Lucene自定义排序-白红宇

Lucene自定义排序

阅读量：4031 次

发布时间：2019-05-24

本文共 5071 字，大约阅读时间需要 16 分钟。

package com.lucene.search;

import java.io.File;

import java.io.FileNotFoundException;

import java.io.FileReader;

import java.io.IOException;

import org.apache.lucene.document.Document;

import org.apache.lucene.document.Field;

import org.apache.lucene.document.NumericField;

import org.apache.lucene.index.CorruptIndexException;

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;

import com.chenlb.mmseg4j.Dictionary;

import com.chenlb.mmseg4j.analysis.ComplexAnalyzer;

public class IndexUtils {

private static Directory directory=null;

static{

try {

directory=FSDirectory.open(new File("E:/lucene/files"));

} catch (IOException e) {

e.printStackTrace();

}

public static Directory getDirectory() {

return directory;

}

/**

* 创建索引

public static void createIndex(){

IndexWriter writer=null;

File file=new File("E:/lucene/resource");

Document document=null;

try {

//创建IndexWriter 使用中文分词器

Dictionary dic=Dictionary.getInstance(new File("F:/官方包/lucene-3.5.0/mmseg4j-1.8.5/data"));

writer=new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_35,new ComplexAnalyzer(dic)));

for(File f:file.listFiles()){

document=new Document();

document.add(new Field("filename", f.getName(), Field.Store.YES, Field.Index.NOT_ANALYZED));

document.add(new Field("content",new FileReader(f)));

document.add(new NumericField("date", Field.Store.YES, true).setLongValue(f.lastModified()));

document.add(new NumericField("size", Field.Store.YES, false).setLongValue(f.length()/1000));

writer.addDocument(document);

}

} catch (FileNotFoundException e) {

e.printStackTrace();

} catch (CorruptIndexException e) {

e.printStackTrace();

} catch (IOException e) {

e.printStackTrace();

}finally{

try {

writer.close();

} catch (CorruptIndexException e) {

e.printStackTrace();

} catch (IOException e) {

e.printStackTrace();

}

######################

package com.lucene.search;

import java.io.IOException;

import java.sql.Date;

import java.text.SimpleDateFormat;

import org.apache.lucene.analysis.standard.StandardAnalyzer;

import org.apache.lucene.document.Document;

import org.apache.lucene.index.CorruptIndexException;

import org.apache.lucene.index.IndexReader;

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.TopDocs;

import org.apache.lucene.util.Version;

public class SearchUtils {

// 定义IndexReader,并使用静态块加载IndexReader

private static IndexReader reader = null;

static {

try {

reader = IndexReader.open(IndexUtils.getDirectory());

} catch (CorruptIndexException e) {

e.printStackTrace();

} catch (IOException e) {

e.printStackTrace();

}

// 获取IndexSearcher

private IndexSearcher getSearcher() {

try {

if (reader == null) {

reader = IndexReader.open(IndexUtils.getDirectory());

} else {

IndexReader ir = IndexReader.openIfChanged(reader);

if (ir != null) {

reader.close();

reader = ir;

}

return new IndexSearcher(reader);

} catch (CorruptIndexException e) {

e.printStackTrace();

} catch (IOException e) {

e.printStackTrace();

}

return null;

}

/**

* 排序查询

* @param querystr

* 查找匹配的字符串

* @param domain

* 查找内容的域

* @param sort

* 排序方式

public void SearchBySort(String querystr, String domain, Sort sort) {

TopDocs docs = null;

IndexSearcher searcher = this.getSearcher();

try {

QueryParser parser = new QueryParser(Version.LUCENE_35, domain,

new StandardAnalyzer(Version.LUCENE_35));

Query query = parser.parse(querystr);

if (sort == null) {

docs = searcher.search(query, 150);

} else {

docs = searcher.search(query, 150, sort);

}

// 输出信息

ScoreDoc[] sds = docs.scoreDocs;

Document d = null;

SimpleDateFormat sdf=new SimpleDateFormat("yyyy-MM-dd hh:mm:ss");

for (ScoreDoc s : sds) {

d = searcher.doc(s.doc);

System.out.println(s.doc+"->"

+s.score+"->"

+d.get("filename")+"->"

+d.get("size")+"->"

+sdf.format(new Date(Long.valueOf(d.get("date")))));

}

} catch (ParseException e) {

e.printStackTrace();

} catch (IOException e) {

e.printStackTrace();

}

############################

package com.lucene.test;

import org.apache.lucene.search.Sort;

import org.apache.lucene.search.SortField;

import org.junit.Before;

import org.junit.Test;

import com.lucene.search.SearchUtils;

public class TestSortSearch {

private SearchUtils su=null;

@Before

public void init(){

su=new SearchUtils();

}

@Test

public void testSortSearch(){

//无排序搜索,默认根据评分降序排序

//su.SearchBySort("中国", "content", null);

//通过doc的id进行排序

//su.SearchBySort("中国", "content", Sort.INDEXORDER);

//通过评分进行排序

//su.SearchBySort("中国", "content", Sort.RELEVANCE);

//根据SortField设置属性对filename进行升序排序

//su.SearchBySort("中国", "content", new Sort(new SortField("filename", SortField.STRING)));

//通过根据SortField设置最后一个属性进行降序排序

su.SearchBySort("中国", "content", new Sort(new SortField("filename", SortField.STRING,true)));

}

转载地址：http://enebi.baihongyu.com/

你可能感兴趣的文章

深入理解Apache Flink核心技术

查看>>

SpringCloud 各组件原理图，面试必备

查看>>

面试题总结：可能是全网最好的MySQL重要知识点

查看>>

MySQL面试之数据库索引

查看>>

完整的项目管理流程，看清PMP42个过程的执行顺序

备受面试官青睐的 Java NIO，到底和传统 IO 有啥不一样

排序算法，看这一篇就够了，含动图+Java实现

查看>>

性能指标：QPS、TPS、系统吞吐量理解

查看>>

搞清适配器模式、代理模式和装饰者模式的不同

SVN E200030: There are unfinished transactions detected

查看>>

搞定Nginx高并发原理：多进程单线程和多路IO复用模型

查看>>

深入NGINX：nginx高性能的实现原理