On 15/09/17 16:39 +0100, Jonathan Wakely wrote:
On 04/09/17 03:31 -0700, Tim Shen via libstdc++ wrote:
This fixes the follow-up comments in 71500.
Back-reference matching is different from other matching, as the
content the back-reference refers to is at "run-time", aka during
regex_match(), not regex() compilation.
For compilation we do have an abstraction layer to catch all
comparison customizations, namely _M_translator in regex_compiler.h.
Until this patch, we don't have an abstraction for "run-time"
matching. I believe that back-reference is the only place that needs
run-time matching, so I just build a _Backref_matcher in
regex_executot.tcc.
Tested on x86_64-linux-gnu.
Thanks!
--
Regards,
Tim Shen
commit a97b7fecd319e031ffc489a956b8cf3dc63eeb26
Author: Tim Shen <tims...@google.com>
Date: Mon Sep 4 03:19:35 2017 -0700
PR libstdc++/71500
* include/bits/regex_executor.tcc: Support icase in
regex_tratis<...> for back reference matches.
* testsuite/28_regex/regression.cc: Test case.
diff --git a/libstdc++-v3/include/bits/regex_executor.tcc
b/libstdc++-v3/include/bits/regex_executor.tcc
index 226e05856e1..f6149fecf9d 100644
--- a/libstdc++-v3/include/bits/regex_executor.tcc
+++ b/libstdc++-v3/include/bits/regex_executor.tcc
@@ -335,6 +335,54 @@ namespace __detail
_M_states._M_queue(__state._M_next, _M_cur_results);
}
+ template<typename _BiIter, typename _TraitsT>
+ struct _Backref_matcher
+ {
+ _Backref_matcher(bool __icase, const _TraitsT& __traits)
+ : _M_traits(__traits) { }
+
+ bool
+ _M_apply(_BiIter __expected_begin,
+ _BiIter __expected_end, _BiIter __actual_begin,
+ _BiIter __actual_end)
+ {
+ return _M_traits.transform(__expected_begin, __expected_end)
+ == _M_traits.transform(__actual_begin, __actual_end);
+ }
+
+ const _TraitsT& _M_traits;
+ };
+
+ template<typename _BiIter, typename _CharT>
+ struct _Backref_matcher<_BiIter, std::regex_traits<_CharT>>
+ {
+ using _TraitsT = std::regex_traits<_CharT>;
+ _Backref_matcher(bool __icase, const _TraitsT& __traits)
+ : _M_icase(__icase), _M_traits(__traits) { }
+
+ bool
+ _M_apply(_BiIter __expected_begin,
+ _BiIter __expected_end, _BiIter __actual_begin,
+ _BiIter __actual_end)
+ {
+ if (!_M_icase)
+ return std::equal(__expected_begin, __expected_end,
+ __actual_begin, __actual_end);
This is only valid in C++14 and higher, because the 4-argument version
of std::equal isn't present in C++11.
+ typedef std::ctype<_CharT> __ctype_type;
+ const auto& __fctyp = use_facet<__ctype_type>(_M_traits.getloc());
+ return std::equal(__expected_begin, __expected_end,
+ __actual_begin, __actual_end,
Same here.
+ [this, &__fctyp](_CharT __lhs, _CharT __rhs)
+ {
+ return __fctyp.tolower(__lhs)
+ == __fctyp.tolower(__rhs);
+ });
We need to rewrite this to check the lengths are equal first, and then
call the 3-argument version of std::equal.
Alternatively, we could move the implementation of the C++14
std::equal overloads to __equal and make that available for C++11.
I'll try that.
Here's a proof of concept patch for that. It's a bit ugly.
diff --git a/libstdc++-v3/include/bits/regex_executor.tcc b/libstdc++-v3/include/bits/regex_executor.tcc
index f6149fecf9d..4b185cc9d1e 100644
--- a/libstdc++-v3/include/bits/regex_executor.tcc
+++ b/libstdc++-v3/include/bits/regex_executor.tcc
@@ -366,17 +366,21 @@ namespace __detail
_BiIter __actual_end)
{
if (!_M_icase)
- return std::equal(__expected_begin, __expected_end,
- __actual_begin, __actual_end);
+ return std::__equal4(__expected_begin, __expected_end,
+ __actual_begin, __actual_end,
+ std::__iterator_category(__expected_begin),
+ std::__iterator_category(__actual_begin));
typedef std::ctype<_CharT> __ctype_type;
const auto& __fctyp = use_facet<__ctype_type>(_M_traits.getloc());
- return std::equal(__expected_begin, __expected_end,
- __actual_begin, __actual_end,
- [this, &__fctyp](_CharT __lhs, _CharT __rhs)
- {
- return __fctyp.tolower(__lhs)
- == __fctyp.tolower(__rhs);
- });
+ return std::__equal4_p(__expected_begin, __expected_end,
+ __actual_begin, __actual_end,
+ [this, &__fctyp](_CharT __lhs, _CharT __rhs)
+ {
+ return __fctyp.tolower(__lhs)
+ == __fctyp.tolower(__rhs);
+ },
+ std::__iterator_category(__expected_begin),
+ std::__iterator_category(__actual_begin));
}
bool _M_icase;
diff --git a/libstdc++-v3/include/bits/stl_algobase.h b/libstdc++-v3/include/bits/stl_algobase.h
index f68ecb22b82..b7848b3de99 100644
--- a/libstdc++-v3/include/bits/stl_algobase.h
+++ b/libstdc++-v3/include/bits/stl_algobase.h
@@ -1082,6 +1082,59 @@ _GLIBCXX_BEGIN_NAMESPACE_ALGO
return true;
}
+#if __cplusplus >= 201103L
+ template<typename _II1, typename _II2>
+ inline bool
+ __equal4(_II1 __first1, _II1 __last1, _II2 __first2, _II2 __last2,
+ random_access_iterator_tag, random_access_iterator_tag)
+ {
+ auto __d1 = std::distance(__first1, __last1);
+ auto __d2 = std::distance(__first2, __last2);
+ if (__d1 != __d2)
+ return false;
+ return _GLIBCXX_STD_A::equal(__first1, __last1, __first2);
+ }
+
+ template<typename _II1, typename _II2, typename _Cat1, typename _Cat2>
+ inline bool
+ __equal4(_II1 __first1, _II1 __last1, _II2 __first2, _II2 __last2,
+ _Cat1, _Cat2)
+ {
+ for (; __first1 != __last1 && __first2 != __last2;
+ ++__first1, (void)++__first2)
+ if (!(*__first1 == *__first2))
+ return false;
+ return __first1 == __last1 && __first2 == __last2;
+ }
+
+ template<typename _II1, typename _II2, typename _BinaryPredicate>
+ inline bool
+ __equal4_p(_II1 __first1, _II1 __last1, _II2 __first2, _II2 __last2,
+ _BinaryPredicate __binary_pred, random_access_iterator_tag,
+ random_access_iterator_tag)
+ {
+ auto __d1 = std::distance(__first1, __last1);
+ auto __d2 = std::distance(__first2, __last2);
+ if (__d1 != __d2)
+ return false;
+ return _GLIBCXX_STD_A::equal(__first1, __last1, __first2,
+ __binary_pred);
+ }
+
+ template<typename _II1, typename _II2, typename _BinaryPredicate,
+ typename _Cat1, typename _Cat2>
+ inline bool
+ __equal4_p(_II1 __first1, _II1 __last1, _II2 __first2, _II2 __last2,
+ _BinaryPredicate __binary_pred, _Cat1, _Cat2)
+ {
+ for (; __first1 != __last1 && __first2 != __last2;
+ ++__first1, (void)++__first2)
+ if (!bool(__binary_pred(*__first1, *__first2)))
+ return false;
+ return __first1 == __last1 && __first2 == __last2;
+ }
+#endif // C++11
+
#if __cplusplus > 201103L
#define __cpp_lib_robust_nonmodifying_seq_ops 201304
@@ -1112,24 +1165,9 @@ _GLIBCXX_BEGIN_NAMESPACE_ALGO
__glibcxx_requires_valid_range(__first1, __last1);
__glibcxx_requires_valid_range(__first2, __last2);
- using _RATag = random_access_iterator_tag;
- using _Cat1 = typename iterator_traits<_II1>::iterator_category;
- using _Cat2 = typename iterator_traits<_II2>::iterator_category;
- using _RAIters = __and_<is_same<_Cat1, _RATag>, is_same<_Cat2, _RATag>>;
- if (_RAIters())
- {
- auto __d1 = std::distance(__first1, __last1);
- auto __d2 = std::distance(__first2, __last2);
- if (__d1 != __d2)
- return false;
- return _GLIBCXX_STD_A::equal(__first1, __last1, __first2);
- }
-
- for (; __first1 != __last1 && __first2 != __last2;
- ++__first1, (void)++__first2)
- if (!(*__first1 == *__first2))
- return false;
- return __first1 == __last1 && __first2 == __last2;
+ return _GLIBCXX_STD_A::__equal4(__first1, __last1, __first2, __last2,
+ __iterator_category(__first1),
+ __iterator_category(__first2));
}
/**
@@ -1159,27 +1197,12 @@ _GLIBCXX_BEGIN_NAMESPACE_ALGO
__glibcxx_requires_valid_range(__first1, __last1);
__glibcxx_requires_valid_range(__first2, __last2);
- using _RATag = random_access_iterator_tag;
- using _Cat1 = typename iterator_traits<_IIter1>::iterator_category;
- using _Cat2 = typename iterator_traits<_IIter2>::iterator_category;
- using _RAIters = __and_<is_same<_Cat1, _RATag>, is_same<_Cat2, _RATag>>;
- if (_RAIters())
- {
- auto __d1 = std::distance(__first1, __last1);
- auto __d2 = std::distance(__first2, __last2);
- if (__d1 != __d2)
- return false;
- return _GLIBCXX_STD_A::equal(__first1, __last1, __first2,
- __binary_pred);
- }
-
- for (; __first1 != __last1 && __first2 != __last2;
- ++__first1, (void)++__first2)
- if (!bool(__binary_pred(*__first1, *__first2)))
- return false;
- return __first1 == __last1 && __first2 == __last2;
+ return _GLIBCXX_STD_A::__equal4_p(__first1, __last1, __first2, __last2,
+ __binary_pred,
+ __iterator_category(__first1),
+ __iterator_category(__first2));
}
-#endif
+#endif // C++14
/**
* @brief Performs @b dictionary comparison on ranges.
