Lucene创建索引

Lucene创建索引

对索引的文档进行增删改查

拷贝Maven依赖

http://mvnrepository.com/

<dependencies>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>4.12</version>
    </dependency>
</dependencies>

1创建索引

IndexingTest.java

package com.matrix.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.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.junit.Before;
import org.junit.Test;

public class IndexingTest {

    // 测试数据
    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:\\software\\lucene\\demo2"));
        IndexWriter writer = getWriter();
        // 遍历数组
        for (int i = 0; i < ids.length; i++) {
            Document doc = new Document();
            // 存储的话，能提高效率，用空间换时间
            doc.add(new StringField("id", ids[i], Field.Store.YES));
            doc.add(new StringField("city", citys[i], Field.Store.YES));
            // 存储内容很多的时候用TextField
            doc.add(new TextField("desc", descs[i], Field.Store.NO));
            // 添加文档操作
            writer.addDocument(doc);
            // 写的时候在内存中有缓存
        }
        // 关闭
        writer.close();
    }

    /**
     * 
     * 描述：获取IndexWriter实例<BR>
     * 方法名：getWriter<BR>
     * 创建人：Matrix <BR>
     * 时间：2016年4月26日-上午1:51:47 <BR>
     * 
     * @return
     * @throws Exception
     *             IndexWriter<BR>
     * @exception <BR>
     * @see
     * @since 1.0.0
     */
    private IndexWriter getWriter() throws Exception {
        // 创建标准分词器
        Analyzer analyzer = new StandardAnalyzer();
        // 配置，传入分析器实例
        // 要将索引写入到数据源目录下文件中的时候需要解析/分析
        IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
        IndexWriter writer = new IndexWriter(dir, iwc);
        return writer;
    }

    /**
     * 
     * 描述：测试写了几个文档<BR>
     * 方法名：testIndexWriter<BR>
     * 创建人：Matrix <BR>
     * 时间：2016年4月26日-上午2:08:05 <BR>
     * 
     * @throws Exception
     *             void<BR>
     * @exception <BR>
     * @see
     * @since 1.0.0
     */
    @Test
    public void testIndexWriter() throws Exception {
        IndexWriter writer = getWriter();
        System.out.println("写入了" + writer.numDocs() + "个文档");
        writer.close();
    }
}

E:\software\lucene\demo2

1.1使用luke工具查看索引

前提：安装JDK1.8,并配置环境变量

2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();
}

3删除文档在合并前

// 第一种方式：不合并索引，删除文档，索引不动，只是做标记
// 第二种方式：
@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("删除后：最大文档数即writer.maxDoc()" + writer.maxDoc());
    System.out.println("删除后：实际文档数即writer.numDocs()" + writer.numDocs());
    writer.close();
}

4删除文档在合并后

@Test
public void testDeleteAfterMerge() throws Exception {
    IndexWriter writer = getWriter();
    System.out.println("删除前："+writer.numDocs());
    writer.deleteDocuments(new Term("id","1"));
    // 强制删除
    writer.forceMergeDeletes();
    writer.commit();
    System.out.println("writer.maxDocs()："+writer.maxDoc());
    System.out.println("writer.numDocs()："+writer.numDocs());
    writer.close();
}

使用工具查看索引是否删除

5测试更新

@Test
public void testUpdate() throws Exception {
    IndexWriter writer = getWriter();
    // 进行更新操作
    Document doc = new Document();
    doc.add(new StringField("id", "1", Field.Store.YES));
    doc.add(new StringField("city", "shenzhen", Field.Store.YES));
    doc.add(new TextField("city", "shenzhen is a great city", Field.Store.NO));
    writer.updateDocument(new Term("id", "1"), doc);
    writer.close(); 
}

6文档域加权

加权之后，搜索排名会提高

生成索引

@Test
public void index() throws Exception {
    // 打开索引目录,该目录存放创建的索引文件
    dir = FSDirectory.open(Paths.get("E:\\software\\lucene\\demo3"));
    IndexWriter writer = getWriter();
    // 遍历数组
    for (int i = 0; i < ids.length; i++) {
        Document doc = new Document();
        // 存储的话，能提高效率，用空间换时间
        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));
        // 使用StringField字段则不会进行分词
        doc.add(new TextField("title", titles[i], Field.Store.YES));
        // 存储内容很多的时候用TextField
        doc.add(new TextField("content", contents[i], Field.Store.NO));
        // 添加文档
        writer.addDocument(doc);
        // 写的时候在内存中有缓存
    }
    // 关闭
    writer.close();
}

查询

@Test
public void search() throws Exception {
    dir = FSDirectory.open(Paths.get("E:\\software\\lucene\\demo3"));
    IndexReader reader = DirectoryReader.open(dir);
    IndexSearcher is = new IndexSearcher(reader);
    // 定义要查询的字段
    String seachField = "title";
    // 定义要查询的值
    String q = "java";
    Term t = new Term(seachField, 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");
    // 遍历TopDocs
    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = is.doc(scoreDoc.doc);
        System.out.println("document：" + doc.get("author"));
    }
    reader.close();
}

加权操作

IndexingText2.java

package com.matrix.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 IndexingText2 {

    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
    // indexDir：将索引写入到索引目录(该目录存放创建的索引文件)去
    public IndexWriter getWriter() throws Exception {
        // 创建标准分词器
        Analyzer analyzer = new StandardAnalyzer();
        // 配置，传入分析器实例
        // 要将索引写入到数据源目录下文件中的时候需要解析/分析
        IndexWriterConfig wc = new IndexWriterConfig(analyzer);
        IndexWriter writer = new IndexWriter(dir, wc);
        return writer;
    }

    // 生成索引
    @Test
    public void index() throws Exception {
        // 打开索引目录,该目录存放创建的索引文件
        dir = FSDirectory.open(Paths.get("E:\\software\\lucene\\demo3"));
        IndexWriter writer = getWriter();
        // 遍历数组
        for (int i = 0; i < ids.length; i++) {
            Document doc = new Document();
            // 存储的话，能提高效率，用空间换时间
            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));
            // 使用StringField字段则不会进行分词
            TextField field = new TextField("title", titles[i], Field.Store.YES);
            // 加权操作
            if ("boss".equals(positions[i])) {
                field.setBoost(1.5f);
            }
            doc.add(field);
            // 存储内容很多的时候用TextField
            doc.add(new TextField("content", contents[i], Field.Store.NO));
            // 添加文档
            writer.addDocument(doc);
            // 写的时候在内存中有缓存
        }
        // 关闭
        writer.close();
    }

    // 查询
    @Test
    public void search() throws Exception {
        dir = FSDirectory.open(Paths.get("E:\\software\\lucene\\demo3"));
        IndexReader reader = DirectoryReader.open(dir);
        IndexSearcher is = new IndexSearcher(reader);
        // 定义要查询的字段
        String seachField = "title";
        // 定义要查询的值
        String q = "java";
        Term t = new Term(seachField, 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");
        // 遍历TopDocs
        for (ScoreDoc scoreDoc : hits.scoreDocs) {
            Document doc = is.doc(scoreDoc.doc);
            System.out.println("document：" + doc.get("author"));
        }
        reader.close();
    }

    public static void main(String[] args) {

    }
}

Json在最前面是因为权值变高了