f) throws Exception {
System.out.println("Indexing " + f.getCanonicalPath());
Document doc = getDocument(f);
writer.addDocument(doc); //10
}
}
/*
#1 Create index in this directory
#2 Index *.txt files from this directory
#3 Create Lucene IndexWriter
#4 Close IndexWriter
#5 Return number of documents indexed
#6 Index .txt files only, using FileFilter
#7 Index file content
#8 Index file name
#9 Index file full path
#10 Add document to Lucene index
*/

 

程序运行结果如下:

程序运行结束后,在指定目录下生成索引文件:

 

推荐一个自己业余时间开发的网盘搜索引擎,360盘搜www.360panso.com

posted on 2011-11-21 22:35  上品物语  阅读(5038)  评论(4编辑  收藏  举报