I didn't realized that we can actually escape a dash inside bracket expression: R"([\-])", in which case the dash should be treated literally.
Tell me if you feel like we need more documentations. :P Bootstrapped and tested on x86_64-linux-gnu. Thanks! -- Regards, Tim Shen
commit 404a69b17f7fddc9856e9664e304f122601f212f Author: Tim Shen <tims...@google.com> Date: Wed Aug 24 00:06:54 2016 -0700 2016-08-25 Tim Shen <tims...@google.com> PR libstdc++/77356 * include/bits/regex_compiler.tcc(_M_insert_bracket_matcher, _M_expression_term): Modify to support dash literal. * include/bits/regex_scanner.h: Add dash as a token type to make a different from the mandated dash literal by escaping. * include/bits/regex_scanner.tcc(_M_scan_in_bracket): Emit dash token in bracket expression parsing. * testsuite/28_regex/regression.cc: Add new testcase. diff --git a/libstdc++-v3/include/bits/regex_compiler.tcc b/libstdc++-v3/include/bits/regex_compiler.tcc index ff69e16..3ffa170 100644 --- a/libstdc++-v3/include/bits/regex_compiler.tcc +++ b/libstdc++-v3/include/bits/regex_compiler.tcc @@ -426,13 +426,21 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION pair<bool, _CharT> __last_char; // Optional<_CharT> __last_char.first = false; if (!(_M_flags & regex_constants::ECMAScript)) - if (_M_try_char()) - { - __matcher._M_add_char(_M_value[0]); - __last_char.first = true; - __last_char.second = _M_value[0]; - } + { + if (_M_try_char()) + { + __last_char.first = true; + __last_char.second = _M_value[0]; + } + else if (_M_match_token(_ScannerT::_S_token_bracket_dash)) + { + __last_char.first = true; + __last_char.second = '-'; + } + } while (_M_expression_term(__last_char, __matcher)); + if (__last_char.first) + __matcher._M_add_char(__last_char.second); __matcher._M_ready(); _M_stack.push(_StateSeqT( *_M_nfa, @@ -449,19 +457,35 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION if (_M_match_token(_ScannerT::_S_token_bracket_end)) return false; + const auto __push_char = [&](_CharT __ch) + { + if (__last_char.first) + __matcher._M_add_char(__last_char.second); + else + __last_char.first = true; + __last_char.second = __ch; + }; + if (_M_match_token(_ScannerT::_S_token_collsymbol)) { auto __symbol = __matcher._M_add_collate_element(_M_value); if (__symbol.size() == 1) - { - __last_char.first = true; - __last_char.second = __symbol[0]; - } + __push_char(__symbol[0]); + else + __last_char.first = false; } else if (_M_match_token(_ScannerT::_S_token_equiv_class_name)) - __matcher._M_add_equivalence_class(_M_value); + { + __last_char.first = false; + __matcher._M_add_equivalence_class(_M_value); + } else if (_M_match_token(_ScannerT::_S_token_char_class_name)) - __matcher._M_add_character_class(_M_value, false); + { + __last_char.first = false; + __matcher._M_add_character_class(_M_value, false); + } + else if (_M_try_char()) + __push_char(_M_value[0]); // POSIX doesn't allow '-' as a start-range char (say [a-z--0]), // except when the '-' is the first or last character in the bracket // expression ([--0]). ECMAScript treats all '-' after a range as a @@ -472,55 +496,55 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION // Clang (3.5) always uses ECMAScript style even in its POSIX syntax. // // It turns out that no one reads BNFs ;) - else if (_M_try_char()) + else if (_M_match_token(_ScannerT::_S_token_bracket_dash)) { if (!__last_char.first) { - __matcher._M_add_char(_M_value[0]); - if (_M_value[0] == '-' - && !(_M_flags & regex_constants::ECMAScript)) + if (!(_M_flags & regex_constants::ECMAScript)) { if (_M_match_token(_ScannerT::_S_token_bracket_end)) - return false; + { + __push_char('-'); + return false; + } __throw_regex_error( regex_constants::error_range, "Unexpected dash in bracket expression. For POSIX syntax, " "a dash is not treated literally only when it is at " "beginning or end."); } - __last_char.first = true; - __last_char.second = _M_value[0]; + __push_char('-'); } else { - if (_M_value[0] == '-') + if (_M_try_char()) { - if (_M_try_char()) - { - __matcher._M_make_range(__last_char.second , _M_value[0]); - __last_char.first = false; - } - else - { - if (_M_scanner._M_get_token() - != _ScannerT::_S_token_bracket_end) - __throw_regex_error( - regex_constants::error_range, - "Unexpected end of bracket expression."); - __matcher._M_add_char(_M_value[0]); - } + __matcher._M_make_range(__last_char.second, _M_value[0]); + __last_char.first = false; + } + else if (_M_match_token(_ScannerT::_S_token_bracket_dash)) + { + __matcher._M_make_range(__last_char.second, '-'); + __last_char.first = false; } else { - __matcher._M_add_char(_M_value[0]); - __last_char.second = _M_value[0]; + if (_M_scanner._M_get_token() + != _ScannerT::_S_token_bracket_end) + __throw_regex_error( + regex_constants::error_range, + "Character is expected after a dash."); + __push_char(_M_value[0]); } } } else if (_M_match_token(_ScannerT::_S_token_quoted_class)) - __matcher._M_add_character_class(_M_value, - _M_ctype.is(_CtypeT::upper, - _M_value[0])); + { + __last_char.first = false; + __matcher._M_add_character_class(_M_value, + _M_ctype.is(_CtypeT::upper, + _M_value[0])); + } else __throw_regex_error(regex_constants::error_brack, "Unexpected character in bracket expression."); diff --git a/libstdc++-v3/include/bits/regex_scanner.h b/libstdc++-v3/include/bits/regex_scanner.h index 37dea84..2a83d1c 100644 --- a/libstdc++-v3/include/bits/regex_scanner.h +++ b/libstdc++-v3/include/bits/regex_scanner.h @@ -73,6 +73,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION _S_token_comma, _S_token_dup_count, _S_token_eof, + _S_token_bracket_dash, _S_token_unknown }; diff --git a/libstdc++-v3/include/bits/regex_scanner.tcc b/libstdc++-v3/include/bits/regex_scanner.tcc index fedba09..a734bb1 100644 --- a/libstdc++-v3/include/bits/regex_scanner.tcc +++ b/libstdc++-v3/include/bits/regex_scanner.tcc @@ -210,7 +210,9 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION auto __c = *_M_current++; - if (__c == '[') + if (__c == '-') + _M_token = _S_token_bracket_dash; + else if (__c == '[') { if (_M_current == _M_end) __throw_regex_error(regex_constants::error_brack, diff --git a/libstdc++-v3/testsuite/28_regex/regression.cc b/libstdc++-v3/testsuite/28_regex/regression.cc index d367c8b..0896a74 100644 --- a/libstdc++-v3/testsuite/28_regex/regression.cc +++ b/libstdc++-v3/testsuite/28_regex/regression.cc @@ -61,12 +61,23 @@ test03() VERIFY(!regex_search_debug("a", regex(R"(\b$)"), regex_constants::match_not_eow)); } +// PR libstdc++/77356 +void +test04() +{ + bool test __attribute__((unused)) = true; + static const char* kNumericAnchor ="(\\$|usd)(usd|\\$|to|and|up to|[0-9,\\.\\-\\sk])+"; + const std::regex re(kNumericAnchor); + (void)re; +} + int main() { test01(); test02(); test03(); + test04(); return 0; }