`

Java搜索工具——Lucene实例总结(一)

阅读更多

    参考网页:http://footman265.iteye.com/blog/849744

    搞了一天半,终于利用lucene工具Demo完了我想要的功能,这其中包括为数据库建立增量索引、从索引文件根据id删除索引、单字段查询功能、多字段查询功能、多条件查询功能以及查询结果关键字高亮显示的功能。今天晚些的时候把这些功能进行了整理。看样子一时半会还下不了班,就把Demo的结果 一 一 列举下来吧。。。

   

    理论参考:http://lianj-lee.iteye.com/category/69005?show_full=true

    Lucene3.0对数据库建立索引:http://269181927.iteye.com/blog/789779

 

1. 所需要的文件(见附件)

 

    依赖包:

    lucene-core-2.4.0.jar                   lucene工具包

    lucene-highlighter-2.4.0.jar          高亮显示工具包

    IKAnalyzer2.0.2OBF.jar                分词工具(支持字典分词)

    mysql-connector-java-5.0.3-bin    链接mysql驱动

 

    数据表:

    pd_ugc.sql(所在数据库为lucenetest)

 

    类文件:

    在附件index.rar和test.rar,解压后放入java工程中的src下即可

 

2. 为数据库建立增量索引

    参考网页:http://www.blogjava.net/laoding/articles/279230.html

package index;
//--------------------- Change Logs----------------------
// <p>@author zhiqiang.zhang Initial Created at 2010-12-23<p>
//-------------------------------------------------------
import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
import java.io.PrintWriter;
import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.Statement;
import java.util.Date;

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.index.IndexWriter;

//增量索引
/*
 * 实现思路:首次查询数据库表所有记录,对每条记录建立索引,并将最后一条记录的id存储到storeId.txt文件中
 *         当新插入一条记录时,再建立索引时不必再对所有数据重新建一遍索引,
 *         可根据存放在storeId.txt文件中的id查出新插入的数据,只对新增的数据新建索引,并把新增的索引追加到原来的索引文件中
 * */
public class IncrementIndex {

    public static void main(String[] args) {
        try {
            IncrementIndex index = new IncrementIndex();
            String path = "E:\\workspace2\\Test\\lucene_test\\poiIdext";//索引文件的存放路径
            String storeIdPath = "E:\\workspace2\\Test\\lucene_test\\storeId.txt";//存储ID的路径
            String storeId = "";
            Date date1 = new Date();
            storeId = index.getStoreId(storeIdPath);
            ResultSet rs = index.getResult(storeId);
            System.out.println("开始建立索引。。。。");
            index.indexBuilding(path, storeIdPath, rs);
            Date date2 = new Date();
            System.out.println("耗时:"+(date2.getTime()-date1.getTime())+"ms");
            storeId = index.getStoreId(storeIdPath);
            System.out.println(storeId);//打印出这次存储起来的ID
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    public static void buildIndex(String indexFile, String storeIdFile) {
        try {
            String path = indexFile;//索引文件的存放路径
            String storeIdPath = storeIdFile;//存储ID的路径
            String storeId = "";
            storeId = getStoreId(storeIdPath);
            ResultSet rs = getResult(storeId);
            indexBuilding(path, storeIdPath, rs);
            storeId = getStoreId(storeIdPath);
            System.out.println(storeId);//打印出这次存储起来的ID
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    public static ResultSet getResult(String storeId) throws Exception {
        Class.forName("com.mysql.jdbc.Driver").newInstance();
        String url = "jdbc:mysql://localhost:3306/lucenetest";
        String userName = "root";
        String password = "****";
        Connection conn = DriverManager.getConnection(url, userName, password);
        Statement stmt = conn.createStatement();
        String sql = "select  * from pd_ugc";
        ResultSet rs = stmt.executeQuery(sql + " where id > '" + storeId + "'order by id");
        return rs;
    }

    public static boolean indexBuilding(String path, String storeIdPath, ResultSet rs) {
        try {
            Analyzer luceneAnalyzer = new StandardAnalyzer();
            // 取得存储起来的ID,以判定是增量索引还是重新索引
            boolean isEmpty = true;
            try {
                File file = new File(storeIdPath);
                if (!file.exists()) {
                    file.createNewFile();
                }
                FileReader fr = new FileReader(storeIdPath);
                BufferedReader br = new BufferedReader(fr);
                if (br.readLine() != null) {
                    isEmpty = false;
                }
                br.close();
                fr.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
            //isEmpty=false表示增量索引
            IndexWriter writer = new IndexWriter(path, luceneAnalyzer, isEmpty);
            String storeId = "";
            boolean indexFlag = false;
            String id;
            String name;
            String address;
            String citycode;
            while (rs.next()) {
                id = rs.getInt("id") + "";
                name = rs.getString("name");
                address = rs.getString("address");
                citycode = rs.getString("citycode");
                writer.addDocument(Document(id, name, address, citycode));
                storeId = id;//将拿到的id给storeId,这种拿法不合理,这里为了方便
                indexFlag = true;
            }
            writer.optimize();
            writer.close();
            if (indexFlag) {
                // 将最后一个的ID存到磁盘文件中
                writeStoreId(storeIdPath, storeId);
            }
            return true;
        } catch (Exception e) {
            e.printStackTrace();
            System.out.println("出错了" + e.getClass() + "\n   错误信息为:   " + e.getMessage());
            return false;
        }

    }

    public static Document Document(String id, String name, String address, String citycode) {
        Document doc = new Document();
        doc.add(new Field("id", id, Field.Store.YES, Field.Index.TOKENIZED));
        doc.add(new Field("name", name, Field.Store.YES, Field.Index.TOKENIZED));//查询字段
        doc.add(new Field("address", address, Field.Store.YES, Field.Index.TOKENIZED));
        doc.add(new Field("citycode", citycode, Field.Store.YES, Field.Index.TOKENIZED));//查询字段
        return doc;
    }

    // 取得存储在磁盘中的ID
    public static String getStoreId(String path) {
        String storeId = "";
        try {
            File file = new File(path);
            if (!file.exists()) {
                file.createNewFile();
            }
            FileReader fr = new FileReader(path);
            BufferedReader br = new BufferedReader(fr);
            storeId = br.readLine();
            if (storeId == null || storeId == "") storeId = "0";
            br.close();
            fr.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return storeId;
    }

    // 将ID写入到磁盘文件中
    public static boolean writeStoreId(String path, String storeId) {
        boolean b = false;
        try {
            File file = new File(path);
            if (!file.exists()) {
                file.createNewFile();
            }
            FileWriter fw = new FileWriter(path);
            PrintWriter out = new PrintWriter(fw);
            out.write(storeId);
            out.close();
            fw.close();
            b = true;
        } catch (IOException e) {
            e.printStackTrace();
        }
        return b;
    }
}

 

3. 索引操作

package index;

import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocCollector;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.mira.lucene.analysis.IK_CAnalyzer;

public class IndexUtils {

    //0. 创建增量索引
    public static void buildIndex(String indexFile, String storeIdFile) {
        IncrementIndex.buildIndex(indexFile, storeIdFile);
    }

    //1. 单字段查询
    @SuppressWarnings("deprecation")
    public static List<IndexResult> queryByOneKey(IndexSearcher indexSearcher, String field,
            String key) {
        try {
            Date date1 = new Date();
            QueryParser queryParser = new QueryParser(field, new StandardAnalyzer());
            Query query = queryParser.parse(key);
            Hits hits = indexSearcher.search(query);
            Date date2 = new Date();
            System.out.println("耗时:" + (date2.getTime() - date1.getTime()) + "ms");
            List<IndexResult> list = new ArrayList<IndexResult>();
            for (int i = 0; i < hits.length(); i++) {
                list.add(getIndexResult(hits.doc(i)));
            }
            return list;
        } catch (ParseException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;
    }

    //2. 多条件查询。这里实现的是and操作
    //注:要查询的字段必须是index的
    //即doc.add(new Field("pid", rs.getString("pid"), Field.Store.YES,Field.Index.TOKENIZED));   
    @SuppressWarnings("deprecation")
    public static List<IndexResult> queryByMultiKeys(IndexSearcher indexSearcher, String[] fields,
            String[] keys) {

        try {
            BooleanQuery m_BooleanQuery = new BooleanQuery();
            if (keys != null && keys.length > 0) {
                for (int i = 0; i < keys.length; i++) {
                    QueryParser queryParser = new QueryParser(fields[i], new StandardAnalyzer());
                    Query query = queryParser.parse(keys[i]);
                    m_BooleanQuery.add(query, BooleanClause.Occur.MUST);//and操作
                }
                Hits hits = indexSearcher.search(m_BooleanQuery);
                List<IndexResult> list = new ArrayList<IndexResult>();
                for (int i = 0; i < hits.length(); i++) {
                    list.add(getIndexResult(hits.doc(i)));
                }
                return list;
            }
        } catch (ParseException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;
    }

    //3.高亮显示  实现了单条件查询
    //可改造为多条件查询
    public static List<IndexResult> highlight(IndexSearcher indexSearcher, String key) {
        try {
            QueryParser queryParser = new QueryParser("name", new StandardAnalyzer());
            Query query = queryParser.parse(key);
            TopDocCollector collector = new TopDocCollector(800);
            indexSearcher.search(query, collector);
            ScoreDoc[] hits = collector.topDocs().scoreDocs;

            Highlighter highlighter = null;
            SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<font color='red'>",
                    "</font>");
            highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query));
            highlighter.setTextFragmenter(new SimpleFragmenter(200));
            List<IndexResult> list = new ArrayList<IndexResult>();
            Document doc;
            for (int i = 0; i < hits.length; i++) {
                //System.out.println(hits[i].score);
                doc = indexSearcher.doc(hits[i].doc);
                TokenStream tokenStream = new StandardAnalyzer().tokenStream("name",
                        new StringReader(doc.get("name")));
                IndexResult ir = getIndexResult(doc);
                ir.setName(highlighter.getBestFragment(tokenStream, doc.get("name")));
                list.add(ir);
            }
            return list;
        } catch (ParseException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;

    }

    //4. 多字段查询
    @SuppressWarnings("deprecation")
    public static List<IndexResult> queryByMultiFileds(IndexSearcher indexSearcher,
            String[] fields, String key) {
        try {
            MultiFieldQueryParser mfq = new MultiFieldQueryParser(fields, new StandardAnalyzer());
            Query query = mfq.parse(key);
            Hits hits = indexSearcher.search(query);
            List<IndexResult> list = new ArrayList<IndexResult>();
            for (int i = 0; i < hits.length(); i++) {
                list.add(getIndexResult(hits.doc(i)));
            }

            return list;
        } catch (ParseException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;
    }

    //5. 删除索引
    public static void deleteIndex(String indexFile, String id) throws CorruptIndexException,
            IOException {
        IndexReader indexReader = IndexReader.open(indexFile);
        indexReader.deleteDocuments(new Term("id", id));
        indexReader.close();
    }

    //6. 一元分词
    @SuppressWarnings("deprecation")
    public static String Standard_Analyzer(String str) {
        Analyzer analyzer = new StandardAnalyzer();
        Reader r = new StringReader(str);
        StopFilter sf = (StopFilter) analyzer.tokenStream("", r);
        System.out.println("=====StandardAnalyzer====");
        System.out.println("分析方法:默认没有词只有字(一元分词)");
        Token t;
        String results = "";
        try {
            while ((t = sf.next()) != null) {
                System.out.println(t.termText());
                results = results + " " + t.termText();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        return results;
    }

    //7. 字典分词
    @SuppressWarnings("deprecation")
    public static String ik_CAnalyzer(String str) {
        Analyzer analyzer = new IK_CAnalyzer();
        Reader r = new StringReader(str);
        TokenStream ts = (TokenStream) analyzer.tokenStream("", r);
        System.out.println("=====IK_CAnalyzer====");
        System.out.println("分析方法:字典分词,正反双向搜索");
        Token t;
        String results = "";
        try {
            while ((t = ts.next()) != null) {
                System.out.println(t.termText());
                results = results + " " + t.termText();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        return results;
    }

    //在结果中搜索
    public static void queryFromResults() {

    }

    //组装对象
    public static IndexResult getIndexResult(Document doc) {
        IndexResult ir = new IndexResult();
        ir.setId(doc.get("id"));
        ir.setName(doc.get("name"));
        ir.setAddress(doc.get("address"));
        ir.setCitycode(doc.get("citycode"));
        return ir;
    }
}

 

    查询索引结果对象:IndexResult

package index;

public class IndexResult {

    private String id;

    private String name;

    private String address;

    private String citycode;

    
    public String getId() {
        return id;
    }
    public void setId(String id) {
        this.id = id;
    }
    public String getName() {
        return name;
    }
    public void setName(String name) {
        this.name = name;
    }

    
    public String getAddress() {
        return address;
    }
    public void setAddress(String address) {
        this.address = address;
    }
    public String getCitycode() {
        return citycode;
    }
    public void setCitycode(String citycode) {
        this.citycode = citycode;
    }
    
}

 

4. 测试类

package test;

/**
 * $Id$
 * Copyright 2009-2010 Oak Pacific Interactive. All rights reserved.
 */

import index.IndexResult;
import index.IndexUtils;

import java.util.Date;
import java.util.List;

import org.apache.lucene.search.IndexSearcher;

public class Test {

    //存放索引文件
    private static String indexFile = "E:\\workspace2\\Test\\lucene_test\\poiIdext";

    //存放id
    private static String storeIdFile = "E:\\workspace2\\Test\\lucene_test\\storeId.txt";

    public static void main(String[] args) throws Exception {
        //0. 创建增量索引
        IndexUtils.buildIndex(indexFile, storeIdFile);
        
        IndexSearcher indexSearcher = new IndexSearcher(indexFile);
        String key = IndexUtils.ik_CAnalyzer("静安中心");

        //1.单字段查询
        Date date1 = new Date();
        List<IndexResult> list = IndexUtils.queryByOneKey(indexSearcher, "name", key);
        Date date2 = new Date();
        System.out.println("耗时:" + (date2.getTime() - date1.getTime()) + "ms\n" + list.size()
                + "条=======================================单字段查询");
        //printResults(list);

        //2.多条件查询
        String[] fields = { "name", "citycode" };
        String[] keys = { IndexUtils.ik_CAnalyzer("静安中心"), "0000" };
        date1 = new Date();
        list = IndexUtils.queryByMultiKeys(indexSearcher, fields, keys);
        date2 = new Date();
        System.out.println("耗时:" + (date2.getTime() - date1.getTime()) + "ms\n" + list.size()
                + "条\n===============================多条件查询");
        printResults(list);

        //3.高亮显示  单字段查询
        System.out.println("\n\n");
        date1 = new Date();
        list = IndexUtils.highlight(indexSearcher, key);
        date2 = new Date();
        System.out.println("耗时:" + (date2.getTime() - date1.getTime()) + "ms\n" + list.size()
                + "条\n======================================高亮显示");
       // printResults(list);

        //4. 多字段查询
        date1 = new Date();
        list = IndexUtils.queryByMultiFileds(indexSearcher, fields, key);
        date2 = new Date();
        System.out.println("耗时:" + (date2.getTime() - date1.getTime()) + "ms\n" + list.size()
                + "条\n=====================================多字段查询");
       // printResults(list);

        //5. 删除索引中的字段  根据id进行删除
        IndexUtils.deleteIndex(indexFile, "123");
    }

    //打印结果
    public static void printResults(List<IndexResult> list) {
        if (list != null && list.size() > 0) {
            for (int i = 0; i < list.size(); i++) {
                System.out.println(list.get(i).getId() + "," + list.get(i).getName() + ","
                        + list.get(i).getAddress() + "," + list.get(i).getCitycode()+"--->"+i);
            }
        }
    }
}

 

5. 其它

 

全文索引:

目前的情况是,搜索hello,"hello world"、"hi hello, how are you"但"worldhello"显示不出来

 

默认情况下,QueryParser不支持通配符打头的查询(如,*ook)。不过在Lucene 2.1版本以后,他们可以通过调用QueryParser.setAllowLeadingWildcard( true )的 方法打开这一功能。注意,这是一个开销很大的操作:它需要扫描索引中全部记号的列表,来寻找匹配这个模式的词。(译注:高效支持这种后缀查询的办法是,建立反序的记号表,Lucene没有实现这一模式。)http://www.codechina.org/faq/show/42/

 

支持空格分词搜索:"厕所 26 沈阳" 这是三个词

不支持:“厕所沈阳”这是一个词

 

Lucene能实现“在搜索结果中搜索”的功能么,也就是说第二个搜索仅在第一个搜索结果中进行?

http://www.codechina.org/faq/show/63/

可以。主要有两种做法:

  • 使用QueryFilter把第一个查询当作一个过滤器处理。(你可以在Lucene的邮件列表里面搜索 QueryFilter, Doug Cutting(Lucene的最初作者)反对这种做法。
  • BooleanQuery把前后两个查询结合起来,前一个查询使用 required选项。

我们推荐使用BooleanQuery的方法。

 

============

 // 创建标准文本分析器, 标准的是可以支持的中文的

   Analyzer luceneAnalyzer = new StandardAnalyzer();

   indexWriter = new IndexWriter(indexDir, luceneAnalyzer, true);

   // 可以说是创建一个新的写入工具

   // 第一个参数是要索引建立在哪个目录里

   // 第二个参数是新建一个文本分析器,这里用的是标准的大家也可以自己写一个

   // 第三个参数如果是true,在建立索引之前先将c: \\index目录清空

 

 

 

poi_data_ugc搜索中,索引放在内存里还是磁盘上????


针对于lucene使用和优化

http://hi.baidu.com/lewutian/blog/item/48a86d03de58b984d43f7c1b.html

 

ucene入门实例(1):索引文本文件

http://www.java3z.com/cwbwebhome/article/article5/51021.html

分享到:

相关推荐

Global site tag (gtag.js) - Google Analytics