_M_insert_bracket_matcher(bool __neg)
{
_BracketMatcher<_TraitsT, __icase, __collate> __matcher(__neg, _M_traits);
+ 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];
+ }
while (!_M_match_token(_ScannerT::_S_token_bracket_end))
- _M_expression_term(__matcher);
+ _M_expression_term(__last_char, __matcher);
__matcher._M_ready();
- _M_stack.push(_StateSeqT(_M_nfa,
- _M_nfa._M_insert_matcher(std::move(__matcher))));
+ _M_stack.push(_StateSeqT(
+ _M_nfa,
+ _M_nfa._M_insert_matcher(std::move(__matcher))));
}
template<typename _TraitsT>
template<bool __icase, bool __collate>
void
_Compiler<_TraitsT>::
- _M_expression_term(_BracketMatcher<_TraitsT, __icase, __collate>& __matcher)
+ _M_expression_term(pair<bool, _CharT>& __last_char,
+ _BracketMatcher<_TraitsT, __icase, __collate>& __matcher)
+
{
if (_M_match_token(_ScannerT::_S_token_collsymbol))
__matcher._M_add_collating_element(_M_value);
__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);
- else if (_M_try_char()) // [a
+ // POSIX doesn't permit '-' as a start-range char (say [a-z--0]),
+ // except when the '-' is the first character in the bracket expression
+ // ([--0]). ECMAScript treats all '-' after a range as a normal character.
+ // Also see above, where _M_expression_term gets called.
+ //
+ // As a result, POSIX rejects [-----], but ECMAScript doesn't.
+ // Boost (1.57.0) always uses POSIX style even in its ECMAScript syntax.
+ // 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())
{
- auto __ch = _M_value[0];
- if (_M_try_char())
+ if (!__last_char.first)
+ {
+ if (_M_value[0] == '-'
+ && !(_M_flags & regex_constants::ECMAScript))
+ __throw_regex_error(regex_constants::error_range);
+ __matcher._M_add_char(_M_value[0]);
+ __last_char.first = true;
+ __last_char.second = _M_value[0];
+ }
+ else
{
- if (_M_value[0] == '-') // [a-
+ if (_M_value[0] == '-')
{
- if (_M_try_char()) // [a-z]
+ if (_M_try_char())
+ {
+ __matcher._M_make_range(__last_char.second , _M_value[0]);
+ __last_char.first = false;
+ }
+ else
{
- __matcher._M_make_range(__ch, _M_value[0]);
- return;
+ if (_M_scanner._M_get_token()
+ != _ScannerT::_S_token_bracket_end)
+ __throw_regex_error(regex_constants::error_range);
+ __matcher._M_add_char(_M_value[0]);
}
- // If the dash is the last character in the bracket
- // expression, it is not special.
- if (_M_scanner._M_get_token()
- != _ScannerT::_S_token_bracket_end)
- __throw_regex_error(regex_constants::error_range);
}
- __matcher._M_add_char(_M_value[0]);
+ else
+ {
+ __matcher._M_add_char(_M_value[0]);
+ __last_char.second = _M_value[0];
+ }
}
- __matcher._M_add_char(__ch);
}
else if (_M_match_token(_ScannerT::_S_token_quoted_class))
__matcher._M_add_character_class(_M_value,
//
// 2013-08-01 Tim Shen <timshen91@gmail.com>
//
-// Copyright (C) 2013-2014 Free Software Foundation, Inc.
+// Copyright (C) 2013-2015 Free Software Foundation, Inc.
//
// This file is part of the GNU ISO C++ Library. This library is free
// software; you can redistribute it and/or modify it under the
}
}
+void
+test02()
+{
+ bool test __attribute__((unused)) = true;
+
+ try
+ {
+ std::regex re("[-----]", std::regex::extended);
+ VERIFY(false);
+ }
+ catch (const std::regex_error& e)
+ {
+ VERIFY(e.code() == std::regex_constants::error_range);
+ }
+ std::regex re("[-----]", std::regex::ECMAScript);
+}
+
+void
+test03()
+{
+ bool test __attribute__((unused)) = true;
+
+ try
+ {
+ std::regex re("[z-a]", std::regex::extended);
+ VERIFY(false);
+ }
+ catch (const std::regex_error& e)
+ {
+ VERIFY(e.code() == std::regex_constants::error_range);
+ }
+}
+
+void
+test04()
+{
+ bool test __attribute__((unused)) = true;
+
+ std::regex re("[-0-9a-z]");
+ VERIFY(regex_match_debug("-", re));
+ VERIFY(regex_match_debug("1", re));
+ VERIFY(regex_match_debug("w", re));
+ re.assign("[-0-9a-z]", regex_constants::basic);
+ VERIFY(regex_match_debug("-", re));
+ VERIFY(regex_match_debug("1", re));
+ VERIFY(regex_match_debug("w", re));
+}
+
int
main()
{
test01();
+ test02();
+ test03();
+ test04();
return 0;
}