Lucene索引的【增、删、改、查】

前言

　　搞检索的，应该多少都会了解Lucene一些，它开源而且简单上手，官方API足够编写些小DEMO。并且根据倒排索引，实现快速检索。本文就简单的实现增量添加索引，删除索引，通过关键字查询，以及更新索引等操作。

　　目前博猪使用的不爽的地方就是，读取文件内容进行全文检索时，需要自己编写读取过程（这个solr免费帮我们实现）。而且创建索引的过程比较慢，还有很大的优化空间，这个就要细心下来研究了。

创建索引

　　Lucene在进行创建索引时，根据前面一篇博客，已经讲完了大体的流程，这里再简单说下：

1 Directory directory = FSDirectory.open("/tmp/testindex");
2 IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_CURRENT, analyzer);
3 IndexWriter iwriter = new IndexWriter(directory, config);
4 Document doc = new Document();
5 String text = "This is the text to be indexed.";
6 doc.add(new Field("fieldname", text, TextField.TYPE_STORED)); iwriter.close();

　　

1 创建Directory，获取索引目录

　　2 创建词法分析器，创建IndexWriter对象

　　3 创建document对象，存储数据

　　4 关闭IndexWriter，提交

1 创建Directory，获取索引目录

　　2 创建词法分析器，创建IndexWriter对象

　　3 创建document对象，存储数据

　　4 关闭IndexWriter，提交

　　

　增量添加索引

　　Lucene拥有增量添加索引的功能，在不会影响之前的索引情况下，添加索引，它会在何时的时机，自动合并索引文件。

/**
     * 增加索引
     *
     * @throws Exception
     */
    public static void insert() throws Exception {
        String text5 = "hello,goodbye,man,woman";
        Date date1 = new Date();
        analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
        directory = FSDirectory.open(new File(INDEX_DIR));

        IndexWriterConfig config = new IndexWriterConfig(
                Version.LUCENE_CURRENT, analyzer);
        indexWriter = new IndexWriter(directory, config);

        Document doc1 = new Document();
        doc1.add(new TextField("filename", "text5", Store.YES));
        doc1.add(new TextField("content", text5, Store.YES));
        indexWriter.addDocument(doc1);

        indexWriter.commit();
        indexWriter.close();

        Date date2 = new Date();
        System.out.println("增加索引耗时：" + (date2.getTime() - date1.getTime()) + "ms\n");
    }

　　

　　

删除索引

　　Lucene也是通过IndexWriter调用它的delete方法，来删除索引。我们可以通过关键字，删除与这个关键字有关的所有内容。如果仅仅是想要删除一个文档，那么最好就顶一个唯一的ID域，通过这个ID域，来进行删除操作。

/**
     * 删除索引
     *
     * @param str 删除的关键字
     * @throws Exception
     */
    public static void delete(String str) throws Exception {
        Date date1 = new Date();
        analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
        directory = FSDirectory.open(new File(INDEX_DIR));

        IndexWriterConfig config = new IndexWriterConfig(
                Version.LUCENE_CURRENT, analyzer);
        indexWriter = new IndexWriter(directory, config);

        indexWriter.deleteDocuments(new Term("filename",str));  

        indexWriter.close();

        Date date2 = new Date();
        System.out.println("删除索引耗时：" + (date2.getTime() - date1.getTime()) + "ms\n");
    }

　　

　　

更新索引

　　Lucene没有真正的更新操作，通过某个fieldname，可以更新这个域对应的索引，但是实质上，它是先删除索引，再重新建立的。

/**
     * 更新索引
     *
     * @throws Exception
     */
    public static void update() throws Exception {
        String text1 = "update,hello,man!";
        Date date1 = new Date();
         analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
         directory = FSDirectory.open(new File(INDEX_DIR));

         IndexWriterConfig config = new IndexWriterConfig(
                 Version.LUCENE_CURRENT, analyzer);
         indexWriter = new IndexWriter(directory, config);

         Document doc1 = new Document();
        doc1.add(new TextField("filename", "text1", Store.YES));
        doc1.add(new TextField("content", text1, Store.YES));

        indexWriter.updateDocument(new Term("filename","text1"), doc1);

         indexWriter.close();

         Date date2 = new Date();
         System.out.println("更新索引耗时：" + (date2.getTime() - date1.getTime()) + "ms\n");
    }

　　

通过索引查询关键字

　　Lucene的查询方式有很多种，这里就不做详细介绍了。它会返回一个ScoreDoc的集合，类似ResultSet的集合，我们可以通过域名获取想要获取的内容。

/**
     * 关键字查询
     *
     * @param str
     * @throws Exception
     */
    public static void search(String str) throws Exception {
        directory = FSDirectory.open(new File(INDEX_DIR));
        analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
        DirectoryReader ireader = DirectoryReader.open(directory);
        IndexSearcher isearcher = new IndexSearcher(ireader);

        QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, "content",analyzer);
        Query query = parser.parse(str);

        ScoreDoc[] hits = isearcher.search(query, null, 1000).scoreDocs;
        for (int i = 0; i < hits.length; i++) {
            Document hitDoc = isearcher.doc(hits[i].doc);
            System.out.println(hitDoc.get("filename"));
            System.out.println(hitDoc.get("content"));
        }
        ireader.close();
        directory.close();
    }

　　

全部代码

package test;

import java.io.File;
import java.util.Date;
import java.util.List;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.LongField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.index.DirectoryReader;
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.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class TestLucene {
    // 保存路径
    private static String INDEX_DIR = "D:\\luceneIndex";
    private static Analyzer analyzer = null;
    private static Directory directory = null;
    private static IndexWriter indexWriter = null;

    public static void main(String[] args) {
        try {
//            index();
            search("man");
//            insert();
//            delete("text5");
//            update();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
    /**
     * 更新索引
     *
     * @throws Exception
     */
    public static void update() throws Exception {
        String text1 = "update,hello,man!";
        Date date1 = new Date();
         analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
         directory = FSDirectory.open(new File(INDEX_DIR));

         IndexWriterConfig config = new IndexWriterConfig(
                 Version.LUCENE_CURRENT, analyzer);
         indexWriter = new IndexWriter(directory, config);

         Document doc1 = new Document();
        doc1.add(new TextField("filename", "text1", Store.YES));
        doc1.add(new TextField("content", text1, Store.YES));

        indexWriter.updateDocument(new Term("filename","text1"), doc1);

         indexWriter.close();

         Date date2 = new Date();
         System.out.println("更新索引耗时：" + (date2.getTime() - date1.getTime()) + "ms\n");
    }
    /**
     * 删除索引
     *
     * @param str 删除的关键字
     * @throws Exception
     */
    public static void delete(String str) throws Exception {
        Date date1 = new Date();
        analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
        directory = FSDirectory.open(new File(INDEX_DIR));

        IndexWriterConfig config = new IndexWriterConfig(
                Version.LUCENE_CURRENT, analyzer);
        indexWriter = new IndexWriter(directory, config);

        indexWriter.deleteDocuments(new Term("filename",str));  

        indexWriter.close();

        Date date2 = new Date();
        System.out.println("删除索引耗时：" + (date2.getTime() - date1.getTime()) + "ms\n");
    }
    /**
     * 增加索引
     *
     * @throws Exception
     */
    public static void insert() throws Exception {
        String text5 = "hello,goodbye,man,woman";
        Date date1 = new Date();
        analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
        directory = FSDirectory.open(new File(INDEX_DIR));

        IndexWriterConfig config = new IndexWriterConfig(
                Version.LUCENE_CURRENT, analyzer);
        indexWriter = new IndexWriter(directory, config);

        Document doc1 = new Document();
        doc1.add(new TextField("filename", "text5", Store.YES));
        doc1.add(new TextField("content", text5, Store.YES));
        indexWriter.addDocument(doc1);

        indexWriter.commit();
        indexWriter.close();

        Date date2 = new Date();
        System.out.println("增加索引耗时：" + (date2.getTime() - date1.getTime()) + "ms\n");
    }
    /**
     * 建立索引
     *
     * @param args
     */
    public static void index() throws Exception {

        String text1 = "hello,man!";
        String text2 = "goodbye,man!";
        String text3 = "hello,woman!";
        String text4 = "goodbye,woman!";

        Date date1 = new Date();
        analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
        directory = FSDirectory.open(new File(INDEX_DIR));

        IndexWriterConfig config = new IndexWriterConfig(
                Version.LUCENE_CURRENT, analyzer);
        indexWriter = new IndexWriter(directory, config);

        Document doc1 = new Document();
        doc1.add(new TextField("filename", "text1", Store.YES));
        doc1.add(new TextField("content", text1, Store.YES));
        indexWriter.addDocument(doc1);

        Document doc2 = new Document();
        doc2.add(new TextField("filename", "text2", Store.YES));
        doc2.add(new TextField("content", text2, Store.YES));
        indexWriter.addDocument(doc2);

        Document doc3 = new Document();
        doc3.add(new TextField("filename", "text3", Store.YES));
        doc3.add(new TextField("content", text3, Store.YES));
        indexWriter.addDocument(doc3);

        Document doc4 = new Document();
        doc4.add(new TextField("filename", "text4", Store.YES));
        doc4.add(new TextField("content", text4, Store.YES));
        indexWriter.addDocument(doc4);

        indexWriter.commit();
        indexWriter.close();

        Date date2 = new Date();
        System.out.println("创建索引耗时：" + (date2.getTime() - date1.getTime()) + "ms\n");
    }

    /**
     * 关键字查询
     *
     * @param str
     * @throws Exception
     */
    public static void search(String str) throws Exception {
        directory = FSDirectory.open(new File(INDEX_DIR));
        analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
        DirectoryReader ireader = DirectoryReader.open(directory);
        IndexSearcher isearcher = new IndexSearcher(ireader);

        QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, "content",analyzer);
        Query query = parser.parse(str);

        ScoreDoc[] hits = isearcher.search(query, null, 1000).scoreDocs;
        for (int i = 0; i < hits.length; i++) {
            Document hitDoc = isearcher.doc(hits[i].doc);
            System.out.println(hitDoc.get("filename"));
            System.out.println(hitDoc.get("content"));
        }
        ireader.close();
        directory.close();
    }
}