timshen created this revision.
Herald added a subscriber: sanjoy.
Herald added a reviewer: EricWF.
Always lookup the class name, even when the traits type is regex_traits<>.
The lookup happens at regex compile time, so it shouldn't affect the
performance.
I also added ja_JP.UTF-8 as a common locale.
https://reviews.llvm.org/D37958
Files:
libcxx/include/regex
libcxx/test/std/re/re.traits/lookup_classname_user_defined.pass.cpp
libcxx/utils/libcxx/test/target_info.py
Index: libcxx/utils/libcxx/test/target_info.py
===================================================================
--- libcxx/utils/libcxx/test/target_info.py
+++ libcxx/utils/libcxx/test/target_info.py
@@ -55,6 +55,7 @@
('fr_FR.UTF-8', 'French_France.1252'),
('ru_RU.UTF-8', 'Russian_Russia.1251'),
('zh_CN.UTF-8', 'Chinese_China.936'),
+ ('ja_JP.UTF-8', 'Japanese_Japan.932'),
('fr_CA.ISO8859-1', 'French_Canada.1252'),
('cs_CZ.ISO8859-2', 'Czech_Czech Republic.1250')
]
Index: libcxx/test/std/re/re.traits/lookup_classname_user_defined.pass.cpp
===================================================================
--- /dev/null
+++ libcxx/test/std/re/re.traits/lookup_classname_user_defined.pass.cpp
@@ -0,0 +1,54 @@
+//===----------------------------------------------------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+// REQUIRES: locale.ja_JP.UTF-8
+
+// <regex>
+
+// template <class charT> struct regex_traits;
+
+// template <class ForwardIterator>
+// char_class_type
+// lookup_classname(ForwardIterator first, ForwardIterator last,
+// bool icase = false) const;
+
+#include <regex>
+#include <cassert>
+#include "test_macros.h"
+#include "platform_support.h" // locale name macros
+
+struct wctype_traits : std::regex_traits<wchar_t>
+{
+ using char_class_type = std::wctype_t;
+ template<class ForwardIt>
+ char_class_type lookup_classname(ForwardIt first, ForwardIt last, bool icase = false ) const {
+ (void)icase;
+ return std::wctype(std::string(first, last).c_str());
+ }
+ bool isctype(wchar_t c, char_class_type f) const {
+ return std::iswctype(c, f);
+ }
+};
+
+int main()
+{
+ std::locale::global(std::locale("ja_JP.utf8"));
+ std::wsmatch m;
+ std::wstring in = L"風の谷のナウシカ";
+
+ // matches all characters (they are classified as alnum)
+ std::wstring re1 = L"([[:alnum:]]+)";
+ std::regex_search(in, m, std::wregex(re1));
+ assert(m[1] == L"風の谷のナウシカ");
+
+ // matches only the kanji
+ std::wstring re2 = L"([[:jkata:]]+)";
+ std::regex_search(in, m, std::basic_regex<wchar_t, wctype_traits>(re2));
+ assert(m[1] == L"ナウシカ");
+}
Index: libcxx/include/regex
===================================================================
--- libcxx/include/regex
+++ libcxx/include/regex
@@ -2213,8 +2213,8 @@
vector<pair<string_type, string_type> > __ranges_;
vector<pair<_CharT, _CharT> > __digraphs_;
vector<string_type> __equivalences_;
- typename regex_traits<_CharT>::char_class_type __mask_;
- typename regex_traits<_CharT>::char_class_type __neg_mask_;
+ typename _Traits::char_class_type __mask_;
+ typename _Traits::char_class_type __neg_mask_;
bool __negate_;
bool __icase_;
bool __collate_;
@@ -2307,12 +2307,26 @@
_LIBCPP_INLINE_VISIBILITY
void __add_equivalence(const string_type& __s)
{__equivalences_.push_back(__s);}
+
+ template<typename _Iter>
_LIBCPP_INLINE_VISIBILITY
- void __add_class(typename regex_traits<_CharT>::char_class_type __mask)
- {__mask_ |= __mask;}
+ void __add_class(_Iter __begin, _Iter __end)
+ {
+ auto __class_type = __traits_.lookup_classname(__begin, __end, __icase_);
+ if (__class_type == 0)
+ __throw_regex_error<regex_constants::error_brack>();
+ __mask_ |= __class_type;
+ }
+
+ template<typename _Iter>
_LIBCPP_INLINE_VISIBILITY
- void __add_neg_class(typename regex_traits<_CharT>::char_class_type __mask)
- {__neg_mask_ |= __mask;}
+ void __add_neg_class(_Iter __begin, _Iter __end)
+ {
+ auto __class_type = __traits_.lookup_classname(__begin, __end, true);
+ if (__class_type == 0)
+ __throw_regex_error<regex_constants::error_brack>();
+ __neg_mask_ |= __class_type;
+ }
};
template <class _CharT, class _Traits>
@@ -3841,23 +3855,23 @@
__str = _CharT(8);
return ++__first;
case 'd':
- __ml->__add_class(ctype_base::digit);
+ __ml->__add_class(__first, std::next(__first));
return ++__first;
case 'D':
- __ml->__add_neg_class(ctype_base::digit);
+ __ml->__add_neg_class(__first, std::next(__first));
return ++__first;
case 's':
- __ml->__add_class(ctype_base::space);
+ __ml->__add_class(__first, std::next(__first));
return ++__first;
case 'S':
- __ml->__add_neg_class(ctype_base::space);
+ __ml->__add_neg_class(__first, std::next(__first));
return ++__first;
case 'w':
- __ml->__add_class(ctype_base::alnum);
+ __ml->__add_class(__first, std::next(__first));
__ml->__add_char('_');
return ++__first;
case 'W':
- __ml->__add_neg_class(ctype_base::alnum);
+ __ml->__add_neg_class(__first, std::next(__first));
__ml->__add_neg_char('_');
return ++__first;
}
@@ -4003,12 +4017,7 @@
if (__temp == __last)
__throw_regex_error<regex_constants::error_brack>();
// [__first, __temp) contains all text in [: ... :]
- typedef typename _Traits::char_class_type char_class_type;
- char_class_type __class_type =
- __traits_.lookup_classname(__first, __temp, __flags_ & icase);
- if (__class_type == 0)
- __throw_regex_error<regex_constants::error_brack>();
- __ml->__add_class(__class_type);
+ __ml->__add_class(__first, __temp);
__first = _VSTD::next(__temp, 2);
return __first;
}
@@ -4341,33 +4350,33 @@
{
case 'd':
__ml = __start_matching_list(false);
- __ml->__add_class(ctype_base::digit);
+ __ml->__add_class(__first, std::next(__first));
++__first;
break;
case 'D':
__ml = __start_matching_list(true);
- __ml->__add_class(ctype_base::digit);
+ __ml->__add_class(__first, std::next(__first));
++__first;
break;
case 's':
__ml = __start_matching_list(false);
- __ml->__add_class(ctype_base::space);
+ __ml->__add_class(__first, std::next(__first));
++__first;
break;
case 'S':
__ml = __start_matching_list(true);
- __ml->__add_class(ctype_base::space);
+ __ml->__add_class(__first, std::next(__first));
++__first;
break;
case 'w':
__ml = __start_matching_list(false);
- __ml->__add_class(ctype_base::alnum);
+ __ml->__add_class(__first, std::next(__first));
__ml->__add_char('_');
++__first;
break;
case 'W':
__ml = __start_matching_list(true);
- __ml->__add_class(ctype_base::alnum);
+ __ml->__add_class(__first, std::next(__first));
__ml->__add_char('_');
++__first;
break;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
