Lucene++ - a full-featured, c++ search engine
API Documentation


KeywordTokenizer.h
Go to the documentation of this file.
1 // Copyright (c) 2009-2014 Alan Wright. All rights reserved.
3 // Distributable under the terms of either the Apache License (Version 2.0)
4 // or the GNU Lesser General Public License.
6 
7 #ifndef KEYWORDTOKENIZER_H
8 #define KEYWORDTOKENIZER_H
9 
10 #include "Tokenizer.h"
11 
12 namespace Lucene {
13 
15 class LPPAPI KeywordTokenizer : public Tokenizer {
16 public:
17  KeywordTokenizer(const ReaderPtr& input);
18  KeywordTokenizer(const ReaderPtr& input, int32_t bufferSize);
19  KeywordTokenizer(const AttributeSourcePtr& source, const ReaderPtr& input, int32_t bufferSize);
20  KeywordTokenizer(const AttributeFactoryPtr& factory, const ReaderPtr& input, int32_t bufferSize);
21 
22  virtual ~KeywordTokenizer();
23 
25 
26 protected:
27  static const int32_t DEFAULT_BUFFER_SIZE;
28 
29  bool done;
30  int32_t finalOffset;
33 
34 protected:
35  void init(int32_t bufferSize);
36 
37 public:
38  virtual bool incrementToken();
39  virtual void end();
40  virtual void reset();
41 };
42 
43 }
44 
45 #endif
Lucene::KeywordTokenizer::init
void init(int32_t bufferSize)
Lucene::KeywordTokenizer::end
virtual void end()
This method is called by the consumer after the last token has been consumed, after incrementToken() ...
LUCENE_CLASS
#define LUCENE_CLASS(Name)
Definition: LuceneObject.h:24
Lucene::KeywordTokenizer::KeywordTokenizer
KeywordTokenizer(const ReaderPtr &input, int32_t bufferSize)
Lucene::ReaderPtr
boost::shared_ptr< Reader > ReaderPtr
Definition: LuceneTypes.h:547
Lucene::KeywordTokenizer::finalOffset
int32_t finalOffset
Definition: KeywordTokenizer.h:30
Lucene::KeywordTokenizer::~KeywordTokenizer
virtual ~KeywordTokenizer()
Lucene::KeywordTokenizer::done
bool done
Definition: KeywordTokenizer.h:29
Lucene::KeywordTokenizer::termAtt
TermAttributePtr termAtt
Definition: KeywordTokenizer.h:31
Lucene
Definition: AbstractAllTermDocs.h:12
Lucene::OffsetAttributePtr
boost::shared_ptr< OffsetAttribute > OffsetAttributePtr
Definition: LuceneTypes.h:40
Lucene::AttributeSourcePtr
boost::shared_ptr< AttributeSource > AttributeSourcePtr
Definition: LuceneTypes.h:520
Lucene::KeywordTokenizer
Emits the entire input as a single token.
Definition: KeywordTokenizer.h:15
Lucene::Tokenizer
A Tokenizer is a TokenStream whose input is a Reader.
Definition: Tokenizer.h:20
Lucene::KeywordTokenizer::KeywordTokenizer
KeywordTokenizer(const AttributeFactoryPtr &factory, const ReaderPtr &input, int32_t bufferSize)
Lucene::KeywordTokenizer::DEFAULT_BUFFER_SIZE
static const int32_t DEFAULT_BUFFER_SIZE
Definition: KeywordTokenizer.h:24
Lucene::TermAttributePtr
boost::shared_ptr< TermAttribute > TermAttributePtr
Definition: LuceneTypes.h:58
Lucene::KeywordTokenizer::KeywordTokenizer
KeywordTokenizer(const AttributeSourcePtr &source, const ReaderPtr &input, int32_t bufferSize)
Lucene::KeywordTokenizer::KeywordTokenizer
KeywordTokenizer(const ReaderPtr &input)
Tokenizer.h
Lucene::KeywordTokenizer::offsetAtt
OffsetAttributePtr offsetAtt
Definition: KeywordTokenizer.h:32
Lucene::KeywordTokenizer::reset
virtual void reset()
Resets this stream to the beginning. This is an optional operation, so subclasses may or may not impl...
Lucene::KeywordTokenizer::incrementToken
virtual bool incrementToken()
Consumers (ie., IndexWriter) use this method to advance the stream to the next token....
Lucene::AttributeFactoryPtr
boost::shared_ptr< AttributeFactory > AttributeFactoryPtr
Definition: LuceneTypes.h:519

clucene.sourceforge.net