lucene分词器与搜索

 1 package com.test.lucene;
 2 
 3 import java.io.IOException;
 4 import java.io.StringReader;
 5 
 6 import org.apache.lucene.analysis.Analyzer;
 7 import org.apache.lucene.analysis.TokenStream;
 8 import org.apache.lucene.analysis.cjk.CJKAnalyzer;
 9 import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
10 import org.apache.lucene.analysis.core.KeywordAnalyzer;
11 import org.apache.lucene.analysis.core.SimpleAnalyzer;
12 import org.apache.lucene.analysis.core.StopAnalyzer;
13 import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
14 import org.apache.lucene.analysis.standard.StandardAnalyzer;
15 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
16 
17 /**
18  * 分词器
19  */
20 public class AnalyzerStudy {
21 
22     /**
23      * 分词并打印分词结果
24      * 
25      * @param analyzer
26      *            分词器种类
27      * @param content
28      *            需要分词的内容
29      */
30     private static void print(Analyzer analyzer, String content) {
31         StringReader reader = new StringReader(content);
32         try {
33             TokenStream tokenStream = analyzer.tokenStream("", reader);
34             tokenStream.reset();
35             CharTermAttribute term = tokenStream.getAttribute(CharTermAttribute.class);
36             System.out.println("分词技术" + analyzer.getClass());
37             while (tokenStream.incrementToken()) {
38                 System.out.print(term.toString() + "|");
39             }
40             System.out.println();
41         } catch (IOException e) {
42             e.printStackTrace();
43         }
44     }
45 
46     public static void main(String[] args) {
47         String content = "上海广州， lucene 软件 开发";
48         Analyzer analyzer = null;
49         // 标准分词
50         analyzer = new StandardAnalyzer();
51         print(analyzer, content);
52 
53         // 空格分词
54         analyzer = new WhitespaceAnalyzer();
55         print(analyzer, content);
56 
57         // 简单分词
58         analyzer = new SimpleAnalyzer();
59         print(analyzer, content);
60 
61         // 二分法分词
62         analyzer = new CJKAnalyzer();
63         print(analyzer, content);
64 
65         // 关键字分词
66         analyzer = new KeywordAnalyzer();
67         print(analyzer, content);
68 
69         // 被忽略词分词
70         analyzer = new StopAnalyzer();
71         print(analyzer, content);
72 
73         // 中文分词
74         analyzer = new SmartChineseAnalyzer();
75         print(analyzer, content);
76     }
77 
78 }

 1 package com.test.lucene;
 2 
 3 import org.apache.lucene.analysis.Analyzer;
 4 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 5 import org.apache.lucene.index.Term;
 6 import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
 7 import org.apache.lucene.queryparser.classic.ParseException;
 8 import org.apache.lucene.queryparser.classic.QueryParser;
 9 import org.apache.lucene.search.BooleanClause.Occur;
10 import org.apache.lucene.search.BooleanQuery;
11 import org.apache.lucene.search.PhraseQuery;
12 import org.apache.lucene.search.PrefixQuery;
13 import org.apache.lucene.search.Query;
14 import org.apache.lucene.search.TermQuery;
15 import org.apache.lucene.search.TermRangeQuery;
16 
17 /**
18  * 查询条件
19  */
20 public class QueryStudy {
21     public static void main(String[] args) {
22         // 搜索关键词
23         String keyword = "上海";
24         // 搜索域名
25         String field = "name";
26         // 搜索多个域的域名数组
27         String[] fields = { "name", "content" };
28         // Query 创建过程中的分词技术
29         Analyzer analyzer = new StandardAnalyzer();
30         Query query = null;
31         // 对单个域创建查询语句
32         QueryParser parser = new QueryParser(field, analyzer);
33         try {
34             query = parser.parse(keyword);
35         } catch (ParseException e) {
36             e.printStackTrace();
37         }
38         System.out.println(QueryParser.class + " " + query.toString());
39 
40         // 对多个域创建查询语句
41         MultiFieldQueryParser parser2 = new MultiFieldQueryParser(fields, analyzer);
42         try {
43             query = parser2.parse(keyword);
44         } catch (ParseException e) {
45             e.printStackTrace();
46         }
47         System.out.println(MultiFieldQueryParser.class + " " + query.toString());
48 
49         // 词条查询语句
50         query = new TermQuery(new Term(field, keyword));
51         System.out.println(TermQuery.class + " " + query.toString());
52 
53         // 前缀查询语句
54         query = new PrefixQuery(new Term(field, keyword));
55         System.out.println(PrefixQuery.class + " " + query.toString());
56 
57         // 多余查询语句
58         PhraseQuery query2 = new PhraseQuery();
59         // 设置短语之间的最大距离
60         query2.add(new Term(field, "上海"));
61         query2.add(new Term(field, "lucene开发"));
62         System.out.println(PhraseQuery.class + " " + query2.toString());
63 
64         // 通配符查询语句，Lucene中有 * ? 两个通配符， *表示任意多个字符，?表示一个任意字符
65         query = TermRangeQuery.newStringRange(field, "abc", "azz", false, false);
66         System.out.println(TermRangeQuery.class + " " + query.toString());
67 
68         // 布尔查询
69         BooleanQuery query3 = new BooleanQuery();
70         query3.add(new TermQuery(new Term(field, "上海")), Occur.SHOULD);
71         query3.add(new TermQuery(new Term(field, "lucene")), Occur.SHOULD);
72         query3.add(new TermQuery(new Term(field, "案例")), Occur.MUST_NOT);
73         System.out.println(BooleanQuery.class + " " + query3.toString());
74     }
75 }