1 // class template regex -*- C++ -*-
2
3 // Copyright (C) 2013-2014 Free Software Foundation, Inc.
4 //
5 // This file is part of the GNU ISO C++ Library. This library is free
6 // software; you can redistribute it and/or modify it under the
7 // terms of the GNU General Public License as published by the
8 // Free Software Foundation; either version 3, or (at your option)
9 // any later version.
10
11 // This library is distributed in the hope that it will be useful,
12 // but WITHOUT ANY WARRANTY; without even the implied warranty of
13 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 // GNU General Public License for more details.
15
16 // Under Section 7 of GPL version 3, you are granted additional
17 // permissions described in the GCC Runtime Library Exception, version
18 // 3.1, as published by the Free Software Foundation.
19
20 // You should have received a copy of the GNU General Public License and
21 // a copy of the GCC Runtime Library Exception along with this program;
22 // see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
23 // <http://www.gnu.org/licenses/>.
24
25 /**
26 * @file bits/regex_scanner.h
27 * This is an internal header file, included by other library headers.
28 * Do not attempt to use it directly. @headername{regex}
29 */
30
_GLIBCXX_VISIBILITY(default)31 namespace std _GLIBCXX_VISIBILITY(default)
32 {
33 namespace __detail
34 {
35 _GLIBCXX_BEGIN_NAMESPACE_VERSION
36
37 /**
38 * @addtogroup regex-detail
39 * @{
40 */
41
42 struct _ScannerBase
43 {
44 public:
45 /// Token types returned from the scanner.
46 enum _TokenT
47 {
48 _S_token_anychar,
49 _S_token_ord_char,
50 _S_token_oct_num,
51 _S_token_hex_num,
52 _S_token_backref,
53 _S_token_subexpr_begin,
54 _S_token_subexpr_no_group_begin,
55 _S_token_subexpr_lookahead_begin, // neg if _M_value[0] == 'n'
56 _S_token_subexpr_end,
57 _S_token_bracket_begin,
58 _S_token_bracket_neg_begin,
59 _S_token_bracket_end,
60 _S_token_interval_begin,
61 _S_token_interval_end,
62 _S_token_quoted_class,
63 _S_token_char_class_name,
64 _S_token_collsymbol,
65 _S_token_equiv_class_name,
66 _S_token_opt,
67 _S_token_or,
68 _S_token_closure0,
69 _S_token_closure1,
70 _S_token_ungreedy,
71 _S_token_line_begin,
72 _S_token_line_end,
73 _S_token_word_bound, // neg if _M_value[0] == 'n'
74 _S_token_comma,
75 _S_token_dup_count,
76 _S_token_eof,
77 _S_token_unknown
78 };
79
80 protected:
81 typedef regex_constants::syntax_option_type _FlagT;
82
83 enum _StateT
84 {
85 _S_state_normal,
86 _S_state_in_brace,
87 _S_state_in_bracket,
88 };
89
90 protected:
91 _ScannerBase(_FlagT __flags)
92 : _M_state(_S_state_normal),
93 _M_flags(__flags),
94 _M_escape_tbl(_M_is_ecma()
95 ? _M_ecma_escape_tbl
96 : _M_awk_escape_tbl),
97 _M_spec_char(_M_is_ecma()
98 ? _M_ecma_spec_char
99 : _M_is_basic()
100 ? _M_basic_spec_char
101 : _M_extended_spec_char),
102 _M_at_bracket_start(false)
103 { }
104
105 protected:
106 const char*
107 _M_find_escape(char __c)
108 {
109 auto __it = _M_escape_tbl;
110 for (; __it->first != '\0'; ++__it)
111 if (__it->first == __c)
112 return &__it->second;
113 return nullptr;
114 }
115
116 bool
117 _M_is_ecma() const
118 { return _M_flags & regex_constants::ECMAScript; }
119
120 bool
121 _M_is_basic() const
122 { return _M_flags & (regex_constants::basic | regex_constants::grep); }
123
124 bool
125 _M_is_extended() const
126 {
127 return _M_flags & (regex_constants::extended
128 | regex_constants::egrep
129 | regex_constants::awk);
130 }
131
132 bool
133 _M_is_grep() const
134 { return _M_flags & (regex_constants::grep | regex_constants::egrep); }
135
136 bool
137 _M_is_awk() const
138 { return _M_flags & regex_constants::awk; }
139
140 protected:
141 const std::pair<char, _TokenT> _M_token_tbl[9] =
142 {
143 {'^', _S_token_line_begin},
144 {'$', _S_token_line_end},
145 {'.', _S_token_anychar},
146 {'*', _S_token_closure0},
147 {'+', _S_token_closure1},
148 {'?', _S_token_opt},
149 {'|', _S_token_or},
150 {'\n', _S_token_or}, // grep and egrep
151 {'\0', _S_token_or},
152 };
153 const std::pair<char, char> _M_ecma_escape_tbl[8] =
154 {
155 {'0', '\0'},
156 {'b', '\b'},
157 {'f', '\f'},
158 {'n', '\n'},
159 {'r', '\r'},
160 {'t', '\t'},
161 {'v', '\v'},
162 {'\0', '\0'},
163 };
164 const std::pair<char, char> _M_awk_escape_tbl[11] =
165 {
166 {'"', '"'},
167 {'/', '/'},
168 {'\\', '\\'},
169 {'a', '\a'},
170 {'b', '\b'},
171 {'f', '\f'},
172 {'n', '\n'},
173 {'r', '\r'},
174 {'t', '\t'},
175 {'v', '\v'},
176 {'\0', '\0'},
177 };
178 const char* _M_ecma_spec_char = "^$\\.*+?()[]{}|";
179 const char* _M_basic_spec_char = ".[\\*^$";
180 const char* _M_extended_spec_char = ".[\\()*+?{|^$";
181
182 _StateT _M_state;
183 _FlagT _M_flags;
184 _TokenT _M_token;
185 const std::pair<char, char>* _M_escape_tbl;
186 const char* _M_spec_char;
187 bool _M_at_bracket_start;
188 };
189
190 /**
191 * @brief Scans an input range for regex tokens.
192 *
193 * The %_Scanner class interprets the regular expression pattern in
194 * the input range passed to its constructor as a sequence of parse
195 * tokens passed to the regular expression compiler. The sequence
196 * of tokens provided depends on the flag settings passed to the
197 * constructor: different regular expression grammars will interpret
198 * the same input pattern in syntactically different ways.
199 */
200 template<typename _CharT>
201 class _Scanner
202 : public _ScannerBase
203 {
204 public:
205 typedef const _CharT* _IterT;
206 typedef std::basic_string<_CharT> _StringT;
207 typedef regex_constants::syntax_option_type _FlagT;
208 typedef const std::ctype<_CharT> _CtypeT;
209
210 _Scanner(_IterT __begin, _IterT __end,
211 _FlagT __flags, std::locale __loc);
212
213 void
214 _M_advance();
215
216 _TokenT
217 _M_get_token() const
218 { return _M_token; }
219
220 const _StringT&
221 _M_get_value() const
222 { return _M_value; }
223
224 #ifdef _GLIBCXX_DEBUG
225 std::ostream&
226 _M_print(std::ostream&);
227 #endif
228
229 private:
230 void
231 _M_scan_normal();
232
233 void
234 _M_scan_in_bracket();
235
236 void
237 _M_scan_in_brace();
238
239 void
240 _M_eat_escape_ecma();
241
242 void
243 _M_eat_escape_posix();
244
245 void
246 _M_eat_escape_awk();
247
248 void
249 _M_eat_class(char);
250
251 _IterT _M_current;
252 _IterT _M_end;
253 _CtypeT& _M_ctype;
254 _StringT _M_value;
255 void (_Scanner::* _M_eat_escape)();
256 };
257
258 //@} regex-detail
259 _GLIBCXX_END_NAMESPACE_VERSION
260 } // namespace __detail
261 } // namespace std
262
263 #include <bits/regex_scanner.tcc>
264