00001 // class template regex -*- C++ -*- 00002 00003 // Copyright (C) 2010 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_constants.h 00027 * @brief Constant definitions for the std regex library. 00028 * 00029 * This is an internal header file, included by other library headers. 00030 * You should not attempt to use it directly. 00031 */ 00032 00033 namespace std 00034 { 00035 00036 /** 00037 * @namespace std::regex_constants 00038 * @brief ISO C++-0x entities sub namespace for regex. 00039 */ 00040 namespace regex_constants 00041 { 00042 /** 00043 * @name 5.1 Regular Expression Syntax Options 00044 */ 00045 //@{ 00046 enum __syntax_option 00047 { 00048 _S_icase, 00049 _S_nosubs, 00050 _S_optimize, 00051 _S_collate, 00052 _S_ECMAScript, 00053 _S_basic, 00054 _S_extended, 00055 _S_awk, 00056 _S_grep, 00057 _S_egrep, 00058 _S_syntax_last 00059 }; 00060 00061 /** 00062 * @brief This is a bitmask type indicating how to interpret the regex. 00063 * 00064 * The @c syntax_option_type is implementation defined but it is valid to 00065 * perform bitwise operations on these values and expect the right thing to 00066 * happen. 00067 * 00068 * A valid value of type syntax_option_type shall have exactly one of the 00069 * elements @c ECMAScript, @c basic, @c extended, @c awk, @c grep, @c egrep 00070 * %set. 00071 */ 00072 typedef unsigned int syntax_option_type; 00073 00074 /** 00075 * Specifies that the matching of regular expressions against a character 00076 * sequence shall be performed without regard to case. 00077 */ 00078 static const syntax_option_type icase = 1 << _S_icase; 00079 00080 /** 00081 * Specifies that when a regular expression is matched against a character 00082 * container sequence, no sub-expression matches are to be stored in the 00083 * supplied match_results structure. 00084 */ 00085 static const syntax_option_type nosubs = 1 << _S_nosubs; 00086 00087 /** 00088 * Specifies that the regular expression engine should pay more attention to 00089 * the speed with which regular expressions are matched, and less to the 00090 * speed with which regular expression objects are constructed. Otherwise 00091 * it has no detectable effect on the program output. 00092 */ 00093 static const syntax_option_type optimize = 1 << _S_optimize; 00094 00095 /** 00096 * Specifies that character ranges of the form [a-b] should be locale 00097 * sensitive. 00098 */ 00099 static const syntax_option_type collate = 1 << _S_collate; 00100 00101 /** 00102 * Specifies that the grammar recognized by the regular expression engine is 00103 * that used by ECMAScript in ECMA-262 [Ecma International, ECMAScript 00104 * Language Specification, Standard Ecma-262, third edition, 1999], as 00105 * modified in section [28.13]. This grammar is similar to that defined 00106 * in the PERL scripting language but extended with elements found in the 00107 * POSIX regular expression grammar. 00108 */ 00109 static const syntax_option_type ECMAScript = 1 << _S_ECMAScript; 00110 00111 /** 00112 * Specifies that the grammar recognized by the regular expression engine is 00113 * that used by POSIX basic regular expressions in IEEE Std 1003.1-2001, 00114 * Portable Operating System Interface (POSIX), Base Definitions and 00115 * Headers, Section 9, Regular Expressions [IEEE, Information Technology -- 00116 * Portable Operating System Interface (POSIX), IEEE Standard 1003.1-2001]. 00117 */ 00118 static const syntax_option_type basic = 1 << _S_basic; 00119 00120 /** 00121 * Specifies that the grammar recognized by the regular expression engine is 00122 * that used by POSIX extended regular expressions in IEEE Std 1003.1-2001, 00123 * Portable Operating System Interface (POSIX), Base Definitions and Headers, 00124 * Section 9, Regular Expressions. 00125 */ 00126 static const syntax_option_type extended = 1 << _S_extended; 00127 00128 /** 00129 * Specifies that the grammar recognized by the regular expression engine is 00130 * that used by POSIX utility awk in IEEE Std 1003.1-2001. This option is 00131 * identical to syntax_option_type extended, except that C-style escape 00132 * sequences are supported. These sequences are: 00133 * \\\\, \\a, \\b, \\f, \\n, \\r, \\t , \\v, \\', ', 00134 * and \\ddd (where ddd is one, two, or three octal digits). 00135 */ 00136 static const syntax_option_type awk = 1 << _S_awk; 00137 00138 /** 00139 * Specifies that the grammar recognized by the regular expression engine is 00140 * that used by POSIX utility grep in IEEE Std 1003.1-2001. This option is 00141 * identical to syntax_option_type basic, except that newlines are treated 00142 * as whitespace. 00143 */ 00144 static const syntax_option_type grep = 1 << _S_grep; 00145 00146 /** 00147 * Specifies that the grammar recognized by the regular expression engine is 00148 * that used by POSIX utility grep when given the -E option in 00149 * IEEE Std 1003.1-2001. This option is identical to syntax_option_type 00150 * extended, except that newlines are treated as whitespace. 00151 */ 00152 static const syntax_option_type egrep = 1 << _S_egrep; 00153 00154 //@} 00155 00156 /** 00157 * @name 5.2 Matching Rules 00158 * 00159 * Matching a regular expression against a sequence of characters [first, 00160 * last) proceeds according to the rules of the grammar specified for the 00161 * regular expression object, modified according to the effects listed 00162 * below for any bitmask elements set. 00163 * 00164 */ 00165 //@{ 00166 00167 enum __match_flag 00168 { 00169 _S_not_bol, 00170 _S_not_eol, 00171 _S_not_bow, 00172 _S_not_eow, 00173 _S_any, 00174 _S_not_null, 00175 _S_continuous, 00176 _S_prev_avail, 00177 _S_sed, 00178 _S_no_copy, 00179 _S_first_only, 00180 _S_match_flag_last 00181 }; 00182 00183 /** 00184 * @brief This is a bitmask type indicating regex matching rules. 00185 * 00186 * The @c match_flag_type is implementation defined but it is valid to 00187 * perform bitwise operations on these values and expect the right thing to 00188 * happen. 00189 */ 00190 typedef std::bitset<_S_match_flag_last> match_flag_type; 00191 00192 /** 00193 * The default matching rules. 00194 */ 00195 static const match_flag_type match_default = 0; 00196 00197 /** 00198 * The first character in the sequence [first, last) is treated as though it 00199 * is not at the beginning of a line, so the character (^) in the regular 00200 * expression shall not match [first, first). 00201 */ 00202 static const match_flag_type match_not_bol = 1 << _S_not_bol; 00203 00204 /** 00205 * The last character in the sequence [first, last) is treated as though it 00206 * is not at the end of a line, so the character ($) in the regular 00207 * expression shall not match [last, last). 00208 */ 00209 static const match_flag_type match_not_eol = 1 << _S_not_eol; 00210 00211 /** 00212 * The expression \\b is not matched against the sub-sequence 00213 * [first,first). 00214 */ 00215 static const match_flag_type match_not_bow = 1 << _S_not_bow; 00216 00217 /** 00218 * The expression \\b should not be matched against the sub-sequence 00219 * [last,last). 00220 */ 00221 static const match_flag_type match_not_eow = 1 << _S_not_eow; 00222 00223 /** 00224 * If more than one match is possible then any match is an acceptable 00225 * result. 00226 */ 00227 static const match_flag_type match_any = 1 << _S_any; 00228 00229 /** 00230 * The expression does not match an empty sequence. 00231 */ 00232 static const match_flag_type match_not_null = 1 << _S_not_null; 00233 00234 /** 00235 * The expression only matches a sub-sequence that begins at first . 00236 */ 00237 static const match_flag_type match_continuous = 1 << _S_continuous; 00238 00239 /** 00240 * --first is a valid iterator position. When this flag is set then the 00241 * flags match_not_bol and match_not_bow are ignored by the regular 00242 * expression algorithms 7.11 and iterators 7.12. 00243 */ 00244 static const match_flag_type match_prev_avail = 1 << _S_prev_avail; 00245 00246 /** 00247 * When a regular expression match is to be replaced by a new string, the 00248 * new string is constructed using the rules used by the ECMAScript replace 00249 * function in ECMA- 262 [Ecma International, ECMAScript Language 00250 * Specification, Standard Ecma-262, third edition, 1999], part 15.5.4.11 00251 * String.prototype.replace. In addition, during search and replace 00252 * operations all non-overlapping occurrences of the regular expression 00253 * are located and replaced, and sections of the input that did not match 00254 * the expression are copied unchanged to the output string. 00255 * 00256 * Format strings (from ECMA-262 [15.5.4.11]): 00257 * @li $$ The dollar-sign itself ($) 00258 * @li $& The matched substring. 00259 * @li $` The portion of @a string that precedes the matched substring. 00260 * This would be match_results::prefix(). 00261 * @li $' The portion of @a string that follows the matched substring. 00262 * This would be match_results::suffix(). 00263 * @li $n The nth capture, where n is in [1,9] and $n is not followed by a 00264 * decimal digit. If n <= match_results::size() and the nth capture 00265 * is undefined, use the empty string instead. If n > 00266 * match_results::size(), the result is implementation-defined. 00267 * @li $nn The nnth capture, where nn is a two-digit decimal number on 00268 * [01, 99]. If nn <= match_results::size() and the nth capture is 00269 * undefined, use the empty string instead. If 00270 * nn > match_results::size(), the result is implementation-defined. 00271 */ 00272 static const match_flag_type format_default = 0; 00273 00274 /** 00275 * When a regular expression match is to be replaced by a new string, the 00276 * new string is constructed using the rules used by the POSIX sed utility 00277 * in IEEE Std 1003.1- 2001 [IEEE, Information Technology -- Portable 00278 * Operating System Interface (POSIX), IEEE Standard 1003.1-2001]. 00279 */ 00280 static const match_flag_type format_sed = 1 << _S_sed; 00281 00282 /** 00283 * During a search and replace operation, sections of the character 00284 * container sequence being searched that do not match the regular 00285 * expression shall not be copied to the output string. 00286 */ 00287 static const match_flag_type format_no_copy = 1 << _S_no_copy; 00288 00289 /** 00290 * When specified during a search and replace operation, only the first 00291 * occurrence of the regular expression shall be replaced. 00292 */ 00293 static const match_flag_type format_first_only = 1 << _S_first_only; 00294 00295 //@} 00296 00297 } // namespace regex_constants 00298 } // namespace std 00299