gnustep/libs-base
0
0
Fork 0
mirror of https://github.com/gnustep/libs-base.git synced 2025-05-20 20:26:42 +00:00
Code Issues Projects Releases Packages Wiki Activity

Validate data returned by dataUsingEncoding:allowLossyConversion: for unicode

Browse source 
git-svn-id: svn+ssh://svn.gna.org/svn/gnustep/libs/base/trunk@22713 72102866-910b-0410-8b05-ffd578937521
This commit is contained in:
Richard Frith-MacDonald 2006-03-26 11:34:47 +00:00
parent 55e0ca9228
commit f9cf084fcf
3 changed files with 52 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

25
Source/Additions/Unicode.m
View file

@ -1094,28 +1094,29 @@ int encode_cstrtoustr(unichar *dst, int dl, const char *src, int sl,
* Function to check a block of data for validity as a unicode string and
* say whether it contains solely ASCII or solely Latin1 data.<br />
* Any leading BOM must already have been removed and the data must already
* be in native byte order.
* be in native byte order.<br />
* Returns the number of characters which were found valid.
*/
BOOL
GSIsUnicode(const unichar *chars, unsigned length,
unsigned
GSUnicode(const unichar *chars, unsigned length,
BOOL *isASCII, BOOL *isLatin1)
{
unsigned i = 0;
unichar c;
*isASCII = YES;
*isLatin1 = YES;
if (isASCII) *isASCII = YES;
if (isLatin1) *isLatin1 = YES;
while (i < length)
{
if ((c = chars[i++]) > 127)
{
*isASCII = NO;
if (isASCII) *isASCII = NO;
i--;
while (i < length)
{
if ((c = chars[i++]) > 255)
{
*isLatin1 = NO;
if (isLatin1) *isLatin1 = NO;
i--;
while (i < length)
{
@ -1123,23 +1124,23 @@ GSIsUnicode(const unichar *chars, unsigned length,
if (c == 0xfffe || c == 0xffff
|| (c >= 0xfdd0 && c <= 0xfdef))
{
return NO; // Non-characters.
return i - 1; // Non-characters.
}
if (c >= 0xdc00 && c <= 0xdfff)
{
return NO; // Second half of a surrogate pair.
return i - 1; // Second half of a surrogate pair.
}
if (c >= 0xd800 && c <= 0xdbff)
{
// First half of a surrogate pair.
if (i >= length)
{
return NO; // Second half missing
return i - 1; // Second half missing
}
c = chars[i];
if (c < 0xdc00 || c > 0xdfff)
{
return NO; // Second half missing
return i - 1; // Second half missing
}
i++; // Step past second half
}
@ -1148,7 +1149,7 @@ GSIsUnicode(const unichar *chars, unsigned length,
}
}
}
return YES;
return i;
}
#define GROW() \