package org.apache.lucene.demo;
/**
* 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.
*/
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.index.IndexWriter;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.util.Date;
/** Index all text files under a directory. */
public class IndexFiles {
private IndexFiles() {}
static final File INDEX_DIR = new File("index");//索引止录。建在当前目录的/index下
/** Index all text files under a directory. */
public static void main(String[] args) {//args[0] 文件路径. main 方法:对args[0]指定的文件路径下的所有文件建立索引。
final File docDir = new File(args[0]);
if (!docDir.exists() || !docDir.canRead()) {
System.out .println("Document directory '" + docDir.getAbsolutePath() + "' does not exist or is not readable, please check the path");
System.exit(1);
}
Date start = new Date();
try {
IndexWriter writer = new IndexWriter(INDEX_DIR, new StandardAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
//IndexWriter负责创建和维护索引
//IndexWriter(String path, Analyzer a, boolean create, IndexWriter.MaxFieldLength mfl)
//path:路径 Analyzer:文本分析器 create:是否创建新索引 mfl 最大field数量
System.out.println("Indexing to directory '" + INDEX_DIR + "'...");
indexDocs(writer, docDir);
System.out.println("Optimizing...");
writer.optimize();//优化索引
writer.close();//关闭
Date end = new Date();
System.out.println(end.getTime() - start.getTime() + " total milliseconds");
} catch (IOException e) {
System.out.println(" caught a " + e.getClass()
+ "\n with message: " + e.getMessage());
}
}
static void indexDocs(IndexWriter writer, File file) throws IOException {
// do not try to index files that cannot be read
if (file.canRead()) {
if (file.isDirectory()) {
String[] files = file.list();
// an IO error could occur
if (files != null) {
for (int i = 0; i < files.length; i++) {
indexDocs(writer, new File(file, files[i]));
}
}
} else {
System.out.println("adding " + file);
try {
writer.addDocument(FileDocument.Document(file));
}
// at least on windows, some temporary files raise this
// exception with an "access denied" message
// checking if the file can be read doesn't help
catch (FileNotFoundException fnfe) {
;
}
}
}
}
}
package org.apache.lucene.demo;
/**
* 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.
*/
import java.io.File;
import java.io.FileReader;
import org.apache.lucene.document.DateTools;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
/** A utility for making Lucene Documents from a File. */
public class FileDocument {
public static Document Document(File f)
throws java.io.FileNotFoundException {
// make a new, empty document
Document doc = new Document();
doc.add(new Field("contents", new FileReader(f)));
doc.add(new Field("path", f.getPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add(new Field("modified", DateTools.timeToString(f.lastModified(), DateTools.Resolution.MINUTE),Field.Store.YES, Field.Index.ANALYZED));
doc.add(new Field("name",f.getName(),Field.Store.YES,Field.Index.NOT_ANALYZED));
//Field
// return the document
return doc;
}
private FileDocument() {}
}