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
|
/*------------------------------------------------------------------------------
* Copyright (C) 2003-2006 Ben van Klinken and the CLucene Team
*
* Distributable under the terms of either the Apache License (Version 2.0) or
* the GNU Lesser General Public License, as specified in the COPYING file.
------------------------------------------------------------------------------*/
#ifndef _lucene_analysis_snowball_analyser_
#define _lucene_analysis_snowball_analyser_
extern "C" {
#include "lib.h"
#include "unichar.h"
};
#include "CLucene/analysis/AnalysisHeader.h"
CL_CLASS_DEF(util,BufferedReader)
CL_NS_DEF2(analysis,snowball)
/** Filters {@link StandardTokenizer} with {@link StandardFilter}, {@link
* LowerCaseFilter}, {@link StopFilter} and {@link SnowballFilter}.
*
* Available stemmers are listed in {@link net.sf.snowball.ext}. The name of a
* stemmer is the part of the class name before "Stemmer", e.g., the stemmer in
* {@link EnglishStemmer} is named "English".
*/
class CLUCENE_CONTRIBS_EXPORT SnowballAnalyzer: public Analyzer {
char* language;
normalizer_func_t *normalizer;
CLTCSetList* stopSet;
TokenStream *prevstream;
public:
/** Builds the named analyzer with no stop words. */
SnowballAnalyzer(normalizer_func_t *normalizer, const char* language="english");
/** Builds the named analyzer with the given stop words.
*/
SnowballAnalyzer(const char* language, const TCHAR** stopWords);
~SnowballAnalyzer();
/** Constructs a {@link StandardTokenizer} filtered by a {@link
StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}. */
TokenStream* tokenStream(const TCHAR* fieldName, CL_NS(util)::Reader* reader);
TokenStream* tokenStream(const TCHAR* fieldName, CL_NS(util)::Reader* reader, bool deleteReader);
TokenStream* reusableTokenStream(const TCHAR* fieldName, CL_NS(util)::Reader* reader);
};
CL_NS_END2
#endif
|
