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
| /**
* @Description:
* @Author: lizhang
* @CreateDate: 2018/7/31 22:35
* @UpdateDate: 2018/7/31 22:35
* @Version: 1.0
*/
import org.wltea.analyzer.core.IKSegmenter;
import org.wltea.analyzer.core.Lexeme;
import java.io.IOException;
import java.io.StringReader;
import java.util.*;
public class Test {
/**
* 对语句进行分词
*
* @param text 语句
* @return 分词后的集合
* @throws IOException
*/
private static Map segment(String text) throws IOException {
Map<String, Integer> map = new HashMap<String, Integer>();
StringReader re = new StringReader(text);
IKSegmenter ik = new IKSegmenter(re, false);//true 使用smart分词，false使用最小颗粒分词
Lexeme lex;
while ((lex = ik.next()) != null) {
if (lex.getLexemeText().length() > 1) {
if (map.containsKey(lex.getLexemeText())) {
map.put(lex.getLexemeText(), map.get(lex.getLexemeText()) + 1);
} else {
map.put(lex.getLexemeText(), 1);
}
}
}
return map;
}
public static void main(String[] args) throws IOException {
Map<String, Integer> map = segment("中国，中国，我爱你");
System.out.println(map.toString());
}
}
|
