Lucene构建索引

阅读更多

1. 添加、删除、修改文档

New maven project ->
Create a simple project ->
    Group Id: com.andrew.lucene
    Artifact Id: Lucene02
    Version: 0.0.1-SNAPSHOT
    Packaging: jar

pom.xml


  4.0.0
  com.andrew.lucene
  Lucene02
  0.0.1-SNAPSHOT
  
      
        org.apache.lucene
        lucene-core
        5.3.1
    
    
    org.apache.lucene
        lucene-queryparser
        5.3.1
    
    
        org.apache.lucene
        lucene-analyzers-common
        5.3.1
    
    
        junit
        junit
        4.12
    
  

IndexingTest.java代码

package com.andrew.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.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.junit.Before;
import org.junit.Test;

public class IndexingTest {
    private String ids[] = { "1", "2", "3" };
    private String citys[] = { "qingdao", "nanjing", "shanghai" };
    private String descs[] = { "Qingdao is a beautiful city.", "Nanjing is a city of culture.",
            "Shanghai is a bustling city." };
    private Directory dir;

    @Before
    public void setUp() throws Exception {
        dir = FSDirectory.open(Paths.get("E:\\lucene2"));
        IndexWriter writer = getWriter();
        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("city", citys[i], Field.Store.YES));
            doc.add(new TextField("desc", descs[i], Field.Store.NO));
            writer.addDocument(doc); // 添加文档
        }
        writer.close();
    }
    // 获取IndexWriter实例
    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;
    }
    // 测试写了几个文档
    @Test
    public void testIndexWriter() throws Exception {
        IndexWriter writer = getWriter();
        System.out.println("写入了" + writer.numDocs() + "个文档");
        writer.close();
    }
    // 测试读取文档
    @Test
    public void testIndexReader() throws Exception {
        IndexReader reader = DirectoryReader.open(dir);
        System.out.println("最大文档数：" + reader.maxDoc());
        System.out.println("实际文档数：" + reader.numDocs());
        reader.close();
    }
    // 测试删除 在合并前
    @Test
    public void testDeleteBeforeMerge() throws Exception {
        IndexWriter writer = getWriter();
        System.out.println("删除前：" + writer.numDocs());
        writer.deleteDocuments(new Term("id", "1"));
        writer.commit();
        System.out.println("writer.maxDoc()：" + writer.maxDoc());
        System.out.println("writer.numDocs()：" + writer.numDocs());
        writer.close();
    }
    // 测试删除 在合并后
    @Test
    public void testDeleteAfterMerge() throws Exception {
        IndexWriter writer = getWriter();
        System.out.println("删除前：" + writer.numDocs());
        writer.deleteDocuments(new Term("id", "1"));
        writer.forceMergeDeletes(); // 强制删除
        writer.commit();
        System.out.println("writer.maxDoc()：" + writer.maxDoc());
        System.out.println("writer.numDocs()：" + writer.numDocs());
        writer.close();
    }
    // 测试更新
    @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));
        writer.updateDocument(new Term("id", "1"), doc);
        writer.close();
    }
}

执行结果

最大文档数：3
实际文档数：3

删除前：3
writer.maxDoc()：3
writer.numDocs()：2

删除前：3
writer.maxDoc()：2
writer.numDocs()：2

2. 文档域加权

IndexingTest2.java代码

package com.andrew.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 IndexingTest2 {

    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;

    // 获取IndexWriter实例
    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
    @Test
    public void index() throws Exception {
        dir = FSDirectory.open(Paths.get("E:\\lucene3"));
        IndexWriter writer = getWriter();
        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
    @Test
    public void search() throws Exception {
        dir = FSDirectory.open(Paths.get("E:\\lucene3"));
        IndexReader reader = DirectoryReader.open(dir);
        IndexSearcher is = new IndexSearcher(reader);
        String searchField = "title";
        String q = "java";
        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();
    }
}

执行结果

未使用加权：
匹配 'java'，总共查询到4个文档
John
Jack
Marry
Json
使用加权：
匹配 'java'，总共查询到4个文档
Json
John
Jack
Marry