Lucene学习

yanwu

浏览: 33963 次
性别:
来自: 北京

最近访客更多访客>>

zaghost

随意而生

adobey

yanwu6

博主相关

博客

微博

相册

留言

关于我

文章分类

社区版块

存档分类

博客分类：

Lucene

近来项目需要使用Lucene，工作之余上网学习了下相关内容，做个笔记
1.创建索引
步骤：创建IndexWriter

Java代码
IndexWriter writer = new IndexWriter(
                new NIOFSDirectory(new File(path)), new StandardAnalyzer(
                        Version.LUCENE_30), MaxFieldLength.LIMITED);

IndexWriter writer = new IndexWriter(
new NIOFSDirectory(new File(path)), new StandardAnalyzer(
Version.LUCENE_30), MaxFieldLength.LIMITED);
        创建Document
        创建Field 包含 field名和field值
        将Field通过Document的add方法添加到Document中

Java代码
Document doc = new Document();

        doc.add(new Field("text", "It is a text area", Store.YES,
                Index.ANALYZED_NO_NORMS));
        doc.add(new Field("info", "It is a Infomation area", Store.YES,
                Index.ANALYZED_NO_NORMS));

Document doc = new Document();

doc.add(new Field("text", "It is a text area", Store.YES,
Index.ANALYZED_NO_NORMS));
doc.add(new Field("info", "It is a Infomation area", Store.YES,
Index.ANALYZED_NO_NORMS));
        将Document通过IndexWriter的addDocument方法添加到IndexWriter中
        关闭IndexWriter

Java代码
writer.addDocument(doc);writer.close();

writer.addDocument(doc);writer.close();
2从索引中根据关键字查询
        创建IndexSearcher

Java代码
IndexSearcher searcher = new IndexSearcher(new NIOFSDirectory(new File(
                path)));

IndexSearcher searcher = new IndexSearcher(new NIOFSDirectory(new File(
path)));
        创建Query

Java代码
Query query = new QueryParser(Version.LUCENE_30, field,
                new StandardAnalyzer(Version.LUCENE_30)).parse(keyword);

Query query = new QueryParser(Version.LUCENE_30, field,
new StandardAnalyzer(Version.LUCENE_30)).parse(keyword);
        通过IndexSearcher的search方法查找关键字，使用TopDocs封装结果集

Java代码
TopDocs docs = searcher.search(query, 10);

TopDocs docs = searcher.search(query, 10);

全部代码：(包换了合并内存索引到硬盘索引中)
Java代码
import java.io.File;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriter.MaxFieldLength;
import org.apache.lucene.queryParser.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.NIOFSDirectory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;

public class TestLucen {

    public static final String path = "E:\\workspaces\\lucene\\index";

    public static void main(String[] args) throws Exception {
        writeIndex();
        readIndex("text", "area");
    }

    public static void writeIndex() throws Exception {
        // 硬盘索引
        IndexWriter writer = new IndexWriter(
                new NIOFSDirectory(new File(path)), new StandardAnalyzer(
                        Version.LUCENE_30), MaxFieldLength.LIMITED);
        // Ram索引
        RAMDirectory ram = new RAMDirectory();
        IndexWriter ramwriter = new IndexWriter(ram, new StandardAnalyzer(
                Version.LUCENE_30), MaxFieldLength.LIMITED);
        Document doc = new Document();
        Document doc1 = new Document();

        doc.add(new Field("text", "It is a text area", Store.YES,
                Index.ANALYZED_NO_NORMS));
        doc.add(new Field("info", "It is a Infomation area", Store.YES,
                Index.ANALYZED_NO_NORMS));
        writer.addDocument(doc);

        doc1.add(new Field("text", "it is another area", Store.YES,
                Index.ANALYZED));
        ramwriter.addDocument(doc1);
        ramwriter.optimize();
        ramwriter.close();
        // 将Ram索引合并到硬盘索引上，必须先调用ram的close方法
        writer.addIndexes(IndexReader.open(ram));
        writer.optimize();
        writer.close();
    }

    public static void readIndex(String field, String keyword) throws Exception {
        IndexSearcher searcher = new IndexSearcher(new NIOFSDirectory(new File(
                path)));
        Query query = new QueryParser(Version.LUCENE_30, field,
                new StandardAnalyzer(Version.LUCENE_30)).parse(keyword);
        TopDocs docs = searcher.search(query, 10);
        System.out.println("查找到" + docs.totalHits + "个\n对应的text为：");
        ScoreDoc[] doc = docs.scoreDocs;
        for (ScoreDoc d : doc) {
            Document docu = searcher.doc(d.doc);
            System.out.println(docu.get(field));
        }
    }
}

import java.io.File;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriter.MaxFieldLength;
import org.apache.lucene.queryParser.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.NIOFSDirectory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;

public class TestLucen {

public static final String path = "E:\\workspaces\\lucene\\index";

public static void main(String[] args) throws Exception {
writeIndex();
readIndex("text", "area");
}

public static void writeIndex() throws Exception {
// 硬盘索引
IndexWriter writer = new IndexWriter(
new NIOFSDirectory(new File(path)), new StandardAnalyzer(
Version.LUCENE_30), MaxFieldLength.LIMITED);
// Ram索引
RAMDirectory ram = new RAMDirectory();
IndexWriter ramwriter = new IndexWriter(ram, new StandardAnalyzer(
Version.LUCENE_30), MaxFieldLength.LIMITED);
Document doc = new Document();
Document doc1 = new Document();

doc.add(new Field("text", "It is a text area", Store.YES,
Index.ANALYZED_NO_NORMS));
doc.add(new Field("info", "It is a Infomation area", Store.YES,
Index.ANALYZED_NO_NORMS));
writer.addDocument(doc);

doc1.add(new Field("text", "it is another area", Store.YES,
Index.ANALYZED));
ramwriter.addDocument(doc1);
ramwriter.optimize();
ramwriter.close();
// 将Ram索引合并到硬盘索引上，必须先调用ram的close方法
writer.addIndexes(IndexReader.open(ram));
writer.optimize();
writer.close();
}

public static void readIndex(String field, String keyword) throws Exception {
IndexSearcher searcher = new IndexSearcher(new NIOFSDirectory(new File(
path)));
Query query = new QueryParser(Version.LUCENE_30, field,
new StandardAnalyzer(Version.LUCENE_30)).parse(keyword);
TopDocs docs = searcher.search(query, 10);
System.out.println("查找到" + docs.totalHits + "个\n对应的text为：");
ScoreDoc[] doc = docs.scoreDocs;
for (ScoreDoc d : doc) {
Document docu = searcher.doc(d.doc);
System.out.println(docu.get(field));
}
}
}

执行结果：

查找到2个

对应的text为：

It is a text area

it is another area

分享到：