X-Git-Url: https://git.distorted.org.uk/u/mdw/putty/blobdiff_plain/4a693cfc5c3ee0e639bbee0215345e921715ab04..88ea89339783ee587180b645981967f6cb8bcd20:/windows/winucs.c diff --git a/windows/winucs.c b/windows/winucs.c index 9abd83c7..cd509835 100644 --- a/windows/winucs.c +++ b/windows/winucs.c @@ -390,6 +390,8 @@ struct cp_list_item { }; static const struct cp_list_item cp_list[] = { + {"UTF-8", CP_UTF8}, + {"ISO-8859-1:1998 (Latin-1, West Europe)", 0, 96, iso_8859_1}, {"ISO-8859-2:1999 (Latin-2, East Europe)", 0, 96, iso_8859_2}, {"ISO-8859-3:1999 (Latin-3, South Europe)", 0, 96, iso_8859_3}, @@ -406,8 +408,6 @@ static const struct cp_list_item cp_list[] = { {"ISO-8859-15:1999 (Latin-9, \"euro\")", 0, 96, iso_8859_15}, {"ISO-8859-16:2001 (Latin-10, Balkan)", 0, 96, iso_8859_16}, - {"UTF-8", CP_UTF8}, - {"KOI8-U", 0, 128, koi8_u}, {"KOI8-R", 20866}, {"HP-ROMAN8", 0, 96, roman8}, @@ -427,6 +427,7 @@ static const struct cp_list_item cp_list[] = { {"CP437", 437}, {"CP620 (Mazovia)", 0, 128, mazovia}, {"CP819", 28591}, + {"CP852", 852}, {"CP878", 20866}, {"Use font encoding", -1}, @@ -1015,48 +1016,8 @@ int decode_codepage(char *cp_name) int codepage = -1; CPINFO cpinfo; - if (!*cp_name) { - /* - * Here we select a plausible default code page based on - * the locale the user is in. We wish to select an ISO code - * page or appropriate local default _rather_ than go with - * the Win125* series, because it's more important to have - * CSI and friends enabled by default than the ghastly - * Windows extra quote characters, and because it's more - * likely the user is connecting to a remote server that - * does something Unixy or VMSy and hence standards- - * compliant than that they're connecting back to a Windows - * box using horrible nonstandard charsets. - * - * Accordingly, Robert de Bath suggests a method for - * picking a default character set that runs as follows: - * first call GetACP to get the system's ANSI code page - * identifier, and translate as follows: - * - * 1250 -> ISO 8859-2 - * 1251 -> KOI8-U - * 1252 -> ISO 8859-1 - * 1253 -> ISO 8859-7 - * 1254 -> ISO 8859-9 - * 1255 -> ISO 8859-8 - * 1256 -> ISO 8859-6 - * 1257 -> ISO 8859-13 (changed from 8859-4 on advice of a Lithuanian) - * - * and for anything else, choose direct-to-font. - */ - int cp = GetACP(); - switch (cp) { - case 1250: cp_name = "ISO-8859-2"; break; - case 1251: cp_name = "KOI8-U"; break; - case 1252: cp_name = "ISO-8859-1"; break; - case 1253: cp_name = "ISO-8859-7"; break; - case 1254: cp_name = "ISO-8859-9"; break; - case 1255: cp_name = "ISO-8859-8"; break; - case 1256: cp_name = "ISO-8859-6"; break; - case 1257: cp_name = "ISO-8859-13"; break; - /* default: leave it blank, which will select -1, direct->font */ - } - } + if (!*cp_name) + return CP_UTF8; /* default */ if (cp_name && *cp_name) for (cpi = cp_list; cpi->name; cpi++) { @@ -1204,7 +1165,7 @@ void get_unitab(int codepage, wchar_t * unitab, int ftype) } } -int wc_to_mb(int codepage, int flags, wchar_t *wcstr, int wclen, +int wc_to_mb(int codepage, int flags, const wchar_t *wcstr, int wclen, char *mbstr, int mblen, char *defchr, int *defused, struct unicode_data *ucsdata) { @@ -1242,7 +1203,7 @@ int wc_to_mb(int codepage, int flags, wchar_t *wcstr, int wclen, mbstr, mblen, defchr, defused); } -int mb_to_wc(int codepage, int flags, char *mbstr, int mblen, +int mb_to_wc(int codepage, int flags, const char *mbstr, int mblen, wchar_t *wcstr, int wclen) { return MultiByteToWideChar(codepage, flags, mbstr, mblen, wcstr, wclen);