Lucene 2.4的实例
import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
import java.util.Map;
import java.util.Set;
import net.paoding.analysis.analyzer.PaodingAnalyzer;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Fieldable;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.IndexWriter.MaxFieldLength;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocCollector;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.RAMDirectory;
import com.ole.factory.BeanFactory;
public class TestLucene {
//索引目录
public static final String INDEX_DIR=System.getProperty("user.dir")+
?? "/index_dir";
public static final String LUCENE_DATA=System.getProperty("user.dir")+
?? "/lucene_data";
private String[] columnNameArr ={"id","ordercode","incompanyname","outcompanyname",
??? "buydate","saledate","buygoodsnum","salegoodsnum","buyprice","saleprice",
??? "trucknum","empcode1","empcode2","losskg","goodscode","orderemp",
??? "orderdate","orderstate","batchno_out","batchno_in","ys","ss","ysye",
??? "yf","sf","yfye","carry_in","carry_out"};
/**
?? * 获取数据库数据
?? */
@SuppressWarnings("unchecked")
public List<Map<String,Object>> queryOrderIO(){
?? BeanFactory beanFac = BeanFactory.getInstance();
??? IOrderIOService orderService= (IOrderIOService)beanFac.
???? getApplicationnContext().getBean("orderIOService");
?? return (List<Map<String,Object>>)orderService.queryOrderIO();
}
/**
* 创建索引
*/
public void createIndex() {
?? synchronized (INDEX_DIR) {
??? List<Map<String,Object>> resultList = queryOrderIO();
????????? Date start=new Date();??????
????????? Analyzer analyzer=new StandardAnalyzer();??
????????? try {??
??????? IndexWriter writer=new IndexWriter(INDEX_DIR,analyzer,
????????? true,MaxFieldLength.UNLIMITED);
??????? /***********************/
??????? for(Map<String,Object> rowItem : resultList){
???????? Document doc=new Document();
//???????? Set<String> columns = rowItem.keySet();
???????? for(String columnItem : columnNameArr){
????????? Field fieldvalue= new Field(columnItem,
??????????? rowItem.get(columnItem)!=null?rowItem.get(columnItem).toString():"",
??????????? Field.Store.YES,Field.Index.ANALYZED,Field.TermVector.WITH_POSITIONS_OFFSETS);//Field.TermVector.NO暂不需要分词
????????? doc.add(field_value);
???????? }
???????? writer.addDocument(doc);
??????? }
???????
???????? writer.optimize();??
???????? writer.close();??
???????? Date end=new Date();??
???????? long indexTime=end.getTime()-start.getTime();??
???????? System.out.println("索引完成所需时间:(ms)");??
???????? System.out.println(indexTime);??
????? } catch (CorruptIndexException e) {??
?????? e.printStackTrace();??
????? } catch (LockObtainFailedException e) {??
?????? e.printStackTrace();??
????? } catch (IOException e) {??
?????? e.printStackTrace();??
????? }??
????????? System.out.println("创建索引完成!");
?? }
}
/**
?? * 跟据关键字查询
?? */
public void searchIndex(String queryString,String columnName){
?? try{
??? IndexSearcher isearcher = new IndexSearcher(INDEX_DIR);
//??? BooleanClause.Occur[] clauses = { BooleanClause.Occur.SHOULD};
//??????? TopDocCollector collector = new TopDocCollector(10000);
//??????? QueryParser parser = new QueryParser(INDEX_DIR, new StandardAnalyzer());
//??????? Query query = parser.parse(queryString);
??????? Query query = new QueryParser(columnName,new StandardAnalyzer()).parse(queryString);
//????? ?? MultiFieldQueryParser.parse(queryString,
//????? ???? columnName, new StandardAnalyzer());
//??????? isearcher.search(query, collector);
??????? ScoreDoc[] hits = isearcher.search(query, isearcher.maxDoc()).scoreDocs;
??????? System.out.println("hits.length="+hits.length);
??????? for (int i = 0; i < hits.length; i++) {
?????????? Document doc = isearcher.doc(hits[i].doc);
?????????? for(String column : columnNameArr){
?????????? System.out.println(column+"="+doc.get(column));
?????????? }
?????????? System.out.println("=========================");
??? }
??????? isearcher.close();
?? }catch (Exception e) {
??????? e.printStackTrace();
?? }
}
??
???
// /**
//?? * 庖丁解牛分析器
//?? */
// public synchronized Analyzer getAnalyzer() {
//????? return new PaodingAnalyzer();
// }
public static void main(String[] args){
?? TestLucene testLucene = new TestLucene();
//?? testLucene.createIndex();
?? testLucene.searchIndex("2009-08-01","buydate");
//?? testLucene.searchIndex("ordercode","S200908040062",
//???? new StandardAnalyzer());
}
}??
/*
* 索引域:Field是Document对象的基本组成单位,每个Field存储了实际的所有文本数据,这些文本数据在内部调用了分析器Aanlyzer的索引项结果
* Field内的检索查询最终以索引项为单位的.比索引更小的单位无法检索到
* 中文的索引项一中文分词的结果为检索单元，英文的索引项是以单词为检索单元,检索单元为最小的检索单位
* 1.public Field(String name, byte[] value, Store store)
* 2.public Field(String name, byte[] value, int offset, int length, Store store)
* 3.public Field(String name, String value, Store store, Index index)
* 4.public Field(String name, String value, Store store, Index index, TermVector termVector)
* 5.public Field(String name, Reader reader)
* 6.public Field(String name, Reader reader, TermVector termVector)
* 7.public Field(String name, TokenStream tokenStream)
* 8.public Field(String name, TokenStream tokenStream, TermVector termVector)
* 第1,2个函数用于二进制数据索引;3,4用于直接给定字符串的索引，5，6用于文件内容的索引，即Reader数据流（常用）
* name-域名为固定的参数,用于指定添加域的标识,限定检索的范围或提取属性值
* value-
* Store-控制域数据的存储，表示数据本身是否存储(注意:并不是指索引是否存储)
*?????? 1.Store.NO 只保存索引,不包含数据本身信息,减少空间采用
*?????? 2.Store.YES 保存索引并保存数据原始信息
*?????? 3.Store.COMPRESS 存储并压缩原始信息
* Index-控制索引格式的参数,表示数据是否需要索引,即当前域是否需要用于检索
*?????? 1.Index.NO 不索引,只作为辅助信息
*?????? 2.Index.ANALYZER?? 2.4版本替换6
*?????? 3.Index.NOT_ANALYZER 2.4版本替换7
*?????? 4.Index.ANALYZER_NO_NORMS
*?????? 5.Index.NOT_ANALYZER_NO_NOTRMS??
*?????? 6.Index.TOKENIZED 使用分词器并建立索引
*?????? 7.Index.UN_TOKENIZED 不分词建立索引(某些内容的整体作为索引)
*?????? 8.Index.NO_NORMS 禁用分析器处理
* TermVector-域内信息是否需要分词,在中文处理中分词是索引的基础
*???????? TermVector保存Token.getPositionIncrement() 和Token.startOffset() 以及Token.endOffset() 信息
*?????? 1.Field.TermVector.NO:不保存term vectors
*?????? 2.Field.TermVector.YES:保存term vectors
*?????? 3.Field.TermVector.WITH_POSITIONS:保存term vectors.(保存值和token位置信息)
*?????? 4.Field.TermVector.WITH_OFFSETS:保存term vectors.(保存值和Token的offset)
*?????? 5.Field.TermVector.WITH_POSITIONS_OFFSETS:保存term vectors.(保存值和token位置信息和Token的offset)??
*/
