package org.apache.lucene.demo;/*各位抱歉，还在学习中，自己也是初学。 * 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. *//* firefaith 2013-6-9 edited该demo 为文档建立索引，后文对索引进行搜索；该demo 运行前提01. 已正确配置lucene,jdk ,其中 javax.sevelet.jar jdk没有，从官网下载02. 在本地建立存放index结果的文件夹，和存放源数据的data文件夹，data文件夹内放需要检索的txt文件03. 编译环境为eclipse，需要从commandline 输入参数，故运行时选 run as configrationlucene 作为全文检索工具，大致流程如下：1. 为文档建立索引2. 搜索索引3. 反馈结果*/import org.apache.lucene.analysis.Analyzer;import org.apache.lucene.analysis.standard.StandardAnalyzer;import org.apache.lucene.document.Document;import org.apache.lucene.document.Field;import org.apache.lucene.document.LongField;import org.apache.lucene.document.StringField;import org.apache.lucene.document.TextField;import org.apache.lucene.index.IndexWriter;import org.apache.lucene.index.IndexWriterConfig.OpenMode;import org.apache.lucene.index.IndexWriterConfig;import org.apache.lucene.index.Term;import org.apache.lucene.store.Directory;import org.apache.lucene.store.FSDirectory;import org.apache.lucene.util.Version;import java.io.BufferedReader;import java.io.File;import java.io.FileInputStream;import java.io.FileNotFoundException;import java.io.IOException;import java.io.InputStreamReader;import java.util.Date;/** Index all text files under a directory. * <p> * This is a command-line application demonstrating simple Lucene indexing. * Run it with no command-line arguments for usage information. */public class IndexFiles { private IndexFiles() {} /** Index all text files under a directory. */ public static void main(String[] args) { String usage = "java org.apache.lucene.demo.IndexFiles" + " [-index INDEX_PATH] [-docs DOCS_PATH] [-update]\n\n" + "This indexes the documents in DOCS_PATH, creating a Lucene index" + "in INDEX_PATH that can be searched with SearchFiles"; //usage 作为报错信息，在commandline 输入参数不符合规范时，报出；从usage中也可看出index需要的参数，两个路径，一个update参数 String indexPath = "index"; // 默认路径，可以修改为具体路径，run as application 就可以 String docsPath = null; boolean create = true; //即为update标记，update表示，需要update一个新的index，而不是create；默认情况总是create //read from command line begin,每隔空格一读， for(int i=0;i<args.length;i++) { if ("-index".equals(args[i])) { indexPath = args[i+1]; i++; } else if ("-docs".equals(args[i])) { docsPath = args[i+1]; i++; } else if ("-update".equals(args[i])) { create = false; } } // read from command line end // data文件路径未给，则报错 if (docsPath == null) { System.err.println("Usage: " + usage); System.exit(1); }//data 文件不存在或不可读，报错 final File docDir = new File(docsPath); 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); } /*总流程通过IndexWriter writer的 addDocument(Iterable<? extends IndexableField> doc) 将doc添加入索引IndexWriter addDocument （doc）
└IndexWriter addDocuments(doc, analyzer); analyzer为IndexWriter内成员，在上一级方法中赋值 └IndexWriter updateDocuments(null, doc, analyzer);null 作为term参数，此处传入null └DocumentsWriter docWriter.updateDocument(doc, analyzer,null); docWriter 是 IndexWriter 的DocumentsWriter成员 └DocumentsWriter dwpt.updateDocument(doc, analyzer, delTerm=null); DocumentsWriterPerThread dwpt=flushControl.obtainAndLock().dwpt;flushControl 为DocumentsWriter的 DocumentsWriterFlushControl成员变量
└DocumentsWriterPerThread updateDocument(doc, analyzer, delTerm=null){ docState.analyzer = analyzer; DocState是内部类， docState.doc = doc;consumer.processDocument(fieldInfos); DocConsumer成员，fieldInfos 是FieldInfos.Builder 类型，也是私有成员};而writer 由构造函数 IndexWriter(Directory d, IndexWriterConfig conf)生成 index 开始：indexDocs(writer, docDir); 由demo自己实现，见后文；1. 需要一个分析器，Analyzer*/ Date start = new Date(); try { System.out.println("Indexing to directory '" + indexPath + "'..."); Directory dir = FSDirectory.open(new File(indexPath));Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_43); IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_43, analyzer); //设置config,是update还是create if (create){ // Create a new index in the directory, removing any // previously indexed documents: iwc.setOpenMode(OpenMode.CREATE); } else { // Add new documents to an existing index: iwc.setOpenMode(OpenMode.CREATE_OR_APPEND); } // Optional: for better indexing performance, if you // are indexing many documents, increase the RAM // buffer. But if you do this, increase the max heap // size to the JVM (eg add -Xmx512m or -Xmx1g): //可选项，已被注释，对性能可调，不影响功能 // iwc.setRAMBufferSizeMB(256.0); ndexWriter writer = new IndexWriter(dir, iwc); indexDocs(writer, docDir); // NOTE: if you want to maximize search performance, // you can optionally call forceMerge here. This can be // a terribly costly operation, so generally it's only // worth it when your index is relatively static (ie // you're done adding documents to it): // // writer.forceMerge(1); writer.close(); 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()); } } /** * Indexes the given file using the given writer, or if a directory is given, * recurses over files and directories found under the given directory. * * NOTE: This method indexes one document per input file. This is slow. For good * throughput, put multiple documents into your input file(s). An example of this is * in the benchmark module, which can create "line doc" files, one document per line, * using the* <a href="../../../../../contrib-benchmark/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTask.html" * >WriteLineDocTask</a>. * * @param writer Writer to the index where the given file/dir info will be stored * @param file The file to index, or the directory to recurse into to find files to index * @throws IOException If there is a low-level I/O error */ 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 { FileInputStream fis; try { fis = new FileInputStream(file); } catch (FileNotFoundException fnfe) { // 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 return; } try { // make a new, empty document Document doc = new Document(); // Add the path of the file as a field named "path". Use a // field that is indexed (i.e. searchable), but don't tokenize // the field into separate words and don't index term frequency // or positional information: Field pathField = new StringField("path", file.getPath(), Field.Store.YES); doc.add(pathField);// Add the last modified date of the file a field named "modified".// Use a LongField that is indexed (i.e. efficiently filterable with // NumericRangeFilter). This indexes to milli-second resolution, which // is often too fine. You could instead create a number based on// year/month/day/hour/minutes/seconds, down the resolution you require. // For example the long value 2011021714 would mean // February 17, 2011, 2-3 PM. doc.add(new LongField("modified", file.lastModified(), Field.Store.NO)); // Add the contents of the file to a field named "contents". Specify a Reader, // so that the text of the file is tokenized and indexed, but not stored. // Note that FileReader expects the file to be in UTF-8 encoding. // If that's not the case searching for special characters will fail. doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(fis, "UTF-8")))); if (writer.getConfig().getOpenMode() == OpenMode.CREATE) { // New index, so we just add the document (no old document can be there): System.out.println("adding " + file); writer.addDocument(doc); } else { // Existing index (an old copy of this document may have been indexed) so // we use updateDocument instead to replace the old one matching the exact // path, if present: System.out.println("updating " + file); writer.updateDocument(new Term("path", file.getPath()), doc); } } finally { fis.close(); } } } }}
