Lucene学习笔记

SOLR基于Lucene,那就首先从Lucene开始学习

看到这篇文章http://www.ibm.com/developerworks/cn/java/j-lo-lucene1/

不过因为是2006年的文章，所以代码部分需要更新了：

 package com.lucene; import java.io.File; import java.io.FileReader; import java.io.Reader; import java.util.Date; 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.Field.Store; import org.apache.lucene.document.Field.Index; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriter.MaxFieldLength; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; /** * This class demonstrate the process of creating index with Lucene * for text files */ public class TxtFileIndexer { public static void main(String[] args) throws Exception{ //indexDir is the directory that hosts Lucene's index files Directory indexDir = FSDirectory.open(new File("E://workspace//solr//indexData")); //dataDir is the directory that hosts the text files that to be indexed File dataDir = new File("E://workspace//solr//Data"); Analyzer luceneAnalyzer = new StandardAnalyzer(Version.LUCENE_30); File[] dataFiles = dataDir.listFiles(); IndexWriter indexWriter = new IndexWriter(indexDir,luceneAnalyzer,MaxFieldLength.LIMITED); long startTime = new Date().getTime(); for(int i = 0; i < dataFiles.length; i++){ if(dataFiles[i].isFile() && dataFiles[i].getName().toLowerCase().endsWith(".txt")){ System.out.println("Indexing file " + dataFiles[i].getCanonicalPath()); Document document = new Document(); Reader txtReader = new FileReader(dataFiles[i]); document.add(new Field("path",dataFiles[i].getCanonicalPath(),Store.YES,Index.NO)); document.add(new Field("contents",txtReader)); indexWriter.addDocument(document); } } indexWriter.optimize(); indexWriter.close(); long endTime = new Date().getTime(); System.out.println("It takes " + (endTime - startTime) + " milliseconds to create index for the files in directory " + dataDir.getPath()); } }

 

 package com.tower.lucene; import java.io.File; import org.apache.lucene.document.Document; 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.FSDirectory; public class TxtFileSearcher { public static void main(String[] args) throws Exception{ String queryStr = "microsoft"; int iSearchNum = 100; //This is the directory that hosts the Lucene index File indexDir = new File("E://workspace//solr//indexData"); FSDirectory directory = FSDirectory.open(indexDir); IndexSearcher searcher = new IndexSearcher(directory); if(!indexDir.exists()){ System.out.println("The Lucene index is not exist"); return; } Term term = new Term("contents",queryStr.toLowerCase()); TermQuery luceneQuery = new TermQuery(term); TopDocs hits = searcher.search(luceneQuery,iSearchNum); System.out.println(hits.totalHits); iSearchNum = iSearchNum<hits.totalHits?iSearchNum:hits.totalHits; for(int i = 0; i < iSearchNum ; i++){ ScoreDoc document = hits.scoreDocs[i]; Document realDoc = searcher.doc(document.doc); System.out.println("File: " + realDoc.get("path")); } } }

 

通过这些调整，也可以看出Lucene这几年的变化，比如把Hits舍弃了，返回的是对象TopDocs