regex_scanner.tcc: (_Scanner<>::_M_scan_normal...

2013-10-18  Tim Shen  <timshen91@gmail.com>

	* include/bits/regex_scanner.tcc: (_Scanner<>::_M_scan_normal,
	_Scanner<>::_M_eat_escape_ecma, _Scanner<>::_M_eat_escape_posix,
	_Scanner<>::_M_eat_escape_awk): Narrow character before finding in maps.
	* testsuite/28_regex/algorithms/regex_match/ecma/wchar_t/cjk_match.cc:
	New.

From-SVN: r203827

diff --git a/libstdc++-v3/ChangeLog b/libstdc++-v3/ChangeLog
index 5ae46af37811514117dece310b723107a2da0120..b37fdb64aa7935c6ea9ad1d7edfc5a1a2f803793 100644 (file)
--- a/libstdc++-v3/ChangeLog
+++ b/libstdc++-v3/ChangeLog
@@ -1,3 +1,11 @@
+2013-10-18  Tim Shen  <timshen91@gmail.com>
+
+       * include/bits/regex_scanner.tcc: (_Scanner<>::_M_scan_normal,
+       _Scanner<>::_M_eat_escape_ecma, _Scanner<>::_M_eat_escape_posix,
+       _Scanner<>::_M_eat_escape_awk): Narrow character before finding in maps.
+       * testsuite/28_regex/algorithms/regex_match/ecma/wchar_t/cjk_match.cc:
+       New.
+
 2013-10-17  Tim Shen  <timshen91@gmail.com>
 
        * include/bits/regex.h (regex_token_iterator<>::regex_token_iterator):

diff --git a/libstdc++-v3/include/bits/regex_scanner.tcc b/libstdc++-v3/include/bits/regex_scanner.tcc
index 21d1e91f5f72ec5c203390c4e9240693ae517954..f6cef6a04c2d2183bf4f7cb293d2a173d9843c1a 100644 (file)
--- a/libstdc++-v3/include/bits/regex_scanner.tcc
+++ b/libstdc++-v3/include/bits/regex_scanner.tcc
@@ -244,7 +244,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
          _M_state = _S_state_in_brace;
          _M_token = _S_token_interval_begin;
        }
-      else if ((_M_spec_char.count(__c)
+      else if ((_M_spec_char.count(_M_ctype.narrow(__c, '\0'))
                && __c != ']'
                && __c != '}')
               || (_M_is_grep() && __c == '\n'))
@@ -367,7 +367,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
 
       auto __c = *_M_current++;
 
-      if (_M_escape_map.count(__c)
+      if (_M_escape_map.count(_M_ctype.narrow(__c, '\0'))
          && (__c != 'b' || _M_state == _S_state_in_bracket))
        {
          _M_token = _S_token_ord_char;
@@ -441,7 +441,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
 
       auto __c = *_M_current;
 
-      if (_M_spec_char.count(__c))
+      if (_M_spec_char.count(_M_ctype.narrow(__c, '\0')))
        {
          _M_token = _S_token_ord_char;
          _M_value.assign(1, __c);
@@ -476,7 +476,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
     {
       auto __c = *_M_current++;
 
-      if (_M_escape_map.count(__c))
+      if (_M_escape_map.count(_M_ctype.narrow(__c, '\0')))
        {
          _M_token = _S_token_ord_char;
          _M_value.assign(1, _M_escape_map.at(__c));

diff --git a/libstdc++-v3/testsuite/28_regex/algorithms/regex_match/ecma/wchar_t/cjk_match.cc b/libstdc++-v3/testsuite/28_regex/algorithms/regex_match/ecma/wchar_t/cjk_match.cc
new file mode 100644 (file)
index 0000000..15929dd
--- /dev/null
+++ b/libstdc++-v3/testsuite/28_regex/algorithms/regex_match/ecma/wchar_t/cjk_match.cc
@@ -0,0 +1,50 @@
+// { dg-options "-std=gnu++11" }
+
+//
+// 2013-10-18  Tim Shen <timshen91@gmail.com>
+//
+// Copyright (C) 2013 Free Software Foundation, Inc.
+//
+// This file is part of the GNU ISO C++ Library.  This library is free
+// software; you can redistribute it and/or modify it under the
+// terms of the GNU General Public License as published by the
+// Free Software Foundation; either version 3, or (at your option)
+// any later version.
+//
+// This library is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License along
+// with this library; see the file COPYING3.  If not see
+// <http://www.gnu.org/licenses/>.
+
+// 28.11.2 regex_match
+// Tests CJK support.
+
+#include <regex>
+#include <testsuite_hooks.h>
+#include <testsuite_regex.h>
+
+using namespace __gnu_test;
+using namespace std;
+
+void
+test01()
+{
+  bool test __attribute__((unused)) = true;
+
+  const wchar_t * s = L"\u4f60\u597d\u002c\u0020\u4e16\u002b\u754c";
+
+  wregex re(s);
+  VERIFY(regex_match_debug(L"\u4f60\u597d\u002c\u0020\u4e16\u4e16\u4e16\u754c",
+                          re));
+}
+
+int
+main()
+{
+  test01();
+  return 0;
+}