JAVA实现中文分词程序_java 中文分词实现

中文分词程序

package test03;
import java.io.IOException;
import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.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.store.Directory;
import org.apache.lucene.store.FSDirectory;

import com.hankcs.lucene.HanLPAnalyzer;

public class Demo2 {

	public static void main(String[] args) {
		try {
			Directory directory=FSDirectory.open(Paths.get("F:/index"));
			IndexReader reader=DirectoryReader.open(directory);
			IndexSearcher searcher=new IndexSearcher(reader);
			String text="我想要苹果手机";
			String field="title";
			Analyzer analyzer=new HanLPAnalyzer();
			QueryParser parser=new QueryParser(field,analyzer);
			Query query=parser.parse(text);
			TopDocs docs=searcher.search(query, 100);
			System.out.println("命中的记录数："+docs.totalHits);
			ScoreDoc[] array=docs.scoreDocs;
			for(ScoreDoc one:array) {
				Document document=searcher.doc(one.doc);
				String id=document.get("id");
				String title=document.get("title");
				System.out.println("商品编号"+id);
				System.out.println("商品名称"+title);
			}
			reader.close();
		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
}


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