SHOGUN
v3.0.0
Main Page
Related Pages
Modules
Classes
Files
File List
File Members
All
Classes
Namespaces
Files
Functions
Variables
Typedefs
Enumerations
Enumerator
Friends
Macros
Groups
Pages
src
shogun
lib
Tokenizer.h
Go to the documentation of this file.
1
/*
2
* This program is free software; you can redistribute it and/or modify
3
* it under the terms of the GNU General Public License as published by
4
* the Free Software Foundation; either version 3 of the License, or
5
* (at your option) any later version.
6
*
7
* Written (W) 2013 Evangelos Anagnostopoulos
8
* Copyright (C) 2013 Evangelos Anagnostopoulos
9
*/
10
11
#ifndef _TOKENIZER__H__
12
#define _TOKENIZER__H__
13
14
#include <
shogun/base/SGObject.h
>
15
#include <
shogun/lib/SGString.h
>
16
#include <
shogun/lib/SGVector.h
>
17
18
namespace
shogun
19
{
20
class
CSGObject;
21
template
<
class
T>
class
SGVector;
22
27
class
CTokenizer
:
public
CSGObject
28
{
29
public
:
31
CTokenizer
();
32
34
CTokenizer
(
const
CTokenizer
& orig);
35
37
virtual
~CTokenizer
() { };
38
43
virtual
void
set_text
(
SGVector<char>
txt);
44
50
virtual
bool
has_next
()=0;
51
58
virtual
index_t
next_token_idx
(
index_t
& start)=0;
59
64
virtual
CTokenizer
*
get_copy
()=0;
65
66
private
:
67
void
init();
68
69
protected
:
71
SGVector<char>
text
;
72
};
73
}
74
75
#endif
/* _TOKENIZER__H__ */
SHOGUN
Machine Learning Toolbox - Documentation