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
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
|
// Copyright (c) 2001-2011 Hartmut Kaiser
//
// Distributed under the Boost Software License, Version 1.0. (See accompanying
// file LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt)
#include <boost/spirit/include/lex_lexertl.hpp>
#include <boost/spirit/include/lex_lexertl_position_token.hpp>
#include <boost/core/lightweight_test.hpp>
#include <boost/phoenix/object.hpp>
#include <boost/phoenix/operator.hpp>
#include <boost/phoenix/stl/container.hpp>
namespace lex = boost::spirit::lex;
namespace phoenix = boost::phoenix;
namespace mpl = boost::mpl;
///////////////////////////////////////////////////////////////////////////////
enum tokenids
{
ID_INT = 1000,
ID_DOUBLE
};
template <typename Lexer>
struct token_definitions : lex::lexer<Lexer>
{
token_definitions()
{
this->self.add_pattern("HEXDIGIT", "[0-9a-fA-F]");
this->self.add_pattern("OCTALDIGIT", "[0-7]");
this->self.add_pattern("DIGIT", "[0-9]");
this->self.add_pattern("OPTSIGN", "[-+]?");
this->self.add_pattern("EXPSTART", "[eE][-+]");
this->self.add_pattern("EXPONENT", "[eE]{OPTSIGN}{DIGIT}+");
// define tokens and associate them with the lexer
int_ = "(0x|0X){HEXDIGIT}+|0{OCTALDIGIT}*|{OPTSIGN}[1-9]{DIGIT}*";
int_.id(ID_INT);
double_ = "{OPTSIGN}({DIGIT}*\\.{DIGIT}+|{DIGIT}+\\.){EXPONENT}?|{DIGIT}+{EXPONENT}";
double_.id(ID_DOUBLE);
whitespace = "[ \t\n]+";
this->self =
double_
| int_
| whitespace[ lex::_pass = lex::pass_flags::pass_ignore ]
;
}
lex::token_def<lex::omit> int_;
lex::token_def<lex::omit> double_;
lex::token_def<lex::omit> whitespace;
};
template <typename Lexer>
struct token_definitions_with_state : lex::lexer<Lexer>
{
token_definitions_with_state()
{
this->self.add_pattern("HEXDIGIT", "[0-9a-fA-F]");
this->self.add_pattern("OCTALDIGIT", "[0-7]");
this->self.add_pattern("DIGIT", "[0-9]");
this->self.add_pattern("OPTSIGN", "[-+]?");
this->self.add_pattern("EXPSTART", "[eE][-+]");
this->self.add_pattern("EXPONENT", "[eE]{OPTSIGN}{DIGIT}+");
this->self.add_state();
this->self.add_state("INT");
this->self.add_state("DOUBLE");
// define tokens and associate them with the lexer
int_ = "(0x|0X){HEXDIGIT}+|0{OCTALDIGIT}*|{OPTSIGN}[1-9]{DIGIT}*";
int_.id(ID_INT);
double_ = "{OPTSIGN}({DIGIT}*\\.{DIGIT}+|{DIGIT}+\\.){EXPONENT}?|{DIGIT}+{EXPONENT}";
double_.id(ID_DOUBLE);
whitespace = "[ \t\n]+";
this->self("*") =
double_ [ lex::_state = "DOUBLE"]
| int_ [ lex::_state = "INT" ]
| whitespace[ lex::_pass = lex::pass_flags::pass_ignore ]
;
}
lex::token_def<lex::omit> int_;
lex::token_def<lex::omit> double_;
lex::token_def<lex::omit> whitespace;
};
///////////////////////////////////////////////////////////////////////////////
template <typename Token>
inline bool
test_token_ids(int const* ids, std::vector<Token> const& tokens)
{
for (std::size_t i = 0, len = tokens.size(); i < len; ++i)
{
if (*ids == -1)
return false; // reached end of expected data
if (tokens[i].id() != static_cast<std::size_t>(*ids)) // token id must match
return false;
++ids;
}
return (*ids == -1) ? true : false;
}
template <typename Token>
inline bool
test_token_states(std::size_t const* states, std::vector<Token> const& tokens)
{
for (std::size_t i = 0, len = tokens.size(); i < len; ++i)
{
if (*states == std::size_t(-1))
return false; // reached end of expected data
if (tokens[i].state() != *states) // token state must match
return false;
++states;
}
return (*states == std::size_t(-1)) ? true : false;
}
///////////////////////////////////////////////////////////////////////////////
struct position_type
{
std::size_t begin, end;
};
template <typename Iterator, typename Token>
inline bool
test_token_positions(Iterator begin, position_type const* positions,
std::vector<Token> const& tokens)
{
for (std::size_t i = 0, len = tokens.size(); i < len; ++i)
{
if (positions->begin == std::size_t(-1) &&
positions->end == std::size_t(-1))
{
return false; // reached end of expected data
}
boost::iterator_range<Iterator> matched = tokens[i].matched();
std::size_t start = std::distance(begin, matched.begin());
std::size_t end = std::distance(begin, matched.end());
// position must match
if (start != positions->begin || end != positions->end)
return false;
++positions;
}
return (positions->begin == std::size_t(-1) &&
positions->end == std::size_t(-1)) ? true : false;
}
///////////////////////////////////////////////////////////////////////////////
int main()
{
typedef std::string::iterator base_iterator_type;
std::string input(" 01 1.2 -2 0x3 2.3e6 -3.4");
int ids[] = { ID_INT, ID_DOUBLE, ID_INT, ID_INT, ID_DOUBLE, ID_DOUBLE, -1 };
std::size_t states[] = { 0, 1, 2, 1, 1, 2, std::size_t(-1) };
position_type positions[] =
{
{ 1, 3 }, { 4, 7 }, { 8, 10 }, { 11, 14 }, { 15, 20 }, { 21, 25 },
{ std::size_t(-1), std::size_t(-1) }
};
// token type: token id, iterator_pair as token value, no state
{
typedef lex::lexertl::token<
base_iterator_type, mpl::vector<>, mpl::false_> token_type;
typedef lex::lexertl::actor_lexer<token_type> lexer_type;
token_definitions<lexer_type> lexer;
std::vector<token_type> tokens;
base_iterator_type first = input.begin();
using phoenix::arg_names::_1;
BOOST_TEST(lex::tokenize(first, input.end(), lexer
, phoenix::push_back(phoenix::ref(tokens), _1)));
BOOST_TEST(test_token_ids(ids, tokens));
}
{
typedef lex::lexertl::position_token<
base_iterator_type, mpl::vector<>, mpl::false_> token_type;
typedef lex::lexertl::actor_lexer<token_type> lexer_type;
token_definitions<lexer_type> lexer;
std::vector<token_type> tokens;
base_iterator_type first = input.begin();
using phoenix::arg_names::_1;
BOOST_TEST(lex::tokenize(first, input.end(), lexer
, phoenix::push_back(phoenix::ref(tokens), _1)));
BOOST_TEST(test_token_ids(ids, tokens));
BOOST_TEST(test_token_positions(input.begin(), positions, tokens));
}
// token type: holds token id, state, iterator_pair as token value
{
typedef lex::lexertl::token<
base_iterator_type, mpl::vector<>, mpl::true_> token_type;
typedef lex::lexertl::actor_lexer<token_type> lexer_type;
token_definitions_with_state<lexer_type> lexer;
std::vector<token_type> tokens;
base_iterator_type first = input.begin();
using phoenix::arg_names::_1;
BOOST_TEST(lex::tokenize(first, input.end(), lexer
, phoenix::push_back(phoenix::ref(tokens), _1)));
BOOST_TEST(test_token_ids(ids, tokens));
BOOST_TEST(test_token_states(states, tokens));
}
{
typedef lex::lexertl::position_token<
base_iterator_type, mpl::vector<>, mpl::true_> token_type;
typedef lex::lexertl::actor_lexer<token_type> lexer_type;
token_definitions_with_state<lexer_type> lexer;
std::vector<token_type> tokens;
base_iterator_type first = input.begin();
using phoenix::arg_names::_1;
BOOST_TEST(lex::tokenize(first, input.end(), lexer
, phoenix::push_back(phoenix::ref(tokens), _1)));
BOOST_TEST(test_token_ids(ids, tokens));
BOOST_TEST(test_token_states(states, tokens));
BOOST_TEST(test_token_positions(input.begin(), positions, tokens));
}
return boost::report_errors();
}
|
