int sceCccStrlenUTF16(u32 strAddr)
{
const auto str = PSPConstWCharPointer::Create(strAddr);
if (!str.IsValid())
{
ERROR_LOG(HLE, "sceCccStrlenUTF16(%08x): invalid pointer", strAddr);
return 0;
}
DEBUG_LOG(HLE, "sceCccStrlenUTF16(%08x): invalid pointer", strAddr);
return UTF16LE(str).length();
}
int sceCccStrlenUTF16(u32 strAddr)
{
PSPWCharPointer str;
str = strAddr;
if (!str.IsValid())
{
ERROR_LOG(HLE, "sceCccStrlenUTF16(%08x): invalid pointer", strAddr);
return 0;
}
DEBUG_LOG(HLE, "sceCccStrlenUTF16(%08x): invalid pointer", strAddr);
return UTF16LE(str).length();
}
TextEncoding TextEncoding::Palm(UInt8 encoding)
{
switch (encoding) {
// Latin Palm OS character encoding, and subsets.
// PalmOS variant of CP1252, with 10 extra Greek characters
case charEncodingPalmGSM:
ThrowError(kTextUnsupportedEncodingErr);
// PalmOS version of CP1252
case charEncodingPalmLatin:
return PalmLatin1();
// Windows variant of 8859-1
case charEncodingCP1252:
return WindowsLatin1();
// ISO 8859 Part 1
case charEncodingISO8859_1:
return ISOLatin1();
// ISO 646-1991
case charEncodingAscii:
return ASCII();
// Japanese Palm OS character encoding, and subsets.
// PalmOS version of CP932
case charEncodingPalmSJIS:
return PalmShiftJIS();
// Windows variant of ShiftJIS
case charEncodingCP932:
return WindowsShiftJIS();
// Encoding for JIS 0208-1990 + 1-byte katakana
case charEncodingShiftJIS:
return ShiftJIS();
// Unicode character encodings
// UCS2 is UTF16 minus the surrogate pairs
case charEncodingUCS2:
return UCS2();
case charEncodingUTF8:
return UTF8();
case charEncodingUTF7:
return UTF7();
case charEncodingUTF16:
return UTF16();
case charEncodingUTF16BE:
return UTF16BE();
case charEncodingUTF16LE:
return UTF16LE();
case charEncodingUTF32:
return UTF32();
case charEncodingUTF32BE:
return UTF32BE();
case charEncodingUTF32LE:
return UTF32LE();
// A variant of UTF7 used by the IMAP mail protocol to encode
// mail folder names. Documented in RFC 2060. This does not
// seem to be supported by the Macintosh text encoding converter.
case charEncodingUTF7_IMAP:
ThrowError(kTextUnsupportedEncodingErr);
// I really don't know how this is different from UTF32...
case charEncodingUCS4:
return UTF32();
// Latin character encodings
case charEncodingCP850:
return TextEncoding(kTextEncodingDOSLatin1, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP437:
return TextEncoding(kTextEncodingDOSLatinUS, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP865:
return TextEncoding(kTextEncodingDOSNordic, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP860:
return TextEncoding(kTextEncodingDOSPortuguese, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP861:
return TextEncoding(kTextEncodingDOSIcelandic, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP863:
return TextEncoding(kTextEncodingDOSCanadianFrench, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP775:
return TextEncoding(kTextEncodingDOSBalticRim, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingMacIslande:
return TextEncoding(kTextEncodingMacIcelandic, kMacIcelandicStdDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingMacintosh:
return TextEncoding(kTextEncodingMacRoman, kMacRomanDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP1257:
return TextEncoding(kTextEncodingWindowsBalticRim, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingISO8859_3:
return TextEncoding(kTextEncodingISOLatin3, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingISO8859_4:
return TextEncoding(kTextEncodingISOLatin4, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// Extended Latin character encodings
case charEncodingISO8859_2:
return TextEncoding(kTextEncodingISOLatin2, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP1250:
return TextEncoding(kTextEncodingWindowsLatin2, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP852:
return TextEncoding(kTextEncodingDOSLatin2, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// This doesn't seem to be implemented on the Mac, though there's
// a description of it at http://www.kiv.zcu.cz/~luki/cs/cs-encodings-faq.html
case charEncodingXKamenicky:
ThrowError(kTextUnsupportedEncodingErr);
case charEncodingMacXCroate:
return TextEncoding(kTextEncodingMacCroatian, kMacCroatianDefaultVariant,
kTextEncodingDefaultFormat);
// I just can't figure out which encoding this refers to.
// It seems like Mac OS X Latin-2, but I don't know what that is.
case charEncodingMacXLat2:
ThrowError(kTextUnsupportedEncodingErr);
case charEncodingMacXRomania:
return TextEncoding(kTextEncodingMacRomanian, kMacRomanianDefaultVariant,
kTextEncodingDefaultFormat);
// I think this must be the character set used by GSM phones in Europe.
// http://www.csoft.co.uk/character_sets/gsm.htm
case charEncodingGSM:
ThrowError(kTextUnsupportedEncodingErr);
// Japanese character encodings
case charEncodingEucJp:
return TextEncoding(kTextEncodingEUC_JP, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingISO2022Jp:
return TextEncoding(kTextEncodingISO_2022_JP, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// This isn't so much an encoding as a heuristic...
case charEncodingXAutoJp:
ThrowError(kTextUnsupportedEncodingErr);
// Greek character encodings
case charEncodingISO8859_7:
return TextEncoding(kTextEncodingISOLatinGreek, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP1253:
return TextEncoding(kTextEncodingWindowsGreek, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP869:
return TextEncoding(kTextEncodingDOSGreek2, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP737:
return TextEncoding(kTextEncodingDOSGreek, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingMacXGr:
return TextEncoding(kTextEncodingMacGreek, kMacGreekDefaultVariant,
kTextEncodingDefaultFormat);
// Cyrillic character encodings
case charEncodingCP1251:
return TextEncoding(kTextEncodingWindowsCyrillic, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingISO8859_5:
return TextEncoding(kTextEncodingISOLatinCyrillic, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingKoi8R:
return TextEncoding(kTextEncodingKOI8_R, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// I'm just guessing by elimination that they mean RFC 2319, Ukrainian here.
case charEncodingKoi8:
return TextEncoding(kTextEncodingKOI8_U, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP855:
return TextEncoding(kTextEncodingDOSCyrillic, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP866:
return TextEncoding(kTextEncodingDOSRussian, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingMacCyr:
return TextEncoding(kTextEncodingMacCyrillic, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingMacUkraine:
return TextEncoding(kTextEncodingMacUkrainian, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// Turkish character encodings
case charEncodingCP1254:
return TextEncoding(kTextEncodingWindowsLatin5, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingISO8859_9:
return TextEncoding(kTextEncodingISOLatin5, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP857:
return TextEncoding(kTextEncodingDOSTurkish, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingMacTurc:
return TextEncoding(kTextEncodingMacTurkish, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// This seems to be DOS Latin 3, but it's not listed in the Mac tables.
case charEncodingCP853:
ThrowError(kTextUnsupportedEncodingErr);
// Arabic character encodings
// The Mac tables don't make any distinction between ISO 8859-6, Asmo 708,
// and DOS 708. I hope it's OK to merge them...
case charEncodingISO8859_6:
case charEncodingAsmo708:
case charEncodingAsmo708Plus:
case charEncodingAsmo708Fr:
return TextEncoding(kTextEncodingISOLatinArabic, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP1256:
return TextEncoding(kTextEncodingWindowsArabic, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP864:
return TextEncoding(kTextEncodingDOSArabic, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingMacAra:
return TextEncoding(kTextEncodingMacArabic, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// Simplified Chinese character encodings
case charEncodingGB2312:
return TextEncoding(kTextEncodingGB_2312_80, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingHZ:
return TextEncoding(kTextEncodingHZ_GB_2312, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingGBK:
return TextEncoding(kTextEncodingGBK_95, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// I'm guessing that this is a Palm variation on GB 2312...
case charEncodingPalmGB:
return TextEncoding(kTextEncodingGB_2312_80, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// Traditional Chinese character encodings
case charEncodingBig5:
return TextEncoding(kTextEncodingBig5, kBig5_BasicVariant,
kTextEncodingDefaultFormat);
case charEncodingBig5_HKSCS:
return TextEncoding(kTextEncodingBig5_HKSCS_1999, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// I'm just guessing that by "Plus" Palm means the ETenVariant that Apple
// says "adds kana, Cyrillic, radicals, etc with hi bytes C6-C8,F9"
case charEncodingBig5Plus:
return TextEncoding(kTextEncodingBig5, kBig5_ETenVariant,
kTextEncodingDefaultFormat);
// No clue what Palm changed, so just use Big-5.
case charEncodingPalmBig5:
return TextEncoding(kTextEncodingBig5, kBig5_BasicVariant,
kTextEncodingDefaultFormat);
case charEncodingISO2022CN:
return TextEncoding(kTextEncodingISO_2022_CN, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// Vietnamese character encodings
case charEncodingViscii:
return TextEncoding(kTextEncodingVISCII, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// VIQR stands for VIetnamese Quoted-Readable,
// which is a convention to write Vietnamese letters using 7-bit ASCII.
// http://www.nonsong.org/viqr.html
case charEncodingViqr:
ThrowError(kTextUnsupportedEncodingErr);
// Also known as VPS
// http://homepages.cwi.nl/~dik/english/codes/stand.html#vncii
case charEncodingVncii:
ThrowError(kTextUnsupportedEncodingErr);
// Several web site seem to think Vietnet is the same as VIQR
case charEncodingVietnet:
ThrowError(kTextUnsupportedEncodingErr);
case charEncodingCP1258:
return TextEncoding(kTextEncodingWindowsVietnamese, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// Korean character encodings
case charEncodingEucKr:
return TextEncoding(kTextEncodingEUC_KR, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingCP949:
return TextEncoding(kTextEncodingDOSKorean, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
case charEncodingISO2022Kr:
return TextEncoding(kTextEncodingISO_2022_KR, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// Hebrew character encodings
case charEncodingISO8859_8I:
return TextEncoding(kTextEncodingISOLatinHebrew, kISOLatinHebrewImplicitOrderVariant,
kTextEncodingDefaultFormat);
// Comments in the Mac TextCommon.h make it clear that the "default"
// variant of ISO 8859-8 is visual ordering.
case charEncodingISO8859_8:
return TextEncoding(kTextEncodingISOLatinHebrew, kISOLatinHebrewVisualOrderVariant,
kTextEncodingDefaultFormat);
case charEncodingCP1255:
return TextEncoding(kTextEncodingWindowsHebrew, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// There's no explicit visual variant for cp1255, so I'm hoping that
// using the default variant is better than throwing an exception...
case charEncodingCP1255V:
return TextEncoding(kTextEncodingWindowsHebrew, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
// Thai character encodings
// TIS-620, http://www.langbox.com/codeset/tis620.html
case charEncodingTis620:
ThrowError(kTextUnsupportedEncodingErr);
case charEncodingCP874:
return TextEncoding(kTextEncodingDOSThai, kTextEncodingDefaultVariant,
kTextEncodingDefaultFormat);
default:
ThrowError(kTextUnsupportedEncodingErr);
}
// not reached
return TextEncoding();
}