blob: f90745001a3bc73df153d4b2d55d388410e79f9f (
plain)
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
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
|
/*
Ousía
Copyright (C) 2014 Benjamin Paaßen, Andreas Stöckel
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
/**
* @file Token.hpp
*
* Definition of the TokenId id and constants for some special tokens.
*
* @author Andreas Stöckel (astoecke@techfak.uni-bielefeld.de)
*/
#ifndef _OUSIA_TOKEN_HPP_
#define _OUSIA_TOKEN_HPP_
#include <cstdint>
#include <limits>
#include <string>
#include <core/common/Location.hpp>
namespace ousia {
/**
* The TokenId is used to give each token id a unique id.
*/
using TokenId = uint32_t;
/**
* Type used for storing token lengths.
*/
using TokenLength = uint16_t;
/**
* Namespace containing constants for TokenId instances with special meaning.
*/
namespace Tokens {
/**
* Token which is not a token.
*/
constexpr TokenId Empty = std::numeric_limits<TokenId>::max();
/**
* Token which represents data (represented as TokenizedData).
*/
constexpr TokenId Data = std::numeric_limits<TokenId>::max() - 1;
/**
* Token which represents a newline token.
*/
constexpr TokenId Newline = std::numeric_limits<TokenId>::max() - 2;
/**
* Token which represents a paragraph token -- issued if two consecutive
* newlines occur with optionally any amout of whitespace between them.
*/
constexpr TokenId Paragraph = std::numeric_limits<TokenId>::max() - 3;
/**
* Token which represents an indentation token -- issued if the indentation of
* this line is larget than the indentation of the previous line.
*/
constexpr TokenId Indentation = std::numeric_limits<TokenId>::max() - 4;
/**
* Maximum token id to be used. Tokens allocated for users should not surpass
* this value.
*/
constexpr TokenId MaxTokenId = std::numeric_limits<TokenId>::max() - 255;
}
/**
* The Token structure describes a token discovered by the Tokenizer or read
* from the TokenizedData struct.
*/
struct Token {
/**
* Id of the id of this token.
*/
TokenId id;
/**
* String that was matched.
*/
std::string content;
/**
* Location from which the string was extracted.
*/
SourceLocation location;
/**
* Default constructor.
*/
Token() : id(Tokens::Empty) {}
/**
* Constructor of the Token struct.
*
* @param id represents the token id.
* @param content is the string content that has been extracted.
* @param location is the location of the extracted string content in the
* source file.
*/
Token(TokenId id, const std::string &content, SourceLocation location)
: id(id), content(content), location(location)
{
}
/**
* Constructor of the Token struct, only initializes the token id
*
* @param id is the id corresponding to the id of the token.
*/
Token(TokenId id) : id(id) {}
/**
* The getLocation function allows the tokens to be directly passed as
* parameter to Logger or LoggableException instances.
*
* @return a reference at the location field
*/
const SourceLocation &getLocation() const { return location; }
};
}
#endif /* _OUSIA_TOKENS_HPP_ */
|
