Patchwork [libstdc++-v3] Add newlib specific ctype_members.cc

login
register
mail settings
Submitter Yufeng Zhang
Date June 6, 2011, 5:33 p.m.
Message ID <000101cc246f$cc935840$65ba08c0$@Zhang@arm.com>
Download mbox | patch
Permalink /patch/98963/
State New
Headers show

Comments

Yufeng Zhang - June 6, 2011, 5:33 p.m.
This time with the patch attached.

Yufeng

> -----Original Message-----
> From: Yufeng Zhang [mailto:Yufeng.Zhang@arm.com]
> Sent: 06 June 2011 18:31
> To: gcc-patches@gcc.gnu.org
> Subject: [PATCH, libstdc++-v3] Add newlib specific ctype_members.cc
> 
> Hi,
> 
> This patch fixes an issue in the ctype<wchar_t> implementation when the
> newlib C library is used.
> 
> The generic version of ctype<wchar_t>::_M_convert_to_wmask() in
> config/locale/generic/ctype_members.cc assumes that a character type
> mask is either a bitmask with only 1 bit set or a bitwise-OR result of
> other character type masks; for instance, as illustrated in the C++
> Standard 2003 TC1 [lib.category.ctype]:
> 
>   enum mask { // numeric values are for exposition only.
>     space=1<<0, print=1<<1, cntrl=1<<2, upper=1<<3, lower=1<<4,
>     alpha=1<<5, digit=1<<6, punct=1<<7, xdigit=1<<8,
>     alnum=alpha|digit, graph=alnum|punct
>   };
> 
> The newlibc has a more compact character type mask definition; it uses
> one byte only to represent the masks:
> 
> (newlib/libc/include/ctype.h)
>     #define _U 01
>     #define _L 02
>     #define _N 04
>     #define _S 010
>     #define _P 020
>     #define _C 040
>     #define _X 0100
>     #define _B 0200
> 
> (libstdc++-v3/config/os/newlib/ctype_base.h)
>     typedef char mask;
>     static const mask upper = _U;
>     static const mask lower = _L;
>     static const mask alpha = _U | _L;
>     static const mask digit = _N;
>     static const mask xdigit = _X | _N;
>     static const mask space = _S;
>     static const mask print = _P | _U | _L | _N | _B;
>     static const mask graph = _P | _U | _L | _N;
>     static const mask cntrl = _C;
>     static const mask punct = _P;
>     static const mask alnum = _U | _L | _N;
> 
> For _X and _B, the generic version of
> ctype<wchar_t>::_M_convert_to_wmask() fails to obtain their
> corresponding wmasks, while other ctype_members.cc variants at
> config/locale/{gnu,darwin}/ are not capable in handling this case
> either.
> 
> Therefore, in this patch, a newlib specific ctype_members.cc is added
> at config/locale/newlib/, and acinclude.m4 is modified to use the new
> ctype_members.cc when with_newlib is enabled. The main difference in
> this
> ctype_members.cc from the generic version is the addition of the
> special
> handling of xdigit and print at the end of
> ctype<wchar_t>::_M_convert_to_wmask().
> 
> With this patch the following test failure (when the C library is the
> newlib C) will be fixed:
>     libstdc++-v3/testsuite/22_locale/ctype/scan/wchar_t/1.cc.
> 
> The patch has passed the regression test with armv7-a arm-eabi on qemu.
> 
> Is it OK for trunk?
> 
> Thanks,
> Yufeng
> 
> 
> libstdc++-v3/ChangeLog
> 2011-06-06  Yufeng Zhang  <yufeng.zhang@arm.com>
> 
>         * config/locale/newlib/ctype_members.cc: New file.
>         * acinclude.m4 (GLIBCXX_ENABLE_CLOCALE): Add a new C locale
>         kind: newlib.  Configure to use the newlib specific
>         ctype_members.cc when with_newlib is enabled.
>         * configure: Regenerate.

Patch

diff --git a/libstdc++-v3/acinclude.m4 b/libstdc++-v3/acinclude.m4
index ed8b129..7f9231c 100644
--- a/libstdc++-v3/acinclude.m4
+++ b/libstdc++-v3/acinclude.m4
@@ -1753,7 +1753,7 @@  dnl
 AC_DEFUN([GLIBCXX_ENABLE_CLOCALE], [
   GLIBCXX_ENABLE(clocale,auto,[[[=MODEL]]],
     [use MODEL for target locale package],
-    [permit generic|gnu|ieee_1003.1-2001|yes|no|auto])
+    [permit generic|gnu|ieee_1003.1-2001|newlib|yes|no|auto])
 
   # Deal with gettext issues.  Default to not using it (=no) until we detect
   # support for it later.  Let the user turn it off via --e/d, but let that
@@ -1764,7 +1764,7 @@  AC_DEFUN([GLIBCXX_ENABLE_CLOCALE], [
     [],
     [enable_nls=yes])
 
-  # Either a known packaage, or "auto"
+  # Either a known package, or "auto"
   if test $enable_clocale = no || test $enable_clocale = yes; then
      enable_clocale=auto
   fi
@@ -1781,7 +1781,11 @@  AC_DEFUN([GLIBCXX_ENABLE_CLOCALE], [
 	enable_clocale_flag=darwin
 	;;
       *)
-	enable_clocale_flag=generic
+	if test x"$with_newlib" = x"yes"; then
+	  enable_clocale_flag=newlib
+	else
+	  enable_clocale_flag=generic
+	fi
 	;;
     esac
   fi
@@ -1915,6 +1919,22 @@  AC_DEFUN([GLIBCXX_ENABLE_CLOCALE], [
       CTIME_CC=config/locale/generic/time_members.cc
       CLOCALE_INTERNAL_H=config/locale/generic/c++locale_internal.h
       ;;
+    newlib)
+      AC_MSG_RESULT(newlib)
+
+      CLOCALE_H=config/locale/generic/c_locale.h
+      CLOCALE_CC=config/locale/generic/c_locale.cc
+      CCODECVT_CC=config/locale/generic/codecvt_members.cc
+      CCOLLATE_CC=config/locale/generic/collate_members.cc
+      CCTYPE_CC=config/locale/newlib/ctype_members.cc
+      CMESSAGES_H=config/locale/generic/messages_members.h
+      CMESSAGES_CC=config/locale/generic/messages_members.cc
+      CMONEY_CC=config/locale/generic/monetary_members.cc
+      CNUMERIC_CC=config/locale/generic/numeric_members.cc
+      CTIME_H=config/locale/generic/time_members.h
+      CTIME_CC=config/locale/generic/time_members.cc
+      CLOCALE_INTERNAL_H=config/locale/generic/c++locale_internal.h
+      ;;
   esac
 
   # This is where the testsuite looks for locale catalogs, using the
diff --git a/libstdc++-v3/config/locale/newlib/ctype_members.cc b/libstdc++-v3/config/locale/newlib/ctype_members.cc
new file mode 100644
index 0000000..ee91baf
--- /dev/null
+++ b/libstdc++-v3/config/locale/newlib/ctype_members.cc
@@ -0,0 +1,281 @@ 
+// std::ctype implementation details, newlib version -*- C++ -*-
+
+// Copyright (C) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010
+// 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.
+
+// Under Section 7 of GPL version 3, you are granted additional
+// permissions described in the GCC Runtime Library Exception, version
+// 3.1, as published by the Free Software Foundation.
+
+// You should have received a copy of the GNU General Public License and
+// a copy of the GCC Runtime Library Exception along with this program;
+// see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+// <http://www.gnu.org/licenses/>.
+
+//
+// ISO C++ 14882: 22.2.1.1.2  ctype virtual functions.
+//
+
+#include <locale>
+#include <cstdlib>
+#include <cstring>
+#include <cstdio>
+
+namespace std _GLIBCXX_VISIBILITY(default)
+{
+_GLIBCXX_BEGIN_NAMESPACE_VERSION
+
+  // NB: The other ctype<char> specializations are in src/locale.cc and
+  // various /config/os/* files.
+  ctype_byname<char>::ctype_byname(const char* __s, size_t __refs)
+  : ctype<char>(0, false, __refs)
+  {
+    if (std::strcmp(__s, "C") != 0 && std::strcmp(__s, "POSIX") != 0)
+      {
+	this->_S_destroy_c_locale(this->_M_c_locale_ctype);
+	this->_S_create_c_locale(this->_M_c_locale_ctype, __s);
+      }
+  }
+
+  ctype_byname<char>::~ctype_byname()
+  { }
+
+#ifdef _GLIBCXX_USE_WCHAR_T
+  ctype<wchar_t>::__wmask_type
+  ctype<wchar_t>::_M_convert_to_wmask(const mask __m) const throw()
+  {
+    __wmask_type __ret;
+    switch (__m)
+      {
+      case space:
+	__ret = wctype("space");
+	break;
+      case print:
+	__ret = wctype("print");
+	break;
+      case cntrl:
+	__ret = wctype("cntrl");
+	break;
+      case upper:
+	__ret = wctype("upper");
+	break;
+      case lower:
+	__ret = wctype("lower");
+	break;
+      case alpha:
+	__ret = wctype("alpha");
+	break;
+      case digit:
+	__ret = wctype("digit");
+	break;
+      case punct:
+	__ret = wctype("punct");
+	break;
+      case xdigit:
+	__ret = wctype("xdigit");
+	break;
+      case alnum:
+	__ret = wctype("alnum");
+	break;
+      case graph:
+	__ret = wctype("graph");
+	break;
+      default:
+	// Different from the generic version, xdigit and print in
+	// newlib are defined as bitwise-OR result of bitmasks:
+	//   xdigit = _X | _N;
+	//   print  = _P | _U | _L | _N | _B;
+	// in which _X and _B don't correspond to any ctype mask.
+	// In order to get the wmask correctly converted when __m is
+	// equal to _X or _B, the two cases are specifically handled
+	// here.
+	if (__m & xdigit)
+	  __ret = wctype("xdigit");
+	else if (__m & print)
+	  __ret = wctype("print");
+	else
+	  __ret = __wmask_type();
+      }
+    return __ret;
+  };
+
+  wchar_t
+  ctype<wchar_t>::do_toupper(wchar_t __c) const
+  { return towupper(__c); }
+
+  const wchar_t*
+  ctype<wchar_t>::do_toupper(wchar_t* __lo, const wchar_t* __hi) const
+  {
+    while (__lo < __hi)
+      {
+        *__lo = towupper(*__lo);
+        ++__lo;
+      }
+    return __hi;
+  }
+
+  wchar_t
+  ctype<wchar_t>::do_tolower(wchar_t __c) const
+  { return towlower(__c); }
+
+  const wchar_t*
+  ctype<wchar_t>::do_tolower(wchar_t* __lo, const wchar_t* __hi) const
+  {
+    while (__lo < __hi)
+      {
+        *__lo = towlower(*__lo);
+        ++__lo;
+      }
+    return __hi;
+  }
+
+  bool
+  ctype<wchar_t>::
+  do_is(mask __m, wchar_t __c) const
+  {
+    bool __ret = false;
+    // Newlib C library has a compact encoding that uses 8 bits only.
+    const size_t __bitmasksize = 7;
+    for (size_t __bitcur = 0; __bitcur <= __bitmasksize; ++__bitcur)
+      if (__m & _M_bit[__bitcur]
+	  && iswctype(__c, _M_wmask[__bitcur]))
+	{
+	  __ret = true;
+	  break;
+	}
+    return __ret;
+  }
+
+  const wchar_t*
+  ctype<wchar_t>::
+  do_is(const wchar_t* __lo, const wchar_t* __hi, mask* __vec) const
+  {
+    for (; __lo < __hi; ++__vec, ++__lo)
+      {
+	// Newlib C library has a compact encoding that uses 8 bits only.
+	const size_t __bitmasksize = 7;
+	mask __m = 0;
+	for (size_t __bitcur = 0; __bitcur <= __bitmasksize; ++__bitcur)
+	  if (iswctype(*__lo, _M_wmask[__bitcur]))
+	    __m |= _M_bit[__bitcur];
+	*__vec = __m;
+      }
+    return __hi;
+  }
+
+  const wchar_t*
+  ctype<wchar_t>::
+  do_scan_is(mask __m, const wchar_t* __lo, const wchar_t* __hi) const
+  {
+    while (__lo < __hi && !this->do_is(__m, *__lo))
+      ++__lo;
+    return __lo;
+  }
+
+  const wchar_t*
+  ctype<wchar_t>::
+  do_scan_not(mask __m, const char_type* __lo, const char_type* __hi) const
+  {
+    while (__lo < __hi && this->do_is(__m, *__lo) != 0)
+      ++__lo;
+    return __lo;
+  }
+
+  wchar_t
+  ctype<wchar_t>::
+  do_widen(char __c) const
+  { return _M_widen[static_cast<unsigned char>(__c)]; }
+
+  const char*
+  ctype<wchar_t>::
+  do_widen(const char* __lo, const char* __hi, wchar_t* __dest) const
+  {
+    while (__lo < __hi)
+      {
+	*__dest = _M_widen[static_cast<unsigned char>(*__lo)];
+	++__lo;
+	++__dest;
+      }
+    return __hi;
+  }
+
+  char
+  ctype<wchar_t>::
+  do_narrow(wchar_t __wc, char __dfault) const
+  {
+    if (__wc >= 0 && __wc < 128 && _M_narrow_ok)
+      return _M_narrow[__wc];
+    const int __c = wctob(__wc);
+    return (__c == EOF ? __dfault : static_cast<char>(__c));
+  }
+
+  const wchar_t*
+  ctype<wchar_t>::
+  do_narrow(const wchar_t* __lo, const wchar_t* __hi, char __dfault,
+	    char* __dest) const
+  {
+    if (_M_narrow_ok)
+      while (__lo < __hi)
+	{
+	  if (*__lo >= 0 && *__lo < 128)
+	    *__dest = _M_narrow[*__lo];
+	  else
+	    {
+	      const int __c = wctob(*__lo);
+	      *__dest = (__c == EOF ? __dfault : static_cast<char>(__c));
+	    }
+	  ++__lo;
+	  ++__dest;
+	}
+    else
+      while (__lo < __hi)
+	{
+	  const int __c = wctob(*__lo);
+	  *__dest = (__c == EOF ? __dfault : static_cast<char>(__c));
+	  ++__lo;
+	  ++__dest;
+	}
+    return __hi;
+  }
+
+  void
+  ctype<wchar_t>::_M_initialize_ctype() throw()
+  {
+    wint_t __i;
+    for (__i = 0; __i < 128; ++__i)
+      {
+	const int __c = wctob(__i);
+	if (__c == EOF)
+	  break;
+	else
+	  _M_narrow[__i] = static_cast<char>(__c);
+      }
+    if (__i == 128)
+      _M_narrow_ok = true;
+    else
+      _M_narrow_ok = false;
+    for (size_t __i = 0;
+	 __i < sizeof(_M_widen) / sizeof(wint_t); ++__i)
+      _M_widen[__i] = btowc(__i);
+
+    for (size_t __i = 0; __i <= 7; ++__i)
+      {
+	_M_bit[__i] = static_cast<mask>(1 << __i);
+	_M_wmask[__i] = _M_convert_to_wmask(_M_bit[__i]);
+      }
+  }
+#endif //  _GLIBCXX_USE_WCHAR_T
+
+_GLIBCXX_END_NAMESPACE_VERSION
+} // namespace
diff --git a/libstdc++-v3/configure b/libstdc++-v3/configure
index fa6a1a5..6854313 100755
--- a/libstdc++-v3/configure
+++ b/libstdc++-v3/configure
@@ -15642,7 +15642,7 @@  $as_echo "stdio" >&6; }
 if test "${enable_clocale+set}" = set; then :
   enableval=$enable_clocale;
       case "$enableval" in
-       generic|gnu|ieee_1003.1-2001|yes|no|auto) ;;
+       generic|gnu|ieee_1003.1-2001|newlib|yes|no|auto) ;;
        *) as_fn_error "Unknown argument to enable/disable clocale" "$LINENO" 5 ;;
 	  	        esac
 
@@ -15664,7 +15664,7 @@  else
 fi
 
 
-  # Either a known packaage, or "auto"
+  # Either a known package, or "auto"
   if test $enable_clocale = no || test $enable_clocale = yes; then
      enable_clocale=auto
   fi
@@ -15681,7 +15681,11 @@  fi
 	enable_clocale_flag=darwin
 	;;
       *)
-	enable_clocale_flag=generic
+	if test x"$with_newlib" = x"yes"; then
+	  enable_clocale_flag=newlib
+	else
+	  enable_clocale_flag=generic
+	fi
 	;;
     esac
   fi
@@ -15907,6 +15911,23 @@  $as_echo "IEEE 1003.1" >&6; }
       CTIME_CC=config/locale/generic/time_members.cc
       CLOCALE_INTERNAL_H=config/locale/generic/c++locale_internal.h
       ;;
+    newlib)
+      { $as_echo "$as_me:${as_lineno-$LINENO}: result: newlib" >&5
+$as_echo "newlib" >&6; }
+
+      CLOCALE_H=config/locale/generic/c_locale.h
+      CLOCALE_CC=config/locale/generic/c_locale.cc
+      CCODECVT_CC=config/locale/generic/codecvt_members.cc
+      CCOLLATE_CC=config/locale/generic/collate_members.cc
+      CCTYPE_CC=config/locale/newlib/ctype_members.cc
+      CMESSAGES_H=config/locale/generic/messages_members.h
+      CMESSAGES_CC=config/locale/generic/messages_members.cc
+      CMONEY_CC=config/locale/generic/monetary_members.cc
+      CNUMERIC_CC=config/locale/generic/numeric_members.cc
+      CTIME_H=config/locale/generic/time_members.h
+      CTIME_CC=config/locale/generic/time_members.cc
+      CLOCALE_INTERNAL_H=config/locale/generic/c++locale_internal.h
+      ;;
   esac
 
   # This is where the testsuite looks for locale catalogs, using the