Lucene3.5例子

论坛 › 期权论坛 › 脚本     
匿名技术用户   2021-1-12 13:51   611   0

原文地址：http://www.juziku.com/sunlightcs/wiki/4205.htm

Lucene3.5+IK分词器的例子，Lucene3.5改动有点大，很多方法都不推荐使用了。
示例代码如下所示：

?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
import java.io.File;
import java.io.IOException;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.Formatter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.Scorer;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;
import org.wltea.analyzer.lucene.IKSimilarity;
/**
* lucene3.5+ik的例子
*
* @author steven
* @date 2012-3-1 下午2:12:24
*/
public class LuceneDemo {
//索引文件位置
File dataFile = new File( "D://indexFile" );
//使用IK分词器
Analyzer analyzer = new IKAnalyzer();
public void bulidIndex(){
Directory directory = null ;
IndexWriter writer = null ;
try {
directory = FSDirectory.open(dataFile);
IndexWriterConfig writerConfig = new IndexWriterConfig(Version.LUCENE_35, analyzer);
writer = new IndexWriter(directory, writerConfig);
writer.addDocument(addDocument( 1 , "聚资库" , "聚资库，是以分享知识与经验的学习交流平台，加入聚资库，学习新知识、结交新朋友、塑造个人形象。" ));
writer.addDocument(addDocument( 2 , "聚资库" , "聚资库，是以分享知识与经验的学习交流平台，加入聚资库，学习新知识、结交新朋友、塑造个人形象。" ));
writer.addDocument(addDocument( 3 , "聚资库" , "聚资库，是以分享知识与经验的学习交流平台，加入聚资库，学习新知识、结交新朋友、塑造个人形象。" ));
writer.addDocument(addDocument( 4 , "资料" , "聚资库，是以分享知识与经验的学习交流平台，加入聚资库，学习新知识、结交新朋友、塑造个人形象。" ));
writer.addDocument(addDocument( 5 , "微知识" , "聚资库，是以分享知识与经验的学习交流平台，加入聚资库，学习新知识、结交新朋友、塑造个人形象。" ));
} catch (Exception ex){
ex.printStackTrace();
} finally {
try {
writer.close();
directory.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
/**
* 添加Document
*/
public Document addDocument(Integer id, String title, String content) {
Document doc = new Document();
//Field.Index.NO 表示不索引
//Field.Index.ANALYZED 表示分词且索引
//Field.Index.NOT_ANALYZED 表示不分词且索引
doc.add( new Field( "id" , String.valueOf(id), Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.add( new Field( "title" , title, Field.Store.YES, Field.Index.ANALYZED));
doc.add( new Field( "content" , content, Field.Store.YES, Field.Index.ANALYZED));
return doc;
}
/**
* 更新索引
*/
public void update(Integer id, String title, String content) {
try {
Directory directory = FSDirectory.open(dataFile);
IndexWriterConfig writerConfig = new IndexWriterConfig(Version.LUCENE_35, analyzer);
IndexWriter writer = new IndexWriter(directory, writerConfig);
Document doc = addDocument(id, title, content);
Term term = new Term( "id" , String.valueOf(id));
writer.updateDocument(term, doc);
writer.close();
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 删除索引
*/
public void delete(Integer id) {
try {
Directory directory = FSDirectory.open(dataFile);
IndexWriterConfig writerConfig = new IndexWriterConfig(Version.LUCENE_35, analyzer);
IndexWriter writer = new IndexWriter(directory, writerConfig);
Term term = new Term( "id" , String.valueOf(id));
writer.deleteDocuments(term);
writer.close();
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 搜索
* @param where 搜索条件
* @param after 分页时要用到，不分页时为null
*/
public void search(String where, ScoreDoc after) {
IndexSearcher isearcher = null ;
Directory directory = null ;
try {
directory = FSDirectory.open(dataFile);
//创建索引搜索器 且只读
IndexReader reader = IndexReader.open(FSDirectory.open(dataFile), true );
isearcher = new IndexSearcher(reader);
//在索引器中使用IKSimilarity相似度评估器
isearcher.setSimilarity( new IKSimilarity());
QueryParser parser = new QueryParser(Version.LUCENE_35, null , analyzer);
Query query = parser.parse(where);
//lucene3.5深度分页，每页显示10条记录
TopDocs topDocs = isearcher.searchAfter(after, query, 10 );
ScoreDoc[] hits = topDocs.scoreDocs;
//关键字高亮
Formatter formatter = new SimpleHTMLFormatter( "<font color='red'>" , "</font>" );
Scorer scorer = new QueryScorer(query);
Highlighter highlighter = new Highlighter(formatter, scorer);
for (ScoreDoc scoreDoc : hits){
Document hitDoc = isearcher.doc(scoreDoc.doc);
String id = hitDoc.get( "id" );
String title = hitDoc.get( "title" );
String content = hitDoc.get( "content" );
float score = scoreDoc.score;
title = highlighter.getBestFragment(analyzer, "title" , title);
content = highlighter.getBestFragment(analyzer, "content" , content);
if (title == null ){
title = hitDoc.get( "title" );
}
if (content == null ){
content = hitDoc.get( "content" );
}
System.out.println( "doc:" + scoreDoc.doc + " score:" + score + " id:" + id + " title:" + title + " content:" + content);
}
} catch (Exception e) {
throw new RuntimeException(e);
} finally {
try {
isearcher.close();
directory.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}


测试代码如下所示：
?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
2

import org.apache.lucene.search.ScoreDoc;
import org.junit.AfterClass;
import org.junit.BeforeClass;
import org.junit.Test;
public class LuceneDemoTest {
static LuceneDemo luceneDemo = null ;
@BeforeClass
public static void setUpBeforeClass() throws Exception {
luceneDemo = new LuceneDemo();
}
@AfterClass
public static void tearDownAfterClass() throws Exception {
}
@Test
public void testBulidIndex() {
luceneDemo.bulidIndex();
}
@Test
public void testUpdate() {
luceneDemo.update( 1 , "测试更新" , "更新内容。。。。" );
}
@Test
public void testDelete() {
luceneDemo.delete( 1 );
}
@Test
public void testSearch() {
String where = "title:聚资库 content:学习" ; //类似SQL为：title='聚资库' or content='学习'
//String where = "title:聚资库 +content:学习 -id:1"; //类似SQL为：title='聚资库' and content='学习' and id!=1
//String where = "title:聚资库 -content:学习"; // 类似SQL为：title='聚资库' and content!='学习'
ScoreDoc after = new ScoreDoc( 0 , ( float ) 0.032529574 );
luceneDemo.search(where, after);
//luceneDemo.search(where, null);
}
}
如果想使用庖丁(paoding)分词器，请参考： http://www.juziku.com/wiki/2327.htm

回复
分享到 :
0 人收藏
返回列表
高级模式
B Color Image Link Quote Code Smilies
您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

16级独孤
匿名技术用户

积分:7942463
帖子:1588486
精华:0
+ 关注 私信
期权论坛 期权论坛
期权网络科技版权所有
关于我们
联系我们
加入我们
反馈问题
免责声明
积分充值
统一社会信用代码
积分规则
网站地图
爱文库
下属网站
官方
新浪微博
微信公众号
◆
下载
表情包
App下载
期权论坛 期权论坛

QQ咨询|关于我们|Archiver|手机版|小黑屋|( 辽ICP备15012455号-4 ) Powered by 期权论坛 X3.2 © 2001-2016 期权工具网&期权论坛 Inc.

发布
内容

下载期权论坛手机APP