lucene 5.2.0学习笔记

Posted 2020-09-08 duenboa

package com.bc.cas.manager;

import com.bc.cas.dao.BookDao;

import com.bc.cas.model.entity.Book;

import com.google.common.base.Objects;

import com.google.common.collect.Lists;

import org.apache.log4j.helpers.LogLog;

import org.apache.lucene.analysis.Analyzer;

import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;

import org.apache.lucene.analysis.util.CharArraySet;

import org.apache.lucene.document.*;

import org.apache.lucene.index.*;

import org.apache.lucene.queryparser.classic.ParseException;

import org.apache.lucene.queryparser.classic.QueryParser;

import org.apache.lucene.search.*;

import org.apache.lucene.store.FSDirectory;

import org.junit.Test;

import org.springframework.beans.factory.annotation.Autowired;

import org.springframework.stereotype.Repository;

import org.springframework.util.CollectionUtils;

import java.io.IOException;

import java.nio.file.Paths;

import java.util.Arrays;

import java.util.Iterator;

import java.util.List;

/**

 * @Copyright 2012-2016 duenboa 版权所有

 * @Author Created by Administrator on 2016/11/29.

 * @Version V 1.0.0

 * @Desc 索引管理器

 */

@Repository

public class IndexManager {

    @Autowired

    private BookDao bookDao;

    static FSDirectory dir;

    static {

        try {

            dir = FSDirectory.open(Paths.get("d:/lucene/lucene052_index05"));

        } catch (IOException e) {

            e.printStackTrace();

        }

    }

    /**

     * 创建索引 -common

     */

    @Test

    public void createIndex(List<Document> docs) throws IOException {

        if (docs == null) {

            return;

        }

        // 自定义停用词

        List<String> strings = Arrays.asList("的", "在", "了", "呢", "，", "0", "：", ",", "是", "这", "那", "么");

        CharArraySet unUsefulWorlds = new CharArraySet(strings, true);

        // 加入系统默认停用词

        Iterator<Object> itor = SmartChineseAnalyzer.getDefaultStopSet().iterator();

        while (itor.hasNext()) unUsefulWorlds.add(itor.next());

        //指定了停用词的分词器

        Analyzer analyzer = new SmartChineseAnalyzer(unUsefulWorlds);

        IndexWriterConfig config = new IndexWriterConfig(analyzer);

        IndexWriter writer = new IndexWriter(dir, config);

        writer.addDocuments(docs);

        writer.commit();

        writer.close();

    }

    /**

     * 执行查询 -common

     *

     * @param query

     * @throws IOException

     * @throws ParseException

     */

    private static void doQuery(Query query) throws IOException, ParseException {

        IndexReader reader = DirectoryReader.open(dir);

        IndexSearcher searcher = new IndexSearcher(reader);

        //执行query,获取指定条数的顶行记录

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

        System.out.println("搜索出的总记录数为: " + topDocs.totalHits);

        //评分文档集合

        ScoreDoc[] docs = topDocs.scoreDocs;

        for (ScoreDoc doc : docs) {

            //获取文档id

            int id = doc.doc;

            //根据文档id查询文档对象

            Document document = searcher.doc(id);

            //打印信息

            System.out.println(

                    Objects.toStringHelper("docuemnt")

                            .add("文档id", document.get("id"))

                            .add("文档名称", document.get("name"))

                            .add("文档图片", document.get("pic"))

                            .add("文档描述", document.get("description"))

                            .toString());

        }

        reader.close();

    }

    /**

     * 测试新建索引

     */

    public void testCreateIndex() {

        List<Book> bookList = bookDao.findAll();

        if (CollectionUtils.isEmpty(bookList)) return;

        List<Document> docList = Lists.newArrayList();

        Document doc;

        for (Book book : bookList) {

            doc = new Document();

            doc.add(new StoredField("id", book.getId()));

            doc.add(new StringField("name", book.getName(), Field.Store.YES));

            doc.add(new TextField("pic", book.getPic(), Field.Store.YES));

            doc.add(new TextField("description", book.getDescription(), Field.Store.YES));

            docList.add(doc);

        }

        try {

            createIndex(docList);

        } catch (IOException e) {

            LogLog.error(e.getMessage(), e);

        }

    }

    /**

     *

     * 查询

     *

     * @throws IOException

     */

    @Test

    public static void testQuery() throws IOException, ParseException {

        QueryParser parser = new QueryParser("description", new SmartChineseAnalyzer());

        Query query = parser.parse("description:java AND lucene");

        doQuery(query);

    }

}

Field类的子类和说明, 以及用法:

StoredField(FieldName, FieldValue)	重载,支持多种类型	不分词	不索引	示例:
StringField(FieldName,  String FieldValue, Store.YES)	字符串类型数据	不分词	索引	示例: 订单号, id, 手机号等
LongField(FieldName, Long FieldValue,   Store.YES)	Long型数据	分词	索引	示例: 价格
TextField(FieldName, FieldValue, Store.YES)    或 TextField(FieldName, Reader)	字符串或者流	分词	索引

来自为知笔记(Wiz)