FuzzyQuery:
创建索引:
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
|
IndexWriter writer =
new
IndexWriter(path,
new
StandardAnalyzer(),
false
);
writer.setUseCompoundFile(
false
);
Document doc1 =
new
Document();
Document doc2 =
new
Document();
Document doc3 =
new
Document();
Document doc4 =
new
Document();
Document doc5 =
new
Document();
Document doc6 =
new
Document();
Field f1 =
new
Field(
"content"
,
"word"
, Field.Store.YES,
Field.Index.TOKENIZED);
Field f2 =
new
Field(
"content"
,
"work"
, Field.Store.YES,
Field.Index.TOKENIZED);
Field f3 =
new
Field(
"content"
,
"seed"
, Field.Store.YES,
Field.Index.TOKENIZED);
Field f4 =
new
Field(
"content"
,
"sword"
, Field.Store.YES,
Field.Index.TOKENIZED);
Field f5 =
new
Field(
"content"
,
"world"
, Field.Store.YES,
Field.Index.TOKENIZED);
Field f6 =
new
Field(
"content"
,
"ford"
, Field.Store.YES,
Field.Index.TOKENIZED);
doc1.add(f1);
doc2.add(f2);
doc3.add(f3);
doc4.add(f4);
doc5.add(f5);
doc6.add(f6);
writer.addDocument(doc1);
writer.addDocument(doc2);
writer.addDocument(doc3);
writer.addDocument(doc4);
writer.addDocument(doc5);
writer.addDocument(doc6);
writer.close();
|
注:IndexWriter中的create的变量值一般设为true
搜索:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
|
IndexSearcher searcher =
new
IndexSearcher(path);
//构建一个Term,然后对其进行模糊查找
Term t =
new
Term(
"content"
,
"work"
);
FuzzyQuery query =
new
FuzzyQuery(t);
//FuzzyQuery还有两个构造函数,来限制模糊匹配的程度
// 在FuzzyQuery中,默认的匹配度是0.5,当这个值越小时,通过模糊查找出的文档的匹配程度就
// 越低,查出的文档量就越多,反之亦然
FuzzyQuery query1 =
new
FuzzyQuery(t,
0
.1f);
FuzzyQuery query2 =
new
FuzzyQuery(t,
0
.1f,
1
);
Hits hits = searcher.search(query2);
for
(
int
i =
0
; i < hits.length(); i++) {
System.out.println(hits.doc(i));
}
searcher.close();
|
模糊搜索的三种构造函数,具体讲一下参数的用法(以第三个为例);
第一个参数当然是词条对象,第二个参数指的是levenshtein算法的最小相似度,第三个参数指的是要有多少个前缀字母完全匹配:
WildCardQuery:
通配符就更简单了,只要知道“*”表示0到多个字符,而使用“?”表示一个字符就行了:
1
2
3
4
5
6
7
8
|
IndexSearcher searcher=
new
IndexSearcher(path);
Term t1=
new
Term(
"content"
,
"?o*"
);
WildcardQuery query=
new
WildcardQuery(t1);
Hits hits=searcher.search(query);
for
(
int
i=
0
;i<hits.length();i++)
{
System.out.println(hits.doc(i));
}
|
That“s all!
http://my.oschina.net/MrMichael/blog/338925