libstdc++
regex_scanner.h
Go to the documentation of this file.
00001 // class template regex -*- C++ -*-
00002 
00003 // Copyright (C) 2013-2015 Free Software Foundation, Inc.
00004 //
00005 // This file is part of the GNU ISO C++ Library.  This library is free
00006 // software; you can redistribute it and/or modify it under the
00007 // terms of the GNU General Public License as published by the
00008 // Free Software Foundation; either version 3, or (at your option)
00009 // any later version.
00010 
00011 // This library is distributed in the hope that it will be useful,
00012 // but WITHOUT ANY WARRANTY; without even the implied warranty of
00013 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
00014 // GNU General Public License for more details.
00015 
00016 // Under Section 7 of GPL version 3, you are granted additional
00017 // permissions described in the GCC Runtime Library Exception, version
00018 // 3.1, as published by the Free Software Foundation.
00019 
00020 // You should have received a copy of the GNU General Public License and
00021 // a copy of the GCC Runtime Library Exception along with this program;
00022 // see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
00023 // <http://www.gnu.org/licenses/>.
00024 
00025 /**
00026  *  @file bits/regex_scanner.h
00027  *  This is an internal header file, included by other library headers.
00028  *  Do not attempt to use it directly. @headername{regex}
00029  */
00030 
00031 namespace std _GLIBCXX_VISIBILITY(default)
00032 {
00033 namespace __detail
00034 {
00035 _GLIBCXX_BEGIN_NAMESPACE_VERSION
00036 
00037   /**
00038    * @addtogroup regex-detail
00039    * @{
00040    */
00041 
00042   struct _ScannerBase
00043   {
00044   public:
00045     /// Token types returned from the scanner.
00046     enum _TokenT
00047     {
00048       _S_token_anychar,
00049       _S_token_ord_char,
00050       _S_token_oct_num,
00051       _S_token_hex_num,
00052       _S_token_backref,
00053       _S_token_subexpr_begin,
00054       _S_token_subexpr_no_group_begin,
00055       _S_token_subexpr_lookahead_begin, // neg if _M_value[0] == 'n'
00056       _S_token_subexpr_end,
00057       _S_token_bracket_begin,
00058       _S_token_bracket_neg_begin,
00059       _S_token_bracket_end,
00060       _S_token_interval_begin,
00061       _S_token_interval_end,
00062       _S_token_quoted_class,
00063       _S_token_char_class_name,
00064       _S_token_collsymbol,
00065       _S_token_equiv_class_name,
00066       _S_token_opt,
00067       _S_token_or,
00068       _S_token_closure0,
00069       _S_token_closure1,
00070       _S_token_line_begin,
00071       _S_token_line_end,
00072       _S_token_word_bound, // neg if _M_value[0] == 'n'
00073       _S_token_comma,
00074       _S_token_dup_count,
00075       _S_token_eof,
00076       _S_token_unknown
00077     };
00078 
00079   protected:
00080     typedef regex_constants::syntax_option_type _FlagT;
00081 
00082     enum _StateT
00083     {
00084       _S_state_normal,
00085       _S_state_in_brace,
00086       _S_state_in_bracket,
00087     };
00088 
00089   protected:
00090     _ScannerBase(_FlagT __flags)
00091     : _M_state(_S_state_normal),
00092     _M_flags(__flags),
00093     _M_escape_tbl(_M_is_ecma()
00094                   ? _M_ecma_escape_tbl
00095                   : _M_awk_escape_tbl),
00096     _M_spec_char(_M_is_ecma()
00097                  ? _M_ecma_spec_char
00098                  : _M_flags & regex_constants::basic
00099                  ? _M_basic_spec_char
00100                  : _M_flags & regex_constants::extended
00101                  ? _M_extended_spec_char
00102                  : _M_flags & regex_constants::grep
00103                  ?  ".[\\*^$\n"
00104                  : _M_flags & regex_constants::egrep
00105                  ? ".[\\()*+?{|^$\n"
00106                  : _M_flags & regex_constants::awk
00107                  ? _M_extended_spec_char
00108                  : nullptr),
00109     _M_at_bracket_start(false)
00110     { __glibcxx_assert(_M_spec_char); }
00111 
00112   protected:
00113     const char*
00114     _M_find_escape(char __c)
00115     {
00116       auto __it = _M_escape_tbl;
00117       for (; __it->first != '\0'; ++__it)
00118         if (__it->first == __c)
00119           return &__it->second;
00120       return nullptr;
00121     }
00122 
00123     bool
00124     _M_is_ecma() const
00125     { return _M_flags & regex_constants::ECMAScript; }
00126 
00127     bool
00128     _M_is_basic() const
00129     { return _M_flags & (regex_constants::basic | regex_constants::grep); }
00130 
00131     bool
00132     _M_is_extended() const
00133     {
00134       return _M_flags & (regex_constants::extended
00135                          | regex_constants::egrep
00136                          | regex_constants::awk);
00137     }
00138 
00139     bool
00140     _M_is_grep() const
00141     { return _M_flags & (regex_constants::grep | regex_constants::egrep); }
00142 
00143     bool
00144     _M_is_awk() const
00145     { return _M_flags & regex_constants::awk; }
00146 
00147   protected:
00148     // TODO: Make them static in the next abi change.
00149     const std::pair<char, _TokenT> _M_token_tbl[9] =
00150       {
00151         {'^', _S_token_line_begin},
00152         {'$', _S_token_line_end},
00153         {'.', _S_token_anychar},
00154         {'*', _S_token_closure0},
00155         {'+', _S_token_closure1},
00156         {'?', _S_token_opt},
00157         {'|', _S_token_or},
00158         {'\n', _S_token_or}, // grep and egrep
00159         {'\0', _S_token_or},
00160       };
00161     const std::pair<char, char> _M_ecma_escape_tbl[8] =
00162       {
00163         {'0', '\0'},
00164         {'b', '\b'},
00165         {'f', '\f'},
00166         {'n', '\n'},
00167         {'r', '\r'},
00168         {'t', '\t'},
00169         {'v', '\v'},
00170         {'\0', '\0'},
00171       };
00172     const std::pair<char, char> _M_awk_escape_tbl[11] =
00173       {
00174         {'"', '"'},
00175         {'/', '/'},
00176         {'\\', '\\'},
00177         {'a', '\a'},
00178         {'b', '\b'},
00179         {'f', '\f'},
00180         {'n', '\n'},
00181         {'r', '\r'},
00182         {'t', '\t'},
00183         {'v', '\v'},
00184         {'\0', '\0'},
00185       };
00186     const char* _M_ecma_spec_char = "^$\\.*+?()[]{}|";
00187     const char* _M_basic_spec_char = ".[\\*^$";
00188     const char* _M_extended_spec_char = ".[\\()*+?{|^$";
00189 
00190     _StateT                       _M_state;
00191     _FlagT                        _M_flags;
00192     _TokenT                       _M_token;
00193     const std::pair<char, char>*  _M_escape_tbl;
00194     const char*                   _M_spec_char;
00195     bool                          _M_at_bracket_start;
00196   };
00197 
00198   /**
00199    * @brief Scans an input range for regex tokens.
00200    *
00201    * The %_Scanner class interprets the regular expression pattern in
00202    * the input range passed to its constructor as a sequence of parse
00203    * tokens passed to the regular expression compiler.  The sequence
00204    * of tokens provided depends on the flag settings passed to the
00205    * constructor: different regular expression grammars will interpret
00206    * the same input pattern in syntactically different ways.
00207    */
00208   template<typename _CharT>
00209     class _Scanner
00210     : public _ScannerBase
00211     {
00212     public:
00213       typedef const _CharT*                                       _IterT;
00214       typedef std::basic_string<_CharT>                           _StringT;
00215       typedef regex_constants::syntax_option_type                 _FlagT;
00216       typedef const std::ctype<_CharT>                            _CtypeT;
00217 
00218       _Scanner(_IterT __begin, _IterT __end,
00219                _FlagT __flags, std::locale __loc);
00220 
00221       void
00222       _M_advance();
00223 
00224       _TokenT
00225       _M_get_token() const
00226       { return _M_token; }
00227 
00228       const _StringT&
00229       _M_get_value() const
00230       { return _M_value; }
00231 
00232 #ifdef _GLIBCXX_DEBUG
00233       std::ostream&
00234       _M_print(std::ostream&);
00235 #endif
00236 
00237     private:
00238       void
00239       _M_scan_normal();
00240 
00241       void
00242       _M_scan_in_bracket();
00243 
00244       void
00245       _M_scan_in_brace();
00246 
00247       void
00248       _M_eat_escape_ecma();
00249 
00250       void
00251       _M_eat_escape_posix();
00252 
00253       void
00254       _M_eat_escape_awk();
00255 
00256       void
00257       _M_eat_class(char);
00258 
00259       _IterT                        _M_current;
00260       _IterT                        _M_end;
00261       _CtypeT&                      _M_ctype;
00262       _StringT                      _M_value;
00263       void (_Scanner::* _M_eat_escape)();
00264     };
00265 
00266  //@} regex-detail
00267 _GLIBCXX_END_NAMESPACE_VERSION
00268 } // namespace __detail
00269 } // namespace std
00270 
00271 #include <bits/regex_scanner.tcc>