1 // class template regex -*- C++ -*-
2 
3 // Copyright (C) 2013-2016 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_line_begin,
71       _S_token_line_end,
72       _S_token_word_bound, // neg if _M_value[0] == 'n'
73       _S_token_comma,
74       _S_token_dup_count,
75       _S_token_eof,
76       _S_token_unknown
77     };
78 
79   protected:
80     typedef regex_constants::syntax_option_type _FlagT;
81 
82     enum _StateT
83     {
84       _S_state_normal,
85       _S_state_in_brace,
86       _S_state_in_bracket,
87     };
88 
89   protected:
90     _ScannerBase(_FlagT __flags)
91     : _M_state(_S_state_normal),
92     _M_flags(__flags),
93     _M_escape_tbl(_M_is_ecma()
94 		  ? _M_ecma_escape_tbl
95 		  : _M_awk_escape_tbl),
96     _M_spec_char(_M_is_ecma()
97 		 ? _M_ecma_spec_char
98 		 : _M_flags & regex_constants::basic
99 		 ? _M_basic_spec_char
100 		 : _M_flags & regex_constants::extended
101 		 ? _M_extended_spec_char
102 		 : _M_flags & regex_constants::grep
103 		 ?  ".[\\*^$\n"
104 		 : _M_flags & regex_constants::egrep
105 		 ? ".[\\()*+?{|^$\n"
106 		 : _M_flags & regex_constants::awk
107 		 ? _M_extended_spec_char
108 		 : nullptr),
109     _M_at_bracket_start(false)
110     { __glibcxx_assert(_M_spec_char); }
111 
112   protected:
113     const char*
114     _M_find_escape(char __c)
115     {
116       auto __it = _M_escape_tbl;
117       for (; __it->first != '\0'; ++__it)
118 	if (__it->first == __c)
119 	  return &__it->second;
120       return nullptr;
121     }
122 
123     bool
124     _M_is_ecma() const
125     { return _M_flags & regex_constants::ECMAScript; }
126 
127     bool
128     _M_is_basic() const
129     { return _M_flags & (regex_constants::basic | regex_constants::grep); }
130 
131     bool
132     _M_is_extended() const
133     {
134       return _M_flags & (regex_constants::extended
135 			 | regex_constants::egrep
136 			 | regex_constants::awk);
137     }
138 
139     bool
140     _M_is_grep() const
141     { return _M_flags & (regex_constants::grep | regex_constants::egrep); }
142 
143     bool
144     _M_is_awk() const
145     { return _M_flags & regex_constants::awk; }
146 
147   protected:
148     // TODO: Make them static in the next abi change.
149     const std::pair<char, _TokenT> _M_token_tbl[9] =
150       {
151 	{'^', _S_token_line_begin},
152 	{'$', _S_token_line_end},
153 	{'.', _S_token_anychar},
154 	{'*', _S_token_closure0},
155 	{'+', _S_token_closure1},
156 	{'?', _S_token_opt},
157 	{'|', _S_token_or},
158 	{'\n', _S_token_or}, // grep and egrep
159 	{'\0', _S_token_or},
160       };
161     const std::pair<char, char> _M_ecma_escape_tbl[8] =
162       {
163 	{'0', '\0'},
164 	{'b', '\b'},
165 	{'f', '\f'},
166 	{'n', '\n'},
167 	{'r', '\r'},
168 	{'t', '\t'},
169 	{'v', '\v'},
170 	{'\0', '\0'},
171       };
172     const std::pair<char, char> _M_awk_escape_tbl[11] =
173       {
174 	{'"', '"'},
175 	{'/', '/'},
176 	{'\\', '\\'},
177 	{'a', '\a'},
178 	{'b', '\b'},
179 	{'f', '\f'},
180 	{'n', '\n'},
181 	{'r', '\r'},
182 	{'t', '\t'},
183 	{'v', '\v'},
184 	{'\0', '\0'},
185       };
186     const char* _M_ecma_spec_char = "^$\\.*+?()[]{}|";
187     const char* _M_basic_spec_char = ".[\\*^$";
188     const char* _M_extended_spec_char = ".[\\()*+?{|^$";
189 
190     _StateT                       _M_state;
191     _FlagT                        _M_flags;
192     _TokenT                       _M_token;
193     const std::pair<char, char>*  _M_escape_tbl;
194     const char*                   _M_spec_char;
195     bool                          _M_at_bracket_start;
196   };
197 
198   /**
199    * @brief Scans an input range for regex tokens.
200    *
201    * The %_Scanner class interprets the regular expression pattern in
202    * the input range passed to its constructor as a sequence of parse
203    * tokens passed to the regular expression compiler.  The sequence
204    * of tokens provided depends on the flag settings passed to the
205    * constructor: different regular expression grammars will interpret
206    * the same input pattern in syntactically different ways.
207    */
208   template<typename _CharT>
209     class _Scanner
210     : public _ScannerBase
211     {
212     public:
213       typedef const _CharT*                                       _IterT;
214       typedef std::basic_string<_CharT>                           _StringT;
215       typedef regex_constants::syntax_option_type                 _FlagT;
216       typedef const std::ctype<_CharT>                            _CtypeT;
217 
218       _Scanner(_IterT __begin, _IterT __end,
219 	       _FlagT __flags, std::locale __loc);
220 
221       void
222       _M_advance();
223 
224       _TokenT
225       _M_get_token() const
226       { return _M_token; }
227 
228       const _StringT&
229       _M_get_value() const
230       { return _M_value; }
231 
232 #ifdef _GLIBCXX_DEBUG
233       std::ostream&
234       _M_print(std::ostream&);
235 #endif
236 
237     private:
238       void
239       _M_scan_normal();
240 
241       void
242       _M_scan_in_bracket();
243 
244       void
245       _M_scan_in_brace();
246 
247       void
248       _M_eat_escape_ecma();
249 
250       void
251       _M_eat_escape_posix();
252 
253       void
254       _M_eat_escape_awk();
255 
256       void
257       _M_eat_class(char);
258 
259       _IterT                        _M_current;
260       _IterT                        _M_end;
261       _CtypeT&                      _M_ctype;
262       _StringT                      _M_value;
263       void (_Scanner::* _M_eat_escape)();
264     };
265 
266  //@} regex-detail
267 _GLIBCXX_END_NAMESPACE_VERSION
268 } // namespace __detail
269 } // namespace std
270 
271 #include <bits/regex_scanner.tcc>
272