package edu.dlnu.xeon.dao.impl;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriter.MaxFieldLength;
import org.apache.lucene.index.Term;
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.Formatter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.Scorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.util.NumericUtils;
import org.wltea.analyzer.lucene.IKQueryParser;
import org.wltea.analyzer.lucene.IKSimilarity;
import edu.dlnu.xeon.dao.HTMLIndexDao;
import edu.dlnu.xeon.domain.HTML;
import edu.dlnu.xeon.domain.QueryResult;
import edu.dlnu.xeon.util.HTMLDocumentUtils;
import edu.dlnu.xeon.util.LuceneUtils;
public class HTMLIndexDaoImpl implements HTMLIndexDao{
/**
* 保存javaBean到索引库
* @param HTML 要保存的javaBean
*/
public void save(HTML html){
Document doc=HTMLDocumentUtils.HTML2Document(html);
doc.setBoost(0.5F); // 1F表示正常得分，大于1表示高分，小于1表示低分
IndexWriter indexWriter=LuceneUtils.getIndexWriter();
try {
indexWriter.addDocument(doc);//添加
} catch (Exception e) {
throw new RuntimeException(e);
}
}
public void indexCommit() throws CorruptIndexException, IOException{
LuceneUtils.getIndexWriter().commit();
}
/**
* 分页查询
* @param queryString 执行查询的条件
* @param first 为刚开始查询的记录索引
* @param max 为查询的最大记录数
* @return
*/
public QueryResult<HTML> query(String queryString,QueryResult<HTML> result){
List<HTML> list=new ArrayList<HTML>();
//1.首先转换查询对象(从多个字段中查询),则要用到QueryParser的子类MultiFieldQueryParser
// QueryParser queryParser=new MultiFieldQueryParser(Version.LUCENE_30,new String[]{"title","content"}, LuceneUtils.getAnalyzer());
IndexSearcher indexSearcher=null;
int rowCount=0;
int first=result.getPageNow()*result.getPageSize();
try {
Query query=IKQueryParser.parseMultiField(new String[]{"title","description"}, queryString);
indexSearcher=new IndexSearcher(LuceneUtils.getDirectory());
indexSearcher.setSimilarity(new IKSimilarity());
Sort sort = new Sort(new SortField("title", SortField.STRING, true));//设置排序条件
TopDocs topDocs=indexSearcher.search(query,null,first+result.getPageSize(),sort);
// ========================================================================================== 【创建高亮器】
Query myQuery = query; // 查询条件
String preTag = "<font color='red'>"; // 前缀
String postTag = "</font>"; // 后缀
int size = 40; // 摘要大小
Formatter formatter = new SimpleHTMLFormatter(preTag, postTag); // 前缀、后缀
Scorer scorer = new QueryScorer(myQuery);
Highlighter highlighter = new Highlighter(formatter, scorer);
highlighter.setTextFragmenter(new SimpleFragmenter(size)); // 摘要大小（字数）
// ==========================================================================================
rowCount=topDocs.totalHits;
//2.返回中间过程处理结果
ScoreDoc[] scoreDocs=topDocs.scoreDocs;
HTML html=null;
//3.处理得到最终结果
int endIndex=Math.min(result.getPageSize()+first,scoreDocs.length);
for(int i=first;i<endIndex;i++){
int docId=scoreDocs[i].doc;
Document doc=indexSearcher.doc(docId);
// ======================================================================================== 【使用高亮器】
// 一次高亮一个字段，返回高亮后的结果，如果要高亮的字段值中没有出现关键字，就会返回null
String text = highlighter.getBestFragment(LuceneUtils.getAnalyzer(), "description", doc.get("description"));
if (text != null) {
doc.getField("description").setValue(text); // 使用高亮后的文本替换原始内容
}
text=highlighter.getBestFragment(LuceneUtils.getAnalyzer(), "title", doc.get("title"));
if (text != null) {
doc.getField("title").setValue(text);
}
// ========================================================================================
html=HTMLDocumentUtils.document2HTML(doc);
list.add(html);
}
} catch (Exception e) {
e.printStackTrace();
}finally{
if(indexSearcher!=null){
try {
indexSearcher.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
return new QueryResult<HTML>(list,rowCount);
}
public QueryResult<HTML> query(String queryString){
List<HTML> list=new ArrayList<HTML>();
//1.首先转换查询对象(从多个字段中查询),则要用到QueryParser的子类MultiFieldQueryParser
// QueryParser queryParser=new MultiFieldQueryParser(Version.LUCENE_30,, LuceneUtils.getAnalyzer());
IndexSearcher indexSearcher=null;
try {
Query query=IKQueryParser.parseMultiField(new String[]{"title","description"}, queryString);
indexSearcher=new IndexSearcher(LuceneUtils.getDirectory());
indexSearcher.setSimilarity(new IKSimilarity());
TopDocs topDocs=indexSearcher.search(query, 1000);
//2.返回中间过程处理结果
ScoreDoc[] scoreDocs=topDocs.scoreDocs;
HTML html=null;
//3.处理得到最终结果
for(ScoreDoc scoreDoc:scoreDocs){
int docId=scoreDoc.doc;
Document doc=indexSearcher.doc(docId);
html=HTMLDocumentUtils.document2HTML(doc);
list.add(html);
}
} catch (Exception e) {
e.printStackTrace();
}finally{
if(indexSearcher!=null){
try {
indexSearcher.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
return new QueryResult<HTML>(list);
}
/**
* 删除索引库中的记录
* Term为最小查询单位，查询某个字段的值
* @param id
*/
public void delete(Integer id){
IndexWriter indexWriter=null;
try {
//用唯一标示符id来删除，删除的一定是唯一的一条记录，根据目录区的索引来删除数据区中的记录
Term term=new Term("id", NumericUtils.intToPrefixCoded(id));
indexWriter=new IndexWriter(LuceneUtils.getDirectory(), LuceneUtils.getAnalyzer(), MaxFieldLength.LIMITED);
indexWriter.deleteDocuments(term);//删除
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 更新索引
* 更新就是先删除后创建
* @param HTML
*/
public void update(HTML HTML){
Document doc=HTMLDocumentUtils.HTML2Document(HTML);
IndexWriter indexWriter=null;
try {
// Term term=new Term("id",NumericUtils.intToPrefixCoded(HTML.getId()));
// indexWriter=new IndexWriter(LuceneUtils.getDirectory(), LuceneUtils.getAnalyzer(), MaxFieldLength.LIMITED);
// indexWriter.updateDocument(term, doc);//更新索引库中的记录
//indexWriter.deleteDocuments(term);
//indexWriter.addDocument(doc);//添加
} catch (Exception e) {
e.printStackTrace();
}
}
}
基于Hadoop平台的分布式搜索引擎的设计与实现+部署文档+全部资料 高分项目.zip
版权申诉
82 浏览量
2024-05-13
18:09:38
上传
评论
收藏 45.62MB ZIP 举报
基于Hadoop平台的分布式搜索引擎的设计与实现+部署文档+全部资料 高分项目.zip （116个子文件） 
_1.cfs 811KB _0.cfs 293KB .classpath 834B org.eclipse.wst.common.component 488B org.eclipse.wst.jsdt.ui.superType.container 49B index.css 1KB ext_stopword.dic 153B segments.gen 20B .gitignore 8B
jruby-complete-1.6.5.jar 12.7MB hadoop-core-1.2.1.jar 4.01MB hadoop-core-1.0.0.jar 3.57MB core-3.1.1.jar 3.4MB hadoop-test-1.2.1.jar 2.98MB hbase-0.92.0.jar 2.96MB hbase-0.92.0-tests.jar 1.42MB IKAnalyzer3.2.0Stable.jar 1.11MB guava-r09.jar 1.09MB lucene-core-3.0.3.jar 1010KB jsp-2.1-6.1.14.jar 1001KB snappy-java-1.0.3.2.jar 972KB jaxb-impl-2.1.12.jar 847KB commons-math-2.1.jar 813KB netty-3.2.4.Final.jar 772KB zookeeper-3.4.2.jar 747KB jersey-server-1.4.jar 662KB commons-collections-3.2.1.jar 562KB jetty-6.1.26.jar 527KB jackson-mapper-asl-1.5.5.jar 474KB log4j-1.2.16.jar 470KB jersey-core-1.4.jar 445KB protobuf-java-2.4.0a.jar 439KB velocity-1.7.jar 439KB jasper-compiler-5.5.23.jar 399KB hadoop-tools-1.2.1.jar 377KB commons-httpclient-3.1.jar 298KB libthrift-0.7.0.jar 294KB jsoup-1.8.1.jar 294KB commons-configuration-1.6.jar 292KB httpclient-4.0.1.jar 284KB commons-lang-2.5.jar 273KB avro-1.5.3.jar 257KB commons-lang-2.4.jar 256KB commons-beanutils-core-1.8.0.jar 201KB lucene-analyzers-3.0.3.jar 196KB commons-beanutils-1.7.0.jar 184KB commons-net-1.4.1.jar 177KB jetty-util-6.1.26.jar 173KB httpcore-4.0.1.jar 169KB jackson-core-asl-1.5.5.jar 168KB avro-ipc-1.5.3.jar 164KB commons-digester-1.8.jar 140KB jersey-json-1.4.jar 139KB hadoop-examples-1.2.1.jar 139KB jsp-api-2.1-6.1.14.jar 132KB servlet-api-2.5-6.1.14.jar 129KB commons-el-1.0.jar 110KB servlet-api-2.5.jar 103KB jaxb-api-2.1.jar 101KB high-scale-lib-1.1.1.jar 94KB jasper-runtime-5.5.23.jar 75KB jettison-1.1.jar 66KB activation-1.1.jar 62KB commons-logging-1.1.1.jar 59KB commons-codec-1.4.jar 57KB lucene-highlighter-3.0.3.jar 46KB asm-3.1.jar 42KB commons-cli-1.2.jar 40KB lucene-memory-3.0.3.jar 27KB stax-api-1.0.1.jar 26KB jackson-xc-1.5.5.jar 24KB slf4j-api-1.5.8.jar 23KB jamon-runtime-2.3.1.jar 20KB jackson-jaxrs-1.5.5.jar 17KB xmlenc-0.52.jar 15KB slf4j-log4j12-1.5.8.jar 9KB hadoop-ant-1.2.1.jar 7KB hadoop-minicluster-1.2.1.jar 417B hadoop-client-1.2.1.jar 414B HTMLIndexDaoImpl.java 7KB HBaseDaoImpl.java 6KB PagingSearchServlet.java 2KB LuceneUtils.java 2KB QueryResult.java 1KB SnapShotServlet.java 1KB HTML.java 1KB SearchServiceImpl.java 1KB HTMLDocumentUtils.java 1KB IndexServiceImpl.java 928B SearchService.java 380B HTMLIndexDao.java 353B HBaseDao.java 180B
index_bg.jpg 347KB 404.jpg 164KB index.js 834B .jsdtscope 503B pagingSearchResult.jsp 3KB search.jsp 2KB index.jsp 2KB footer.jsp 1KB共 116 条
- 1
- 2
资源评论
