| [12] | 1 | /* |
|---|
| 2 | * |
|---|
| 3 | * Copyright (c) 1998-2002 |
|---|
| 4 | * John Maddock |
|---|
| 5 | * |
|---|
| 6 | * Use, modification and distribution are subject to the |
|---|
| 7 | * Boost Software License, Version 1.0. (See accompanying file |
|---|
| 8 | * LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt) |
|---|
| 9 | * |
|---|
| 10 | */ |
|---|
| 11 | |
|---|
| 12 | /* |
|---|
| 13 | * LOCATION: see http://www.boost.org for most recent version. |
|---|
| 14 | * FILE cregex.cpp |
|---|
| 15 | * VERSION see <boost/version.hpp> |
|---|
| 16 | * DESCRIPTION: Declares POSIX API functions |
|---|
| 17 | * + boost::RegEx high level wrapper. |
|---|
| 18 | */ |
|---|
| 19 | |
|---|
| 20 | #ifndef BOOST_RE_CREGEX_HPP_INCLUDED |
|---|
| 21 | #define BOOST_RE_CREGEX_HPP_INCLUDED |
|---|
| 22 | |
|---|
| 23 | #ifndef BOOST_REGEX_CONFIG_HPP |
|---|
| 24 | #include <boost/regex/config.hpp> |
|---|
| 25 | #endif |
|---|
| 26 | #include <boost/regex/v4/match_flags.hpp> |
|---|
| 27 | #include <boost/regex/v4/error_type.hpp> |
|---|
| 28 | |
|---|
| 29 | #ifdef __cplusplus |
|---|
| 30 | #include <cstddef> |
|---|
| 31 | #else |
|---|
| 32 | #include <stddef.h> |
|---|
| 33 | #endif |
|---|
| 34 | |
|---|
| 35 | #ifdef BOOST_HAS_ABI_HEADERS |
|---|
| 36 | # include BOOST_ABI_PREFIX |
|---|
| 37 | #endif |
|---|
| 38 | |
|---|
| 39 | /* include these defs only for POSIX compatablity */ |
|---|
| 40 | #ifdef __cplusplus |
|---|
| 41 | namespace boost{ |
|---|
| 42 | extern "C" { |
|---|
| 43 | #endif |
|---|
| 44 | |
|---|
| 45 | #if defined(__cplusplus) && !defined(BOOST_NO_STDC_NAMESPACE) |
|---|
| 46 | typedef std::ptrdiff_t regoff_t; |
|---|
| 47 | typedef std::size_t regsize_t; |
|---|
| 48 | #else |
|---|
| 49 | typedef ptrdiff_t regoff_t; |
|---|
| 50 | typedef size_t regsize_t; |
|---|
| 51 | #endif |
|---|
| 52 | |
|---|
| 53 | typedef struct |
|---|
| 54 | { |
|---|
| 55 | unsigned int re_magic; |
|---|
| 56 | #ifdef __cplusplus |
|---|
| 57 | std::size_t re_nsub; /* number of parenthesized subexpressions */ |
|---|
| 58 | #else |
|---|
| 59 | size_t re_nsub; |
|---|
| 60 | #endif |
|---|
| 61 | const char* re_endp; /* end pointer for REG_PEND */ |
|---|
| 62 | void* guts; /* none of your business :-) */ |
|---|
| 63 | match_flag_type eflags; /* none of your business :-) */ |
|---|
| 64 | } regex_tA; |
|---|
| 65 | |
|---|
| 66 | #ifndef BOOST_NO_WREGEX |
|---|
| 67 | typedef struct |
|---|
| 68 | { |
|---|
| 69 | unsigned int re_magic; |
|---|
| 70 | #ifdef __cplusplus |
|---|
| 71 | std::size_t re_nsub; /* number of parenthesized subexpressions */ |
|---|
| 72 | #else |
|---|
| 73 | size_t re_nsub; |
|---|
| 74 | #endif |
|---|
| 75 | const wchar_t* re_endp; /* end pointer for REG_PEND */ |
|---|
| 76 | void* guts; /* none of your business :-) */ |
|---|
| 77 | match_flag_type eflags; /* none of your business :-) */ |
|---|
| 78 | } regex_tW; |
|---|
| 79 | #endif |
|---|
| 80 | |
|---|
| 81 | typedef struct |
|---|
| 82 | { |
|---|
| 83 | regoff_t rm_so; /* start of match */ |
|---|
| 84 | regoff_t rm_eo; /* end of match */ |
|---|
| 85 | } regmatch_t; |
|---|
| 86 | |
|---|
| 87 | /* regcomp() flags */ |
|---|
| 88 | typedef enum{ |
|---|
| 89 | REG_BASIC = 0000, |
|---|
| 90 | REG_EXTENDED = 0001, |
|---|
| 91 | REG_ICASE = 0002, |
|---|
| 92 | REG_NOSUB = 0004, |
|---|
| 93 | REG_NEWLINE = 0010, |
|---|
| 94 | REG_NOSPEC = 0020, |
|---|
| 95 | REG_PEND = 0040, |
|---|
| 96 | REG_DUMP = 0200, |
|---|
| 97 | REG_NOCOLLATE = 0400, |
|---|
| 98 | REG_ESCAPE_IN_LISTS = 01000, |
|---|
| 99 | REG_NEWLINE_ALT = 02000, |
|---|
| 100 | REG_PERLEX = 04000, |
|---|
| 101 | |
|---|
| 102 | REG_PERL = REG_EXTENDED | REG_NOCOLLATE | REG_ESCAPE_IN_LISTS | REG_PERLEX, |
|---|
| 103 | REG_AWK = REG_EXTENDED | REG_ESCAPE_IN_LISTS, |
|---|
| 104 | REG_GREP = REG_BASIC | REG_NEWLINE_ALT, |
|---|
| 105 | REG_EGREP = REG_EXTENDED | REG_NEWLINE_ALT, |
|---|
| 106 | |
|---|
| 107 | REG_ASSERT = 15, |
|---|
| 108 | REG_INVARG = 16, |
|---|
| 109 | REG_ATOI = 255, /* convert name to number (!) */ |
|---|
| 110 | REG_ITOA = 0400 /* convert number to name (!) */ |
|---|
| 111 | } reg_comp_flags; |
|---|
| 112 | |
|---|
| 113 | /* regexec() flags */ |
|---|
| 114 | typedef enum{ |
|---|
| 115 | REG_NOTBOL = 00001, |
|---|
| 116 | REG_NOTEOL = 00002, |
|---|
| 117 | REG_STARTEND = 00004 |
|---|
| 118 | } reg_exec_flags; |
|---|
| 119 | |
|---|
| 120 | // |
|---|
| 121 | // POSIX error codes: |
|---|
| 122 | // |
|---|
| 123 | typedef unsigned reg_error_t; |
|---|
| 124 | typedef reg_error_t reg_errcode_t; // backwards compatibility |
|---|
| 125 | |
|---|
| 126 | static const reg_error_t REG_NOERROR = 0; /* Success. */ |
|---|
| 127 | static const reg_error_t REG_NOMATCH = 1; /* Didn't find a match (for regexec). */ |
|---|
| 128 | |
|---|
| 129 | /* POSIX regcomp return error codes. (In the order listed in the |
|---|
| 130 | standard.) */ |
|---|
| 131 | static const reg_error_t REG_BADPAT = 2; /* Invalid pattern. */ |
|---|
| 132 | static const reg_error_t REG_ECOLLATE = 3; /* Undefined collating element. */ |
|---|
| 133 | static const reg_error_t REG_ECTYPE = 4; /* Invalid character class name. */ |
|---|
| 134 | static const reg_error_t REG_EESCAPE = 5; /* Trailing backslash. */ |
|---|
| 135 | static const reg_error_t REG_ESUBREG = 6; /* Invalid back reference. */ |
|---|
| 136 | static const reg_error_t REG_EBRACK = 7; /* Unmatched left bracket. */ |
|---|
| 137 | static const reg_error_t REG_EPAREN = 8; /* Parenthesis imbalance. */ |
|---|
| 138 | static const reg_error_t REG_EBRACE = 9; /* Unmatched \{. */ |
|---|
| 139 | static const reg_error_t REG_BADBR = 10; /* Invalid contents of \{\}. */ |
|---|
| 140 | static const reg_error_t REG_ERANGE = 11; /* Invalid range end. */ |
|---|
| 141 | static const reg_error_t REG_ESPACE = 12; /* Ran out of memory. */ |
|---|
| 142 | static const reg_error_t REG_BADRPT = 13; /* No preceding re for repetition op. */ |
|---|
| 143 | static const reg_error_t REG_EEND = 14; /* unexpected end of expression */ |
|---|
| 144 | static const reg_error_t REG_ESIZE = 15; /* expression too big */ |
|---|
| 145 | static const reg_error_t REG_ERPAREN = 8; /* = REG_EPAREN : unmatched right parenthesis */ |
|---|
| 146 | static const reg_error_t REG_EMPTY = 17; /* empty expression */ |
|---|
| 147 | static const reg_error_t REG_E_MEMORY = 15; /* = REG_ESIZE : out of memory */ |
|---|
| 148 | static const reg_error_t REG_ECOMPLEXITY = 18; /* complexity too high */ |
|---|
| 149 | static const reg_error_t REG_ESTACK = 19; /* out of stack space */ |
|---|
| 150 | static const reg_error_t REG_E_UNKNOWN = 20; /* unknown error */ |
|---|
| 151 | static const reg_error_t REG_ENOSYS = 20; /* = REG_E_UNKNOWN : Reserved. */ |
|---|
| 152 | |
|---|
| 153 | BOOST_REGEX_DECL int BOOST_REGEX_CCALL regcompA(regex_tA*, const char*, int); |
|---|
| 154 | BOOST_REGEX_DECL regsize_t BOOST_REGEX_CCALL regerrorA(int, const regex_tA*, char*, regsize_t); |
|---|
| 155 | BOOST_REGEX_DECL int BOOST_REGEX_CCALL regexecA(const regex_tA*, const char*, regsize_t, regmatch_t*, int); |
|---|
| 156 | BOOST_REGEX_DECL void BOOST_REGEX_CCALL regfreeA(regex_tA*); |
|---|
| 157 | |
|---|
| 158 | #ifndef BOOST_NO_WREGEX |
|---|
| 159 | BOOST_REGEX_DECL int BOOST_REGEX_CCALL regcompW(regex_tW*, const wchar_t*, int); |
|---|
| 160 | BOOST_REGEX_DECL regsize_t BOOST_REGEX_CCALL regerrorW(int, const regex_tW*, wchar_t*, regsize_t); |
|---|
| 161 | BOOST_REGEX_DECL int BOOST_REGEX_CCALL regexecW(const regex_tW*, const wchar_t*, regsize_t, regmatch_t*, int); |
|---|
| 162 | BOOST_REGEX_DECL void BOOST_REGEX_CCALL regfreeW(regex_tW*); |
|---|
| 163 | #endif |
|---|
| 164 | |
|---|
| 165 | #ifdef UNICODE |
|---|
| 166 | #define regcomp regcompW |
|---|
| 167 | #define regerror regerrorW |
|---|
| 168 | #define regexec regexecW |
|---|
| 169 | #define regfree regfreeW |
|---|
| 170 | #define regex_t regex_tW |
|---|
| 171 | #else |
|---|
| 172 | #define regcomp regcompA |
|---|
| 173 | #define regerror regerrorA |
|---|
| 174 | #define regexec regexecA |
|---|
| 175 | #define regfree regfreeA |
|---|
| 176 | #define regex_t regex_tA |
|---|
| 177 | #endif |
|---|
| 178 | |
|---|
| 179 | #ifdef BOOST_HAS_ABI_HEADERS |
|---|
| 180 | # include BOOST_ABI_SUFFIX |
|---|
| 181 | #endif |
|---|
| 182 | |
|---|
| 183 | #ifdef __cplusplus |
|---|
| 184 | } // extern "C" |
|---|
| 185 | } // namespace |
|---|
| 186 | #endif |
|---|
| 187 | |
|---|
| 188 | // |
|---|
| 189 | // C++ high level wrapper goes here: |
|---|
| 190 | // |
|---|
| 191 | #if defined(__cplusplus) |
|---|
| 192 | #include <string> |
|---|
| 193 | #include <vector> |
|---|
| 194 | namespace boost{ |
|---|
| 195 | |
|---|
| 196 | #ifdef BOOST_HAS_ABI_HEADERS |
|---|
| 197 | # include BOOST_ABI_PREFIX |
|---|
| 198 | #endif |
|---|
| 199 | |
|---|
| 200 | class RegEx; |
|---|
| 201 | |
|---|
| 202 | namespace re_detail{ |
|---|
| 203 | |
|---|
| 204 | class RegExData; |
|---|
| 205 | struct pred1; |
|---|
| 206 | struct pred2; |
|---|
| 207 | struct pred3; |
|---|
| 208 | struct pred4; |
|---|
| 209 | |
|---|
| 210 | } // namespace re_detail |
|---|
| 211 | |
|---|
| 212 | #if (defined(BOOST_MSVC) || defined(__BORLANDC__)) && !defined(BOOST_DISABLE_WIN32) |
|---|
| 213 | typedef bool (__cdecl *GrepCallback)(const RegEx& expression); |
|---|
| 214 | typedef bool (__cdecl *GrepFileCallback)(const char* file, const RegEx& expression); |
|---|
| 215 | typedef bool (__cdecl *FindFilesCallback)(const char* file); |
|---|
| 216 | #else |
|---|
| 217 | typedef bool (*GrepCallback)(const RegEx& expression); |
|---|
| 218 | typedef bool (*GrepFileCallback)(const char* file, const RegEx& expression); |
|---|
| 219 | typedef bool (*FindFilesCallback)(const char* file); |
|---|
| 220 | #endif |
|---|
| 221 | |
|---|
| 222 | class BOOST_REGEX_DECL RegEx |
|---|
| 223 | { |
|---|
| 224 | private: |
|---|
| 225 | re_detail::RegExData* pdata; |
|---|
| 226 | public: |
|---|
| 227 | RegEx(); |
|---|
| 228 | RegEx(const RegEx& o); |
|---|
| 229 | ~RegEx(); |
|---|
| 230 | explicit RegEx(const char* c, bool icase = false); |
|---|
| 231 | explicit RegEx(const std::string& s, bool icase = false); |
|---|
| 232 | RegEx& operator=(const RegEx& o); |
|---|
| 233 | RegEx& operator=(const char* p); |
|---|
| 234 | RegEx& operator=(const std::string& s){ return this->operator=(s.c_str()); } |
|---|
| 235 | unsigned int SetExpression(const char* p, bool icase = false); |
|---|
| 236 | unsigned int SetExpression(const std::string& s, bool icase = false){ return SetExpression(s.c_str(), icase); } |
|---|
| 237 | std::string Expression()const; |
|---|
| 238 | unsigned int error_code()const; |
|---|
| 239 | // |
|---|
| 240 | // now matching operators: |
|---|
| 241 | // |
|---|
| 242 | bool Match(const char* p, match_flag_type flags = match_default); |
|---|
| 243 | bool Match(const std::string& s, match_flag_type flags = match_default) { return Match(s.c_str(), flags); } |
|---|
| 244 | bool Search(const char* p, match_flag_type flags = match_default); |
|---|
| 245 | bool Search(const std::string& s, match_flag_type flags = match_default) { return Search(s.c_str(), flags); } |
|---|
| 246 | unsigned int Grep(GrepCallback cb, const char* p, match_flag_type flags = match_default); |
|---|
| 247 | unsigned int Grep(GrepCallback cb, const std::string& s, match_flag_type flags = match_default) { return Grep(cb, s.c_str(), flags); } |
|---|
| 248 | unsigned int Grep(std::vector<std::string>& v, const char* p, match_flag_type flags = match_default); |
|---|
| 249 | unsigned int Grep(std::vector<std::string>& v, const std::string& s, match_flag_type flags = match_default) { return Grep(v, s.c_str(), flags); } |
|---|
| 250 | unsigned int Grep(std::vector<std::size_t>& v, const char* p, match_flag_type flags = match_default); |
|---|
| 251 | unsigned int Grep(std::vector<std::size_t>& v, const std::string& s, match_flag_type flags = match_default) { return Grep(v, s.c_str(), flags); } |
|---|
| 252 | #ifndef BOOST_REGEX_NO_FILEITER |
|---|
| 253 | unsigned int GrepFiles(GrepFileCallback cb, const char* files, bool recurse = false, match_flag_type flags = match_default); |
|---|
| 254 | unsigned int GrepFiles(GrepFileCallback cb, const std::string& files, bool recurse = false, match_flag_type flags = match_default) { return GrepFiles(cb, files.c_str(), recurse, flags); } |
|---|
| 255 | unsigned int FindFiles(FindFilesCallback cb, const char* files, bool recurse = false, match_flag_type flags = match_default); |
|---|
| 256 | unsigned int FindFiles(FindFilesCallback cb, const std::string& files, bool recurse = false, match_flag_type flags = match_default) { return FindFiles(cb, files.c_str(), recurse, flags); } |
|---|
| 257 | #endif |
|---|
| 258 | |
|---|
| 259 | std::string Merge(const std::string& in, const std::string& fmt, |
|---|
| 260 | bool copy = true, match_flag_type flags = match_default); |
|---|
| 261 | std::string Merge(const char* in, const char* fmt, |
|---|
| 262 | bool copy = true, match_flag_type flags = match_default); |
|---|
| 263 | |
|---|
| 264 | std::size_t Split(std::vector<std::string>& v, std::string& s, match_flag_type flags = match_default, unsigned max_count = ~0); |
|---|
| 265 | // |
|---|
| 266 | // now operators for returning what matched in more detail: |
|---|
| 267 | // |
|---|
| 268 | std::size_t Position(int i = 0)const; |
|---|
| 269 | std::size_t Length(int i = 0)const; |
|---|
| 270 | bool Matched(int i = 0)const; |
|---|
| 271 | std::size_t Marks()const; |
|---|
| 272 | std::string What(int i = 0)const; |
|---|
| 273 | std::string operator[](int i)const { return What(i); } |
|---|
| 274 | |
|---|
| 275 | static const std::size_t npos; |
|---|
| 276 | |
|---|
| 277 | friend struct re_detail::pred1; |
|---|
| 278 | friend struct re_detail::pred2; |
|---|
| 279 | friend struct re_detail::pred3; |
|---|
| 280 | friend struct re_detail::pred4; |
|---|
| 281 | }; |
|---|
| 282 | |
|---|
| 283 | #ifdef BOOST_HAS_ABI_HEADERS |
|---|
| 284 | # include BOOST_ABI_SUFFIX |
|---|
| 285 | #endif |
|---|
| 286 | |
|---|
| 287 | } // namespace boost |
|---|
| 288 | |
|---|
| 289 | #endif |
|---|
| 290 | |
|---|
| 291 | #endif // include guard |
|---|
| 292 | |
|---|
| 293 | |
|---|
| 294 | |
|---|
| 295 | |
|---|
| 296 | |
|---|
| 297 | |
|---|
| 298 | |
|---|
| 299 | |
|---|
| 300 | |
|---|
| 301 | |
|---|