* ctype.cc (_CTYPE_DATA_0_127): Add _B class to TAB character.
(__ctype_default): New character class array for default ASCII character set. (__ctype_iso): New array of character class array for ISO charsets. (__ctype_cp): Ditto for singlebyte Windows codepages. (tolower): Implement as distinct function to support any singlebyte charset. (toupper): Ditto. (__set_ctype): New function to copy singlebyte character classes corresponding to current charset to ctype_b array. Align copyright text to upstream. * dcrt0.cc (dll_crt0_1): Reset current locale to "C" per POSIX. * environ.cc (set_file_api_mode): Remove. (codepage_init): Remove. (parse_thing): Remove "codepage" setting. (environ_init): Set locale according to environment settings, or to current codepage, before converting environment to multibyte. * fhandler.h (fhandler_console::write_replacement_char): Drop argument. * fhandler_console.cc (dev_console::str_to_con): Call sys_cp_mbstowcs rather than MultiByteToWideChar. (fhandler_console::write_replacement_char): Always print a funny half filled square if a character isn't in the current charset. (fhandler_console::write_normal): Convert to using __mbtowc rather than next_char. * fork.cc (frok::child): Drop call to set_file_api_mode. * globals.cc (enum codepage_type) Remove. (current_codepage): Remove. * miscfuncs.cc (cygwin_wcslwr): Unused, dangerous. Remove. (cygwin_wcsupr): Ditto. (is_cp_multibyte): Remove. (next_char): Remove. * miscfuncs.h (is_cp_multibyte): Drop declaration. (next_char): Ditto. * strfuncs.cc (get_cp): Remove. (__db_wctomb): New function to implement _wctomb_r functionality for doublebyte charsets using WideCharToMultiByte. (__sjis_wctomb): New function to replace unusable newlib function. (__jis_wctomb): Ditto. (__eucjp_wctomb): Ditto. (__gbk_wctomb): New function. (__kr_wctomb): Ditto. (__big5_wctomb): Ditto. (__db_mbtowc): New function to implement _mbtowc_r functionality for doublebyte charsets using MultiByteToWideChar. (__sjis_mbtowc): New function to replace unusable newlib function. (__jis_mbtowc): Ditto. (__eucjp_mbtowc): Ditto. (__gbk_mbtowc): New function. (__kr_mbtowc): New function (__big5_mbtowc): New function (__set_charset_from_codepage): New function. (sys_wcstombs): Reimplement, basically using same wide char to multibyte conversion as newlib's application level functions. Plus extras. Add lengthy comment to explain. Change return type to size_t. (sys_wcstombs_alloc): Just use sys_wcstombs. Change return type to size_t. (sys_cp_mbstowcs): Replace sys_mbstowcs, take additional codepage argument. Explain why. Change return type to size_t. (sys_mbstowcs_alloc): Just use sys_mbstowcs. Change return type to size_t. * wchar.h: Declare internal functions implemented in strfuncs.cc. (wcscasecmp): Remove. (wcsncasecmp): Remove. (wcslwr): Remove. (wcsupr): Remove. * winsup.h (codepage_init): Remove declaration. (get_cp): Ditto. (sys_wcstombs): Align declaration to new implementation. (sys_wcstombs_alloc): Ditto. (sys_cp_mbstowcs): Add declaration. (sys_mbstowcs): Define as inline function. (sys_mbstowcs_alloc): Align declaration to new implementation. (set_file_api_mode): Remove declaration. * include/ctype.h (isblank): Redefine to use _B character class. (toupper): Remove ASCII-only definition. (tolower): Ditto.
This commit is contained in:
Corinna Vinschen
@@ -141,26 +141,6 @@ cygwin_strncasecmp (const char *cs, const char *ct, size_t n)
|
||||
return RtlCompareUnicodeString (&us, &ut, TRUE);
|
||||
}
|
||||
|
||||
extern "C" wchar_t * __stdcall
|
||||
cygwin_wcslwr (wchar_t *string)
|
||||
{
|
||||
UNICODE_STRING us;
|
||||
|
||||
RtlInitUnicodeString (&us, string);
|
||||
RtlDowncaseUnicodeString (&us, &us, FALSE);
|
||||
return string;
|
||||
}
|
||||
|
||||
extern "C" wchar_t * __stdcall
|
||||
cygwin_wcsupr (wchar_t *string)
|
||||
{
|
||||
UNICODE_STRING us;
|
||||
|
||||
RtlInitUnicodeString (&us, string);
|
||||
RtlUpcaseUnicodeString (&us, &us, FALSE);
|
||||
return string;
|
||||
}
|
||||
|
||||
extern "C" char * __stdcall
|
||||
cygwin_strlwr (char *string)
|
||||
{
|
||||
@@ -189,118 +169,6 @@ cygwin_strupr (char *string)
|
||||
return string;
|
||||
}
|
||||
|
||||
/* FIXME? We only support standard ANSI/OEM codepages according to
|
||||
http://www.microsoft.com/globaldev/reference/cphome.mspx as well
|
||||
as UTF-8 and codepage 1361, which is also mentioned as valid
|
||||
doublebyte codepage in MSDN man pages (e.g. IsDBCSLeadByteEx).
|
||||
Everything else will be hosed. */
|
||||
|
||||
bool
|
||||
is_cp_multibyte (UINT cp)
|
||||
{
|
||||
switch (cp)
|
||||
{
|
||||
case 932:
|
||||
case 936:
|
||||
case 949:
|
||||
case 950:
|
||||
case 1361:
|
||||
case 65001:
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
/* OMYGOD! CharNextExA is not UTF-8 aware! It only works fine with
|
||||
double byte charsets. So we have to do it ourselves for UTF-8.
|
||||
|
||||
While being at it, we do more. If a double-byte or multibyte
|
||||
sequence is truncated due to an early end, we need a way to recognize
|
||||
it. The reason is that multiple buffered write statements might
|
||||
accidentally stop and start in the middle of a single character byte
|
||||
sequence. If we have to interpret the byte sequences (as in
|
||||
fhandler_console), we would print wrong output in these cases.
|
||||
|
||||
So we have four possible return values here:
|
||||
|
||||
ret = end if str >= end
|
||||
ret = NULL if we encounter an invalid byte sequence
|
||||
ret = str if we encounter the start byte of a truncated byte sequence
|
||||
ret = str + n if we encounter a vaild byte sequence
|
||||
*/
|
||||
|
||||
const unsigned char *
|
||||
next_char (UINT cp, const unsigned char *str, const unsigned char *end)
|
||||
{
|
||||
const unsigned char *ret = NULL;
|
||||
|
||||
if (str >= end)
|
||||
return end;
|
||||
|
||||
switch (cp)
|
||||
{
|
||||
case 932:
|
||||
case 936:
|
||||
case 949:
|
||||
case 950:
|
||||
case 1361:
|
||||
if (*str <= 0x7f)
|
||||
ret = str + 1;
|
||||
else if (str == end - 1 && IsDBCSLeadByteEx (cp, *str))
|
||||
ret = str;
|
||||
else
|
||||
ret = (const unsigned char *) CharNextExA (cp, (const CHAR *) str, 0);
|
||||
break;
|
||||
case CP_UTF8:
|
||||
switch (str[0] >> 4)
|
||||
{
|
||||
case 0x0 ... 0x7: /* One byte character. */
|
||||
ret = str + 1;
|
||||
break;
|
||||
case 0x8 ... 0xb: /* Followup byte. Invalid as first byte. */
|
||||
ret = NULL;
|
||||
break;
|
||||
case 0xc ... 0xd: /* Two byte character. */
|
||||
/* Check followup bytes for validity. */
|
||||
if (str >= end - 1)
|
||||
ret = str;
|
||||
else if (str[1] <= 0xbf)
|
||||
ret = str + 2;
|
||||
else
|
||||
ret = NULL;
|
||||
break;
|
||||
case 0xe: /* Three byte character. */
|
||||
if (str >= end - 2)
|
||||
ret = str;
|
||||
else if ((str[1] & 0xc0) == 0x80 && (str[2] & 0xc0) == 0x80
|
||||
&& (str[0] != 0xe0 || str[1] >= 0xa0)
|
||||
&& (str[0] != 0xed || str[1] <= 0x9f))
|
||||
ret = str + 3;
|
||||
else
|
||||
ret = NULL;
|
||||
break;
|
||||
case 0xf: /* Four byte character. */
|
||||
if (str[0] >= 0xf8)
|
||||
ret = NULL;
|
||||
else if (str >= end - 3)
|
||||
ret = str;
|
||||
else if ((str[1] & 0xc0) == 0x80 && (str[2] & 0xc0) == 0x80
|
||||
&& (str[3] & 0xc0) == 0x80
|
||||
&& (str[0] == 0xf0 || str[1] >= 0x90)
|
||||
&& (str[0] == 0xf4 || str[1] <= 0x8f))
|
||||
ret = str + 4;
|
||||
else
|
||||
ret = NULL;
|
||||
break;
|
||||
}
|
||||
break;
|
||||
default:
|
||||
ret = str + 1;
|
||||
break;
|
||||
}
|
||||
return ret;
|
||||
}
|
||||
|
||||
int __stdcall
|
||||
check_invalid_virtual_addr (const void *s, unsigned sz)
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user