Apache Lucene全文检索和IKAnalyzer分词工具类

【文件属性】：

文件名称：Apache Lucene全文检索和IKAnalyzer分词工具类

文件大小：1.71MB

文件格式：ZIP

更新时间：2017-05-12 04:51:07

Lucene IKAnalyzer 91zcm

说明：依赖jar包：lucene-core-2.3.2.jar、IKAnalyzer3.2.8.jar。 一、LuceneUtil 工具类代码： package com.zcm.lucene; 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.standard.StandardAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.Term; import org.apache.lucene.queryParser.MultiFieldQueryParser; import org.apache.lucene.search.BooleanClause; import org.apache.lucene.search.Hits; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.Query; import org.wltea.analyzer.IKSegmentation; import org.wltea.analyzer.Lexeme; /** * Apache Lucene全文检索和IKAnalyzer分词工具类 *

Company: 91注册码

* time:2014-04-22 * @author www.91zcm.com * @date * @version 1.1 */ public class LuceneUtil { /**索引创建的路径**/ private static String LucenePath = "d://index"; /** * 创建索引 * @throws Exception */ public static int createIndex(List list) throws Exception{ /**这里放索引文件的位置**/ File indexDir = new File(LucenePath); Analyzer luceneAnalyzer = new StandardAnalyzer(); /**注意最后一个boolean类型的参数：表示是否重新创建，true表示新创建（以前存在时回覆盖）**/ IndexWriter indexWriter = new IndexWriter(indexDir, luceneAnalyzer,true); for (int i = 0; i < list.size(); i++) { LuceneVO vo = (LuceneVO)list.get(i); Document doc = new Document(); Field FieldId = new Field("aid", String.valueOf(vo.getAid()),Field.Store.YES, Field.Index.NO); Field FieldTitle = new Field("title", vo.getTitle(), Field.Store.YES,Field.Index.TOKENIZED,Field.TermVector.WITH_POSITIONS_OFFSETS); Field FieldRemark = new Field("remark", vo.getRemark(), Field.Store.YES,Field.Index.TOKENIZED,Field.TermVector.WITH_POSITIONS_OFFSETS); doc.add(FieldId); doc.add(FieldTitle); doc.add(FieldRemark); indexWriter.addDocument(doc); } /**查看IndexWriter里面有多少个索引**/ int num = indexWriter.docCount(); System.out.println("总共------》" + num); indexWriter.optimize(); indexWriter.close(); return num; } /** * IKAnalyzer分词 * @param word * @return * @throws IOException */ public static List tokenWord(String word) throws IOException{ List tokenArr = new ArrayList(); StringReader reader = new StringReader(word); /**当为true时，分词器进行最大词长切分**/ IKSegmentation ik = new IKSegmentation(reader, true); Lexeme lexeme = null; while ((lexeme = ik.next()) != null){ tokenArr.add(lexeme.getLexemeText()); } return tokenArr; } /** * 创建索引（单个） * @param list * @throws Exception */ public static void addIndex(LuceneVO vo) throws Exception { /**这里放索引文件的位置**/ File indexDir = new File(LucenePath); Analyzer luceneAnalyzer = new StandardAnalyzer(); IndexWriter indexWriter = new IndexWriter(indexDir, luceneAnalyzer, false); /**增加document到索引去 **/ Document doc = new Document(); Field FieldId = new Field("aid", String.valueOf(vo.getAid()),Field.Store.YES, Field.Index.NO); Field FieldTitle = new Field("title", vo.getTitle(), Field.Store.YES,Field.Index.TOKENIZED,Field.TermVector.WITH_POSITIONS_OFFSETS); Field FieldRemark = new Field("remark", vo.getRemark(), Field.Store.YES,Field.Index.TOKENIZED,Field.TermVector.WITH_POSITIONS_OFFSETS); doc.add(FieldId); doc.add(FieldTitle); doc.add(FieldRemark); indexWriter.addDocument(doc); /**optimize()方法是对索引进行优化 **/ indexWriter.optimize(); indexWriter.close(); } /** * 创建索引（多个） * @param list * @throws Exception */ public static void addIndexs(List list) throws Exception { /**这里放索引文件的位置**/ File indexDir = new File(LucenePath); Analyzer luceneAnalyzer = new StandardAnalyzer(); IndexWriter indexWriter = new IndexWriter(indexDir, luceneAnalyzer,false); /**增加document到索引去 **/ for (int i=0; i list) throws Exception { /**这里放索引文件的位置**/ File indexDir = new File(LucenePath); Analyzer luceneAnalyzer = new StandardAnalyzer(); IndexWriter indexWriter = new IndexWriter(indexDir, luceneAnalyzer,false); /**增加document到索引去 **/ for (int i=0; i list) throws Exception { /**这里放索引文件的位置**/ File indexDir = new File(LucenePath); Analyzer luceneAnalyzer = new StandardAnalyzer(); IndexWriter indexWriter = new IndexWriter(indexDir, luceneAnalyzer,false); /**删除索引 **/ for (int i=0; i search(String word) { List list = new ArrayList(); Hits hits = null; try { IndexSearcher searcher = new IndexSearcher(LucenePath); String[] queries = {word,word}; String[] fields = {"title", "remark"}; BooleanClause.Occur[] flags = {BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD}; Query query = MultiFieldQueryParser.parse(queries, fields, flags, new StandardAnalyzer()); if (searcher != null) { /**hits结果**/ hits = searcher.search(query); LuceneVO vo = null; for (int i = 0; i < hits.length(); i++) { Document doc = hits.doc(i); vo = new LuceneVO(); vo.setAid(Integer.parseInt(doc.get("aid"))); vo.setRemark(doc.get("remark")); vo.setTitle(doc.get("title")); list.add(vo); } } } catch (Exception ex) { ex.printStackTrace(); } return list; } } 二、Lucene用到的JavaBean代码： package com.zcm.lucene; /** * Apache Lucene全文检索用到的Bean *

Company: 91注册码

* time:2014-04-22 * @author www.91zcm.com * @date * @version 1.1 */ public class LuceneVO { private Integer aid; /**文章ID**/ private String title; /**文章标题**/ private String remark; /**文章摘要**/ public Integer getAid() { return aid; } public void setAid(Integer aid) { this.aid = aid; } public String getTitle() { return title; } public void setTitle(String title) { this.title = title; } public String getRemark() { return remark; } public void setRemark(String remark) { this.remark = remark; } } 备注：源码来源于www.91zcm.com 开源博客中的全文检索代码。（http://www.91zcm.com/）

【文件预览】：
lucene
----.settings()
--------org.eclipse.wst.jsdt.ui.superType.name(6B)
--------org.eclipse.core.resources.prefs(88B)
--------org.eclipse.wst.jsdt.ui.superType.container(49B)
--------.jsdtscope(500B)
----src()
--------com()
----.project(1KB)
----WebRoot()
--------META-INF()
--------WEB-INF()
--------index.jsp(834B)
----.mymetadata(291B)
----.classpath(520B)
----.myeclipse()