基于Lucene的搜索引擎的实现

package com.lucene.controller; import java.io.File; import java.io.IOException; import java.io.StringReader; import java.util.ArrayList; import java.util.List; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.index.CorruptIndexException; import org.apache.lucene.index.IndexReader; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriterConfig; import org.apache.lucene.queryParser.MultiFieldQueryParser; import org.apache.lucene.queryParser.ParseException; import org.apache.lucene.queryParser.QueryParser; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.Query; import org.apache.lucene.search.ScoreDoc; import org.apache.lucene.search.Sort; import org.apache.lucene.search.SortField; import org.apache.lucene.search.TopDocs; import org.apache.lucene.search.highlight.Highlighter; import org.apache.lucene.search.highlight.InvalidTokenOffsetsException; import org.apache.lucene.search.highlight.QueryScorer; import org.apache.lucene.search.highlight.SimpleHTMLFormatter; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.store.SimpleFSDirectory; import org.apache.lucene.util.Version; import org.wltea.analyzer.lucene.IKAnalyzer; import com.lucene.entity.Company; import com.lucene.jdbc.Jdbc; public class AnalyseControl { /* 创建简单中文分析器 创建索引使用的分词器必须和查询时候使用的分词器一样，否则查询不到想要的结果 */ private Analyzer analyzer = new IKAnalyzer(true); // 索引保存目录 private File indexFile = new File("./indexDir/"); /** * 创建索引文件到磁盘中永久保存 */ public void createIndexFile() { long startTime = System.currentTimeMillis(); System.out.println("*****************创建索引开始**********************"); Directory directory = null; IndexWriter indexWriter = null; try { // 创建哪个版本的IndexWriterConfig，根据参数可知lucene是向下兼容的，选择对应的版本就好 IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_36, analyzer); // 创建磁盘目录对象 directory = new SimpleFSDirectory(indexFile); indexWriter = new IndexWriter(directory, indexWriterConfig); // indexWriter = new IndexWriter(directory, analyzer, true,IndexWriter.MaxFieldLength.UNLIMITED); // 这上面是使用内存保存索引的创建索引写入对象的例子，和这里的实现方式不一样，但是效果是一样的 Jdbc jdbcdemo=new Jdbc(); List<Company> CompanyList =jdbcdemo.jdbc(); // 为了避免重复插入数据，每次测试前 先删除之前的索引 indexWriter.deleteAll(); // 获取实体对象 for (int i = 0; i < CompanyList.size(); i++) { Company company = CompanyList.get(i); // indexWriter添加索引 Document doc = new Document(); // doc.add(new Field("id", company.getEntID(),Field.Store.YES,Field.Index.NOT_ANALYZED)); doc.add(new Field("name", company.getEntName(),Field.Store.YES,Field.Index.ANALYZED)); doc.add(new Field("regno", company.getREGNO(),Field.Store.YES, Field.Index.NO)); doc.add(new Field("orgno", company.getORGNO(),Field.Store.YES, Field.Index.NO)); doc.add(new Field("dom", company.getDOM(),Field.Store.YES, Field.Index.NO)); doc.add(new Field("lerep", company.getLEREP(),Field.Store.YES, Field.Index.NO)); // doc.add(new Field("regcap", company.getREGCAP(),Field.Store.YES, Field.Index.NO)); doc.add(new Field("enttype", company.getENTTYPE(),Field.Store.YES, Field.Index.NO)); // doc.add(new Field("opscope", company.getOPSCOPE(),Field.Store.YES, Field.Index.NO)); // doc.add(new Field("domdistrict", company.getDOMDISTRICT(),Field.Store.YES, Field.Index.NO)); // doc.add(new Field("regnorg", company.getREGNO(),Field.Store.YES, Field.Index.NO)); // 添加到索引中去 indexWriter.addDocument(doc); // System.out.println("索引添加成功：第" + (i + 1) + "次！！"); } } catch (IOException e) { e.printStackTrace(); } finally { if (indexWriter != null) { try { indexWriter.close(); } catch (IOException e) { e.printStackTrace(); } } if (directory != null) { try { directory.close(); } catch (IOException e) { e.printStackTrace(); } } } long endTime = System.currentTimeMillis(); System.out.println("创建索引文件成功，总共花费" + (endTime - startTime) + "毫秒。"); System.out.println("*****************创建索引结束**********************"); } /** * 直接读取索引文件，查询索引记录 * * @throws IOException */ public void openIndexFile() { long startTime = System.currentTimeMillis(); System.out.println("*****************读取索引开始**********************"); List<Company> companys = new ArrayList<Company>(); // 得到索引的目录 Directory directory = null; IndexReader indexReader = null; try { directory = new SimpleFSDirectory(indexFile); // 根据目录打开一个indexReader indexReader = IndexReader.open(directory); //indexReader = IndexReader.open(directory,false); System.out.println("在索引文件中总共插入了" + indexReader.maxDoc() + "条记录。"); // 获取第一个插入的document对象 Document minDoc = indexReader.document(0); // 获取最后一个插入的document对象 Document maxDoc = indexReader.document(indexReader.maxDoc() - 1); // document对象的get(字段名称)方法获取字段的值 System.out.println("第一个插入的document对象的标题是：" + minDoc.get("name")); System.out.println("最后一个插入的document对象的标题是：" + maxDoc.get("name")); //indexReader.deleteDocument(0); int docLength = indexReader.maxDoc(); for (int i = 0; i < docLength; i++) { Document doc = indexReader.document(i); Company company = new Company(); if (doc.get("name") == null) { System.out.println("name为空"); } else { // company.setEntID(doc.get("id")); company.setEntName(doc.get("name")); company.setREGNO(doc.get("regno")); company.setORGNO(doc.get("orgno")); company.setDOM(doc.get("dom")); company.setLEREP(doc.get("lerep")); // company.setREGCAP(doc.get("regcap")); company.setENTTYPE(doc.get("enttype")); // company.setOPSCOPE(doc.get("opscope")); // company.setDOMDISTRICT(doc.get("domdistrict")); // company.setREGNO(doc.get("regnorg")); companys.add(company); } } System.out.println("显示所有插入的索引记录："); /*for (Company company : companys) { System.out.println(company); }*/ } catch (IOException e) { e.printStackTrace(); } finally { if (indexReader != null) { try { index