regex_scanner.h 6.92 KB
Newer Older
1 2
// class template regex -*- C++ -*-

3
// Copyright (C) 2013-2018 Free Software Foundation, Inc.
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
//
// This file is part of the GNU ISO C++ Library.  This library 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, 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 General Public License for more details.

// Under Section 7 of GPL version 3, you are granted additional
// permissions described in the GCC Runtime Library Exception, version
// 3.1, as published by the Free Software Foundation.

// You should have received a copy of the GNU General Public License and
// a copy of the GCC Runtime Library Exception along with this program;
// see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
// <http://www.gnu.org/licenses/>.

/**
 *  @file bits/regex_scanner.h
 *  This is an internal header file, included by other library headers.
 *  Do not attempt to use it directly. @headername{regex}
 */

namespace std _GLIBCXX_VISIBILITY(default)
{
_GLIBCXX_BEGIN_NAMESPACE_VERSION

35 36
namespace __detail
{
37 38 39 40 41
  /**
   * @addtogroup regex-detail
   * @{
   */

42 43 44 45
  struct _ScannerBase
  {
  public:
    /// Token types returned from the scanner.
46
    enum _TokenT : unsigned
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
    {
      _S_token_anychar,
      _S_token_ord_char,
      _S_token_oct_num,
      _S_token_hex_num,
      _S_token_backref,
      _S_token_subexpr_begin,
      _S_token_subexpr_no_group_begin,
      _S_token_subexpr_lookahead_begin, // neg if _M_value[0] == 'n'
      _S_token_subexpr_end,
      _S_token_bracket_begin,
      _S_token_bracket_neg_begin,
      _S_token_bracket_end,
      _S_token_interval_begin,
      _S_token_interval_end,
      _S_token_quoted_class,
      _S_token_char_class_name,
      _S_token_collsymbol,
      _S_token_equiv_class_name,
      _S_token_opt,
      _S_token_or,
      _S_token_closure0,
      _S_token_closure1,
      _S_token_line_begin,
      _S_token_line_end,
      _S_token_word_bound, // neg if _M_value[0] == 'n'
      _S_token_comma,
      _S_token_dup_count,
      _S_token_eof,
76 77
      _S_token_bracket_dash,
      _S_token_unknown = -1u
78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98
    };

  protected:
    typedef regex_constants::syntax_option_type _FlagT;

    enum _StateT
    {
      _S_state_normal,
      _S_state_in_brace,
      _S_state_in_bracket,
    };

  protected:
    _ScannerBase(_FlagT __flags)
    : _M_state(_S_state_normal),
    _M_flags(__flags),
    _M_escape_tbl(_M_is_ecma()
		  ? _M_ecma_escape_tbl
		  : _M_awk_escape_tbl),
    _M_spec_char(_M_is_ecma()
		 ? _M_ecma_spec_char
99
		 : _M_flags & regex_constants::basic
100
		 ? _M_basic_spec_char
101 102 103 104 105 106 107 108 109
		 : _M_flags & regex_constants::extended
		 ? _M_extended_spec_char
		 : _M_flags & regex_constants::grep
		 ?  ".[\\*^$\n"
		 : _M_flags & regex_constants::egrep
		 ? ".[\\()*+?{|^$\n"
		 : _M_flags & regex_constants::awk
		 ? _M_extended_spec_char
		 : nullptr),
110
    _M_at_bracket_start(false)
111
    { __glibcxx_assert(_M_spec_char); }
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

  protected:
    const char*
    _M_find_escape(char __c)
    {
      auto __it = _M_escape_tbl;
      for (; __it->first != '\0'; ++__it)
	if (__it->first == __c)
	  return &__it->second;
      return nullptr;
    }

    bool
    _M_is_ecma() const
    { return _M_flags & regex_constants::ECMAScript; }

    bool
    _M_is_basic() const
    { return _M_flags & (regex_constants::basic | regex_constants::grep); }

    bool
    _M_is_extended() const
    {
      return _M_flags & (regex_constants::extended
			 | regex_constants::egrep
			 | regex_constants::awk);
    }

    bool
    _M_is_grep() const
    { return _M_flags & (regex_constants::grep | regex_constants::egrep); }

    bool
    _M_is_awk() const
    { return _M_flags & regex_constants::awk; }

  protected:
149
    // TODO: Make them static in the next abi change.
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
    const std::pair<char, _TokenT> _M_token_tbl[9] =
      {
	{'^', _S_token_line_begin},
	{'$', _S_token_line_end},
	{'.', _S_token_anychar},
	{'*', _S_token_closure0},
	{'+', _S_token_closure1},
	{'?', _S_token_opt},
	{'|', _S_token_or},
	{'\n', _S_token_or}, // grep and egrep
	{'\0', _S_token_or},
      };
    const std::pair<char, char> _M_ecma_escape_tbl[8] =
      {
	{'0', '\0'},
	{'b', '\b'},
	{'f', '\f'},
	{'n', '\n'},
	{'r', '\r'},
	{'t', '\t'},
	{'v', '\v'},
	{'\0', '\0'},
      };
    const std::pair<char, char> _M_awk_escape_tbl[11] =
      {
	{'"', '"'},
	{'/', '/'},
	{'\\', '\\'},
	{'a', '\a'},
	{'b', '\b'},
	{'f', '\f'},
	{'n', '\n'},
	{'r', '\r'},
	{'t', '\t'},
	{'v', '\v'},
	{'\0', '\0'},
      };
    const char* _M_ecma_spec_char = "^$\\.*+?()[]{}|";
    const char* _M_basic_spec_char = ".[\\*^$";
    const char* _M_extended_spec_char = ".[\\()*+?{|^$";

    _StateT                       _M_state;
    _FlagT                        _M_flags;
    _TokenT                       _M_token;
    const std::pair<char, char>*  _M_escape_tbl;
    const char*                   _M_spec_char;
    bool                          _M_at_bracket_start;
  };

199
  /**
Tim Shen committed
200
   * @brief Scans an input range for regex tokens.
201 202 203 204 205 206 207 208
   *
   * The %_Scanner class interprets the regular expression pattern in
   * the input range passed to its constructor as a sequence of parse
   * tokens passed to the regular expression compiler.  The sequence
   * of tokens provided depends on the flag settings passed to the
   * constructor: different regular expression grammars will interpret
   * the same input pattern in syntactically different ways.
   */
209
  template<typename _CharT>
210
    class _Scanner
211
    : public _ScannerBase
212 213
    {
    public:
214
      typedef const _CharT*                                       _IterT;
215 216 217 218
      typedef std::basic_string<_CharT>                           _StringT;
      typedef regex_constants::syntax_option_type                 _FlagT;
      typedef const std::ctype<_CharT>                            _CtypeT;

219
      _Scanner(_IterT __begin, _IterT __end,
220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259
	       _FlagT __flags, std::locale __loc);

      void
      _M_advance();

      _TokenT
      _M_get_token() const
      { return _M_token; }

      const _StringT&
      _M_get_value() const
      { return _M_value; }

#ifdef _GLIBCXX_DEBUG
      std::ostream&
      _M_print(std::ostream&);
#endif

    private:
      void
      _M_scan_normal();

      void
      _M_scan_in_bracket();

      void
      _M_scan_in_brace();

      void
      _M_eat_escape_ecma();

      void
      _M_eat_escape_posix();

      void
      _M_eat_escape_awk();

      void
      _M_eat_class(char);

260 261
      _IterT                        _M_current;
      _IterT                        _M_end;
262 263 264 265 266 267 268
      _CtypeT&                      _M_ctype;
      _StringT                      _M_value;
      void (_Scanner::* _M_eat_escape)();
    };

 //@} regex-detail
} // namespace __detail
269
_GLIBCXX_END_NAMESPACE_VERSION
270 271 272
} // namespace std

#include <bits/regex_scanner.tcc>