Home | History | Annotate | Download | only in bits
      1 // class template regex -*- C++ -*-
      2 
      3 // Copyright (C) 2010-2014 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_constants.h
     27  *  @brief Constant definitions for the std regex library.
     28  *
     29  *  This is an internal header file, included by other library headers.
     30  *  Do not attempt to use it directly. @headername{regex}
     31  */
     32 
     33 namespace std _GLIBCXX_VISIBILITY(default)
     34 {
     35 /**
     36  * @defgroup regex Regular Expressions
     37  *
     38  * A facility for performing regular expression pattern matching.
     39  * @{
     40  */
     41 
     42 /**
     43  * @namespace std::regex_constants
     44  * @brief ISO C++-0x entities sub namespace for regex.
     45  */
     46 namespace regex_constants
     47 {
     48 _GLIBCXX_BEGIN_NAMESPACE_VERSION
     49 
     50   /**
     51    * @name 5.1 Regular Expression Syntax Options
     52    */
     53   //@{
     54   enum __syntax_option
     55   {
     56     _S_icase,
     57     _S_nosubs,
     58     _S_optimize,
     59     _S_collate,
     60     _S_ECMAScript,
     61     _S_basic,
     62     _S_extended,
     63     _S_awk,
     64     _S_grep,
     65     _S_egrep,
     66     _S_syntax_last
     67   };
     68 
     69   /**
     70    * @brief This is a bitmask type indicating how to interpret the regex.
     71    *
     72    * The @c syntax_option_type is implementation defined but it is valid to
     73    * perform bitwise operations on these values and expect the right thing to
     74    * happen.
     75    *
     76    * A valid value of type syntax_option_type shall have exactly one of the
     77    * elements @c ECMAScript, @c basic, @c extended, @c awk, @c grep, @c egrep
     78    * %set.
     79    */
     80   enum syntax_option_type : unsigned int
     81   {
     82     /**
     83      * Specifies that the matching of regular expressions against a character
     84      * sequence shall be performed without regard to case.
     85      */
     86     icase      = 1 << _S_icase,
     87 
     88     /**
     89      * Specifies that when a regular expression is matched against a character
     90      * container sequence, no sub-expression matches are to be stored in the
     91      * supplied match_results structure.
     92      */
     93     nosubs     = 1 << _S_nosubs,
     94 
     95     /**
     96      * Specifies that the regular expression engine should pay more attention to
     97      * the speed with which regular expressions are matched, and less to the
     98      * speed with which regular expression objects are constructed. Otherwise
     99      * it has no detectable effect on the program output.
    100      */
    101     optimize   = 1 << _S_optimize,
    102 
    103     /**
    104      * Specifies that character ranges of the form [a-b] should be locale
    105      * sensitive.
    106      */
    107     collate    = 1 << _S_collate,
    108 
    109     /**
    110      * Specifies that the grammar recognized by the regular expression engine is
    111      * that used by ECMAScript in ECMA-262 [Ecma International, ECMAScript
    112      * Language Specification, Standard Ecma-262, third edition, 1999], as
    113      * modified in section [28.13].  This grammar is similar to that defined
    114      * in the PERL scripting language but extended with elements found in the
    115      * POSIX regular expression grammar.
    116      */
    117     ECMAScript = 1 << _S_ECMAScript,
    118 
    119     /**
    120      * Specifies that the grammar recognized by the regular expression engine is
    121      * that used by POSIX basic regular expressions in IEEE Std 1003.1-2001,
    122      * Portable Operating System Interface (POSIX), Base Definitions and
    123      * Headers, Section 9, Regular Expressions [IEEE, Information Technology --
    124      * Portable Operating System Interface (POSIX), IEEE Standard 1003.1-2001].
    125      */
    126     basic      = 1 << _S_basic,
    127 
    128     /**
    129      * Specifies that the grammar recognized by the regular expression engine is
    130      * that used by POSIX extended regular expressions in IEEE Std 1003.1-2001,
    131      * Portable Operating System Interface (POSIX), Base Definitions and
    132      * Headers, Section 9, Regular Expressions.
    133      */
    134     extended   = 1 << _S_extended,
    135 
    136     /**
    137      * Specifies that the grammar recognized by the regular expression engine is
    138      * that used by POSIX utility awk in IEEE Std 1003.1-2001.  This option is
    139      * identical to syntax_option_type extended, except that C-style escape
    140      * sequences are supported.  These sequences are:
    141      * \\\\, \\a, \\b, \\f, \\n, \\r, \\t , \\v, \\&apos,, &apos,,
    142      * and \\ddd (where ddd is one, two, or three octal digits).
    143      */
    144     awk        = 1 << _S_awk,
    145 
    146     /**
    147      * Specifies that the grammar recognized by the regular expression engine is
    148      * that used by POSIX utility grep in IEEE Std 1003.1-2001.  This option is
    149      * identical to syntax_option_type basic, except that newlines are treated
    150      * as whitespace.
    151      */
    152     grep       = 1 << _S_grep,
    153 
    154     /**
    155      * Specifies that the grammar recognized by the regular expression engine is
    156      * that used by POSIX utility grep when given the -E option in
    157      * IEEE Std 1003.1-2001.  This option is identical to syntax_option_type
    158      * extended, except that newlines are treated as whitespace.
    159      */
    160     egrep      = 1 << _S_egrep,
    161   };
    162 
    163   constexpr inline syntax_option_type
    164   operator&(syntax_option_type __a, syntax_option_type __b)
    165   {
    166     return (syntax_option_type)(static_cast<unsigned int>(__a)
    167 				& static_cast<unsigned int>(__b));
    168   }
    169 
    170   constexpr inline syntax_option_type
    171   operator|(syntax_option_type __a, syntax_option_type __b)
    172   {
    173     return (syntax_option_type)(static_cast<unsigned int>(__a)
    174 				| static_cast<unsigned int>(__b));
    175   }
    176 
    177   constexpr inline syntax_option_type
    178   operator^(syntax_option_type __a, syntax_option_type __b)
    179   {
    180     return (syntax_option_type)(static_cast<unsigned int>(__a)
    181 				^ static_cast<unsigned int>(__b));
    182   }
    183 
    184   constexpr inline syntax_option_type
    185   operator~(syntax_option_type __a)
    186   { return (syntax_option_type)(~static_cast<unsigned int>(__a)); }
    187 
    188   inline syntax_option_type&
    189   operator&=(syntax_option_type& __a, syntax_option_type __b)
    190   { return __a = __a & __b; }
    191 
    192   inline syntax_option_type&
    193   operator|=(syntax_option_type& __a, syntax_option_type __b)
    194   { return __a = __a | __b; }
    195 
    196   inline syntax_option_type&
    197   operator^=(syntax_option_type& __a, syntax_option_type __b)
    198   { return __a = __a ^ __b; }
    199 
    200   //@}
    201 
    202   /**
    203    * @name 5.2 Matching Rules
    204    *
    205    * Matching a regular expression against a sequence of characters [first,
    206    * last) proceeds according to the rules of the grammar specified for the
    207    * regular expression object, modified according to the effects listed
    208    * below for any bitmask elements set.
    209    *
    210    */
    211   //@{
    212 
    213   enum __match_flag
    214   {
    215     _S_not_bol,
    216     _S_not_eol,
    217     _S_not_bow,
    218     _S_not_eow,
    219     _S_any,
    220     _S_not_null,
    221     _S_continuous,
    222     _S_prev_avail,
    223     _S_sed,
    224     _S_no_copy,
    225     _S_first_only,
    226     _S_match_flag_last
    227   };
    228 
    229   /**
    230    * @brief This is a bitmask type indicating regex matching rules.
    231    *
    232    * The @c match_flag_type is implementation defined but it is valid to
    233    * perform bitwise operations on these values and expect the right thing to
    234    * happen.
    235    */
    236   enum match_flag_type : unsigned int
    237   {
    238     /**
    239      * The default matching rules.
    240      */
    241     match_default     = 0,
    242 
    243     /**
    244      * The first character in the sequence [first, last) is treated as though it
    245      * is not at the beginning of a line, so the character (^) in the regular
    246      * expression shall not match [first, first).
    247      */
    248     match_not_bol     = 1 << _S_not_bol,
    249 
    250     /**
    251      * The last character in the sequence [first, last) is treated as though it
    252      * is not at the end of a line, so the character ($) in the regular
    253      * expression shall not match [last, last).
    254      */
    255     match_not_eol     = 1 << _S_not_eol,
    256 
    257     /**
    258      * The expression \\b is not matched against the sub-sequence
    259      * [first,first).
    260      */
    261     match_not_bow     = 1 << _S_not_bow,
    262 
    263     /**
    264      * The expression \\b should not be matched against the sub-sequence
    265      * [last,last).
    266      */
    267     match_not_eow     = 1 << _S_not_eow,
    268 
    269     /**
    270      * If more than one match is possible then any match is an acceptable
    271      * result.
    272      */
    273     match_any         = 1 << _S_any,
    274 
    275     /**
    276      * The expression does not match an empty sequence.
    277      */
    278     match_not_null    = 1 << _S_not_null,
    279 
    280     /**
    281      * The expression only matches a sub-sequence that begins at first .
    282      */
    283     match_continuous  = 1 << _S_continuous,
    284 
    285     /**
    286      * --first is a valid iterator position.  When this flag is set then the
    287      * flags match_not_bol and match_not_bow are ignored by the regular
    288      * expression algorithms 28.11 and iterators 28.12.
    289      */
    290     match_prev_avail  = 1 << _S_prev_avail,
    291 
    292     /**
    293      * When a regular expression match is to be replaced by a new string, the
    294      * new string is constructed using the rules used by the ECMAScript replace
    295      * function in ECMA- 262 [Ecma International, ECMAScript Language
    296      * Specification, Standard Ecma-262, third edition, 1999], part 15.5.4.11
    297      * String.prototype.replace. In addition, during search and replace
    298      * operations all non-overlapping occurrences of the regular expression
    299      * are located and replaced, and sections of the input that did not match
    300      * the expression are copied unchanged to the output string.
    301      *
    302      * Format strings (from ECMA-262 [15.5.4.11]):
    303      * @li $$  The dollar-sign itself ($)
    304      * @li $&  The matched substring.
    305      * @li $`  The portion of @a string that precedes the matched substring.
    306      *         This would be match_results::prefix().
    307      * @li $'  The portion of @a string that follows the matched substring.
    308      *         This would be match_results::suffix().
    309      * @li $n  The nth capture, where n is in [1,9] and $n is not followed by a
    310      *         decimal digit.  If n <= match_results::size() and the nth capture
    311      *         is undefined, use the empty string instead.  If n >
    312      *         match_results::size(), the result is implementation-defined.
    313      * @li $nn The nnth capture, where nn is a two-digit decimal number on
    314      *         [01, 99].  If nn <= match_results::size() and the nth capture is
    315      *         undefined, use the empty string instead. If
    316      *         nn > match_results::size(), the result is implementation-defined.
    317      */
    318     format_default    = 0,
    319 
    320     /**
    321      * When a regular expression match is to be replaced by a new string, the
    322      * new string is constructed using the rules used by the POSIX sed utility
    323      * in IEEE Std 1003.1- 2001 [IEEE, Information Technology -- Portable
    324      * Operating System Interface (POSIX), IEEE Standard 1003.1-2001].
    325      */
    326     format_sed        = 1 << _S_sed,
    327 
    328     /**
    329      * During a search and replace operation, sections of the character
    330      * container sequence being searched that do not match the regular
    331      * expression shall not be copied to the output string.
    332      */
    333     format_no_copy    = 1 << _S_no_copy,
    334 
    335     /**
    336      * When specified during a search and replace operation, only the first
    337      * occurrence of the regular expression shall be replaced.
    338      */
    339     format_first_only = 1 << _S_first_only,
    340   };
    341 
    342   constexpr inline match_flag_type
    343   operator&(match_flag_type __a, match_flag_type __b)
    344   {
    345     return (match_flag_type)(static_cast<unsigned int>(__a)
    346 				& static_cast<unsigned int>(__b));
    347   }
    348 
    349   constexpr inline match_flag_type
    350   operator|(match_flag_type __a, match_flag_type __b)
    351   {
    352     return (match_flag_type)(static_cast<unsigned int>(__a)
    353 				| static_cast<unsigned int>(__b));
    354   }
    355 
    356   constexpr inline match_flag_type
    357   operator^(match_flag_type __a, match_flag_type __b)
    358   {
    359     return (match_flag_type)(static_cast<unsigned int>(__a)
    360 				^ static_cast<unsigned int>(__b));
    361   }
    362 
    363   constexpr inline match_flag_type
    364   operator~(match_flag_type __a)
    365   { return (match_flag_type)(~static_cast<unsigned int>(__a)); }
    366 
    367   inline match_flag_type&
    368   operator&=(match_flag_type& __a, match_flag_type __b)
    369   { return __a = __a & __b; }
    370 
    371   inline match_flag_type&
    372   operator|=(match_flag_type& __a, match_flag_type __b)
    373   { return __a = __a | __b; }
    374 
    375   inline match_flag_type&
    376   operator^=(match_flag_type& __a, match_flag_type __b)
    377   { return __a = __a ^ __b; }
    378 
    379   //@}
    380 
    381 _GLIBCXX_END_NAMESPACE_VERSION
    382 } // namespace regex_constants
    383 
    384 /* @} */ // group regex
    385 } // namespace std
    386 
    387