mirror of
https://github.com/gnustep/libs-base.git
synced 2025-04-23 00:41:02 +00:00
Make first moves towards handling the fact that unicode and cString
representations of the same string may contain different numbers of characters. In particular, UTF8 of course. git-svn-id: svn+ssh://svn.gna.org/svn/gnustep/libs/base/trunk@10643 72102866-910b-0410-8b05-ffd578937521
This commit is contained in:
Richard Frith-Macdonald
parent
80eb611458
commit
bf97ef27e6
5 changed files with 504 additions and 425 deletions
|
|
@ -1,3 +1,12 @@
|
|||
2001-08-03 Richard Frith-Macdonald <rfm@gnu.org>
|
||||
|
||||
* Headers/Foundation/Unicode.h: API Change
|
||||
* Source/Unicode.m: API Change ... remove old string conversion
|
||||
functions and replace with two functions, both of which differentiate
|
||||
between lengths of the source strings and sizes of destination buffers.
|
||||
* Source/NSString.m: Update for changes to Unicode.[hm]
|
||||
* Source/GSString.m: Update for changes to Unicode.[hm]
|
||||
|
||||
2001-08-02 Richard Frith-Macdonald <rfm@gnu.org>
|
||||
|
||||
* Source/NSPortNameServer.m: Log the host we are connecting to
|
||||
|
|
|
|||
|
|
@ -40,14 +40,11 @@ GS_EXPORT char unitochar(unichar u);
|
|||
GS_EXPORT unichar encode_chartouni(char c, NSStringEncoding enc);
|
||||
GS_EXPORT char encode_unitochar(unichar u, NSStringEncoding enc);
|
||||
GS_EXPORT unsigned encode_unitochar_strict(unichar u, NSStringEncoding enc);
|
||||
GS_EXPORT int strtoustr(unichar * u1,const char *s1,int size);
|
||||
GS_EXPORT int ustrtostr(char *s2,unichar *u1,int size);
|
||||
GS_EXPORT int encode_strtoustr(unichar* u1,const char*s1,int size,
|
||||
NSStringEncoding enc);
|
||||
GS_EXPORT int encode_ustrtostr(char *s2, unichar *u1, int size,
|
||||
NSStringEncoding enc);
|
||||
GS_EXPORT int encode_ustrtostr_strict(char *s2, unichar *u1, int size,
|
||||
NSStringEncoding enc);
|
||||
|
||||
GS_EXPORT int encode_ustrtocstr(char *dst, int dl, const unichar *src, int sl,
|
||||
NSStringEncoding enc, BOOL strict);
|
||||
GS_EXPORT int encode_cstrtoustr(unichar *dst, int dl, const char *str, int sl,
|
||||
NSStringEncoding enc);
|
||||
|
||||
GS_EXPORT unichar uni_tolower(unichar ch);
|
||||
GS_EXPORT unichar uni_toupper(unichar ch);
|
||||
|
|
|
|||
|
|
@ -513,7 +513,7 @@ boolValue_u(ivars self)
|
|||
unsigned len = self->_count < 10 ? self->_count : 9;
|
||||
char buf[len+1];
|
||||
|
||||
encode_ustrtostr(buf, self->_contents.u, len, defEnc);
|
||||
len = encode_ustrtocstr(buf, len, self->_contents.u, len, defEnc, NO);
|
||||
buf[len] = '\0';
|
||||
if (len == 3
|
||||
&& (buf[0] == 'Y' || buf[0] == 'y')
|
||||
|
|
@ -634,18 +634,18 @@ cString_c(ivars self)
|
|||
static inline char*
|
||||
cString_u(ivars self)
|
||||
{
|
||||
char *r = (char*)_fastMallocBuffer(self->_count+1);
|
||||
int l = self->_count;
|
||||
char *r = (char*)_fastMallocBuffer(l + 1);
|
||||
|
||||
if (self->_count > 0)
|
||||
if (l > 0)
|
||||
{
|
||||
if (encode_ustrtostr_strict(r, self->_contents.u, self->_count, defEnc)
|
||||
== 0)
|
||||
if (encode_ustrtocstr(r, l, self->_contents.u, l, defEnc, YES) == 0)
|
||||
{
|
||||
[NSException raise: NSCharacterConversionException
|
||||
format: @"Can't get cString from Unicode string."];
|
||||
}
|
||||
}
|
||||
r[self->_count] = '\0';
|
||||
r[l] = '\0';
|
||||
|
||||
return r;
|
||||
}
|
||||
|
|
@ -660,19 +660,20 @@ static inline unsigned int
|
|||
cStringLength_u(ivars self)
|
||||
{
|
||||
unsigned c;
|
||||
unsigned l = self->_count;
|
||||
|
||||
if (self->_count > 0)
|
||||
if (l > 0)
|
||||
{
|
||||
char *r;
|
||||
|
||||
r = (char*)NSZoneMalloc(NSDefaultMallocZone(), self->_count+1);
|
||||
if (encode_ustrtostr(r, self->_contents.u, self->_count, defEnc) == 0)
|
||||
r = (char*)NSZoneMalloc(NSDefaultMallocZone(), l + 1);
|
||||
if (encode_ustrtocstr(r, l, self->_contents.u, l, defEnc, NO) == 0)
|
||||
{
|
||||
NSZoneFree(NSDefaultMallocZone(), r);
|
||||
[NSException raise: NSCharacterConversionException
|
||||
format: @"Can't get cStringLength from Unicode string."];
|
||||
}
|
||||
r[self->_count] = '\0';
|
||||
r[l] = '\0';
|
||||
c = strlen(r);
|
||||
NSZoneFree(NSDefaultMallocZone(), r);
|
||||
}
|
||||
|
|
@ -714,31 +715,45 @@ dataUsingEncoding_c(ivars self, NSStringEncoding encoding, BOOL flag)
|
|||
buff = (unichar*)NSZoneMalloc(NSDefaultMallocZone(),
|
||||
sizeof(unichar)*(len+1));
|
||||
buff[0] = 0xFEFF;
|
||||
t = encode_strtoustr(buff+1, self->_contents.c, len, defEnc);
|
||||
t = encode_cstrtoustr(buff+1, len, self->_contents.c, len, defEnc);
|
||||
return [NSDataClass dataWithBytesNoCopy: buff
|
||||
length: sizeof(unichar)*(t+1)];
|
||||
}
|
||||
else
|
||||
{
|
||||
int t;
|
||||
int bsiz;
|
||||
unichar *ubuff;
|
||||
unsigned char *buff;
|
||||
|
||||
ubuff = (unichar*)NSZoneMalloc(NSDefaultMallocZone(),
|
||||
sizeof(unichar)*len);
|
||||
t = encode_strtoustr(ubuff, self->_contents.c, len, defEnc);
|
||||
buff = (unsigned char*)NSZoneMalloc(NSDefaultMallocZone(), t);
|
||||
if (flag)
|
||||
t = encode_ustrtostr(buff, ubuff, t, encoding);
|
||||
else
|
||||
t = encode_ustrtostr_strict(buff, ubuff, t, encoding);
|
||||
t = encode_cstrtoustr(ubuff, len, self->_contents.c, len, defEnc);
|
||||
if (encoding == NSUTF8StringEncoding)
|
||||
{
|
||||
bsiz = t*4;
|
||||
}
|
||||
else
|
||||
{
|
||||
bsiz = t;
|
||||
}
|
||||
buff = (unsigned char*)NSZoneMalloc(NSDefaultMallocZone(), bsiz);
|
||||
flag = (flag == YES) ? NO : YES;
|
||||
t = encode_ustrtocstr(buff, bsiz, ubuff, t, encoding, flag);
|
||||
NSZoneFree(NSDefaultMallocZone(), ubuff);
|
||||
if (t == 0)
|
||||
{
|
||||
NSZoneFree(NSDefaultMallocZone(), buff);
|
||||
return nil;
|
||||
}
|
||||
return [NSDataClass dataWithBytesNoCopy: buff length: t];
|
||||
else
|
||||
{
|
||||
if (t != bsiz)
|
||||
{
|
||||
buff = NSZoneRealloc(NSDefaultMallocZone(), buff, t);
|
||||
}
|
||||
return [NSDataClass dataWithBytesNoCopy: buff length: t];
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -766,19 +781,33 @@ dataUsingEncoding_u(ivars self, NSStringEncoding encoding, BOOL flag)
|
|||
else
|
||||
{
|
||||
int t;
|
||||
int bsiz;
|
||||
unsigned char *buff;
|
||||
|
||||
buff = (unsigned char*)NSZoneMalloc(NSDefaultMallocZone(), len);
|
||||
if (flag == YES)
|
||||
t = encode_ustrtostr(buff, self->_contents.u, len, encoding);
|
||||
else
|
||||
t = encode_ustrtostr_strict(buff, self->_contents.u, len, encoding);
|
||||
if (!t)
|
||||
if (encoding == NSUTF8StringEncoding)
|
||||
{
|
||||
bsiz = len*4;
|
||||
}
|
||||
else
|
||||
{
|
||||
bsiz = len;
|
||||
}
|
||||
buff = (unsigned char*)NSZoneMalloc(NSDefaultMallocZone(), bsiz);
|
||||
flag = (flag == YES) ? NO : YES;
|
||||
t = encode_ustrtocstr(buff, bsiz, self->_contents.u, len, encoding, flag);
|
||||
if (t == 0)
|
||||
{
|
||||
NSZoneFree(NSDefaultMallocZone(), buff);
|
||||
return nil;
|
||||
}
|
||||
return [NSDataClass dataWithBytesNoCopy: buff length: t];
|
||||
else
|
||||
{
|
||||
if (t != bsiz)
|
||||
{
|
||||
buff = NSZoneRealloc(NSDefaultMallocZone(), buff, t);
|
||||
}
|
||||
return [NSDataClass dataWithBytesNoCopy: buff length: t];
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -812,7 +841,7 @@ doubleValue_u(ivars self)
|
|||
unsigned len = self->_count < 32 ? self->_count : 31;
|
||||
char buf[len+1];
|
||||
|
||||
encode_ustrtostr(buf, self->_contents.u, len, defEnc);
|
||||
len = encode_ustrtocstr(buf, len, self->_contents.u, len, defEnc, NO);
|
||||
buf[len] = '\0';
|
||||
return atof(buf);
|
||||
}
|
||||
|
|
@ -863,7 +892,7 @@ fillHole(ivars self, unsigned index, unsigned size)
|
|||
static inline void
|
||||
getCharacters_c(ivars self, unichar *buffer, NSRange aRange)
|
||||
{
|
||||
encode_strtoustr(buffer, self->_contents.c + aRange.location,
|
||||
encode_cstrtoustr(buffer, aRange.length, self->_contents.c + aRange.location,
|
||||
aRange.length, defEnc);
|
||||
}
|
||||
|
||||
|
|
@ -937,8 +966,8 @@ getCString_u(ivars self, char *buffer, unsigned int maxLength,
|
|||
}
|
||||
}
|
||||
|
||||
result = encode_ustrtostr_strict(buffer, &self->_contents.u[aRange.location],
|
||||
len, defEnc);
|
||||
result = encode_ustrtocstr(buffer, len, &self->_contents.u[aRange.location],
|
||||
len, defEnc, YES);
|
||||
if (result != len)
|
||||
{
|
||||
[NSException raise: NSCharacterConversionException
|
||||
|
|
@ -977,7 +1006,7 @@ intValue_u(ivars self)
|
|||
unsigned len = self->_count < 32 ? self->_count : 31;
|
||||
char buf[len+1];
|
||||
|
||||
encode_ustrtostr(buf, self->_contents.u, len, defEnc);
|
||||
len = encode_ustrtocstr(buf, len, self->_contents.u, len, defEnc, NO);
|
||||
buf[len] = '\0';
|
||||
return atol(buf);
|
||||
}
|
||||
|
|
@ -1130,10 +1159,11 @@ lossyCString_c(ivars self)
|
|||
static inline const char*
|
||||
lossyCString_u(ivars self)
|
||||
{
|
||||
unsigned char *r = (unsigned char*)_fastMallocBuffer(self->_count+1);
|
||||
unsigned l = self->_count;
|
||||
unsigned char *r = (unsigned char*)_fastMallocBuffer(l + 1);
|
||||
|
||||
encode_ustrtostr(r, self->_contents.u, self->_count, defEnc);
|
||||
r[self->_count] = '\0';
|
||||
encode_ustrtocstr(r, l, self->_contents.u, l, defEnc, NO);
|
||||
r[l] = '\0';
|
||||
return (const char*)r;
|
||||
}
|
||||
|
||||
|
|
@ -1433,10 +1463,10 @@ transmute(ivars self, NSString *aString)
|
|||
if (transmute == YES)
|
||||
{
|
||||
unichar *tmp;
|
||||
int len;
|
||||
int len = self->_count;
|
||||
|
||||
tmp = NSZoneMalloc(self->_zone, self->_capacity * sizeof(unichar));
|
||||
len = encode_strtoustr(tmp, self->_contents.c, self->_count, defEnc);
|
||||
len = encode_cstrtoustr(tmp, len, self->_contents.c, len, defEnc);
|
||||
if (self->_flags.free == 1)
|
||||
{
|
||||
NSZoneFree(self->_zone, self->_contents.c);
|
||||
|
|
|
|||
|
|
@ -601,7 +601,8 @@ handle_printf_atsign (FILE *stream,
|
|||
unichar *buf;
|
||||
|
||||
buf = (unichar*)NSZoneMalloc(GSObjCZone(self), sizeof(unichar)*length);
|
||||
length = encode_strtoustr(buf, byteString, length, _DefaultStringEncoding);
|
||||
length = encode_cstrtoustr(buf, length, byteString, length,
|
||||
_DefaultStringEncoding);
|
||||
if (flag == YES && byteString != 0)
|
||||
{
|
||||
NSZoneFree(NSZoneFromPointer(byteString), byteString);
|
||||
|
|
@ -694,7 +695,8 @@ handle_printf_atsign (FILE *stream,
|
|||
unichar *s;
|
||||
|
||||
s = NSZoneMalloc(GSObjCZone(self), sizeof(unichar)*length);
|
||||
length = encode_strtoustr(s, bytes, length+1, NSUTF8StringEncoding);
|
||||
length = encode_cstrtoustr(s, length, bytes, length,
|
||||
NSUTF8StringEncoding);
|
||||
self = [self initWithCharactersNoCopy: s
|
||||
length: length
|
||||
freeWhenDone: YES];
|
||||
|
|
@ -1101,7 +1103,8 @@ handle_printf_atsign (FILE *stream,
|
|||
unichar *u;
|
||||
|
||||
u = NSZoneMalloc(GSObjCZone(self), sizeof(unichar)*length);
|
||||
length = encode_strtoustr(u, bytes, length+1, NSUTF8StringEncoding);
|
||||
length = encode_cstrtoustr(u, length, bytes, length,
|
||||
NSUTF8StringEncoding);
|
||||
self = [self initWithCharactersNoCopy: u
|
||||
length: length
|
||||
freeWhenDone: YES];
|
||||
|
|
@ -1141,7 +1144,7 @@ handle_printf_atsign (FILE *stream,
|
|||
}
|
||||
else
|
||||
{
|
||||
count = encode_strtoustr(u, b, len, encoding);
|
||||
count = encode_cstrtoustr(u, len, b, len, encoding);
|
||||
}
|
||||
|
||||
self = [self initWithCharactersNoCopy: u length: count freeWhenDone: YES];
|
||||
|
|
@ -2307,23 +2310,37 @@ handle_printf_atsign (FILE *stream,
|
|||
else
|
||||
{
|
||||
int t;
|
||||
int bsiz;
|
||||
unichar *u;
|
||||
unsigned char *buff;
|
||||
|
||||
u = (unichar*)NSZoneMalloc(NSDefaultMallocZone(), len*sizeof(unichar));
|
||||
[self getCharacters: u];
|
||||
buff = (unsigned char*)NSZoneMalloc(NSDefaultMallocZone(), len);
|
||||
if (flag == YES)
|
||||
t = encode_ustrtostr(buff, u, len, encoding);
|
||||
else
|
||||
t = encode_ustrtostr_strict(buff, u, len, encoding);
|
||||
if (encoding == NSUTF8StringEncoding)
|
||||
{
|
||||
bsiz = len * 4;
|
||||
}
|
||||
else
|
||||
{
|
||||
bsiz = len;
|
||||
}
|
||||
buff = (unsigned char*)NSZoneMalloc(NSDefaultMallocZone(), bsiz);
|
||||
flag = (flag == YES) ? NO : YES;
|
||||
t = encode_ustrtocstr(buff, bsiz, u, len, encoding, flag);
|
||||
NSZoneFree(NSDefaultMallocZone(), u);
|
||||
if (t == 0)
|
||||
{
|
||||
NSZoneFree(NSDefaultMallocZone(), buff);
|
||||
return nil;
|
||||
}
|
||||
return [NSDataClass dataWithBytesNoCopy: buff length: t];
|
||||
else
|
||||
{
|
||||
if (bsiz != t)
|
||||
{
|
||||
buff = NSZoneRealloc(NSDefaultMallocZone(), buff, t);
|
||||
}
|
||||
return [NSDataClass dataWithBytesNoCopy: buff length: t];
|
||||
}
|
||||
}
|
||||
return nil;
|
||||
}
|
||||
|
|
|
|||
770
Source/Unicode.m
770
Source/Unicode.m
|
|
@ -360,7 +360,7 @@ iconv_strtoustr(unichar *u2, int size2, const char *s1, int size1, NSStringEncod
|
|||
}
|
||||
|
||||
int
|
||||
iconv_ustrtostr(char *s2, int size2, unichar *u1, int size1,
|
||||
iconv_ustrtostr(char *s2, int size2, const unichar *u1, int size1,
|
||||
NSStringEncoding enc)
|
||||
{
|
||||
iconv_t conv;
|
||||
|
|
@ -643,378 +643,12 @@ unitochar(unichar u)
|
|||
return encode_unitochar(u, defEnc);
|
||||
}
|
||||
|
||||
int
|
||||
strtoustr(unichar *u1, const char *s1, int size)
|
||||
{
|
||||
if (defEnc == GSUndefinedEncoding)
|
||||
{
|
||||
defEnc = GetDefEncoding();
|
||||
}
|
||||
|
||||
return encode_strtoustr(u1, s1, size, defEnc);
|
||||
}
|
||||
|
||||
int
|
||||
ustrtostr(char *s2, unichar *u1, int size)
|
||||
{
|
||||
if (defEnc == GSUndefinedEncoding)
|
||||
{
|
||||
defEnc = GetDefEncoding();
|
||||
}
|
||||
|
||||
return encode_ustrtostr(s2, u1, size, defEnc);
|
||||
}
|
||||
|
||||
int
|
||||
encode_strtoustr(unichar *u1, const char *s1, int size, NSStringEncoding enc)
|
||||
{
|
||||
int count;
|
||||
|
||||
switch (enc)
|
||||
{
|
||||
case NSNonLossyASCIIStringEncoding:
|
||||
case NSASCIIStringEncoding:
|
||||
case NSISOLatin1StringEncoding:
|
||||
case NSUnicodeStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u1[count] = (unichar)((unc)s1[count]);
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSNEXTSTEPStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
unc c = (unc)s1[count];
|
||||
|
||||
if (c < Next_conv_base)
|
||||
u1[count] = (unichar)c;
|
||||
else
|
||||
u1[count] = Next_char_to_uni_table[c - Next_conv_base];
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSISOCyrillicStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
unc c = (unc)s1[count];
|
||||
|
||||
if (c < Cyrillic_conv_base)
|
||||
u1[count] = (unichar)c;
|
||||
else
|
||||
u1[count] = Cyrillic_char_to_uni_table[c - Cyrillic_conv_base];
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSISOLatin2StringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
unc c = (unc)s1[count];
|
||||
|
||||
if (c < Latin2_conv_base)
|
||||
u1[count] = (unichar)c;
|
||||
else
|
||||
u1[count] = Latin2_char_to_uni_table[c - Latin2_conv_base];
|
||||
}
|
||||
return count;
|
||||
|
||||
#if 0
|
||||
case NSSymbolStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
unc c = (unc)s1[count];
|
||||
|
||||
if (c < Symbol_conv_base)
|
||||
u1[count] = (unichar)c;
|
||||
else
|
||||
u1[count] = Symbol_char_to_uni_table[c - Symbol_conv_base];
|
||||
}
|
||||
return count;
|
||||
#endif
|
||||
|
||||
default:
|
||||
#ifdef HAVE_ICONV
|
||||
return iconv_strtoustr(u1, size, s1, size, enc);
|
||||
#else
|
||||
return 0;
|
||||
#endif
|
||||
}
|
||||
/*
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u1[count] = encode_chartouni(s1[count], enc);
|
||||
}
|
||||
return count;
|
||||
*/
|
||||
}
|
||||
|
||||
int
|
||||
encode_ustrtostr(char *s2, unichar *u1, int size, NSStringEncoding enc)
|
||||
{
|
||||
int count;
|
||||
unichar u;
|
||||
|
||||
switch (enc)
|
||||
{
|
||||
case NSNonLossyASCIIStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < 128)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
s2[count] = '*';
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSASCIIStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < 128)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
s2[count] = '*';
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSISOLatin1StringEncoding:
|
||||
case NSUnicodeStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < 256)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
s2[count] = '*';
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSNEXTSTEPStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < (unichar)Next_conv_base)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Next_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Next_uni_to_char_table_size));
|
||||
s2[count] = res ? '*' : Next_uni_to_char_table[--i].to;
|
||||
}
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSISOCyrillicStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < (unichar)Cyrillic_conv_base)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Cyrillic_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Cyrillic_uni_to_char_table_size));
|
||||
s2[count] = res ? '*' : Cyrillic_uni_to_char_table[--i].to;
|
||||
}
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSISOLatin2StringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < (unichar)Latin2_conv_base)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Latin2_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Latin2_uni_to_char_table_size));
|
||||
s2[count] = res ? '*' : Latin2_uni_to_char_table[--i].to;
|
||||
}
|
||||
}
|
||||
return count;
|
||||
|
||||
#if 0
|
||||
case NSSymbolStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < (unichar)Symbol_conv_base)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Symbol_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Symbol_uni_to_char_table_size));
|
||||
s2[count] = res ? '*' : Symbol_uni_to_char_table[--i].to;
|
||||
}
|
||||
}
|
||||
return count;
|
||||
#endif
|
||||
|
||||
default:
|
||||
#ifdef HAVE_ICONV
|
||||
// FIXME: The non-strict encoding is still missing
|
||||
return iconv_ustrtostr(s2, size, u1, size, enc);
|
||||
#else
|
||||
return 0;
|
||||
#endif
|
||||
}
|
||||
}
|
||||
|
||||
int
|
||||
encode_ustrtostr_strict(char *s2, unichar *u1, int size, NSStringEncoding enc)
|
||||
{
|
||||
int count;
|
||||
unichar u;
|
||||
|
||||
switch (enc)
|
||||
{
|
||||
case NSNonLossyASCIIStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < 128)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSASCIIStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < 128)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSISOLatin1StringEncoding:
|
||||
case NSUnicodeStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < 256)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSNEXTSTEPStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < (unichar)Next_conv_base)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Next_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Next_uni_to_char_table_size));
|
||||
if (!res)
|
||||
s2[count] = Next_uni_to_char_table[--i].to;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSISOCyrillicStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < (unichar)Cyrillic_conv_base)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Cyrillic_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Cyrillic_uni_to_char_table_size));
|
||||
if (!res)
|
||||
s2[count] = Cyrillic_uni_to_char_table[--i].to;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
return count;
|
||||
|
||||
case NSISOLatin2StringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < (unichar)Latin2_conv_base)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Latin2_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Latin2_uni_to_char_table_size));
|
||||
if (!res)
|
||||
s2[count] = Latin2_uni_to_char_table[--i].to;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
return count;
|
||||
|
||||
#if 0
|
||||
case NSSymbolStringEncoding:
|
||||
for (count = 0; count < size; count++)
|
||||
{
|
||||
u = u1[count];
|
||||
if (u < (unichar)Symbol_conv_base)
|
||||
s2[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Symbol_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Symbol_uni_to_char_table_size));
|
||||
if (!res)
|
||||
s2[count] = Symbol_uni_to_char_table[--i].to;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
return count;
|
||||
#endif
|
||||
|
||||
default:
|
||||
#ifdef HAVE_ICONV
|
||||
return iconv_ustrtostr(s2, size, u1, size, enc);
|
||||
#else
|
||||
return 0;
|
||||
#endif
|
||||
}
|
||||
}
|
||||
|
||||
// These two functions use direct access into a two-level table to map cases.
|
||||
// The two-level table method is less space efficient (but still not bad) than
|
||||
// a single table and a linear search, but it reduces the number of
|
||||
// conditional statements to just one.
|
||||
* These two functions use direct access into a two-level table to map cases.
|
||||
* The two-level table method is less space efficient (but still not bad) than
|
||||
* a single table and a linear search, but it reduces the number of
|
||||
* conditional statements to just one.
|
||||
*/
|
||||
unichar
|
||||
uni_tolower(unichar ch)
|
||||
{
|
||||
|
|
@ -1127,3 +761,395 @@ uni_is_decomp(unichar u)
|
|||
return 0;
|
||||
}
|
||||
|
||||
|
||||
int encode_ustrtocstr(char *dst, int dl, const unichar *src, int sl,
|
||||
NSStringEncoding enc, BOOL strict)
|
||||
{
|
||||
if (strict == YES)
|
||||
{
|
||||
int count;
|
||||
unichar u;
|
||||
|
||||
switch (enc)
|
||||
{
|
||||
case NSNonLossyASCIIStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < 128)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSASCIIStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < 128)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSISOLatin1StringEncoding:
|
||||
case NSUnicodeStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < 256)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSNEXTSTEPStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < (unichar)Next_conv_base)
|
||||
{
|
||||
dst[count] = (char)u;
|
||||
}
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Next_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Next_uni_to_char_table_size));
|
||||
if (!res)
|
||||
dst[count] = Next_uni_to_char_table[--i].to;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSISOCyrillicStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < (unichar)Cyrillic_conv_base)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Cyrillic_uni_to_char_table[i++].from)
|
||||
> 0) && (i < Cyrillic_uni_to_char_table_size));
|
||||
if (!res)
|
||||
dst[count] = Cyrillic_uni_to_char_table[--i].to;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSISOLatin2StringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < (unichar)Latin2_conv_base)
|
||||
{
|
||||
dst[count] = (char)u;
|
||||
}
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Latin2_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Latin2_uni_to_char_table_size));
|
||||
if (!res)
|
||||
dst[count] = Latin2_uni_to_char_table[--i].to;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
#if 0
|
||||
case NSSymbolStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < (unichar)Symbol_conv_base)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Symbol_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Symbol_uni_to_char_table_size));
|
||||
if (!res)
|
||||
dst[count] = Symbol_uni_to_char_table[--i].to;
|
||||
else
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
#endif
|
||||
|
||||
default:
|
||||
#ifdef HAVE_ICONV
|
||||
return iconv_ustrtostr(dst, dl, src, sl, enc);
|
||||
#else
|
||||
return 0;
|
||||
#endif
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
int count;
|
||||
unichar u;
|
||||
|
||||
switch (enc)
|
||||
{
|
||||
case NSNonLossyASCIIStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < 128)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
dst[count] = '*';
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSASCIIStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < 128)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
dst[count] = '*';
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSISOLatin1StringEncoding:
|
||||
case NSUnicodeStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < 256)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
dst[count] = '*';
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSNEXTSTEPStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < (unichar)Next_conv_base)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Next_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Next_uni_to_char_table_size));
|
||||
dst[count] = res ? '*' : Next_uni_to_char_table[--i].to;
|
||||
}
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSISOCyrillicStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < (unichar)Cyrillic_conv_base)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Cyrillic_uni_to_char_table[i++].from)
|
||||
> 0) && (i < Cyrillic_uni_to_char_table_size));
|
||||
dst[count] = res ? '*' : Cyrillic_uni_to_char_table[--i].to;
|
||||
}
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSISOLatin2StringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < (unichar)Latin2_conv_base)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Latin2_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Latin2_uni_to_char_table_size));
|
||||
dst[count] = res ? '*' : Latin2_uni_to_char_table[--i].to;
|
||||
}
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
#if 0
|
||||
case NSSymbolStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
u = src[count];
|
||||
if (u < (unichar)Symbol_conv_base)
|
||||
dst[count] = (char)u;
|
||||
else
|
||||
{
|
||||
int res;
|
||||
int i = 0;
|
||||
|
||||
while (((res = u - Symbol_uni_to_char_table[i++].from) > 0)
|
||||
&& (i < Symbol_uni_to_char_table_size));
|
||||
dst[count] = res ? '*' : Symbol_uni_to_char_table[--i].to;
|
||||
}
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
#endif
|
||||
|
||||
default:
|
||||
#ifdef HAVE_ICONV
|
||||
// FIXME: The non-strict encoding is still missing
|
||||
return iconv_ustrtostr(dst, dl, src, sl, enc);
|
||||
#else
|
||||
return 0;
|
||||
#endif
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
int encode_cstrtoustr(unichar *dst, int dl, const char *src, int sl,
|
||||
NSStringEncoding enc)
|
||||
{
|
||||
int count;
|
||||
|
||||
switch (enc)
|
||||
{
|
||||
case NSNonLossyASCIIStringEncoding:
|
||||
case NSASCIIStringEncoding:
|
||||
case NSISOLatin1StringEncoding:
|
||||
case NSUnicodeStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
dst[count] = (unichar)((unc)src[count]);
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSNEXTSTEPStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
unc c = (unc)src[count];
|
||||
|
||||
if (c < Next_conv_base)
|
||||
dst[count] = (unichar)c;
|
||||
else
|
||||
dst[count] = Next_char_to_uni_table[c - Next_conv_base];
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSISOCyrillicStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
unc c = (unc)src[count];
|
||||
|
||||
if (c < Cyrillic_conv_base)
|
||||
dst[count] = (unichar)c;
|
||||
else
|
||||
dst[count] = Cyrillic_char_to_uni_table[c - Cyrillic_conv_base];
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
case NSISOLatin2StringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
unc c = (unc)src[count];
|
||||
|
||||
if (c < Latin2_conv_base)
|
||||
dst[count] = (unichar)c;
|
||||
else
|
||||
dst[count] = Latin2_char_to_uni_table[c - Latin2_conv_base];
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
|
||||
#if 0
|
||||
case NSSymbolStringEncoding:
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
unc c = (unc)src[count];
|
||||
|
||||
if (c < Symbol_conv_base)
|
||||
dst[count] = (unichar)c;
|
||||
else
|
||||
dst[count] = Symbol_char_to_uni_table[c - Symbol_conv_base];
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
#endif
|
||||
|
||||
default:
|
||||
#ifdef HAVE_ICONV
|
||||
return iconv_strtoustr(dst, dl, src, sl, enc);
|
||||
#else
|
||||
return 0;
|
||||
#endif
|
||||
}
|
||||
/*
|
||||
for (count = 0; count < sl && count < dl; count++)
|
||||
{
|
||||
dst[count] = encode_chartouni(src[count], enc);
|
||||
}
|
||||
if (count < sl)
|
||||
return 0; // Not all characters converted.
|
||||
return count;
|
||||
*/
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue