[libcxx] r285352 - [libcxx] Make regex_match backtrack when search fails

Tim Shen via cfe-commits cfe-commits at lists.llvm.org
Thu Oct 27 14:40:34 PDT 2016


Author: timshen
Date: Thu Oct 27 16:40:34 2016
New Revision: 285352

URL: http://llvm.org/viewvc/llvm-project?rev=285352&view=rev
Log:
[libcxx] Make regex_match backtrack when search fails

Summary:
Fixes PR19851.
alg.re.match/ecma.pass.cpp still XFAILS on linux, but after commenting out
locale-related tests, it passes. I don't have a freebsd machine to produce a
full pass.

Reviewers: mclow.lists

Subscribers: cfe-commits, emaste

Differential Revision: https://reviews.llvm.org/D26026

Modified:
    libcxx/trunk/include/regex
    libcxx/trunk/test/std/re/re.alg/re.alg.match/ecma.pass.cpp

Modified: libcxx/trunk/include/regex
URL: http://llvm.org/viewvc/llvm-project/libcxx/trunk/include/regex?rev=285352&r1=285351&r2=285352&view=diff
==============================================================================
--- libcxx/trunk/include/regex (original)
+++ libcxx/trunk/include/regex Thu Oct 27 16:40:34 2016
@@ -865,7 +865,8 @@ enum match_flag_type
     format_sed        = 1 << 8,
     format_no_copy    = 1 << 9,
     format_first_only = 1 << 10,
-    __no_update_pos   = 1 << 11
+    __no_update_pos   = 1 << 11,
+    __full_match      = 1 << 12
 };
 
 inline _LIBCPP_INLINE_VISIBILITY
@@ -2984,10 +2985,12 @@ __lookahead<_CharT, _Traits>::__exec(__s
 {
     match_results<const _CharT*> __m;
     __m.__init(1 + __exp_.mark_count(), __s.__current_, __s.__last_);
-    bool __matched = __exp_.__match_at_start_ecma(__s.__current_, __s.__last_,
-                                                  __m,
-                                                  __s.__flags_ | regex_constants::match_continuous,
-                                                  __s.__at_first_ && __s.__current_ == __s.__first_);
+    bool __matched = __exp_.__match_at_start_ecma(
+        __s.__current_, __s.__last_,
+        __m,
+        (__s.__flags_ | regex_constants::match_continuous) &
+        ~regex_constants::__full_match,
+        __s.__at_first_ && __s.__current_ == __s.__first_);
     if (__matched != __invert_)
     {
         __s.__do_ = __state::__accept_but_not_consume;
@@ -5555,12 +5558,18 @@ basic_regex<_CharT, _Traits>::__match_at
             switch (__s.__do_)
             {
             case __state::__end_state:
-                if (__flags & regex_constants::match_not_null &&
+                if ((__flags & regex_constants::match_not_null) &&
                     __s.__current_ == __first)
                 {
                   __states.pop_back();
                   break;
                 }
+                if ((__flags & regex_constants::__full_match) &&
+                    __s.__current_ != __last)
+                {
+                  __states.pop_back();
+                  break;
+                }
                 __m.__matches_[0].first = __first;
                 __m.__matches_[0].second = _VSTD::next(__first, __s.__current_ - __first);
                 __m.__matches_[0].matched = true;
@@ -5624,12 +5633,18 @@ basic_regex<_CharT, _Traits>::__match_at
             switch (__s.__do_)
             {
             case __state::__end_state:
-                if (__flags & regex_constants::match_not_null &&
+                if ((__flags & regex_constants::match_not_null) &&
                     __s.__current_ == __first)
                 {
                   __states.pop_back();
                   break;
                 }
+                if ((__flags & regex_constants::__full_match) &&
+                    __s.__current_ != __last)
+                {
+                  __states.pop_back();
+                  break;
+                }
                 if (!__matched || __highest_j < __s.__current_ - __s.__first_)
                     __highest_j = __s.__current_ - __s.__first_;
                 __matched = true;
@@ -5715,12 +5730,18 @@ basic_regex<_CharT, _Traits>::__match_at
             switch (__s.__do_)
             {
             case __state::__end_state:
-                if (__flags & regex_constants::match_not_null &&
+                if ((__flags & regex_constants::match_not_null) &&
                     __s.__current_ == __first)
                 {
                   __states.pop_back();
                   break;
                 }
+                if ((__flags & regex_constants::__full_match) &&
+                    __s.__current_ != __last)
+                {
+                  __states.pop_back();
+                  break;
+                }
                 if (!__matched || __highest_j < __s.__current_ - __s.__first_)
                 {
                     __highest_j = __s.__current_ - __s.__first_;
@@ -5951,8 +5972,10 @@ regex_match(_BidirectionalIterator __fir
             const basic_regex<_CharT, _Traits>& __e,
             regex_constants::match_flag_type __flags = regex_constants::match_default)
 {
-    bool __r = _VSTD::regex_search(__first, __last, __m, __e,
-                            __flags | regex_constants::match_continuous);
+    bool __r = _VSTD::regex_search(
+        __first, __last, __m, __e,
+        __flags | regex_constants::match_continuous |
+        regex_constants::__full_match);
     if (__r)
     {
         __r = !__m.suffix().matched;

Modified: libcxx/trunk/test/std/re/re.alg/re.alg.match/ecma.pass.cpp
URL: http://llvm.org/viewvc/llvm-project/libcxx/trunk/test/std/re/re.alg/re.alg.match/ecma.pass.cpp?rev=285352&r1=285351&r2=285352&view=diff
==============================================================================
--- libcxx/trunk/test/std/re/re.alg/re.alg.match/ecma.pass.cpp (original)
+++ libcxx/trunk/test/std/re/re.alg/re.alg.match/ecma.pass.cpp Thu Oct 27 16:40:34 2016
@@ -371,16 +371,37 @@ int main()
     }
     {
         std::cmatch m;
+        // http://www.open-std.org/jtc1/sc22/wg21/docs/lwg-defects.html#2273
         const char s[] = "tournament";
-        assert(!std::regex_match(s, m, std::regex("tour|to|tournament")));
-        assert(m.size() == 0);
+        assert(std::regex_match(s, m, std::regex("tour|to|tournament")));
+        assert(m.size() == 1);
+        assert(!m.prefix().matched);
+        assert(m.prefix().first == s);
+        assert(m.prefix().second == m[0].first);
+        assert(!m.suffix().matched);
+        assert(m.suffix().first == m[0].second);
+        assert(m.suffix().second == m[0].second);
+        assert(m.length(0) == std::char_traits<char>::length(s));
+        assert(m.position(0) == 0);
+        assert(m.str(0) == s);
     }
     {
         std::cmatch m;
+        // http://www.open-std.org/jtc1/sc22/wg21/docs/lwg-defects.html#2273
         const char s[] = "tournamenttotour";
-        assert(!std::regex_match(s, m, std::regex("(tour|to|tournament)+",
-               std::regex_constants::nosubs)));
-        assert(m.size() == 0);
+        assert(
+            std::regex_match(s, m, std::regex("(tour|to|tournament)+",
+                                              std::regex_constants::nosubs)));
+        assert(m.size() == 1);
+        assert(!m.prefix().matched);
+        assert(m.prefix().first == s);
+        assert(m.prefix().second == m[0].first);
+        assert(!m.suffix().matched);
+        assert(m.suffix().first == m[0].second);
+        assert(m.suffix().second == m[0].second);
+        assert(m.length(0) == std::char_traits<char>::length(s));
+        assert(m.position(0) == 0);
+        assert(m.str(0) == s);
     }
     {
         std::cmatch m;
@@ -1036,16 +1057,37 @@ int main()
     }
     {
         std::wcmatch m;
+        // http://www.open-std.org/jtc1/sc22/wg21/docs/lwg-defects.html#2273
         const wchar_t s[] = L"tournament";
-        assert(!std::regex_match(s, m, std::wregex(L"tour|to|tournament")));
-        assert(m.size() == 0);
+        assert(std::regex_match(s, m, std::wregex(L"tour|to|tournament")));
+        assert(m.size() == 1);
+        assert(!m.prefix().matched);
+        assert(m.prefix().first == s);
+        assert(m.prefix().second == m[0].first);
+        assert(!m.suffix().matched);
+        assert(m.suffix().first == m[0].second);
+        assert(m.suffix().second == m[0].second);
+        assert(m.length(0) == std::char_traits<wchar_t>::length(s));
+        assert(m.position(0) == 0);
+        assert(m.str(0) == s);
     }
     {
         std::wcmatch m;
+        // http://www.open-std.org/jtc1/sc22/wg21/docs/lwg-defects.html#2273
         const wchar_t s[] = L"tournamenttotour";
-        assert(!std::regex_match(s, m, std::wregex(L"(tour|to|tournament)+",
-               std::regex_constants::nosubs)));
-        assert(m.size() == 0);
+        assert(
+            std::regex_match(s, m, std::wregex(L"(tour|to|tournament)+",
+                                               std::regex_constants::nosubs)));
+        assert(m.size() == 1);
+        assert(!m.prefix().matched);
+        assert(m.prefix().first == s);
+        assert(m.prefix().second == m[0].first);
+        assert(!m.suffix().matched);
+        assert(m.suffix().first == m[0].second);
+        assert(m.suffix().second == m[0].second);
+        assert(m.length(0) == std::char_traits<wchar_t>::length(s));
+        assert(m.position(0) == 0);
+        assert(m.str(0) == s);
     }
     {
         std::wcmatch m;




More information about the cfe-commits mailing list