lucene建立索引和查询

package cn.ljzblog.ljz.util;

import java.io.IOException;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;

import jeasy.analysis.MMAnalyzer;

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.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.Highlighter;
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.LockObtainFailedException;

import test.LuceneJEAnalyzerText;
import cn.ljzblog.ljz.model.Article;
import cn.ljzblog.ljz.model.LogQueryTemp;
import cn.ljzblog.ljz.model.PicQueryTemp;

/**
* @theme 主要是封装lucene索引和查询索引的方法
* @author ljz
* @since 2010/10/10
*/
public class LuceneQuery {
private static String indexPath;// 索引生成的目录
private static IndexWriter indexWriter;//
private IndexSearcher searcher;
private Directory dir;
private String prefixHTML = "<font color='red'>";
private String suffixHTML = "</font>";
private Date date;
private Date date2;

public LuceneQuery(String indexPath) {
date = new Date();
this.indexPath = indexPath;
}

/**
* 函数功能:建立索引
*
* @param list
*/
public void createIndex(List<Article> list) {

createIndexWriter();// 生成indexWriter对象
for (Article article : list) {
Document document = new Document();// 生成Document对象
Field field = new Field("articleId", String.valueOf(article
.getArticleId()), Field.Store.YES, Field.Index.NO);
Field field2 = new Field("articleName", article.getArticleName(),
Field.Store.YES, Field.Index.ANALYZED);
Field field3 = new Field("articleContent", article
.getArticleContent(), Field.Store.YES, Field.Index.NO);
document.add(field);
document.add(field2);
document.add(field3);
try {
indexWriter.addDocument(document);
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
closeIndexWriter(indexWriter);
}

/**
* 函数功能：建立高亮显示查询的
*
*/
public void createHightLightIndex(List<LogQueryTemp> list) {
createIndexWriter();// 生成indexWriter对象
for (LogQueryTemp logQuery : list) {
Document document = new Document();// 生成Document对象
Field field = new Field("articleId", String.valueOf(logQuery
.getArticleId()), Field.Store.YES, Field.Index.NO);
Field field2 = new Field("articleName", logQuery.getArticleName(),
Field.Store.YES, Field.Index.ANALYZED);
Field field3 = new Field("articleKindName", logQuery
.getArticleKindName(), Field.Store.YES, Field.Index.NO);
Field field4 = new Field("writeTime", logQuery.getWriteTime(),
Field.Store.YES, Field.Index.NO);
Field field5 = new Field("articleContent", logQuery
.getArticleContent(), Field.Store.YES, Field.Index.ANALYZED);
document.add(field);
document.add(field2);
document.add(field3);
document.add(field4);
document.add(field5);
try {
indexWriter.addDocument(document);
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
closeIndexWriter(indexWriter);
}
/**
* 函数功能：建立查询图片的索引
*
*/
public void createPicIndex(List<PicQueryTemp> list) {
createIndexWriter();// 生成indexWriter对象
for (PicQueryTemp picQuery : list) {
Document document = new Document();// 生成Document对象
Field field = new Field("picId", String.valueOf(
picQuery.getPicId()), Field.Store.YES, Field.Index.NO);
Field field2 = new Field("picGroupId", String.valueOf(picQuery.getPicGroupId()),
Field.Store.YES, Field.Index.NO);
Field field3 = new Field("picName",
picQuery.getPicName(), Field.Store.YES, Field.Index.NO);
Field field4 = new Field("pictureDetail", picQuery.getPictureDetail(),
Field.Store.YES, Field.Index.ANALYZED);

document.add(field);
document.add(field2);
document.add(field3);
document.add(field4);
try {
indexWriter.addDocument(document);
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
closeIndexWriter(indexWriter);
}
/**
* 函数功能 ：关闭indexWriter
*
* @param indexWriter
*/
public void closeIndexWriter(IndexWriter indexWriter) {
try {
indexWriter.optimize();
indexWriter.close();
date2 = new Date();
System.out.println("建立索引总共用了:" + (date2.getTime() - date.getTime())
+ "毫秒");
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}

}

/**
* 函数功能:生成indexWriter对象
*/
public void createIndexWriter() {
try {
boolean flag = true;
//如果已存在索引,则追加索引
if(IndexReader.indexExists(indexPath))
{
flag = false;
}

indexWriter = new IndexWriter(indexPath, new StandardAnalyzer(),
flag, IndexWriter.MaxFieldLength.LIMITED);
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (LockObtainFailedException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}

/**
* 函数功能:查询索引
*/
public List<Article> queryIndex(String indexPath, String findContent) {
List<Article> list2 = new ArrayList<Article>();
System.out.println("查询内容为:" + findContent);
try {
dir = FSDirectory.getDirectory(indexPath);
IndexSearcher searcher = new IndexSearcher(dir);
QueryParser parser = new QueryParser("articleName",
new StandardAnalyzer());
try {
Query query = parser.parse(findContent);// 根据查询内容进行查询
TopDocs topDocs = searcher.search(query, 5);
ScoreDoc[] hits = topDocs.scoreDocs;
System.out.println("总共查询到" + hits.length + "条记录");
for (int i = 0; i < hits.length; i++) {
int DocId = hits[i].doc;
Article article = new Article();
Document doc = searcher.doc(DocId);
System.out.println("id:" + doc.get("articleId")
+ ",articleName:" + doc.get("articleName"));
article
.setArticleId(Integer
.parseInt(doc.get("articleId")));
article.setArticleName(doc.get("articleName"));
article.setArticleContent(doc.get("articleContent"));
list2.add(article);
// list2.add(doc.get("sname"));
}

Date date3 = new Date();
System.out.println("查询总共花的时间为:"
+ (date3.getTime() - date2.getTime()) + "毫秒");

} catch (ParseException e) {
e.printStackTrace();
}

} catch (IOException e) {
e.printStackTrace();
}
System.out.println("list2的长度为:" + list2.size());
return list2;

}

/**
* 函数功能:通过booleanQuery方法进行查询索引
*/
public List<Article> queryIndexByBooleanQuery(String indexPath,
String findContent) {
List<Article> list2 = new ArrayList<Article>();
LuceneJEAnalyzerText jeAnalyzer = new LuceneJEAnalyzerText(indexPath);
System.out.println("查询内容为:" + findContent);
BooleanQuery booleanQuery = new BooleanQuery();
try {
dir = FSDirectory.getDirectory(indexPath);
searcher = new IndexSearcher(dir);
String[] str = jeAnalyzer.createAnalyzer(findContent).split(",");
for (int i = 0; i < str.length; i++) {
booleanQuery.add(
new TermQuery(new Term("articleName", str[i])),
BooleanClause.Occur.SHOULD);
}

// QueryParser parser = new QueryParser("articleName", new
// StandardAnalyzer());

// Query query = parser.parse(findContent);//根据查询内容进行查询
TopDocs topDocs = searcher.search(booleanQuery, 3);
ScoreDoc[] hits = topDocs.scoreDocs;
System.out.println("总共查询到" + hits.length + "条记录");
for (int i = 0; i < hits.length; i++) {
int DocId = hits[i].doc;
Article article = new Article();
Document doc = searcher.doc(DocId);
System.out.println("id:" + doc.get("articleId")
+ ",articleName:" + doc.get("articleName"));
article.setArticleId(Integer.parseInt(doc.get("articleId")));
article.setArticleName(doc.get("articleName"));
// article.setArticleContent(doc.get("articleContent"));
list2.add(article);
// list2.add(doc.get("sname"));
}
if (hits.length > 0) {
list2.remove(0);
}
Date date3 = new Date();
System.out.println("查询总共花的时间为:"
+ (date3.getTime() - date2.getTime()) + "毫秒");

} catch (IOException e) {
e.printStackTrace();
}
System.out.println("list2的长度为:" + list2.size());
return list2;

}

/**
* 函数功能:高亮显示查询
*
* @param fieldName
* @param keyword
* @throws CorruptIndexException
* @throws IOException
* @throws ParseException
*/
public List<LogQueryTemp> search( String keyword)
throws CorruptIndexException, IOException, ParseException {
List<LogQueryTemp> listlog = new ArrayList<LogQueryTemp>();

searcher = new IndexSearcher(indexPath);
Analyzer analyzer = new MMAnalyzer();
//QueryParser queryParse = new QueryParser(fieldName, analyzer);
//Query query = queryParse.parse(keyword);

LuceneJEAnalyzerText jeAnalyzer = new LuceneJEAnalyzerText(indexPath);
System.out.println("查询内容为:" + keyword);
BooleanQuery booleanQuery = new BooleanQuery();
try{
dir = FSDirectory.getDirectory(indexPath);
searcher = new IndexSearcher(dir);
String[] str = jeAnalyzer.createAnalyzer(keyword).split(",");
for (int j = 0; j < str.length; j++) {
booleanQuery.add(
new TermQuery(new Term("articleContent", str[j])),
BooleanClause.Occur.SHOULD);
booleanQuery.add(
new TermQuery(new Term("articleName", str[j])),
BooleanClause.Occur.SHOULD);

}


Hits hits = searcher.search(booleanQuery);
for (int i = 0; i < hits.length(); i++) {
LogQueryTemp logQuery = new LogQueryTemp();
Document doc = hits.doc(i);
String text = doc.get("articleContent");
String text2 = doc.get("articleName");
int htmlLength = prefixHTML.length() + suffixHTML.length();
//System.out.println("高亮HTML的总长度为" + htmlLength);
SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter(
prefixHTML, suffixHTML);
Highlighter highlighter = new Highlighter(simpleHTMLFormatter,
new QueryScorer(booleanQuery));
String highLightText = highlighter.getBestFragment(analyzer,
"articleContent", text);
String highLightText2 = highlighter.getBestFragment(analyzer,
"articleName", text2);
System.out.println("★高亮显示第 " + (i + 1) + " 条检索结果如下所示：");
System.out.println(highLightText);
logQuery.setArticleId(doc.get("articleId"));
logQuery.setArticleName(highLightText2);
logQuery.setArticleKindName(doc.get("articleKindName"));
logQuery.setArticleContent(highLightText);
logQuery.setWriteTime(doc.get("writeTime"));
listlog.add(logQuery);
System.out.println("显示第 " + (i + 1) + " 条检索结果摘要的长度为(含高亮HTML代码)："
+ highLightText.length());
}
searcher.close();
}
catch(IOException ex){
ex.printStackTrace();
}
System.out.println("高亮显示的长度为:"+listlog.size());
return listlog;

}
public List<PicQueryTemp> queryPicByLucene(String findContent){
List<PicQueryTemp> list2 = new ArrayList<PicQueryTemp>();
LuceneJEAnalyzerText jeAnalyzer = new LuceneJEAnalyzerText(indexPath);
System.out.println("查询内容为:" + findContent);
BooleanQuery booleanQuery = new BooleanQuery();
try {
dir = FSDirectory.getDirectory(indexPath);
searcher = new IndexSearcher(dir);
String[] str = jeAnalyzer.createAnalyzer(findContent).split(",");
for (int i = 0; i < str.length; i++) {
booleanQuery.add(
new TermQuery(new Term("pictureDetail", str[i])),
BooleanClause.Occur.SHOULD);
}


TopDocs topDocs = searcher.search(booleanQuery,12);
ScoreDoc[] hits = topDocs.scoreDocs;
System.out.println("总共查询到" + hits.length + "条记录");
for (int i = 0; i < hits.length; i++) {
int DocId = hits[i].doc;
PicQueryTemp picQuery = new PicQueryTemp();
Document doc = searcher.doc(DocId);
picQuery.setPicGroupId(Integer.parseInt(doc.get("picGroupId")));
picQuery.setPicId(Integer.parseInt(doc.get("picId")));
picQuery.setPicName(doc.get("picName"));
picQuery.setPictureDetail(doc.get("pictureDetail"));
list2.add(picQuery);
// list2.add(doc.get("sname"));
}

Date date3 = new Date();
System.out.println("查询总共花的时间为:"
+ (date3.getTime() - date2.getTime()) + "毫秒");

} catch (IOException e) {
e.printStackTrace();
}
System.out.println("list2的长度为:" + list2.size());
return list2;

}
}