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
|
/*
** Copyright (C) 2017 Dirk-Jan C. Binnema <djcb@djcbsoftware.nl>
**
** This library is free software; you can redistribute it and/or
** modify it under the terms of the GNU Lesser General Public License
** as published by the Free Software Foundation; either version 2.1
** of the License, or (at your option) any later version.
**
** This library 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
** Lesser General Public License for more details.
**
** You should have received a copy of the GNU Lesser General Public
** License along with this library; if not, write to the Free
** Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA
** 02110-1301, USA.
*/
#ifndef __TOKENIZER_HH__
#define __TOKENIZER_HH__
#include <string>
#include <vector>
#include <deque>
#include <ostream>
#include <stdexcept>
// A simple tokenizer, which turns a string into a deque of tokens
//
// It recognizes '(', ')', '*' 'and', 'or', 'xor', 'not'
//
// Note that even if we recognizes those at the lexical level, they might be demoted to mere strings
// when we're creating the parse tree.
//
// Furthermore, we detect ranges ("a..b") and regexps (/../) at the parser level, since we need a
// bit more context to resolve ambiguities.
namespace Mux {
// A token
struct Token {
enum class Type {
Data, /**< e .g., banana or date:..456 */
// Brackets
Open, /**< ( */
Close, /**< ) */
// Unops
Not, /**< logical not*/
// Binops
And, /**< logical and */
Or, /**< logical not */
Xor, /**< logical xor */
Empty, /**< nothing */
};
size_t pos{}; /**< position in string */
Type type{}; /**< token type */
const std::string str{}; /**< data for this token */
/**
* operator==
*
* @param rhs right-hand side
*
* @return true if rhs is equal to this; false otherwise
*/
bool operator==(const Token& rhs) const {
return pos == rhs.pos &&
type == rhs.type &&
str == rhs.str;
}
};
/**
* operator<<
*
* @param os an output stream
* @param t a token type
*
* @return the updated output stream
*/
inline std::ostream&
operator<< (std::ostream& os, Token::Type t)
{
switch (t) {
case Token::Type::Data: os << "<data>"; break;
case Token::Type::Open: os << "<open>"; break;
case Token::Type::Close: os << "<close>";break;
case Token::Type::Not: os << "<not>"; break;
case Token::Type::And: os << "<and>"; break;
case Token::Type::Or: os << "<or>"; break;
case Token::Type::Xor: os << "<xor>"; break;
default: // can't happen, but pacify compiler
throw std::runtime_error ("<<bug>>");
}
return os;
}
/**
* operator<<
*
* @param os an output stream
* @param t a token
*
* @return the updated output stream
*/
inline std::ostream&
operator<< (std::ostream& os, const Token& t)
{
os << t.pos << ": " << t.type;
if (!t.str.empty())
os << " [" << t.str << "]";
return os;
}
/**
* Tokenize a string into a vector of tokens. The tokenization always succeeds, ie., ignoring errors
* such a missing end-".
*
* @param s a string
*
* @return a deque of tokens
*/
using Tokens = std::deque<Token>;
Tokens tokenize (const std::string& s);
} // namespace Mux
#endif /* __TOKENIZER_HH__ */
|
