about summary refs log tree commit diff
diff options
context:
space:
mode:
-rw-r--r--manual/charset.texi23
-rw-r--r--stdlib/stdlib.h2
-rw-r--r--wcsmbs/Makefile2
-rw-r--r--wcsmbs/tst-mbstowcs.c50
4 files changed, 71 insertions, 6 deletions
diff --git a/manual/charset.texi b/manual/charset.texi
index 9fd0166115..b638323fc2 100644
--- a/manual/charset.texi
+++ b/manual/charset.texi
@@ -1026,6 +1026,10 @@ stores in the pointer pointed to by @var{src} either a null pointer (if
 the NUL byte in the input string was reached) or the address of the byte
 following the last converted multibyte character.
 
+Like @code{mbstowcs} the @var{dst} parameter may be a null pointer and
+the function can be used to count the number of wide characters that
+would be required.
+
 @pindex wchar.h
 @code{mbsrtowcs} was introduced in @w{Amendment 1} to @w{ISO C90} and is
 declared in @file{wchar.h}.
@@ -1101,10 +1105,11 @@ successfully converted.
 
 Except in the case of an encoding error the return value of the
 @code{wcsrtombs} function is the number of bytes in all the multibyte
-character sequences stored in @var{dst}.  Before returning, the state in
-the object pointed to by @var{ps} (or the internal object in case
-@var{ps} is a null pointer) is updated to reflect the state after the
-last conversion.  The state is the initial shift state in case the
+character sequences which were or would have been (if @var{dst} was
+not a null) stored in @var{dst}.  Before returning, the state in the
+object pointed to by @var{ps} (or the internal object in case @var{ps}
+is a null pointer) is updated to reflect the state after the last
+conversion.  The state is the initial shift state in case the
 terminating NUL wide character was converted.
 
 @pindex wchar.h
@@ -1131,6 +1136,10 @@ string @code{*@var{src}} need not be NUL-terminated.  But if a NUL byte
 is found within the @var{nmc} first bytes of the string, the conversion
 stops there.
 
+Like @code{mbstowcs} the @var{dst} parameter may be a null pointer and
+the function can be used to count the number of wide characters that
+would be required.
+
 This function is a GNU extension.  It is meant to work around the
 problems mentioned above.  Now it is possible to convert a buffer with
 multibyte character text piece by piece without having to care about
@@ -1465,6 +1474,12 @@ mbstowcs_alloc (const char *string)
 @}
 @end smallexample
 
+If @var{wstring} is a null pointer then no output is written and the
+conversion proceeds as above, and the result is returned.  In practice
+such behaviour is useful for calculating the exact number of wide
+characters required to convert @var{string}.  This behaviour of
+accepting a null pointer for @var{wstring} is an @w{XPG4.2} extension
+that is not specified in @w{ISO C} and is optional in @w{POSIX}.
 @end deftypefun
 
 @deftypefun size_t wcstombs (char *@var{string}, const wchar_t *@var{wstring}, size_t @var{size})
diff --git a/stdlib/stdlib.h b/stdlib/stdlib.h
index dd779bd740..f971df4247 100644
--- a/stdlib/stdlib.h
+++ b/stdlib/stdlib.h
@@ -932,7 +932,7 @@ extern int wctomb (char *__s, wchar_t __wchar) __THROW;
 /* Convert a multibyte string to a wide char string.  */
 extern size_t mbstowcs (wchar_t *__restrict  __pwcs,
 			const char *__restrict __s, size_t __n) __THROW
-    __attr_access ((__write_only__, 1, 3)) __attr_access ((__read_only__, 2));
+    __attr_access ((__read_only__, 2));
 /* Convert a wide char string to multibyte string.  */
 extern size_t wcstombs (char *__restrict __s,
 			const wchar_t *__restrict __pwcs, size_t __n)
diff --git a/wcsmbs/Makefile b/wcsmbs/Makefile
index f02167fa58..e638e45522 100644
--- a/wcsmbs/Makefile
+++ b/wcsmbs/Makefile
@@ -52,7 +52,7 @@ tests := tst-wcstof wcsmbs-tst1 tst-wcsnlen tst-btowc tst-mbrtowc \
 	 tst-c16c32-1 wcsatcliff tst-wcstol-locale tst-wcstod-nan-locale \
 	 tst-wcstod-round test-char-types tst-fgetwc-after-eof \
 	 tst-wcstod-nan-sign tst-c16-surrogate tst-c32-state \
-	 $(addprefix test-,$(strop-tests))
+	 $(addprefix test-,$(strop-tests)) tst-mbstowcs
 
 include ../Rules
 
diff --git a/wcsmbs/tst-mbstowcs.c b/wcsmbs/tst-mbstowcs.c
new file mode 100644
index 0000000000..b48891553e
--- /dev/null
+++ b/wcsmbs/tst-mbstowcs.c
@@ -0,0 +1,50 @@
+/* Test basic mbstowcs including wstring == NULL (Bug 25219).
+   Copyright (C) 2020 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+
+   The GNU C Library is free software; you can redistribute it and/or
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C 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
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <https://www.gnu.org/licenses/>.  */
+
+#include <stdlib.h>
+#include <string.h>
+#include <support/check.h>
+
+static int
+do_test (void)
+{
+  char string[] = { '1', '2', '3' , '4', '5', '\0' };
+  size_t len = strlen (string);
+  wchar_t wstring[] = { L'1', L'2', L'3', L'4', L'5', L'\0' };
+#define NUM_WCHAR 6
+  wchar_t wout[NUM_WCHAR];
+  size_t result;
+
+  /* The input ASCII string in the C/POSIX locale must convert
+     to the matching WSTRING.  */
+  result = mbstowcs (wout, string, NUM_WCHAR);
+  TEST_VERIFY (result == (NUM_WCHAR - 1));
+  TEST_COMPARE_BLOB (wstring, sizeof (wchar_t) * (NUM_WCHAR - 1),
+		     wout, sizeof (wchar_t) * result);
+
+  /* The input ASCII string in the C/POSIX locale must be the
+     same length when using mbstowcs to compute the length of
+     the string required in the conversion.  Using mbstowcs
+     in this way is an XSI extension to POSIX.  */
+  result = mbstowcs (NULL, string, len);
+  TEST_VERIFY (result == len);
+
+  return 0;
+}
+
+#include <support/test-driver.c>