Lucene常识总结以及小demo总结-原创手记-慕课网

1.Lucene 简介
Apache Lucene是一个基于Java全文搜索引擎，利用它可以轻易地为Java软件加入全文搜寻功能。Lucene的最主要工作是替文件的每一个字作索引，索引让搜寻的效率比传统的逐字比较大大提高，Lucen提供一组解读，过滤，分析文件，编排和使用索引的API
2.创建索引（项目里要导入的几个jar包）

package com.java1234.lucene;

import java.nio.file.Paths;

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.document.IntField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class Indexer {

    private Integer ids[]={1,2,3};
    private String citys[]={"aingdao","banjing","changhai"};
    private String descs[]={
            "Qingdao is b beautiful city.",
            "Nanjing is c city of culture.",
            "Shanghai is d bustling city."
    };

    private Directory dir;

    /**
     * 获取IndexWriter实例
     * @return
     * @throws Exception
     */
    private IndexWriter getWriter()throws Exception{
        Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
        IndexWriterConfig iwc=new IndexWriterConfig(analyzer);
        IndexWriter writer=new IndexWriter(dir, iwc);
        return writer;
    }

    /**
     * 生成索引
     * @param indexDir
     * @throws Exception
     */
    private void index(String indexDir)throws Exception{
        dir=FSDirectory.open(Paths.get(indexDir));
        IndexWriter writer=getWriter();
        for(int i=0;i<ids.length;i++){
            Document doc=new Document();
            doc.add(new IntField("id", ids[i], Field.Store.YES));
            doc.add(new StringField("city",citys[i],Field.Store.YES));
            doc.add(new TextField("desc", descs[i], Field.Store.YES));
            writer.addDocument(doc); // 添加文档
        }
        writer.close();
    }

}

3.对内容进行查询，更新，删除操作

package com.java1234.lucene;

import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.QueryParser;
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.store.Directory;
import org.apache.lucene.store.FSDirectory;
//进行查询搜索
public class Searcher {

    public static void search(String indexDir,String q)throws Exception{
        Directory dir=FSDirectory.open(Paths.get(indexDir));
        IndexReader reader=DirectoryReader.open(dir);
        IndexSearcher is=new IndexSearcher(reader);
        Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
        QueryParser parser=new QueryParser("desc", analyzer);
        Query query=parser.parse(q);
        long start=System.currentTimeMillis();
        TopDocs hits=is.search(query, 10);
        long end=System.currentTimeMillis();
        System.out.println("匹配 "+q+" ，总共花费"+(end-start)+"毫秒"+"查询到"+hits.totalHits+"个记录");
        for(ScoreDoc scoreDoc:hits.scoreDocs){
            Document doc=is.doc(scoreDoc.doc);
            System.out.println(doc.get("city"));
        }
        reader.close();
    }
}
//进行删除操作，第一种方式删除
/**
     * 测试删除 在合并前
     * @throws Exception
     */
    @Test
    public void testDeleteBeforeMerge()throws Exception{
        IndexWriter writer=getWriter();
        System.out.println("删除前："+writer.numDocs());
//deleteDocuments（Term term）是根据term删除document，但是这里的删除并不是真正的删除。而是存储在一个回收站中的，可以恢复删除的document
        writer.deleteDocuments(new Term("id","1"));
        writer.commit();
        System.out.println("writer.maxDoc()："+writer.maxDoc());//最大文档数不变
        System.out.println("writer.numDocs()："+writer.numDocs());//实际文档数减少
        writer.close();
    }
//进行删除操作，第二种方式删除    
    /**
     * 测试删除 在合并后
     * @throws Exception
     */
    @Test
    public void testDeleteAfterMerge()throws Exception{
        IndexWriter writer=getWriter();
        System.out.println("删除前："+writer.numDocs());
        writer.deleteDocuments(new Term("id","1"));
//你想要强制删除回收站的信息可以调用writer.forceMergeDeletes()这个方法，但是这个方法不推荐使用，比较消耗内存，lucene会自动根据容量的大小删除所删除的文件
        writer.forceMergeDeletes(); // 强制删除
        writer.commit();
        System.out.println("writer.maxDoc()："+writer.maxDoc());//最大文档数减少
        System.out.println("writer.numDocs()："+writer.numDocs());//实际文档数减少
        writer.close();
    }

/**
     * 测试更新
     * @throws Exception
     */
    @Test
    public void testUpdate()throws Exception{
        IndexWriter writer=getWriter();
        Document doc=new Document();
        doc.add(new StringField("id", "1", Field.Store.YES));
        doc.add(new StringField("city","qingdao",Field.Store.YES));
        doc.add(new TextField("desc", "dsss is a city.", Field.Store.NO));
//所谓的更新索引是分两步进行的：先删除然后再添加索引，添加的索引占用删除前索引的位置；如果在删除索引时lucene在索引文件中找不到相应的数据，就会在索引文件的最后面添加新的索引
        writer.updateDocument(new Term("id","1"), doc);
        writer.close();
    }

    /**
     * 对特定项搜索(不分词搜索)
     * @throws Exception
     */
    @Test
    public void testTermQuery()throws Exception{
        String searchField="contents";
        String q="particular";
        Term t=new Term(searchField,q);
        Query query=new TermQuery(t);
        TopDocs hits=is.search(query, 10);
        System.out.println("匹配 '"+q+"'，总共查询到"+hits.totalHits+"个文档");
        for(ScoreDoc scoreDoc:hits.scoreDocs){
            Document doc=is.doc(scoreDoc.doc);
            System.out.println(doc.get("fullPath"));
        }
    }

4.Lucene4种方式搜索

    /**
     * 指定项范围搜索
     * @throws Exception
     */
    @Test
    public void testTermRangeQuery()throws Exception{
        TermRangeQuery query=new TermRangeQuery("desc", new BytesRef("b".getBytes()), new BytesRef("c".getBytes()), true, true);
        TopDocs hits=is.search(query, 10);
        for(ScoreDoc scoreDoc:hits.scoreDocs){
            Document doc=is.doc(scoreDoc.doc);
            System.out.println(doc.get("id"));
            System.out.println(doc.get("city"));
            System.out.println(doc.get("desc"));
        }       
    }

    /**
     * 指定数字范围
     * @throws Exception
     */
    @Test
    public void testNumericRangeQuery()throws Exception{
        NumericRangeQuery<Integer> query=NumericRangeQuery.newIntRange("id", 1, 2, true, true);
        TopDocs hits=is.search(query, 10);
        for(ScoreDoc scoreDoc:hits.scoreDocs){
            Document doc=is.doc(scoreDoc.doc);
            System.out.println(doc.get("id"));
            System.out.println(doc.get("city"));
            System.out.println(doc.get("desc"));
        }       
    }

    /**
     * 指定字符串开头搜索
     * @throws Exception
     */
    @Test
    public void testPrefixQuery()throws Exception{
        PrefixQuery query=new PrefixQuery(new Term("city","a"));
        TopDocs hits=is.search(query, 10);
        for(ScoreDoc scoreDoc:hits.scoreDocs){
            Document doc=is.doc(scoreDoc.doc);
            System.out.println(doc.get("id"));
            System.out.println(doc.get("city"));
            System.out.println(doc.get("desc"));
        }   
    }

    /**
     * 多条件查询
     * @throws Exception
     */
    @Test
    public void testBooleanQuery()throws Exception{
        NumericRangeQuery<Integer> query1=NumericRangeQuery.newIntRange("id", 1, 2, true, true);
        PrefixQuery query2=new PrefixQuery(new Term("city","a"));
        BooleanQuery.Builder booleanQuery=new BooleanQuery.Builder();
        booleanQuery.add(query1,BooleanClause.Occur.MUST);
        booleanQuery.add(query2,BooleanClause.Occur.MUST);
        TopDocs hits=is.search(booleanQuery.build(), 10);
        for(ScoreDoc scoreDoc:hits.scoreDocs){
            Document doc=is.doc(scoreDoc.doc);
            System.out.println(doc.get("id"));
            System.out.println(doc.get("city"));
            System.out.println(doc.get("desc"));
        }   
    }
//对多个字段以及多个值进行搜索查询
    /** 
    * 根据信息分类和关键词进行查询 
    * @param type,资源的类型,其值为news或product 
    * @param searchKey,搜索的关键字 
    * @return Hits 
    */  
    public Hits executeSearch(String type,String keyword)  
    {  
      Hits result = null;  
      if(type != null && !type.equals("") && keyword != null && !keyword.equals(""))  
      {  
        try   
        {  
          //根据关键字构造一个数组  
          String[] key = new String[]{keyword,type};  
          //同时声明一个与之对应的字段数组  
          String[] fields = {"title","type"};  
          //声明BooleanClause.Occur[]数组,它表示多个条件之间的关系  
          BooleanClause.Occur[] flags=new BooleanClause.Occur[]{BooleanClause.Occur.MUST,BooleanClause.Occur.MUST};  
          ChineseAnalyzer analyzer = new ChineseAnalyzer();  
          //用MultiFieldQueryParser得到query对象  
          Query query = MultiFieldQueryParser.parse(key, fields, flags, analyzer);  
          //c:/index表示我们的索引文件所在的目录  
          IndexSearcher searcher = new IndexSearcher("c:/index");  
          //查询结果  
          result = searcher.search(query);  
        } catch (Exception e)  
        {  
          e.printStackTrace();  
        }  
      }  
      return result;  
    }  
//这里需要注意的就是BooleanClause.Occur[]数组,它表示多个条件之间的关系,BooleanClause.Occur.MUST表示and,BooleanClause.Occur.MUST_NOT表示not,BooleanClause.Occur.SHOULD表示or.

5.Lucene中文分词器以及高亮显示

public static void search(String indexDir,String q)throws Exception{
        Directory dir=FSDirectory.open(Paths.get(indexDir));
        IndexReader reader=DirectoryReader.open(dir);
        IndexSearcher is=new IndexSearcher(reader);
        // Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
        SmartChineseAnalyzer analyzer=new SmartChineseAnalyzer();
        QueryParser parser=new QueryParser("desc", analyzer);
        Query query=parser.parse(q);
        long start=System.currentTimeMillis();
        TopDocs hits=is.search(query, 10);
        long end=System.currentTimeMillis();
        System.out.println("匹配 "+q+" ，总共花费"+(end-start)+"毫秒"+"查询到"+hits.totalHits+"个记录");

        QueryScorer scorer=new QueryScorer(query);
        Fragmenter fragmenter=new SimpleSpanFragmenter(scorer);
        SimpleHTMLFormatter simpleHTMLFormatter=new SimpleHTMLFormatter("<b><font color='red'>","</font></b>");
        Highlighter highlighter=new Highlighter(simpleHTMLFormatter, scorer);
        highlighter.setTextFragmenter(fragmenter);
        for(ScoreDoc scoreDoc:hits.scoreDocs){
            Document doc=is.doc(scoreDoc.doc);
            System.out.println(doc.get("city"));
            System.out.println(doc.get("desc"));
            String desc=doc.get("desc");
            if(desc!=null){
                TokenStream tokenStream=analyzer.tokenStream("desc", new StringReader(desc));
                System.out.println(highlighter.getBestFragment(tokenStream, desc));
            }
        }
        reader.close();
    }

7.实现分也的两种方式
lucene3.5之前分页提供的方式为再查询方式（每次查询全部记录，然后取其中部分记录，这种方式用的最多），lucene官方的解释：由于我们的速度足够快。处理海量数据时，内存容易内存溢出。
lucene3.5以后提供一个searchAfter，这个是在特大数据量采用（亿级数据量），速度相对慢一点，像google搜索图片的时候，点击更多，然后再出来一批。这种方式就是把数据保存在缓存里面。然后再去取。

/** 
 * 这就是先查询所有的数据，然后去分页数据 
    * 注意 这种方式处理海量数据的时候，容易内存溢出 
 * @param query 
 * @param pageIndex--第几页 
 * @param pageSize--每页显示多少数据 
 */  
public void searchPage(String query,int pageIndex,int pageSize) {  
    try {  
        Directory dir = FileIndexUtils.getDirectory();  
        IndexSearcher searcher = getSearcher(dir);  
        QueryParser parser = new QueryParser(Version.LUCENE_35,"desc",new StandardAnalyzer(Version.LUCENE_35));  
        Query q = parser.parse(query);  
        TopDocs tds = searcher.search(q, 500);  
        //注意 此处把500条数据放在内存里。  
        ScoreDoc[] sds = tds.scoreDocs;  
        int start = (pageIndex-1)*pageSize;  
        int end = pageIndex*pageSize;  
        for(int i=start;i<end;i++) {  
            Document doc = searcher.doc(sds[i].doc);  
            System.out.println(sds[i].doc+":"+doc.get("path")+"-->"+doc.get("filename"));  
        }  

        searcher.close();  
    } catch (org.apache.lucene.queryParser.ParseException e) {  
        e.printStackTrace();  
    } catch (IOException e) {  
        e.printStackTrace();  
    }  
}  
/** 
 * 根据页码和分页大小获取上一次的最后一个scoredocs 
 * @param pageIndex 
 * @param pageSize 
 * @param query 
 * @param searcher 
 * @return 
 * @throws IOException 
 */  
private ScoreDoc getLastScoreDoc(int pageIndex,int pageSize,Query query,IndexSearcher searcher) throws IOException {  
    if(pageIndex==1)return null;//如果是第一页就返回空  
    int num = pageSize*(pageIndex-1);//获取上一页的最后数量  
    TopDocs tds = searcher.search(query, num);  
    return tds.scoreDocs[num-1];  
}  

public void searchPageByAfter(String query,int pageIndex,int pageSize) {  
    try {  
        Directory dir = FileIndexUtils.getDirectory();  
        IndexSearcher searcher = getSearcher(dir);  
        QueryParser parser = new QueryParser(Version.LUCENE_35,"desc",new StandardAnalyzer(Version.LUCENE_35));  
        Query q = parser.parse(query);  
        //获取上一页的最后一个元素  
        ScoreDoc lastSd = getLastScoreDoc(pageIndex, pageSize, q, searcher);  
        //通过最后一个元素去搜索下一页的元素  
        TopDocs tds = searcher.searchAfter(lastSd,q, pageSize);  
        for(ScoreDoc sd:tds.scoreDocs) {  
            Document doc = searcher.doc(sd.doc);  
            System.out.println(sd.doc+":"+doc.get("path")+"-->"+doc.get("filename"));  
        }  
        searcher.close();  
    } catch (org.apache.lucene.queryParser.ParseException e) {  
        e.printStackTrace();  
    } catch (IOException e) {  
        e.printStackTrace();  
    }  
}