HanLPTokenizer HanLP分词器
anlp在功能上的扩展主要体现在以下几个方面:
•关键词提取
•自动摘要
•短语提取
•拼音转换
•简繁转换
•文本推荐
下面是 hanLP分词器的代码
注：使用maven依赖
com.hankcs
hanlp
portable-1.3.4
使用了java8进行处理
import java.util.ArrayList;
import java.util.List;
import java.util.stream.Collectors;
import org.apache.commons.lang3.StringUtils;
import com.hankcs.hanlp.seg.Segment;
import com.hankcs.hanlp.seg.Dijkstra.DijkstraSegment;
import com.hankcs.hanlp.seg.NShort.NShortSegment;
import com.hankcs.hanlp.tokenizer.IndexTokenizer;
import com.hankcs.hanlp.tokenizer.NLPTokenizer;
import com.hankcs.hanlp.tokenizer.SpeedTokenizer;
import com.hankcs.hanlp.tokenizer.StandardTokenizer;
public class HanLPTokenizer {
private static final Segment N_SHORT_SEGMENT = new NShortSegment().enableCustomDictionary(false)
.enablePlaceRecognize(true).enableOrganizationRecognize(true);
private static final Segment DIJKSTRA_SEGMENT = new DijkstraSegment().enableCustomDictionary(false)
.enablePlaceRecognize(true).enableOrganizationRecognize(true);
/**
- 标准分词
- @param text
- @return
*/
public static List standard(String text) {
List list = new ArrayList();
StandardTokenizer.segment(text).forEach(term -> {
if (StringUtils.isNotBlank(term.word)) {
list.add(term.word);
}
});
return list.stream().distinct().collect(Collectors.toList());
}
/**
- NLP分词
- @param text
- @return
*/
public static List nlp(String text) {
List list = new ArrayList();
NLPTokenizer.segment(text).forEach(term -> {
if (StringUtils.isNotBlank(term.word)) {
list.add(term.word);
}
});
return list.stream().distinct().collect(Collectors.toList());
}
/**
- 索引分词
- @param text
- @return
*/
public static List index(String text) {
List list = new ArrayList();
IndexTokenizer.segment(text).forEach(term -> {
if (StringUtils.isNotBlank(term.word)) {
list.add(term.word);
}
});
return list.stream().distinct().collect(Collectors.toList());
}
/**
- 极速词典分词
- @param text
- @return
*/
public static List speed(String text) {
List list = new ArrayList();
SpeedTokenizer.segment(text).forEach(term -> {
if (StringUtils.isNotBlank(term.word)) {
list.add(term.word);
}
});
return list;
}
/**
- N-最短路径分词
- @param text
- @return
*/
public static List nShort(String text) {
List list = new ArrayList();
N_SHORT_SEGMENT.seg(text).forEach(term -> {
if (StringUtils.isNotBlank(term.word)) {
list.add(term.word);
}
});
return list.stream().distinct().collect(Collectors.toList());
}
/**
- 最短路径分词
- @param text
- @return
*/
public static List shortest(String text) {
List list = new ArrayList();
DIJKSTRA_SEGMENT.seg(text).forEach(term -> {
if (StringUtils.isNotBlank(term.word)) {
list.add(term.word);
}
});
return list.stream().distinct().collect(Collectors.toList());
}
public static void main(String[] args) {
String text = "测试勿动12";
System.out.println("标准分词:" + standard(text));
System.out.println("NLP分词:" + nlp(text));
System.out.println("索引分词:" + index(text));
System.out.println("N-最短路径分词:" + nShort(text));
System.out.println("最短路径分词分词:" + shortest(text));
System.out.println("极速词典分词:" + speed(text));
}
}
文章来源于猴德华的博客
