歡迎來到Linux教程網
Linux教程網
Linux教程網
Linux教程網
您现在的位置: Linux教程網 >> UnixLinux >  >> Linux編程 >> Linux編程

Lucene給文本索引和搜索功能的應用

最近一段時間由於公司需要 ,模糊搜索出相似的關鍵詞,所以直接考慮使用了Lucene。

Lucene允許你往程序中添加搜索功能,Lucene能夠把你從文本中解析出來的數據進行索引和搜索 ,Lucene不關心數據來源 甚至不關心語種,不過你需要把它轉換成文本格式。也就是說你可以搜索 html網頁,文本文檔,word文檔 ,pdf,或者其他一些 總之 只要能夠提取出文本信息的即可。同樣你也可以利用Lucene來索引存儲在數據庫中的數據,以給你的用戶提供一些  比如 全文搜索功能等 ,反正Lucene的功能很是強大。裡面還有很多開源的對不同語言進行分析的插件等。

下面我介紹一個例子 ,這裡我進行對 一個txt文檔的 每一行進行了 索引的添加 ,也就是說  把每一行 當作一個document對象來處理,實際上在Lucene中 每一個document 相當於我們在數據庫中的庫名, 而每個field相當於我們的表名 ,它能夠對文本進行自動處理去掉裡面的一些語氣詞,它能把你規定的域當作關鍵詞來進行索引 以備查詢時使用,Lucene比較容易使用 ,但是不如數據庫靈活,速度很快。下面 我用一個例子來說明(這裡我用的Lucene4.7.2,最高版本 ,你需要注意把需要的一些jar包引入的到你的工程中,使用maven可直接引入依賴http://mvnrepository.com/artifact/org.apache.Lucene需要的全部引入)我這裡寫了一個實例 你可以進行參考學習使用方法。

--------------------------------------分割線 --------------------------------------

基於Lucene多索引進行索引和搜索 http://www.linuxidc.com/Linux/2012-05/59757.htm

Lucene 實戰(第2版) 中文版 配套源代碼 http://www.linuxidc.com/Linux/2013-10/91055.htm

Lucene 實戰(第2版) PDF高清中文版 http://www.linuxidc.com/Linux/2013-10/91052.htm

使用Lucene-Spatial實現集成地理位置的全文檢索 http://www.linuxidc.com/Linux/2012-02/53117.htm

Lucene + Hadoop 分布式搜索運行框架 Nut 1.0a9 http://www.linuxidc.com/Linux/2012-02/53113.htm

Lucene + Hadoop 分布式搜索運行框架 Nut 1.0a8 http://www.linuxidc.com/Linux/2012-02/53111.htm

Lucene + Hadoop 分布式搜索運行框架 Nut 1.0a7 http://www.linuxidc.com/Linux/2012-02/53110.htm

Project 2-1: 配置Lucene, 建立WEB查詢系統[Ubuntu 10.10] http://www.linuxidc.com/Linux/2010-11/30103.htm

--------------------------------------分割線 --------------------------------------

package lucene.home.clq;

/**
 * @author chenlongquan
 * Copyright Manning Publications Co..com
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *   
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific lan     
*/

//創建索引
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.Version;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileFilter;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.FileReader;
import java.io.InputStreamReader;
import java.io.LineNumberReader;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
/**
 * This code was originally build for the index
 *
 */
public class Indexer {

  public static void main(String[] args) throws Exception {
   
    String indexDir = "f:\\index";        //1
    String dataDir = "f:\\baidu";          //2


    long start = System.currentTimeMillis();
    Indexer indexer = new Indexer(indexDir);
    int numIndexed;
    try {
      numIndexed = indexer.index(dataDir, new TextFilesFilter());
    } finally {
      indexer.close();
    }
    long end = System.currentTimeMillis();

    System.out.println("Indexing " + numIndexed + " files took "
      + (end - start) + " milliseconds");
  }
  private IndexWriter writer;
  public Indexer(String indexDir) throws IOException {
      Directory dir = FSDirectory.open(new File(indexDir));
      writer = new IndexWriter(dir,indexWriterConfig());
      //在這裡進行索引的調試
            }

  public void close() throws IOException {
    writer.close();                            //4
  }
  private IndexWriterConfig indexWriterConfig()
{
 Analyzer analyzer = new SmartChineseAnalyzer(Version.LUCENE_47);
 IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_47, analyzer);
 return config;
}
  public int index(String dataDir, FileFilter filter)
    throws Exception {


    File[] files = new File(dataDir).listFiles();


    for (File f: files) {
      if (!f.isDirectory() &&
          !f.isHidden() &&
          f.exists() &&
          f.canRead() &&
          (filter == null || filter.accept(f))) {
        indexFile(f);
      }
    }


    return writer.numDocs();                    //5
  }


  private static class TextFilesFilter implements FileFilter {
    public boolean accept(File path) {
      return path.getName().toLowerCase()        //6
            .endsWith(".txt");                  //6
    }
  }
 
  /**
    * 遍歷每一個文件,然後讀出文件中的每一行數據,當成一個document來處理
    * @param f
    * @throws Exception
    */
  private void indexFile(File f) throws Exception {
    System.out.println("Indexing " + f.getCanonicalPath());
  // Document doc = getDocument(f);
    List<String> lists = readFileNoDup(f);
    for(String list:lists){
    Document doc = new Document();
    doc.add(new Field("contents",list,TextField.TYPE_STORED));
    writer.addDocument(doc);   
    }
   
                            //10
  }
  //讀取一個文件
  private List<String> readFile(File filePathAndName)throws IOException {

FileInputStream fis = new FileInputStream(filePathAndName);
InputStreamReader isr = new InputStreamReader(fis, "UTF-8");
BufferedReader br = new BufferedReader(isr);
LineNumberReader lnr = new LineNumberReader(br);

List<String> returnValue = new ArrayList<String>();
int cnt = 0;
while (true) {
cnt++;
String tempStr = lnr.readLine();
if (tempStr == null)
break;
if (tempStr.length() < 2)
continue;
returnValue.add(tempStr);
}
lnr.close();
br.close();
isr.close();
fis.close();
return returnValue;
}
  //讀取一個文件並排重後返回
  public static List<String> readFileNoDup(File filePathAndName)
throws IOException {
 
FileInputStream fis = new FileInputStream(filePathAndName);
InputStreamReader isr = new InputStreamReader(fis, "UTF-8");
BufferedReader br = new BufferedReader(isr);
LineNumberReader lnr = new LineNumberReader(br);

Set<String> set = new HashSet<String>();
while (true) {
String tempStr = lnr.readLine();
if (tempStr == null)
break;
if (tempStr.length() < 2)
continue;
set.add(tempStr.trim());
}
lnr.close();
br.close();
isr.close();
fis.close();
List<String> returnValue = new ArrayList<String>(set.size());
returnValue.addAll(set);
return returnValue;
        }
}

//對剛才已經建好的索引進行搜索

package lucene.home.clq;


 


/**
 * Copyright Manning Publications Co.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific lan     
*/


import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;


import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.ParseException;
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.search.Sort;
import org.apache.lucene.search.SortField;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.TopFieldCollector;
import org.apache.lucene.search.TopFieldDocs;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;


// From chapter 1


/**
 * This code was originally written for  searcher
 *
 */
public class Searcher {


  public static void main(String[] args) throws IllegalArgumentException,
        IOException, ParseException {
                   
    final String indexDir = "e:\\soso\\soso";
        String q = " ";//輸入你添加的所以 進行模糊搜索
    docs = query(indexDir, q)
   
    }
   
  public static void search(String indexDir, String q)
    throws IOException, ParseException {
 IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexDir)));
  // Directory dir = FSDirectory.open(new File(indexDir)); //3
    IndexSearcher is = new IndexSearcher(reader);  //3 


    QueryParser parser = new QueryParser(Version.LUCENE_47,"contents",new SmartChineseAnalyzer(Version.LUCENE_47));       
    Query query = parser.parse(q);              //4 
    long start = System.currentTimeMillis();
    TopDocs hits = is.search(query, 500); //5
 
    //ScoreDoc[] hits = is.search(query, null, 10).scoreDocs;
    long end = System.currentTimeMillis();


    System.err.println("Found " + hits.totalHits +  //6 
      " document(s) (in " + (end - start) +        // 6
      " milliseconds) that matched query '" +    // 6
      q + "':");                                  // 6


    for(ScoreDoc scoreDoc : hits.scoreDocs) {
      Document doc = is.doc(scoreDoc.doc);              //7     
      System.out.println(doc.get("contents"));
    }
    reader.close();
  }
 
    private static List<String> query(String indexDir, String searcher) throws IOException, ParseException{
        if (searcher == null || searcher.length() == -1) {
            return null;
          }
   
        searcher = searcher.trim();
          if (searcher.length() == 0) {
            return null;
          }
         
    IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexDir)));//open the index
    //IndexReader reader = DirectoryReader.open(SimpleFSDirectory.open(new File(indexDir)));//open the index
    IndexSearcher is = new IndexSearcher(reader);//find the content
    QueryParser parser = new QueryParser(Version.LUCENE_47, "contents", new SmartChineseAnalyzer(Version.LUCENE_47));//parser the content
    Query query = parser.parse(searcher);
    TopFieldDocs hits = is.search(query, 100, new Sort(new SortField("contents", SortField.Type.SCORE, false)));
    TopDocs hits1 = is.search(query, 200);//搜索出前200條數據  按照評分進行排序
    List<String> list = new ArrayList<String>();
    for(ScoreDoc scoreDoc : hits.scoreDocs){
    Document doc = is.doc(scoreDoc.doc);
    list.add(doc.get("contents"));
    }
    reader.close();
    return list;
    }
}

//這裡我主要給文檔中的文本進行添加了索引 ,你也可以在Field 中給路徑 等等一些屬性進行添加索引  具體你可以搜索lucene api
 
進行使用 裡面的一些方法。我這裡說的比較粗,有問題歡迎討論。

Lucene 的詳細介紹:請點這裡
Lucene 的下載地址:請點這裡

Copyright © Linux教程網 All Rights Reserved