libstdc++-v3/include/bits/regex_constants.h

   1 // class template regex -*- C++ -*-
   2
   3 // Copyright (C) 2010, 2011 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  * @namespace std::regex_constants
  37  * @brief ISO C++-0x entities sub namespace for regex.
  38  */
  39 namespace regex_constants
  40 {
  41 _GLIBCXX_BEGIN_NAMESPACE_VERSION
  42
  43   /**
  44    * @name 5.1 Regular Expression Syntax Options
  45    */
  46   //@{
  47   enum __syntax_option
  48     {
  49       _S_icase,
  50       _S_nosubs,
  51       _S_optimize,
  52       _S_collate,
  53       _S_ECMAScript,
  54       _S_basic,
  55       _S_extended,
  56       _S_awk,
  57       _S_grep,
  58       _S_egrep,
  59       _S_syntax_last
  60     };
  61
  62   /**
  63    * @brief This is a bitmask type indicating how to interpret the regex.
  64    *
  65    * The @c syntax_option_type is implementation defined but it is valid to
  66    * perform bitwise operations on these values and expect the right thing to
  67    * happen.
  68    *
  69    * A valid value of type syntax_option_type shall have exactly one of the
  70    * elements @c ECMAScript, @c basic, @c extended, @c awk, @c grep, @c egrep
  71    * %set.
  72    */
  73   typedef unsigned int syntax_option_type;
  74
  75   /**
  76    * Specifies that the matching of regular expressions against a character
  77    * sequence shall be performed without regard to case.
  78    */
  79   static const syntax_option_type icase      = 1 << _S_icase;
  80
  81   /**
  82    * Specifies that when a regular expression is matched against a character
  83    * container sequence, no sub-expression matches are to be stored in the
  84    * supplied match_results structure.
  85    */
  86   static const syntax_option_type nosubs     = 1 << _S_nosubs;
  87
  88   /**
  89    * Specifies that the regular expression engine should pay more attention to
  90    * the speed with which regular expressions are matched, and less to the
  91    * speed with which regular expression objects are constructed. Otherwise
  92    * it has no detectable effect on the program output.
  93    */
  94   static const syntax_option_type optimize   = 1 << _S_optimize;
  95
  96   /**
  97    * Specifies that character ranges of the form [a-b] should be locale
  98    * sensitive.
  99    */
 100   static const syntax_option_type collate    = 1 << _S_collate;
 101
 102   /**
 103    * Specifies that the grammar recognized by the regular expression engine is
 104    * that used by ECMAScript in ECMA-262 [Ecma International, ECMAScript
 105    * Language Specification, Standard Ecma-262, third edition, 1999], as
 106    * modified in section [28.13].  This grammar is similar to that defined
 107    * in the PERL scripting language but extended with elements found in the
 108    * POSIX regular expression grammar.
 109    */
 110   static const syntax_option_type ECMAScript = 1 << _S_ECMAScript;
 111
 112   /**
 113    * Specifies that the grammar recognized by the regular expression engine is
 114    * that used by POSIX basic regular expressions in IEEE Std 1003.1-2001,
 115    * Portable Operating System Interface (POSIX), Base Definitions and
 116    * Headers, Section 9, Regular Expressions [IEEE, Information Technology --
 117    * Portable Operating System Interface (POSIX), IEEE Standard 1003.1-2001].
 118    */
 119   static const syntax_option_type basic      = 1 << _S_basic;
 120
 121   /**
 122    * Specifies that the grammar recognized by the regular expression engine is
 123    * that used by POSIX extended regular expressions in IEEE Std 1003.1-2001,
 124    * Portable Operating System Interface (POSIX), Base Definitions and Headers,
 125    * Section 9, Regular Expressions.
 126    */
 127   static const syntax_option_type extended   = 1 << _S_extended;
 128
 129   /**
 130    * Specifies that the grammar recognized by the regular expression engine is
 131    * that used by POSIX utility awk in IEEE Std 1003.1-2001.  This option is
 132    * identical to syntax_option_type extended, except that C-style escape
 133    * sequences are supported.  These sequences are:
 134    * \\\\, \\a, \\b, \\f, \\n, \\r, \\t , \\v, \\&apos;, &apos;,
 135    * and \\ddd (where ddd is one, two, or three octal digits).
 136    */
 137   static const syntax_option_type awk        = 1 << _S_awk;
 138
 139   /**
 140    * Specifies that the grammar recognized by the regular expression engine is
 141    * that used by POSIX utility grep in IEEE Std 1003.1-2001.  This option is
 142    * identical to syntax_option_type basic, except that newlines are treated
 143    * as whitespace.
 144    */
 145   static const syntax_option_type grep       = 1 << _S_grep;
 146
 147   /**
 148    * Specifies that the grammar recognized by the regular expression engine is
 149    * that used by POSIX utility grep when given the -E option in
 150    * IEEE Std 1003.1-2001.  This option is identical to syntax_option_type
 151    * extended, except that newlines are treated as whitespace.
 152    */
 153   static const syntax_option_type egrep      = 1 << _S_egrep;
 154
 155   //@}
 156
 157   /**
 158    * @name 5.2 Matching Rules
 159    *
 160    * Matching a regular expression against a sequence of characters [first,
 161    * last) proceeds according to the rules of the grammar specified for the
 162    * regular expression object, modified according to the effects listed
 163    * below for any bitmask elements set.
 164    *
 165    */
 166   //@{
 167
 168   enum __match_flag
 169     {
 170       _S_not_bol,
 171       _S_not_eol,
 172       _S_not_bow,
 173       _S_not_eow,
 174       _S_any,
 175       _S_not_null,
 176       _S_continuous,
 177       _S_prev_avail,
 178       _S_sed,
 179       _S_no_copy,
 180       _S_first_only,
 181       _S_match_flag_last
 182     };
 183
 184   /**
 185    * @brief This is a bitmask type indicating regex matching rules.
 186    *
 187    * The @c match_flag_type is implementation defined but it is valid to
 188    * perform bitwise operations on these values and expect the right thing to
 189    * happen.
 190    */
 191   typedef std::bitset<_S_match_flag_last> match_flag_type;
 192
 193   /**
 194    * The default matching rules.
 195    */
 196   static const match_flag_type match_default     = 0;
 197
 198   /**
 199    * The first character in the sequence [first, last) is treated as though it
 200    * is not at the beginning of a line, so the character (^) in the regular
 201    * expression shall not match [first, first).
 202    */
 203   static const match_flag_type match_not_bol     = 1 << _S_not_bol;
 204
 205   /**
 206    * The last character in the sequence [first, last) is treated as though it
 207    * is not at the end of a line, so the character ($) in the regular
 208    * expression shall not match [last, last).
 209    */
 210   static const match_flag_type match_not_eol     = 1 << _S_not_eol;
 211
 212   /**
 213    * The expression \\b is not matched against the sub-sequence
 214    * [first,first).
 215    */
 216   static const match_flag_type match_not_bow     = 1 << _S_not_bow;
 217
 218   /**
 219    * The expression \\b should not be matched against the sub-sequence
 220    * [last,last).
 221    */
 222   static const match_flag_type match_not_eow     = 1 << _S_not_eow;
 223
 224   /**
 225    * If more than one match is possible then any match is an acceptable
 226    * result.
 227    */
 228   static const match_flag_type match_any         = 1 << _S_any;
 229
 230   /**
 231    * The expression does not match an empty sequence.
 232    */
 233   static const match_flag_type match_not_null    = 1 << _S_not_null;
 234
 235   /**
 236    * The expression only matches a sub-sequence that begins at first .
 237    */
 238   static const match_flag_type match_continuous  = 1 << _S_continuous;
 239
 240   /**
 241    * --first is a valid iterator position.  When this flag is set then the
 242    * flags match_not_bol and match_not_bow are ignored by the regular
 243    * expression algorithms 7.11 and iterators 7.12.
 244    */
 245   static const match_flag_type match_prev_avail  = 1 << _S_prev_avail;
 246
 247   /**
 248    * When a regular expression match is to be replaced by a new string, the
 249    * new string is constructed using the rules used by the ECMAScript replace
 250    * function in ECMA- 262 [Ecma International, ECMAScript Language
 251    * Specification, Standard Ecma-262, third edition, 1999], part 15.5.4.11
 252    * String.prototype.replace. In addition, during search and replace
 253    * operations all non-overlapping occurrences of the regular expression
 254    * are located and replaced, and sections of the input that did not match
 255    * the expression are copied unchanged to the output string.
 256    *
 257    * Format strings (from ECMA-262 [15.5.4.11]):
 258    * @li $$  The dollar-sign itself ($)
 259    * @li $&  The matched substring.
 260    * @li $`  The portion of @a string that precedes the matched substring.
 261    *         This would be match_results::prefix().
 262    * @li $'  The portion of @a string that follows the matched substring.
 263    *         This would be match_results::suffix().
 264    * @li $n  The nth capture, where n is in [1,9] and $n is not followed by a
 265    *         decimal digit.  If n <= match_results::size() and the nth capture
 266    *         is undefined, use the empty string instead.  If n >
 267    *         match_results::size(), the result is implementation-defined.
 268    * @li $nn The nnth capture, where nn is a two-digit decimal number on
 269    *         [01, 99].  If nn <= match_results::size() and the nth capture is
 270    *         undefined, use the empty string instead. If
 271    *         nn > match_results::size(), the result is implementation-defined.
 272    */
 273   static const match_flag_type format_default    = 0;
 274
 275   /**
 276    * When a regular expression match is to be replaced by a new string, the
 277    * new string is constructed using the rules used by the POSIX sed utility
 278    * in IEEE Std 1003.1- 2001 [IEEE, Information Technology -- Portable
 279    * Operating System Interface (POSIX), IEEE Standard 1003.1-2001].
 280    */
 281   static const match_flag_type format_sed        = 1 << _S_sed;
 282
 283   /**
 284    * During a search and replace operation, sections of the character
 285    * container sequence being searched that do not match the regular
 286    * expression shall not be copied to the output string.
 287    */
 288   static const match_flag_type format_no_copy    = 1 << _S_no_copy;
 289
 290   /**
 291    * When specified during a search and replace operation, only the first
 292    * occurrence of the regular expression shall be replaced.
 293    */
 294   static const match_flag_type format_first_only = 1 << _S_first_only;
 295
 296   //@}
 297
 298 _GLIBCXX_END_NAMESPACE_VERSION
 299 } // namespace regex_constants
 300 } // namespace
 301