lucene学习的小结

pom.xml设置

    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>4.12</version>
        <scope>test</scope>
    </dependency>

      <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-core</artifactId>
        <version>5.3.1</version>
    </dependency>
    
    <dependency>
    <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-queryparser</artifactId>
        <version>5.3.1</version>
    </dependency>
    
    <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-analyzers-common</artifactId>
        <version>5.3.1</version>
    </dependency>
    
    <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-analyzers-smartcn</artifactId>
        <version>5.3.1</version>
    </dependency>
    
    <dependency>
        <groupId>org.apache.lucene</groupId>
        <artifactId>lucene-highlighter</artifactId>
        <version>5.3.1</version>
    </dependency>

生成索引IndexingTest.java

package com.chabansheng.lucene;

import java.nio.file.Paths;

import ...;public class IndexingTest {

    private String ids[]={"1","2","3","4"};
    private String authors[]={"Jack","Marry","John","Json"};
    private String positions[]={"accounting","technician","salesperson","boss"};
    private String titles[]={"Java is a good language.","Java is a cross platform language","Java powerful","You should learn java"};
    private String contents[]={
            "If possible, use the same JRE major version at both index and search time.",
            "When upgrading to a different JRE major version, consider re-indexing. ",
            "Different JRE major versions may implement different versions of Unicode,",
            "For example: with Java 1.4, `LetterTokenizer` will split around the character U+02C6,"
    };
    
    private Directory dir;
    
    /**
     * 生成索引
     * @throws Exception
     */
    @Test
    public void index()throws Exception{
        dir=FSDirectory.open(Paths.get("D:\lucene3"));
        //获取IndexWriter实例
        Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
        IndexWriterConfig iwc=new IndexWriterConfig(analyzer);
        IndexWriter writer=new IndexWriter(dir, iwc);
        
        for(int i=0;i<ids.length;i++){
            Document doc=new Document();
            doc.add(new StringField("id", ids[i], Field.Store.YES));
            doc.add(new StringField("author",authors[i],Field.Store.YES));
            doc.add(new StringField("position",positions[i],Field.Store.YES));
            // 加权操作
            TextField field=new TextField("title", titles[i], Field.Store.YES);
            if("boss".equals(positions[i])){
                field.setBoost(1.5f);
            }
            doc.add(field);
            doc.add(new TextField("content", contents[i], Field.Store.NO));
            writer.addDocument(doc); // 添加文档
        }
        writer.close();
    }

    /**
     * 查询索引方式一
     * @throws Exception
     */
    @Test
    public void search()throws Exception{
        dir=FSDirectory.open(Paths.get("D:\lucene"));
        IndexReader reader=DirectoryReader.open(dir);
        IndexSearcher is=new IndexSearcher(reader);
        String searchField="title";
        String q="java";
        //Term方式查询
        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("author"));
        }
        reader.close();
    }
    
}

查询索引方式二Searcher.java

package com.chabansheng.lucene;

import java.io.StringReader;
import java.nio.file.Paths;

import ...;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);
        //QueryParser查询方式
        // Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
        SmartChineseAnalyzer analyzer=new SmartChineseAnalyzer();
        QueryParser parser=new QueryParser("desc", analyzer);
        Query query=parser.parse(q);
        
        TopDocs hits=is.search(query, 10);
        //高亮行号
        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();
    }
    
    public static void main(String[] args) {
        String indexDir="D:\lucene2";
        String q="南京文明";
        try {
            search(indexDir,q);
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
}

package com.chabansheng.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.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.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.store.Directory;import org.apache.lucene.store.FSDirectory;import org.junit.Test;
public class IndexingTest {
private String ids[]={"1","2","3","4"};private String authors[]={"Jack","Marry","John","Json"};private String positions[]={"accounting","technician","salesperson","boss"};private String titles[]={"Java is a good language.","Java is a cross platform language","Java powerful","You should learn java"};private String contents[]={"If possible, use the same JRE major version at both index and search time.","When upgrading to a different JRE major version, consider re-indexing. ","Different JRE major versions may implement different versions of Unicode,","For example: with Java 1.4, `LetterTokenizer` will split around the character U+02C6,"};private Directory dir;/** * 生成索引 * @throws Exception */@Testpublic void index()throws Exception{dir=FSDirectory.open(Paths.get("D:\lucene3"));//获取IndexWriter实例Analyzer analyzer=new StandardAnalyzer(); // 标准分词器IndexWriterConfig iwc=new IndexWriterConfig(analyzer);IndexWriter writer=new IndexWriter(dir, iwc);for(int i=0;i<ids.length;i++){Document doc=new Document();doc.add(new StringField("id", ids[i], Field.Store.YES));doc.add(new StringField("author",authors[i],Field.Store.YES));doc.add(new StringField("position",positions[i],Field.Store.YES));// 加权操作TextField field=new TextField("title", titles[i], Field.Store.YES);if("boss".equals(positions[i])){field.setBoost(1.5f);}doc.add(field);doc.add(new TextField("content", contents[i], Field.Store.NO));writer.addDocument(doc); // 添加文档}writer.close();}
/** * 查询 * @throws Exception */@Testpublic void search()throws Exception{dir=FSDirectory.open(Paths.get("D:\lucene3"));IndexReader reader=DirectoryReader.open(dir);IndexSearcher is=new IndexSearcher(reader);String searchField="title";String q="java";//Term方式查询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("author"));}reader.close();}}