lucene in action chapter1 code
Indexer.java
package com.shosu.chapter1;
/**
* Copyright Manning Publications Co.
*
* Licensed 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 lan
*/
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
/**
* This code was originally written for Erik's Lucene intro java.net article
*/
public class Indexer {
public static void main(String[] args) throws Exception {
// 如果在运行程序是 args[] 没有连个参数则报错-->com.shosu.test.IllegalArgumentExceptionTest.java
/*if (args.length != 2) {
throw new IllegalArgumentException("Usage: java "
+ Indexer.class.getName() + " <index dir> <data dir>");
}*/
String indexDir = null;//args[0]; // 1
String dataDir = null;//args[1]; // 2
// add
indexDir = "d:\\lucene\\index";
dataDir = "d:\\lucene\\resource\\data";
// 开始时间
long start = System.currentTimeMillis();
Indexer indexer = new Indexer(indexDir);
int numIndexed; // 被索引文档数
try {
numIndexed = indexer.index(dataDir, new TextFilesFilter());
} finally {
indexer.close();
}
// 结束时间
long end = System.currentTimeMillis();
System.out.println("Indexing " + numIndexed + " files took "
+ (end - start) + " milliseconds");
} // main end
private IndexWriter writer;
// 构造函数初始化
public Indexer(String indexDir) throws IOException {
// 打开对应索引文件夹
Directory dir = FSDirectory.open(new File(indexDir));
// 写
writer = new IndexWriter(dir, // 3
new StandardAnalyzer( // 3 分词器
Version.LUCENE_30),// 3
true, // 3
IndexWriter.MaxFieldLength.UNLIMITED); // 3
}
public void close() throws IOException {
writer.close(); // 4
}
/*
* 参数一: 资源路径
* 参数二: 文件
*/
public int index(String dataDir, FileFilter filter) throws Exception {
// 得到路径下的所有文件
File[] files = new File(dataDir).listFiles();
for (File f : files) {
// isDirectory 如果 f 是目录则返回 true
// isHidden 如果 f 是隐藏文件则返回 true
// exists 如果 f 存在则返回 true
// canRead 如果 f 可读则返回 true
// accept 如果 f 是 .txt 文件返回 true
if (!f.isDirectory() && !f.isHidden() && f.exists() && f.canRead()
&& (filter == null || filter.accept(f))) {
indexFile(f);
}
} // forech end
// 被索引文档数
return writer.numDocs(); // 5
}
private static class TextFilesFilter implements FileFilter {
public boolean accept(File path) {
// 将文件名转换成小写，然后判断是否为 .txt 文件
return path.getName().toLowerCase() // 6
.endsWith(".txt"); // 6
}
}
// 将 File 转换成 Document
protected Document getDocument(File f) throws Exception {
Document doc = new Document();
// 创建域 如： contents 、 filename 、 fullpath
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 储存 不分词
doc.add(new Field("fullpath", f.getCanonicalPath(), // 9
Field.Store.YES, Field.Index.NOT_ANALYZED));// 9
return doc;
}
/*
* 将文件加入索引
*/
private void indexFile(File f) throws Exception {
// File.getCanonicalPath-->http://blog.csdn.net/lskyne/article/details/9037233
System.out.println("Indexing " + f.getCanonicalPath());
Document doc = getDocument(f);
// 将文档对象加入索引
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
*/
Searcher.java
package com.shosu.chapter1;
/**
* Copyright Manning Publications Co.
*
* Licensed 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 lan
*/
import org.apache.lucene.document.Document;
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.FSDirectory;
import org.apache.lucene.store.Directory;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.util.Version;
import java.io.File;
import java.io.IOException;
// From chapter 1
/**
* This code was originally written for Erik's Lucene intro java.net article
*/
public class Searcher {
public static void main(String[] args) throws IllegalArgumentException,
IOException, ParseException {
/*if (args.length != 2) {
throw new IllegalArgumentException("Usage: java "
+ Searcher.class.getName() + " <index dir> <query>");
}*/
String indexDir = null;//args[0]; // 1
String q = null;//args[1]; // 2
// add
indexDir = "d:\\lucene\\index";
q = "patent";
search(indexDir, q);
}
// 搜索
public static void search(String indexDir, String q) throws IOException,
ParseException {
// 打开索引文件
Directory dir = FSDirectory.open(new File(indexDir)); // 3
IndexSearcher is = new IndexSearcher(dir); // 3
// 解析查询字符--->配置Query
QueryParser parser = new QueryParser(Version.LUCENE_30, // 4
"contents", // 4 查询域
new StandardAnalyzer( // 4 分词器
Version.LUCENE_30)); // 4 版本号
Query query = parser.parse(q); // 4
// 查询开始时间
long start = System.currentTimeMillis();
TopDocs hits = is.search(query, 10); // 5
// 查询结束时间
long end = System.currentTimeMillis();
// 记录搜索状态
System.err.println("Found " + hits.totalHits + // 6
" document(s) (in " + (end - start) + // 6
" milliseconds) that matched query '" + // 6
q + "':"); // 6
// 搜索结果
for (ScoreDoc scoreDoc : hits.scoreDocs) {
Document doc = is.doc(scoreDoc.doc); // 7
System.out.println(doc.get("fullpath")); // 8
}
is.close(); // 9
}
}
/*
* #1 Parse provided index directory #2 Parse provided query string #3 Open
* index #4 Parse query #5 Search index #6 Write search stats #7 Retrieve
* matching document #8 Display filename #9 Close IndexSearcher
*/