使用Lucene4.8进行索引及搜索的基本操作
jopen
10年前
在Lucene对文本进行处理的过程中，可以大致分为两大部分：
1、索引文件：提取文档内容并分析，生成索引
2、搜索内容：搜索索引内容，根据搜索关键字得出搜索结果
一、索引文件
基本步骤如下：
1、创建索引库IndexWriter
2、根据文件创建文档Document
3、向索引库中写入文档内容
package com.ljh.search.index; import java.io.File; import java.io.FileReader; import java.io.IOException; 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; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; // 1、创建索引库IndexWriter // 2、根据文件创建文档Document // 3、向索引库中写入文档内容 public class IndexFiles { public static void main(String[] args) throws IOException { String usage = "java IndexFiles" + " [-index INDEX_PATH] [-docs DOCS_PATH] \n\n" + "This indexes the documents in DOCS_PATH, creating a Lucene index" + "in INDEX_PATH that can be searched with SearchFiles"; String indexPath = null; String docsPath = null; 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++; } } if (docsPath == null) { System.err.println("Usage: " + usage); System.exit(1); } 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); } IndexWriter writer = null; try { // 1、创建索引库IndexWriter writer = getIndexWriter(indexPath); index(writer, docDir); } catch (IOException e) { e.printStackTrace(); } finally { writer.close(); } } private static IndexWriter getIndexWriter(String indexPath) throws IOException { Directory indexDir = FSDirectory.open(new File(indexPath)); IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_48, new StandardAnalyzer(Version.LUCENE_48)); IndexWriter writer = new IndexWriter(indexDir, iwc); return writer; } private static void index(IndexWriter writer, File file) throws IOException { if (file.isDirectory()) { String[] files = file.list(); if (files != null) { for (int i = 0; i < files.length; i++) { index(writer, new File(file, files[i])); } } } else { // 2、根据文件创建文档Document Document doc = new Document(); Field pathField = new StringField("path", file.getPath(), Field.Store.YES); doc.add(pathField); doc.add(new LongField("modified", file.lastModified(), Field.Store.NO)); doc.add(new TextField("contents", new FileReader(file))); System.out.println("Indexing " + file.getName()); // 3、向索引库中写入文档内容 writer.addDocument(doc); } } } （1）使用“java indexfiles -index d:/index -docs d:/tmp”运行程序，索引d:/tmp中的文件，并将索引文件放置到d:/index。
（2）上述生成的索引文件可以使用Luke进行查看。目前Luke已迁移至github进行托管。
二、搜索文件
1、打开索引库IndexSearcher
2、根据关键词进行搜索
3、遍历结果并处理
package com.ljh.search.search; //1、打开索引库IndexSearcher //2、根据关键词进行搜索 //3、遍历结果并处理 import java.io.File; import java.io.IOException; import org.apache.lucene.index.DirectoryReader; import org.apache.lucene.index.IndexReader; import org.apache.lucene.index.Term; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.ScoreDoc; import org.apache.lucene.search.TermQuery; import org.apache.lucene.search.TopDocs; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; public class Searcher { public static void main(String[] args) throws IOException { String indexPath = null; String term = null; for (int i = 0; i < args.length; i++) { if ("-index".equals(args[i])) { indexPath = args[i + 1]; i++; } else if ("-term".equals(args[i])) { term = args[i + 1]; i++; } } System.out.println("Searching " + term + " in " + indexPath); // 1、打开索引库 Directory indexDir = FSDirectory.open(new File(indexPath)); IndexReader ir = DirectoryReader.open(indexDir); IndexSearcher searcher = new IndexSearcher(ir); // 2、根据关键词进行搜索 TopDocs docs = searcher.search( new TermQuery(new Term("contents", term)), 20); // 3、遍历结果并处理 ScoreDoc[] hits = docs.scoreDocs; System.out.println(hits.length); for (ScoreDoc hit : hits) { System.out.println("doc: " + hit.doc + " score: " + hit.score); } ir.close(); } }