+2015-09-19 Tim Shen <timshen@google.com>
+
+ PR libstdc++/67361
+ * include/bits/regex_error.h: Add __throw_regex_error that
+ supports string.
+ * include/bits/regex_automaton.h: Add more specific exception
+ messages.
+ * include/bits/regex_automaton.tcc: Likewise.
+ * include/bits/regex_compiler.h: Likewise.
+ * include/bits/regex_compiler.tcc: Likewise.
+ * include/bits/regex_scanner.h: Likewise.
+ * include/bits/regex_scanner.tcc: Likewise.
+
2015-09-18 Jonathan Wakely <jwakely@redhat.com>
* include/precompiled/extc++.h: Fix bootstrap error due to
{
this->push_back(std::move(__s));
if (this->size() > _GLIBCXX_REGEX_STATE_LIMIT)
- __throw_regex_error(regex_constants::error_space);
+ __throw_regex_error(
+ regex_constants::error_space,
+ "Number of NFA states exceeds limit. Please use shorter regex "
+ "string, or use smaller brace expression, or make "
+ "_GLIBCXX_REGEX_STATE_LIMIT larger.");
return this->size()-1;
}
_NFA<_TraitsT>::_M_insert_backref(size_t __index)
{
if (this->_M_flags & regex_constants::__polynomial)
- __throw_regex_error(regex_constants::error_complexity);
+ __throw_regex_error(regex_constants::error_complexity,
+ "Unexpected back-reference in polynomial mode.");
// To figure out whether a backref is valid, a stack is used to store
// unfinished sub-expressions. For example, when parsing
// "(a(b)(c\\1(d)))" at '\\1', _M_subexpr_count is 3, indicating that 3
// _M_paren_stack is {1, 3}, for incomplete "(a.." and "(c..". At this
// time, "\\2" is valid, but "\\1" and "\\3" are not.
if (__index >= _M_subexpr_count)
- __throw_regex_error(regex_constants::error_backref);
+ __throw_regex_error(
+ regex_constants::error_backref,
+ "Back-reference index exceeds current sub-expression count.");
for (auto __it : this->_M_paren_stack)
if (__index == __it)
- __throw_regex_error(regex_constants::error_backref);
+ __throw_regex_error(
+ regex_constants::error_backref,
+ "Back-reference referred to an opened sub-expression.");
this->_M_has_backref = true;
_StateT __tmp(_S_opcode_backref);
__tmp._M_backref_index = __index;
auto __st = _M_traits.lookup_collatename(__s.data(),
__s.data() + __s.size());
if (__st.empty())
- __throw_regex_error(regex_constants::error_collate);
+ __throw_regex_error(regex_constants::error_collate,
+ "Invalid collate element.");
_M_char_set.push_back(_M_translator._M_translate(__st[0]));
_GLIBCXX_DEBUG_ONLY(_M_is_ready = false);
return __st;
auto __st = _M_traits.lookup_collatename(__s.data(),
__s.data() + __s.size());
if (__st.empty())
- __throw_regex_error(regex_constants::error_collate);
+ __throw_regex_error(regex_constants::error_collate,
+ "Invalid equivalence class.");
__st = _M_traits.transform_primary(__st.data(),
__st.data() + __st.size());
_M_equiv_set.push_back(__st);
__s.data() + __s.size(),
__icase);
if (__mask == 0)
- __throw_regex_error(regex_constants::error_ctype);
+ __throw_regex_error(regex_constants::error_collate,
+ "Invalid character class.");
if (!__neg)
_M_class_set |= __mask;
else
_M_make_range(_CharT __l, _CharT __r)
{
if (__l > __r)
- __throw_regex_error(regex_constants::error_range);
+ __throw_regex_error(regex_constants::error_range,
+ "Invalid range in bracket expression.");
_M_range_set.push_back(make_pair(_M_translator._M_transform(__l),
_M_translator._M_transform(__r)));
_GLIBCXX_DEBUG_ONLY(_M_is_ready = false);
auto __neg = _M_value[0] == 'n';
this->_M_disjunction();
if (!_M_match_token(_ScannerT::_S_token_subexpr_end))
- __throw_regex_error(regex_constants::error_paren);
+ __throw_regex_error(regex_constants::error_paren,
+ "Parenthesis is not closed.");
auto __tmp = _M_pop();
__tmp._M_append(_M_nfa->_M_insert_accept());
_M_stack.push(
auto __init = [this, &__neg]()
{
if (_M_stack.empty())
- __throw_regex_error(regex_constants::error_badrepeat);
+ __throw_regex_error(regex_constants::error_badrepeat,
+ "Nothing to repeat before a quantifier.");
__neg = __neg && _M_match_token(_ScannerT::_S_token_opt);
};
if (_M_match_token(_ScannerT::_S_token_closure0))
else if (_M_match_token(_ScannerT::_S_token_interval_begin))
{
if (_M_stack.empty())
- __throw_regex_error(regex_constants::error_badrepeat);
+ __throw_regex_error(regex_constants::error_badrepeat,
+ "Nothing to repeat before a quantifier.");
if (!_M_match_token(_ScannerT::_S_token_dup_count))
- __throw_regex_error(regex_constants::error_badbrace);
+ __throw_regex_error(regex_constants::error_badbrace,
+ "Unexpected token in brace expression.");
_StateSeqT __r(_M_pop());
_StateSeqT __e(*_M_nfa, _M_nfa->_M_insert_dummy());
long __min_rep = _M_cur_int_value(10);
else
__n = 0;
if (!_M_match_token(_ScannerT::_S_token_interval_end))
- __throw_regex_error(regex_constants::error_brace);
+ __throw_regex_error(regex_constants::error_brace,
+ "Unexpected end of brace expression.");
__neg = __neg && _M_match_token(_ScannerT::_S_token_opt);
else
{
if (__n < 0)
- __throw_regex_error(regex_constants::error_badbrace);
+ __throw_regex_error(regex_constants::error_badbrace,
+ "Invalid range in brace expression.");
auto __end = _M_nfa->_M_insert_dummy();
// _M_alt is the "match more" branch, and _M_next is the
// "match less" one. Switch _M_alt and _M_next of all created
_StateSeqT __r(*_M_nfa, _M_nfa->_M_insert_dummy());
this->_M_disjunction();
if (!_M_match_token(_ScannerT::_S_token_subexpr_end))
- __throw_regex_error(regex_constants::error_paren);
+ __throw_regex_error(regex_constants::error_paren,
+ "Parenthesis is not closed.");
__r._M_append(_M_pop());
_M_stack.push(__r);
}
_StateSeqT __r(*_M_nfa, _M_nfa->_M_insert_subexpr_begin());
this->_M_disjunction();
if (!_M_match_token(_ScannerT::_S_token_subexpr_end))
- __throw_regex_error(regex_constants::error_paren);
+ __throw_regex_error(regex_constants::error_paren,
+ "Parenthesis is not closed.");
__r._M_append(_M_pop());
__r._M_append(_M_nfa->_M_insert_subexpr_end());
_M_stack.push(__r);
{
if (_M_match_token(_ScannerT::_S_token_bracket_end))
return false;
- __throw_regex_error(regex_constants::error_range);
+ __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];
{
if (_M_scanner._M_get_token()
!= _ScannerT::_S_token_bracket_end)
- __throw_regex_error(regex_constants::error_range);
+ __throw_regex_error(
+ regex_constants::error_range,
+ "Unexpected end of bracket expression.");
__matcher._M_add_char(_M_value[0]);
}
}
_M_ctype.is(_CtypeT::upper,
_M_value[0]));
else
- __throw_regex_error(regex_constants::error_brack);
+ __throw_regex_error(regex_constants::error_brack,
+ "Unexpected character in bracket expression.");
return true;
}
regex_constants::error_type
code() const
{ return _M_code; }
+
+ private:
+ regex_error(regex_constants::error_type __ecode, const char* __what)
+ : std::runtime_error(__what), _M_code(__ecode)
+ { }
+
+ friend void __throw_regex_error(regex_constants::error_type, const char*);
};
//@} // group regex
void
__throw_regex_error(regex_constants::error_type __ecode);
+ inline void
+ __throw_regex_error(regex_constants::error_type __ecode, const char* __what)
+ { _GLIBCXX_THROW_OR_ABORT(regex_error(__ecode, __what)); }
+
_GLIBCXX_END_NAMESPACE_VERSION
} // namespace std
if (__c == '\\')
{
if (_M_current == _M_end)
- __throw_regex_error(regex_constants::error_escape);
+ __throw_regex_error(
+ regex_constants::error_escape,
+ "Unexpected end of regex when escaping.");
if (!_M_is_basic()
|| (*_M_current != '('
if (_M_is_ecma() && *_M_current == '?')
{
if (++_M_current == _M_end)
- __throw_regex_error(regex_constants::error_paren);
+ __throw_regex_error(
+ regex_constants::error_paren,
+ "Unexpected end of regex when in an open parenthesis.");
if (*_M_current == ':')
{
_M_value.assign(1, 'n');
}
else
- __throw_regex_error(regex_constants::error_paren);
+ __throw_regex_error(
+ regex_constants::error_paren,
+ "Invalid special open parenthesis.");
}
else if (_M_flags & regex_constants::nosubs)
_M_token = _S_token_subexpr_no_group_begin;
_M_scan_in_bracket()
{
if (_M_current == _M_end)
- __throw_regex_error(regex_constants::error_brack);
+ __throw_regex_error(
+ regex_constants::error_brack,
+ "Unexpected end of regex when in bracket expression.");
auto __c = *_M_current++;
if (__c == '[')
{
if (_M_current == _M_end)
- __throw_regex_error(regex_constants::error_brack);
+ __throw_regex_error(regex_constants::error_brack,
+ "Unexpected character class open bracket.");
if (*_M_current == '.')
{
_M_scan_in_brace()
{
if (_M_current == _M_end)
- __throw_regex_error(regex_constants::error_brace);
+ __throw_regex_error(
+ regex_constants::error_brace,
+ "Unexpected end of regex when in brace expression.");
auto __c = *_M_current++;
++_M_current;
}
else
- __throw_regex_error(regex_constants::error_badbrace);
+ __throw_regex_error(regex_constants::error_badbrace,
+ "Unexpected character in brace expression.");
}
else if (__c == '}')
{
_M_token = _S_token_interval_end;
}
else
- __throw_regex_error(regex_constants::error_badbrace);
+ __throw_regex_error(regex_constants::error_badbrace,
+ "Unexpected character in brace expression.");
}
template<typename _CharT>
_M_eat_escape_ecma()
{
if (_M_current == _M_end)
- __throw_regex_error(regex_constants::error_escape);
+ __throw_regex_error(regex_constants::error_escape,
+ "Unexpected end of regex when escaping.");
auto __c = *_M_current++;
auto __pos = _M_find_escape(_M_ctype.narrow(__c, '\0'));
else if (__c == 'c')
{
if (_M_current == _M_end)
- __throw_regex_error(regex_constants::error_escape);
+ __throw_regex_error(
+ regex_constants::error_escape,
+ "Unexpected end of regex when reading control code.");
_M_token = _S_token_ord_char;
_M_value.assign(1, *_M_current++);
}
{
if (_M_current == _M_end
|| !_M_ctype.is(_CtypeT::xdigit, *_M_current))
- __throw_regex_error(regex_constants::error_escape);
+ __throw_regex_error(
+ regex_constants::error_escape,
+ "Unexpected end of regex when ascii character.");
_M_value += *_M_current++;
}
_M_token = _S_token_hex_num;
_M_eat_escape_posix()
{
if (_M_current == _M_end)
- __throw_regex_error(regex_constants::error_escape);
+ __throw_regex_error(regex_constants::error_escape,
+ "Unexpected end of regex when escaping.");
auto __c = *_M_current;
auto __pos = std::strchr(_M_spec_char, _M_ctype.narrow(__c, '\0'));
{
#ifdef __STRICT_ANSI__
// POSIX says it is undefined to escape ordinary characters
- __throw_regex_error(regex_constants::error_escape);
+ __throw_regex_error(regex_constants::error_escape,
+ "Unexpected escape character.");
#else
_M_token = _S_token_ord_char;
_M_value.assign(1, __c);
return;
}
else
- __throw_regex_error(regex_constants::error_escape);
+ __throw_regex_error(regex_constants::error_escape,
+ "Unexpected escape character.");
}
// Eats a character class or throws an exception.
|| *_M_current++ != ']') // skip ']'
{
if (__ch == ':')
- __throw_regex_error(regex_constants::error_ctype);
+ __throw_regex_error(regex_constants::error_ctype,
+ "Unexpected end of character class.");
else
- __throw_regex_error(regex_constants::error_collate);
+ __throw_regex_error(regex_constants::error_collate,
+ "Unexpected end of character class.");
}
}
projects / gcc.git / commitdiff