lucene对日期(date)和整形(int)处理

  1 /**
  2  * 
  3  */
  4 package com.b510.lucene.util;
  5 
  6 import java.io.File;
  7 import java.io.IOException;
  8 import java.text.ParseException;
  9 import java.text.SimpleDateFormat;
 10 import java.util.Date;
 11 import java.util.HashMap;
 12 import java.util.Map;
 13 
 14 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 15 import org.apache.lucene.document.Document;
 16 import org.apache.lucene.document.Field;
 17 import org.apache.lucene.document.NumericField;
 18 import org.apache.lucene.index.CorruptIndexException;
 19 import org.apache.lucene.index.IndexReader;
 20 import org.apache.lucene.index.IndexWriter;
 21 import org.apache.lucene.index.IndexWriterConfig;
 22 import org.apache.lucene.index.Term;
 23 import org.apache.lucene.search.IndexSearcher;
 24 import org.apache.lucene.search.ScoreDoc;
 25 import org.apache.lucene.search.TermQuery;
 26 import org.apache.lucene.search.TopDocs;
 27 import org.apache.lucene.store.Directory;
 28 import org.apache.lucene.store.FSDirectory;
 29 import org.apache.lucene.store.LockObtainFailedException;
 30 import org.apache.lucene.util.Version;
 31 
 32 /**
 33  * @author Hongten <br />
 34  * @date 2013-1-31
 35  */
 36 public class LuceneUtil {
 37 
 38     /**
 39      * 邮件id
 40      */
 41     private String[] ids = { "1", "2", "3", "4", "5", "6" };
 42     /**
 43      * 邮箱
 44      */
 45     private String[] emails = { "aa@sina.com", "bb@foxmail.com", "cc@qq.com",
 46             "dd@163.com", "ee@gmail.com", "ff@sina.com" };
 47     /**
 48      * 邮件内容
 49      */
 50     private String[] contents = { "hello,aa,hi,hell world!!", 
 51                                   "hello,bb,i'm a boy", 
 52                                   "hello,cc",
 53                                   "hello,dd,welcome to my zone,this is a test hello", 
 54                                   "hello,ee,haha,xixi,hello world!!", 
 55                                   "hello,ff" };
 56     /**
 57      * 附件数
 58      */
 59     private int[] attachs = {1,5,3,2,1,6};
 60     /**
 61      * 日期
 62      */
 63     private Date[] dates = null;
 64     /**
 65      * 收件人的名称
 66      */
 67     private String[] names = { "hongten", "hanyuan", "Devide", "Tom", "Steven",
 68             "Shala" };
 69 
 70     private Directory directory = null;
 71     /**
 72      * 评分
 73      */
 74     private Map<String, Float> scores = new HashMap<String, Float>();
 75     
 76     public LuceneUtil() {
 77         try {
 78             setDates();
 79             scores.put("sina.com", 1.0f);
 80             scores.put("foxmail.com", 1.1f);
 81             directory = FSDirectory.open(new File(
 82                     "D:/WordPlace/lucene/lucene_0400_dateAndInt/lucene/index"));
 83         } catch (IOException e) {
 84             e.printStackTrace();
 85         }
 86     }
 87 
 88     /**
 89      * 创建日期
 90      */
 91     public void setDates(){
 92         SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd");
 93         try {
 94             dates = new Date[ids.length];
 95             dates[0] = sdf.parse("2012-11-18");
 96             dates[1] = sdf.parse("2010-01-28");
 97             dates[2] = sdf.parse("2011-11-21");
 98             dates[3] = sdf.parse("2012-12-12");
 99             dates[4] = sdf.parse("2011-06-23");
100             dates[5] = sdf.parse("2012-03-15");
101         } catch (ParseException e) {
102             e.printStackTrace();
103         }
104     }
105     
106     /**
107      * 创建索引
108      */
109     public void index() {
110         IndexWriter writer = null;
111         try {
112             writer = new IndexWriter(directory, new IndexWriterConfig(
113                     Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
114             //删除之前所建立的全部索引
115             writer.deleteAll();
116             // 创建文档
117             Document document = null;
118             for (int i = 0; i < ids.length; i++) {
119                 // Field.Store.YES:将会存储域值，原始字符串的值会保存在索引，以此可以进行相应的回复操作，对于主键，标题可以是这种方式存储
120                 // Field.Store.NO:不会存储域值，通常与Index.ANAYLIZED和起来使用，索引一些如文章正文等不需要恢复的文档
121                 // ==============================
122                 // Field.Index.ANALYZED:进行分词和索引，适用于标题，内容等
123                 // Field.Index.NOT_ANALYZED:进行索引，但是不进行分词，如身份证号码，姓名，ID等，适用于精确搜索
124                 // Field.Index.ANALYZED_NOT_NORMS:进行分词，但是不进行存储norms信息，这个norms中包括了创建索引的时间和权值等信息
125                 // Field.Index.NOT_ANALYZED_NOT_NORMS:不进行分词也不进行存储norms信息(不推荐)
126                 // Field.Index.NO:不进行分词
127                 document = new Document();
128                 document.add(new Field("id", ids[i], Field.Store.YES,
129                         Field.Index.NOT_ANALYZED_NO_NORMS));
130                 document.add(new Field("email", emails[i], Field.Store.YES,
131                         Field.Index.NOT_ANALYZED));
132                 document.add(new Field("content", contents[i], Field.Store.YES,
133                         Field.Index.ANALYZED));
134                 document.add(new Field("name", names[i], Field.Store.YES,
135                         Field.Index.NOT_ANALYZED_NO_NORMS));
136                 document.add(new NumericField("attach", Field.Store.YES,true).setIntValue(attachs[i]));
137                 document.add(new NumericField("date",Field.Store.YES,true).setLongValue(dates[i].getTime()));
138                 
139                 //这里进行加权处理
140                 String et = emails[i].substring(emails[i].lastIndexOf("@")+1);
141                 System.out.println(et);
142                 if(scores.containsKey(et)){
143                     document.setBoost(scores.get(et));
144                 }else{
145                     document.setBoost(0.6f);
146                 }
147                 writer.addDocument(document);
148             }
149         } catch (CorruptIndexException e) {
150             e.printStackTrace();
151         } catch (LockObtainFailedException e) {
152             e.printStackTrace();
153         } catch (IOException e) {
154             e.printStackTrace();
155         } finally {
156             if (writer != null) {
157                 try {
158                     writer.close();
159                 } catch (CorruptIndexException e) {
160                     e.printStackTrace();
161                 } catch (IOException e) {
162                     e.printStackTrace();
163                 }
164             }
165         }
166     }
167     
168     /**
169      * 搜索
170      */
171     public void search(){
172         try {
173             IndexReader reader = IndexReader.open(directory);
174             IndexSearcher searcher = new IndexSearcher(reader);
175             TermQuery query = new TermQuery(new Term("content","hello"));
176             TopDocs tds =searcher.search(query, 10);
177             for(ScoreDoc sd : tds.scoreDocs){
178                 Document doc = searcher.doc(sd.doc);
179                 SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd");
180                 Date date = null;
181                 /*try {
182                     date = sdf.parse(doc.get("date"));
183                 } catch (ParseException e) {
184                     e.printStackTrace();
185                 }*/
186                 System.out.println("文档序号：["+sd.doc+"] 得分：["+sd.score+"] 邮件名称：["+doc.get("email")+"] 邮件人：["+doc.get("name")+"] 附件数：["+doc.get("attach")+"] 日期：["+doc.get("date")+"] 内容 : ["+doc.get("content")+"]");
187             }
188         } catch (CorruptIndexException e) {
189             e.printStackTrace();
190         } catch (IOException e) {
191             e.printStackTrace();
192         }
193     }
194 }

 1 /**
 2  * 
 3  */
 4 package com.b510.lucene.test;
 5 
 6 import org.junit.Test;
 7 
 8 import com.b510.lucene.util.LuceneUtil;
 9 
10 /**
11  * @author Hongten <br />
12  * @date 2013-1-31
13  */
14 public class IndexTest {
15 
16     @Test
17     public void testIndex(){
18         LuceneUtil util = new LuceneUtil();
19         util.index();
20     }
21     
22     @Test
23     public void testSearch(){
24         LuceneUtil util = new LuceneUtil();
25         util.search();
26     }
27     
28 }