开发搜索引擎初步（一）建立索引（Lucene实现）

 开发自己的搜索引擎完成了一段时间了，现在准备开始梳理一下思路，把以前的总结一下，为以后做真正的“谷歌”埋下伏笔，呵呵。。。。。。

    一。Lucene的下载

   牛逼的Apache旗下的Lucene，呵呵，无人不知啊，http://lucene.apache.org/,去这个地址自己下载，别说不会Dowmload

    二.使用Lucene建立索引

    将下载下来的包解压，把里面的Core,memory,analyzer啥的都拿出来，配置到自己的Eclipse上面，下面的事情就是写代码了。

view plaincopy to clipboardprint?

1. package com.dreamers.creatindex;  
2.   
3. import java.io.File;  
4. import java.util.ArrayList;  
5.   
6. import org.apache.lucene.analysis.Analyzer;  
7. import org.apache.lucene.document.Document;  
8. import org.apache.lucene.document.Field;  
9. import org.apache.lucene.index.IndexWriter;  
10. import org.apache.lucene.store.FSDirectory;  
11. import org.dom4j.DocumentException;  
12. import org.wltea.analyzer.lucene.IKAnalyzer;  
13.   
14.   
15. import com.dreamers.xml.*;  
16. import com.dreamers.read.*;  
17.   
18. /** 
19.  * @category 创建所有XML索引 
20.  * @author bird 
21.  * 
22.  */  
23. public class CreatIndex {  
24.     private String INDEX_STORE_PATH ;  
25.       
26.     //创建索引   
27.     @SuppressWarnings("deprecation")  
28.     public void creatIndex(){  
29.         try{  
30.             GetPath path = new GetPath();  
31.             INDEX_STORE_PATH = path.getIndexPath();  
32.             File file = new File(INDEX_STORE_PATH);  
33.             Analyzer analyzer = new IKAnalyzer();  
34.             XmlReader xml = new XmlReader();  
35.             FSDirectory directory = FSDirectory.open(file);  
36.             IndexWriter writer = new IndexWriter(directory, analyzer, true,IndexWriter.MaxFieldLength.LIMITED);  
37.             ArrayList<String> lisId = xml.getId();  
38.             ArrayList<String> lisTitle = xml.getTitle();  
39.             ArrayList<String> lisKeyWords = xml.getKeyWords();  
40.             ArrayList<String> lisKind = xml.getKind();  
41.             ArrayList<String> lisDescribe = xml.getDescribe();  
42.             ArrayList<String> lisDate = xml.getDate();  
43.             ArrayList<String> lisUrl = xml.getUrl();  
44.             ArrayList<String> lisAuthor = xml.getAuthor();  
45.             ArrayList<String> lisPublisher = xml.getPublisher();  
46.           
47.             //System.out.println(lisUrl.get(5));  
48.             for (int i = 0; i < xml.getCount();i++){  
49.                 Document doc = new Document();  
50.                 //为ID创建Field   
51.                   
52.                 Field field = new Field("id",lisId.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED );  
53.                 doc.add(field);  
54.                 //为title创建索引   
55.                   
56.                 field = new Field("title",lisTitle.get(i),Field.Store.YES,Field.Index.ANALYZED);  
57.                 doc.add(field);  
58.                 //为keywords创建索引   
59.                   
60.                 field = new Field("keywords",lisKeyWords.get(i),Field.Store.YES,Field.Index.ANALYZED);  
61.                 doc.add(field);  
62.                 //为kind创建索引   
63.                   
64.                 field = new Field("kind",lisKind.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED);  
65.                 doc.add(field);  
66.                 //为describe创建索引   
67.                   
68.                  field = new Field("describe",lisDescribe.get(i),Field.Store.YES,Field.Index.ANALYZED);  
69.                 doc.add(field);  
70.                 //为data创建索引   
71.                   
72.                 field = new Field("date",lisDate.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED);  
73.                 doc.add(field);  
74.                 //为URL创建索引   
75.                   
76.                 field = new Field("url",lisUrl.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED);  
77.                 doc.add(field);  
78.                 //为author创建索引   
79.                   
80.                 field = new Field("author",lisAuthor.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED);  
81.                 doc.add(field);  
82.                 //为publisher创建索引   
83.                   
84.                 field = new Field("publisher",lisPublisher.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED);  
85.                 doc.add(field);  
86.                   
87.                                 }  
88.                   
89.                 writer.addDocument(doc);  
90.             }     
91.               
92.               
93.               
94.               
95.              writer.close();  
96.              //directory.close();   
97.             System.out.println("索引创建完毕");  
98.               
99.               
100.         }  catch (Exception e){  
101.             e.printStackTrace();  
102.           
103.         }  
104.           
105.     }  
106.     
107.     public static void main(String [] args) throws DocumentException{  
108.         CreatIndex index = new CreatIndex();  
109.         index.creatIndex();  
110.     }  
111. }  

package com.dreamers.creatindex;import java.io.File;import java.util.ArrayList;import org.apache.lucene.analysis.Analyzer;import org.apache.lucene.document.Document;import org.apache.lucene.document.Field;import org.apache.lucene.index.IndexWriter;import org.apache.lucene.store.FSDirectory;import org.dom4j.DocumentException;import org.wltea.analyzer.lucene.IKAnalyzer;import com.dreamers.xml.*;import com.dreamers.read.*;/** * @category 创建所有XML索引 * @author bird * */public class CreatIndex {private String INDEX_STORE_PATH ;//创建索引@SuppressWarnings("deprecation")public void creatIndex(){try{GetPath path = new GetPath();INDEX_STORE_PATH = path.getIndexPath();File file = new File(INDEX_STORE_PATH);Analyzer analyzer = new IKAnalyzer();XmlReader xml = new XmlReader();FSDirectory directory = FSDirectory.open(file);IndexWriter writer = new IndexWriter(directory, analyzer, true,IndexWriter.MaxFieldLength.LIMITED);ArrayList<String> lisId = xml.getId();ArrayList<String> lisTitle = xml.getTitle();ArrayList<String> lisKeyWords = xml.getKeyWords();ArrayList<String> lisKind = xml.getKind();ArrayList<String> lisDescribe = xml.getDescribe();ArrayList<String> lisDate = xml.getDate();ArrayList<String> lisUrl = xml.getUrl();ArrayList<String> lisAuthor = xml.getAuthor();ArrayList<String> lisPublisher = xml.getPublisher();//System.out.println(lisUrl.get(5));for (int i = 0; i < xml.getCount();i++){Document doc = new Document();//为ID创建FieldField field = new Field("id",lisId.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED );doc.add(field);//为title创建索引 field = new Field("title",lisTitle.get(i),Field.Store.YES,Field.Index.ANALYZED);doc.add(field);//为keywords创建索引 field = new Field("keywords",lisKeyWords.get(i),Field.Store.YES,Field.Index.ANALYZED);doc.add(field);//为kind创建索引field = new Field("kind",lisKind.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED);doc.add(field);//为describe创建索引 field = new Field("describe",lisDescribe.get(i),Field.Store.YES,Field.Index.ANALYZED);doc.add(field);//为data创建索引 field = new Field("date",lisDate.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED);doc.add(field);//为URL创建索引field = new Field("url",lisUrl.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED);doc.add(field);//为author创建索引field = new Field("author",lisAuthor.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED);doc.add(field);//为publisher创建索引field = new Field("publisher",lisPublisher.get(i),Field.Store.YES,Field.Index.NOT_ANALYZED);doc.add(field);}writer.addDocument(doc);} writer.close(); //directory.close();System.out.println("索引创建完毕");} catch (Exception e){e.printStackTrace();}} public static void main(String [] args) throws DocumentException{CreatIndex index = new CreatIndex();index.creatIndex();}}

 

    这里不多说，最上面的每个list里面都藏有巨大的信息，都是一些字符串，就当是放到容器里的字符窜吧，然后下面的建立索引的过程都是一样的，代码比较短，就不需要什么注释了，呵呵