【代码】Lucene快速入门

发表于 更新于 分类于 阅读次数：

前言

用LuceneAPI生成索引

代码

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
package test;

import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.LongPoint;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.FSDirectory;
import org.junit.Test;

import java.io.File;
import java.io.IOException;

public class Test1 {

    String[] a = {
            "3, 华为 - 电脑, 爆款",
            "4, 华为手机, 旗舰",
            "5, 联想 - Thinkpad, 商务本",
            "6, 联想手机, 自拍神器"
    };

    @Test
    public void test1() throws IOException {
        // 创建索引
        // 存放索引数据的文件夹
        FSDirectory f = FSDirectory.open(new File("~/Downloads/File").toPath());
        // 配置中文分词器
        IndexWriterConfig conf = new IndexWriterConfig(new SmartChineseAnalyzer());
        // 索引输出工具
        IndexWriter writer = new IndexWriter(f, conf);
        // 遍历文档，输出索引
        for (String s:
             a) {
            String[] arr = s.split(",");
            // 用Document封装商品的数据
            // 分字段进行封装
            Document doc = new Document();
            doc.add(new LongPoint("id", Long.parseLong(arr[0])));
            doc.add(new TextField("title", arr[1], Field.Store.YES));
            doc.add(new TextField("sellPoint", arr[2], Field.Store.YES));

            writer.addDocument(doc);
        }

        writer.flush();
        writer.close();
    }

    @Test
    public void test2() throws IOException {
        // 在索引中搜索数据
        // 文件夹
        FSDirectory d = FSDirectory.open(new File("~/Downloads/File").toPath());
        // 索引读取工具
        DirectoryReader reader = DirectoryReader.open(d);
        // 搜索器工具
        IndexSearcher searcher = new IndexSearcher(reader);
        // 封装搜索的关键词
        TermQuery query = new TermQuery(new Term("title", "华为"));
        // 搜索，得到结果：[{doc:3, score:0.679}, {doc:1, score:0.515}]
        TopDocs topDocs = searcher.search(query, 20);
        // 遍历
        for (ScoreDoc sd : topDocs.scoreDocs) {
            int id = sd.doc;
            float score = sd.score;
            Document doc = searcher.doc(id);
            System.out.println(id);
            System.out.println(score);
            System.out.println(doc.get("id"));
            System.out.println(doc.get("title"));
            System.out.println(doc.get("sellPoint"));
            System.out.println("------------------");
        }


    }

}

完成