* 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
@@ -13,6 +13,7 @@ details. */
|
||||
#include <wchar.h>
|
||||
#include <wctype.h>
|
||||
#include <ctype.h>
|
||||
#include <locale.h>
|
||||
#include <assert.h>
|
||||
#include <cygwin/version.h>
|
||||
#include <winnls.h>
|
||||
@@ -552,48 +553,6 @@ glob_init (const char *buf)
|
||||
}
|
||||
}
|
||||
|
||||
void
|
||||
set_file_api_mode (codepage_type cp)
|
||||
{
|
||||
if (cp == oem_cp)
|
||||
{
|
||||
SetFileApisToOEM ();
|
||||
debug_printf ("File APIs set to OEM");
|
||||
}
|
||||
else
|
||||
{
|
||||
SetFileApisToANSI ();
|
||||
debug_printf ("File APIs set to ANSI");
|
||||
}
|
||||
}
|
||||
|
||||
void
|
||||
codepage_init (const char *buf)
|
||||
{
|
||||
if (!buf)
|
||||
buf = "ansi";
|
||||
|
||||
if (ascii_strcasematch (buf, "oem"))
|
||||
{
|
||||
current_codepage = oem_cp;
|
||||
active_codepage = GetOEMCP ();
|
||||
}
|
||||
else if (ascii_strcasematch (buf, "utf8"))
|
||||
{
|
||||
current_codepage = utf8_cp;
|
||||
active_codepage = CP_UTF8;
|
||||
}
|
||||
else
|
||||
{
|
||||
if (!ascii_strcasematch (buf, "ansi"))
|
||||
debug_printf ("Wrong codepage name: %s", buf);
|
||||
/* Fallback to ANSI */
|
||||
current_codepage = ansi_cp;
|
||||
active_codepage = GetACP ();
|
||||
}
|
||||
set_file_api_mode (current_codepage);
|
||||
}
|
||||
|
||||
static void
|
||||
set_chunksize (const char *buf)
|
||||
{
|
||||
@@ -629,7 +588,6 @@ static struct parse_thing
|
||||
} values[2];
|
||||
} known[] NO_COPY =
|
||||
{
|
||||
{"codepage", {func: &codepage_init}, isfunc, NULL, {{0}, {0}}},
|
||||
{"dosfilewarning", {&dos_file_warning}, justset, NULL, {{false}, {true}}},
|
||||
{"envcache", {&envcache}, justset, NULL, {{true}, {false}}},
|
||||
{"error_start", {func: &error_start_init}, isfunc, NULL, {{0}, {0}}},
|
||||
@@ -774,6 +732,8 @@ environ_init (char **envp, int envc)
|
||||
static char NO_COPY cygterm[] = "TERM=cygwin";
|
||||
myfault efault;
|
||||
tmp_pathbuf tp;
|
||||
bool got_lc = false;
|
||||
static const char *lc_arr[] = { "LC_ALL", "LC_CTYPE", "LANG", NULL };
|
||||
|
||||
if (efault.faulted ())
|
||||
api_fatal ("internal error reading the windows environment - too many environment variables?");
|
||||
@@ -818,10 +778,27 @@ environ_init (char **envp, int envc)
|
||||
/* Allocate space for environment + trailing NULL + CYGWIN env. */
|
||||
lastenviron = envp = (char **) malloc ((4 + (envc = 100)) * sizeof (char *));
|
||||
|
||||
/* We need the CYGWIN variable content before we can loop through
|
||||
/* We need the locale variables' content before we can loop through
|
||||
the whole environment, so that the wide-char to multibyte conversion
|
||||
can be done according to the "codepage" setting, as well as the
|
||||
uppercasing according to the "upcaseenv" setting. */
|
||||
can be done according to the $LC_ALL/$LC_CTYPE/$LANG/current_codepage
|
||||
setting, as well as the uppercasing according to the "upcaseenv"
|
||||
setting. Note that we have to reset the LC_CTYPE setting to "C"
|
||||
before calling main() for POSIX compatibility. */
|
||||
for (int lc = 0; lc_arr[lc]; ++lc)
|
||||
{
|
||||
if ((i = GetEnvironmentVariableA (lc_arr[lc], NULL, 0)))
|
||||
{
|
||||
char *buf = (char *) alloca (i);
|
||||
GetEnvironmentVariableA (lc_arr[lc], buf, i);
|
||||
if (_setlocale_r (_GLOBAL_REENT, LC_CTYPE, buf))
|
||||
got_lc = true;
|
||||
}
|
||||
}
|
||||
/* No matching POSIX environment variable, use current codepage. */
|
||||
if (!got_lc)
|
||||
_setlocale_r (_GLOBAL_REENT, LC_CTYPE, "en_US");
|
||||
/* We also need the CYGWIN variable early to know the value of the
|
||||
CYGWIN=upcaseenv setting for the below loop. */
|
||||
if ((i = GetEnvironmentVariableA ("CYGWIN", NULL, 0)))
|
||||
{
|
||||
char *buf = (char *) alloca (i);
|
||||
|
||||
Reference in New Issue
Block a user