lucene操作

package com.java.lucene;

import java.io.StringReader;
import java.nio.file.Paths;
import java.util.Date;
import java.util.LinkedList;
import java.util.List;

import org.apache.commons.lang.StringEscapeUtils;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.Fragmenter;
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.search.highlight.SimpleSpanFragmenter;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import com.java.entity.Blog;
import com.java.util.DateUtil;
import com.java.util.StringUtil;

/**
 * 博客索引类
 * @author Administrator
 *
 */
public class BlogIndex {
	
	private Directory dir;
	
	/**
	 * 获取indexWriter实例
	 * @return
	 * @throws Exception
	 */
	private IndexWriter getWriter()throws Exception{
		dir = FSDirectory.open(Paths.get("d://lucene")); //写索引的目录
		SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer(); //中文分词器
		IndexWriterConfig iwc = new IndexWriterConfig(analyzer); //IndexWriter配置中文分析器
		IndexWriter writer = new IndexWriter(dir,iwc);//实例化一个IndexWriter
		return writer;
	}
		
	/**
	 * 添加博客索引
	 * @param blog
	 * @throws Exception
	 */
	public void addIndex(Blog blog)throws Exception{
		IndexWriter writer = this.getWriter();
		Document doc = new Document();
		//StringField 不进行分词 TextField 进行分词，Store.Yes表示进行存储
		doc.add(new StringField("id",String.valueOf(blog.getId()),Store.YES));
		doc.add(new TextField("title", blog.getTitle(), Store.YES));
		doc.add(new StringField("releaseDate", DateUtil.formatDate(new Date(), "yyyy-MM-dd"), Store.YES));
		doc.add(new TextField("content", blog.getContentNoTag(), Store.YES));
		writer.addDocument(doc);
		writer.close();
	}
	
	/**
	 * 删除索引
	 * @throws Exception
	 */
	public void deleteIndex(String blogId)throws Exception{
		IndexWriter writer = this.getWriter();
		writer.deleteDocuments(new Term("id",blogId));//id唯一标示，并且生成过索引
		writer.forceMergeDeletes();//强制删除索引
		writer.commit();
		writer.close();
	}
	public void updateIndex(Blog blog)throws Exception{
		IndexWriter writer = this.getWriter();
		Document doc = new Document();
		doc.add(new StringField("id",String.valueOf(blog.getId()),Store.YES));
		doc.add(new TextField("title", blog.getTitle(), Store.YES));
		doc.add(new StringField("releaseDate", DateUtil.formatDate(new Date(), "yyyy-MM-dd"), Store.YES));
		doc.add(new TextField("content", blog.getContentNoTag(), Store.YES));
		writer.updateDocument(new Term("id",String.valueOf(blog.getId())), doc);//id标示，生成过索引
		writer.close();
	}
	/**
	 * lucene查询博客信息
	 * @param q
	 * @return
	 * @throws Exception
	 */
	public List searchBlog(String q)throws Exception{
		dir=FSDirectory.open(Paths.get("d://lucene"));
		IndexReader reader=DirectoryReader.open(dir);//通过dir获得IndexReader
		IndexSearcher is=new IndexSearcher(reader);//searcher搜索index
		BooleanQuery.Builder booleanQuery=new BooleanQuery.Builder();//多个字段检索，结果与或非
		SmartChineseAnalyzer analyzer=new SmartChineseAnalyzer();
		QueryParser parser=new QueryParser("title", analyzer);
		Query query=parser.parse(q);
		
		QueryParser parser2=new QueryParser("content", analyzer);
		Query query2=parser2.parse(q);
		
		booleanQuery.add(query, BooleanClause.Occur.SHOULD);//must与，should或，nust_not非
		booleanQuery.add(query2, BooleanClause.Occur.SHOULD);
		
		TopDocs hits=is.search(booleanQuery.build(), 100);//最匹配的前100条
		
		QueryScorer scorer=new QueryScorer(query); 
		Fragmenter fragmenter=new SimpleSpanFragmenter(scorer); //得分高的片段
		SimpleHTMLFormatter simpleHTMLFormatter=new SimpleHTMLFormatter("");//highligther的格式
		Highlighter highlighter=new Highlighter(simpleHTMLFormatter, scorer);
		highlighter.setTextFragmenter(fragmenter);
		
		List blogList=new LinkedList();
		for(ScoreDoc scoreDoc:hits.scoreDocs){ //hits.scoreDocs search存在的有得分的前100 socreDoc
			Document doc=is.doc(scoreDoc.doc);//scoreDoc.doc doc的ID is.doc(id)通过id返回 document
			Blog blog=new Blog();
			blog.setId(Integer.parseInt(doc.get("id")));
			blog.setReleaseDateStr(doc.get("releaseDate"));
			String title=doc.get("title");
			String content=StringEscapeUtils.escapeHtml(doc.get("content"));//由于ueditor存入的content是带html标签对的，所以返回时除去标签对，不然页面foreach时就乱码了
			if(title!=null){
				TokenStream tokenStream=analyzer.tokenStream("title", new StringReader(title));
				String hTitle=highlighter.getBestFragment(tokenStream, title); //取得高分片段到页面进行展示
				if(StringUtil.isEmpty(hTitle)){
					blog.setTitle(title);
				}else{
					blog.setTitle(hTitle);
				}
			}
			
			if(content!=null){
				TokenStream tokenStream=analyzer.tokenStream("content", new StringReader(content));
				String hContent=highlighter.getBestFragment(tokenStream, content);
				if(StringUtil.isEmpty(hContent)){
					if(content.length()<=200){
						blog.setContent(content);						
					}else{
						blog.setContent(content.substring(0, 200));	
					}
				}else{
					blog.setContent(hContent);
				}
			}
			blogList.add(blog);
		}
		return blogList;
	}

}