AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-12-22 19:00:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update.

Browse Source 
2000-10-27  Bruno Haible  <haible@clisp.cons.org>

	* locale/programs/charmap.c (charmap_read): Verify ASCII
	compatibility of charmap.
This commit is contained in:
Ulrich Drepper 2000-11-08 23:08:32 +00:00
parent d3d99893ee
commit bb39c4ef8f
2 changed files with 64 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ChangeLog
View File

@ -1,3 +1,8 @@
2000-10-27 Bruno Haible <haible@clisp.cons.org>
* locale/programs/charmap.c (charmap_read): Verify ASCII
compatibility of charmap.
2000-11-08 Ulrich Drepper <drepper@redhat.com>
* catgets/gencat.c (main): Don't use exit() to avoid warnings with

59
locale/programs/charmap.c
View File

@ -26,6 +26,7 @@
#include <libintl.h>
#include <limits.h>
#include <obstack.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
@ -192,6 +193,64 @@ charmap_read (const char *filename)
DEFAULT_CHARMAP);
}
/* Test of ASCII compatibility of locale encoding.
Verify that the encoding to be used in a locale is ASCII compatible,
at least for the graphic characters, excluding the control characters,
'$' and '@'. This constraint comes from an ISO C 99 restriction.
ISO C 99 section 7.17.(2) (about wchar_t):
the null character shall have the code value zero and each member of
the basic character set shall have a code value equal to its value
when used as the lone character in an integer character constant.
ISO C 99 section 5.2.1.(3):
Both the basic source and basic execution character sets shall have
the following members: the 26 uppercase letters of the Latin alphabet
A B C D E F G H I J K L M N O P Q R S T U V W X Y Z
the 26 lowercase letters of the Latin alphabet
a b c d e f g h i j k l m n o p q r s t u v w x y z
the 10 decimal digits
0 1 2 3 4 5 6 7 8 9
the following 29 graphic characters
! " # % & ' ( ) * + , - . / : ; < = > ? [ \ ] ^ _ { | } ~
the space character, and control characters representing horizontal
tab, vertical tab, and form feed.
Therefore, for all members of the "basic character set", the 'char' code
must have the same value as the 'wchar_t' code, which in glibc is the
same as the Unicode code, which for all of the enumerated characters
is identical to the ASCII code. */
if (result != NULL)
{
static const char basic_charset[] =
{
'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M',
'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm',
'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
'!', '"', '#', '%', '&', '\'', '(', ')', '*', '+', ',', '-',
'.', '/', ':', ';', '<', '=', '>', '?', '[', '\\', ']', '^',
'_', '{', '|', '}', '~', ' ', '\t', '\v', '\f', '\0'
};
int failed = 0;
const char *p = basic_charset;
do
{
struct charseq * seq = charmap_find_symbol (result, p, 1);
if (seq == NULL || seq->ucs4 != *p)
failed = 1;
}
while (*p++ != '\0');
if (failed)
fprintf (stderr, _("\
character map `%s' is not ASCII compatible, locale not ISO C compliant\n"),
result->code_set_name);
}
return result;
}