gnustep/libs-base
0
0
Fork 0
mirror of https://github.com/gnustep/libs-base.git synced 2025-05-30 08:21:25 +00:00
Code Issues Projects Releases Packages Wiki Activity

String encoding fixes

Browse source 
git-svn-id: svn+ssh://svn.gna.org/svn/gnustep/libs/base/trunk@17917 72102866-910b-0410-8b05-ffd578937521
This commit is contained in:
CaS 2003-10-18 06:10:41 +00:00
parent e723e30c14
commit 0627eb75aa
4 changed files with 36 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

13
ChangeLog
View file

@ -1,3 +1,16 @@
Sat Oct 18 07:10:00 2003 Richard Frith-Macdonald <rfm@gnu.org>
* Source/Additions/Unicode.m: Allow GNUSTEP_STRING_ENCODING to give
any supported iconv name in additiuon to OpenStep names. Make check
case insensitive.
Documentation/Base.gsdoc: Remove obsolete comment that
GNUSTEP_STRING_ENCODING may not specify a mu7ltibyte encoding.
2003-10-16 Bruno Haible <bruno@clisp.org>
* Source/NSString.m (initWithContentsOfFile:, initWithContentsOfURL:):
Fix recognition of UTF-8 BOM.
Fri Oct 17 14:28:49 2003 Nicola Pero <n.pero@mi.flashnet.it> Fri Oct 17 14:28:49 2003 Nicola Pero <n.pero@mi.flashnet.it>
* Source/GNUmakefile (LIBRARY_VAR): Unused variable removed. * Source/GNUmakefile (LIBRARY_VAR): Unused variable removed.

3
Documentation/Base.gsdoc
View file

@ -198,8 +198,7 @@
<p> <p>
This is used to specify the default encoding for 8-bit This is used to specify the default encoding for 8-bit
strings. It defaults to NSISOLatin1StringEncoding, but strings. It defaults to NSISOLatin1StringEncoding, but
may be any of the 8-bit encodings supported by your system may be any of the 8-bit encodings supported by your system.
(excluding multi-byte encodings).
</p> </p>
</desc> </desc>
<term>GNUSTEP_HOST_CPU</term> <term>GNUSTEP_HOST_CPU</term>

3
Source/Additions/Unicode.m
View file

@ -573,7 +573,8 @@ GetDefEncoding()
{ {
count = 0; count = 0;
while (str_encoding_table[count].enc while (str_encoding_table[count].enc
&& strcmp(str_encoding_table[count].ename, encoding)) && strcasecmp(str_encoding_table[count].ename, encoding)
&& strcasecmp(str_encoding_table[count].iconv, encoding))
{ {
count++; count++;
} }

30
Source/NSString.m
View file

@ -1321,7 +1321,7 @@ handle_printf_atsign (FILE *stream,
NSStringEncoding enc = _DefaultStringEncoding; NSStringEncoding enc = _DefaultStringEncoding;
NSData *d; NSData *d;
unsigned int len; unsigned int len;
const unichar *test; const unsigned char *data_bytes;
d = [[NSDataClass alloc] initWithContentsOfFile: path]; d = [[NSDataClass alloc] initWithContentsOfFile: path];
if (d == nil) if (d == nil)
@ -1336,15 +1336,20 @@ handle_printf_atsign (FILE *stream,
RELEASE(self); RELEASE(self);
return @""; return @"";
} }
test = [d bytes]; data_bytes = [d bytes];
if ((test != NULL) && (len > 1)) if ((data_bytes != NULL) && (len >= 2))
{ {
if ((test[0] == byteOrderMark) || (test[0] == byteOrderMarkSwapped)) const unichar *data_ucs2chars = (const unichar *) data_bytes;
if ((data_ucs2chars[0] == byteOrderMark)
|| (data_ucs2chars[0] == byteOrderMarkSwapped))
{ {
/* somebody set up us the BOM! */ /* somebody set up us the BOM! */
enc = NSUnicodeStringEncoding; enc = NSUnicodeStringEncoding;
} }
else if (len > 2 && test[0] == 0xEF && test[1] == 0xBB && test[2] == 0xBF) else if (len >= 3
&& data_bytes[0] == 0xEF
&& data_bytes[1] == 0xBB
&& data_bytes[2] == 0xBF)
{ {
enc = NSUTF8StringEncoding; enc = NSUTF8StringEncoding;
} }
@ -1363,7 +1368,7 @@ handle_printf_atsign (FILE *stream,
NSStringEncoding enc = _DefaultStringEncoding; NSStringEncoding enc = _DefaultStringEncoding;
NSData *d = [NSDataClass dataWithContentsOfURL: url]; NSData *d = [NSDataClass dataWithContentsOfURL: url];
unsigned int len = [d length]; unsigned int len = [d length];
const unichar *test; const unsigned char *data_bytes;
if (d == nil) if (d == nil)
{ {
@ -1376,14 +1381,19 @@ handle_printf_atsign (FILE *stream,
RELEASE(self); RELEASE(self);
return @""; return @"";
} }
test = [d bytes]; data_bytes = [d bytes];
if ((test != NULL) && (len > 1)) if ((data_bytes != NULL) && (len >= 2))
{ {
if ((test[0] == byteOrderMark) || (test[0] == byteOrderMarkSwapped)) const unichar *data_ucs2chars = (const unichar *) data_bytes;
if ((data_ucs2chars[0] == byteOrderMark)
|| (data_ucs2chars[0] == byteOrderMarkSwapped))
{ {
enc = NSUnicodeStringEncoding; enc = NSUnicodeStringEncoding;
} }
else if (len > 2 && test[0] == 0xEF && test[1] == 0xBB && test[2] == 0xBF) else if (len >= 3
&& data_bytes[0] == 0xEF
&& data_bytes[1] == 0xBB
&& data_bytes[2] == 0xBF)
{ {
enc = NSUTF8StringEncoding; enc = NSUTF8StringEncoding;
} }