[libcxx-commits] [libcxx] c14ac80 - [FIX][libc++][Regex] Using regex_constants match_prev_avail | match_not_bol | match_not_bow

[Diogo Sampaio via libcxx-commits]

Author: Diogo Sampaio
Date: 2020-04-30T23:36:25+01:00
New Revision: c14ac8043ed1d8128e515c88e78186dd1ca5a655

URL: https://github.com/llvm/llvm-project/commit/c14ac8043ed1d8128e515c88e78186dd1ca5a655
DIFF: https://github.com/llvm/llvm-project/commit/c14ac8043ed1d8128e515c88e78186dd1ca5a655.diff

LOG: [FIX][libc++][Regex] Using regex_constants match_prev_avail | match_not_bol | match_not_bow

Summary:
pr42199
When using regex_constants::match_prev_avail, it is defined that
--first is valid, and match_not_bol and match_not_bow should be
ignored. At the moment these flags are not ignored. This fixis that.

Reviewers: ldionne, miyuki, EricWF, mclow.lists, #libc

Reviewed By: ldionne, miyuki, #libc

Subscribers: broadwaylamb, dexonsmith, libcxx-commits

Tags: #libc

Differential Revision: https://reviews.llvm.org/D75622

Added: 
    libcxx/test/std/re/re.const/re.matchflag/match_prev_avail.pass.cpp

Modified: 
    libcxx/include/regex

Removed: 
    


################################################################################
diff  --git a/libcxx/include/regex b/libcxx/include/regex
index c917c401293d..433ba0ffe1fa 100644
--- a/libcxx/include/regex
+++ b/libcxx/include/regex
@@ -5940,6 +5940,9 @@ basic_regex<_CharT, _Traits>::__search(
         match_results<const _CharT*, _Allocator>& __m,
         regex_constants::match_flag_type __flags) const
 {
+    if (__flags & regex_constants::match_prev_avail)
+        __flags &= ~(regex_constants::match_not_bol | regex_constants::match_not_bow);
+
     __m.__init(1 + mark_count(), __first, __last,
                                     __flags & regex_constants::__no_update_pos);
     if (__match_at_start(__first, __last, __m, __flags,

diff  --git a/libcxx/test/std/re/re.const/re.matchflag/match_prev_avail.pass.cpp b/libcxx/test/std/re/re.const/re.matchflag/match_prev_avail.pass.cpp
new file mode 100644
index 000000000000..e42895b2c159
--- /dev/null
+++ b/libcxx/test/std/re/re.const/re.matchflag/match_prev_avail.pass.cpp
@@ -0,0 +1,82 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+// <regex>
+
+// match_prev_avail:
+//     --first is a valid iterator position. When this flag is set the flags
+//     match_not_bol and match_not_bow shall be ignored by the regular
+//     expression algorithms (30.11) and iterators (30.12)
+
+#include <cassert>
+#include <regex>
+using namespace std;
+
+int main() {
+  char str1[] = "\na";
+  auto str1_scnd = str1 + 1;
+  // Assert that match_prev_avail disables match_not_bol and this matches
+  assert(regex_match(str1 + 1, str1 + 2, regex("^a"),
+                     regex_constants::match_not_bol |
+                         regex_constants::match_prev_avail));
+  // Manually passing match_prev_avail defines that --str1 is a valid position
+  assert(regex_match(str1_scnd, regex("a"),
+                     regex_constants::match_not_bol |
+                         regex_constants::match_prev_avail));
+
+  //Assert that match_prev_avail disables match_not_bow and this matches
+  assert(regex_search(str1, regex("\\ba")));
+  assert(regex_match(str1 + 1, str1 + 2, regex("\\ba\\b"),
+                     regex_constants::match_not_bow |
+                         regex_constants::match_prev_avail));
+  assert(regex_search(str1, regex("\\ba"),
+                      regex_constants::match_not_bow |
+                          regex_constants::match_prev_avail));
+
+  //Assert that match_prev_avail disables both match_not_bow and match_not_bol
+  assert(regex_match(str1 + 1, str1 + 2, regex("^a"),
+                     regex_constants::match_not_bol |
+                         regex_constants::match_not_bow |
+                         regex_constants::match_prev_avail));
+  assert(regex_match(str1_scnd, regex("\\ba"),
+                     regex_constants::match_not_bol |
+                         regex_constants::match_not_bow |
+                         regex_constants::match_prev_avail));
+
+  // pr 42199
+  string S = " cd";
+  string::iterator Start = S.begin() + 1;
+  string::iterator End = S.end();
+  assert(regex_search(Start, End, regex("^cd")));
+
+  assert(
+      !regex_search(Start, End, regex("^cd"), regex_constants::match_not_bol));
+  assert(!regex_search(Start, End, regex(".*\\bcd\\b"),
+                       regex_constants::match_not_bow));
+  assert(!regex_search(Start, End, regex("^cd"),
+                       regex_constants::match_not_bol |
+                           regex_constants::match_not_bow));
+  assert(!regex_search(Start, End, regex(".*\\bcd\\b"),
+                       regex_constants::match_not_bol |
+                           regex_constants::match_not_bow));
+
+  assert(regex_search(Start, End, regex("^cd"),
+                      regex_constants::match_prev_avail));
+
+  assert(regex_search(Start, End, regex("^cd"),
+                      regex_constants::match_not_bol |
+                          regex_constants::match_prev_avail));
+  assert(regex_search(Start, End, regex("^cd"),
+                      regex_constants::match_not_bow |
+                          regex_constants::match_prev_avail));
+  assert(regex_match(Start, End, regex("\\bcd\\b"),
+                     regex_constants::match_not_bol |
+                         regex_constants::match_not_bow |
+                         regex_constants::match_prev_avail));
+  return 0;
+}