diff options
author | Johannes Schickel | 2013-11-23 21:34:54 +0100 |
---|---|---|
committer | Johannes Schickel | 2013-11-23 21:34:54 +0100 |
commit | a6fff7a8054ce84c3482ff7ddc9365fab324200f (patch) | |
tree | 4eda6601ed3fa62c967d2411af65e6f8d6802118 /engines/wintermute/utils/string_util.cpp | |
parent | 9da09f584679553098c748f2839a617ed1774e83 (diff) | |
download | scummvm-rg350-a6fff7a8054ce84c3482ff7ddc9365fab324200f.tar.gz scummvm-rg350-a6fff7a8054ce84c3482ff7ddc9365fab324200f.tar.bz2 scummvm-rg350-a6fff7a8054ce84c3482ff7ddc9365fab324200f.zip |
WINTERMUTE: Switch WideString to U32String.
Diffstat (limited to 'engines/wintermute/utils/string_util.cpp')
-rw-r--r-- | engines/wintermute/utils/string_util.cpp | 247 |
1 files changed, 71 insertions, 176 deletions
diff --git a/engines/wintermute/utils/string_util.cpp b/engines/wintermute/utils/string_util.cpp index d5d6c7f702..702dd04c27 100644 --- a/engines/wintermute/utils/string_util.cpp +++ b/engines/wintermute/utils/string_util.cpp @@ -48,201 +48,96 @@ bool StringUtil::compareNoCase(const AnsiString &str1, const AnsiString &str2) { return (str1lc == str2lc); }*/ -Common::String StringUtil::substituteUtf8Characters(Common::String &str) { - uint strSize = str.size(); - Common::String punctuation("!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"); - - if (isAscii(str)) - return str; - - for (uint32 i = 0; i < strSize; i++) { - if (!Common::isAlnum(str[i]) && str[i] != ' ' && !punctuation.contains(str[i])) { - // Replace some UTF-8 characters with (almost) equivalent ANSII ones - if ((byte)str[i] == 0xc2 && i + 1 < str.size() && (byte)str[i + 1] == 0xa9) { - // UTF-8 copyright character, substitute with 'c' - str.deleteChar(i); - str.setChar('c', i); - strSize--; - } - } - } - - return str; -} - -bool StringUtil::isAscii(const Common::String &str) { - Common::String punctuation("!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"); - - for (uint32 i = 0; i < str.size(); i++) { - if (!Common::isAlnum(str[i]) && str[i] != ' ' && !punctuation.contains(str[i])) - return false; - } - - return true; -} - ////////////////////////////////////////////////////////////////////////// WideString StringUtil::utf8ToWide(const Utf8String &Utf8Str) { - // WORKAROUND: Since wide strings aren't supported yet, we make this function - // work at least with ASCII strings. This should cover all English versions. - Common::String asciiString = Utf8Str; - asciiString = substituteUtf8Characters(asciiString); - if (isAscii(asciiString)) { - // No special (UTF-8) characters found, just return the string - return asciiString; - } else { - warning("String contains special (UTF-8) characters: '%s'", Utf8Str.c_str()); - } - - error("StringUtil::Utf8ToWide - WideString not supported yet for UTF-8 characters"); - - /* size_t WideSize = Utf8Str.size(); - - if (sizeof(wchar_t) == 2) { - wchar_t *WideStringNative = new wchar_t[WideSize + 1]; - - const UTF8 *SourceStart = reinterpret_cast<const UTF8 *>(Utf8Str.c_str()); - const UTF8 *SourceEnd = SourceStart + WideSize; + size_t wideSize = Utf8Str.size(); - UTF16 *TargetStart = reinterpret_cast<UTF16 *>(WideStringNative); - UTF16 *TargetEnd = TargetStart + WideSize + 1; + uint32 *wideStringNative = new uint32[wideSize + 1]; - ConversionResult res = ConvertUTF8toUTF16(&SourceStart, SourceEnd, &TargetStart, TargetEnd, strictConversion); - if (res != conversionOK) { - delete[] WideStringNative; - return L""; - } - *TargetStart = 0; - WideString ResultString(WideStringNative); - delete[] WideStringNative; + const UTF8 *sourceStart = reinterpret_cast<const UTF8 *>(Utf8Str.c_str()); + const UTF8 *sourceEnd = sourceStart + wideSize; - return ResultString; - } else if (sizeof(wchar_t) == 4) { - wchar_t *WideStringNative = new wchar_t[WideSize + 1]; + UTF32 *targetStart = reinterpret_cast<UTF32 *>(wideStringNative); + UTF32 *targetEnd = targetStart + wideSize; - const UTF8 *SourceStart = reinterpret_cast<const UTF8 *>(Utf8Str.c_str()); - const UTF8 *SourceEnd = SourceStart + WideSize; - - UTF32 *TargetStart = reinterpret_cast<UTF32 *>(WideStringNative); - UTF32 *TargetEnd = TargetStart + WideSize; - - ConversionResult res = ConvertUTF8toUTF32(&SourceStart, SourceEnd, &TargetStart, TargetEnd, strictConversion); - if (res != conversionOK) { - delete[] WideStringNative; - return L""; - } - *TargetStart = 0; - WideString ResultString(WideStringNative); - delete[] WideStringNative; - - return ResultString; - } else { - return L""; - }*/ - return ""; + ConversionResult res = ConvertUTF8toUTF32(&sourceStart, sourceEnd, &targetStart, targetEnd, strictConversion); + if (res != conversionOK) { + delete[] wideStringNative; + return WideString(); + } + *targetStart = 0; + WideString resultString(wideStringNative); + delete[] wideStringNative; + return resultString; } ////////////////////////////////////////////////////////////////////////// Utf8String StringUtil::wideToUtf8(const WideString &WideStr) { - // WORKAROUND: Since UTF-8 strings aren't supported yet, we make this function - // work at least with ASCII strings. This should cover all English versions. - Common::String asciiString = WideStr; - asciiString = substituteUtf8Characters(asciiString); - if (isAscii(asciiString)) { - // No special (UTF-8) characters found, just return the string - return asciiString; - } else { - warning("String contains special (UTF-8) characters: '%s'", WideStr.c_str()); - } + size_t wideSize = WideStr.size(); - error("StringUtil::wideToUtf8 - WideString not supported yet for UTF-8 characters"); - - /* size_t WideSize = WideStr.length(); + size_t utf8Size = 4 * wideSize + 1; + char *utf8StringNative = new char[utf8Size]; - if (sizeof(wchar_t) == 2) { - size_t utf8Size = 3 * WideSize + 1; - char *utf8StringNative = new char[Utf8Size]; + const UTF32 *sourceStart = reinterpret_cast<const UTF32 *>(WideStr.c_str()); + const UTF32 *sourceEnd = sourceStart + wideSize; - const UTF16 *SourceStart = reinterpret_cast<const UTF16 *>(WideStr.c_str()); - const UTF16 *SourceEnd = SourceStart + WideSize; + UTF8 *targetStart = reinterpret_cast<UTF8 *>(utf8StringNative); + UTF8 *targetEnd = targetStart + utf8Size; - UTF8 *TargetStart = reinterpret_cast<UTF8 *>(Utf8StringNative); - UTF8 *TargetEnd = TargetStart + Utf8Size; - - ConversionResult res = ConvertUTF16toUTF8(&SourceStart, SourceEnd, &TargetStart, TargetEnd, strictConversion); - if (res != conversionOK) { - delete[] Utf8StringNative; - return (Utf8String)""; - } - *TargetStart = 0; - Utf8String ResultString(Utf8StringNative); - delete[] Utf8StringNative; - return ResultString; - } else if (sizeof(wchar_t) == 4) { - size_t utf8Size = 4 * WideSize + 1; - char *utf8StringNative = new char[Utf8Size]; - - const UTF32 *SourceStart = reinterpret_cast<const UTF32 *>(WideStr.c_str()); - const UTF32 *SourceEnd = SourceStart + WideSize; - - UTF8 *TargetStart = reinterpret_cast<UTF8 *>(Utf8StringNative); - UTF8 *TargetEnd = TargetStart + Utf8Size; - - ConversionResult res = ConvertUTF32toUTF8(&SourceStart, SourceEnd, &TargetStart, TargetEnd, strictConversion); - if (res != conversionOK) { - delete[] Utf8StringNative; - return (Utf8String)""; - } - *TargetStart = 0; - Utf8String ResultString(Utf8StringNative); - delete[] Utf8StringNative; - return ResultString; - } else { - return (Utf8String)""; - }*/ - return ""; + ConversionResult res = ConvertUTF32toUTF8(&sourceStart, sourceEnd, &targetStart, targetEnd, strictConversion); + if (res != conversionOK) { + delete[] utf8StringNative; + return Utf8String(); + } + *targetStart = 0; + Utf8String resultString(utf8StringNative); + delete[] utf8StringNative; + return resultString; } ////////////////////////////////////////////////////////////////////////// WideString StringUtil::ansiToWide(const AnsiString &str) { - // TODO: This function gets called a lot, so warnings like these drown out the usefull information - Common::String converted = ""; - uint32 index = 0; - while (index != str.size()) { - byte c = str[index]; - if (c == 146) { - converted += (char)39; // Replace right-quote with apostrophe - } else if (c == 133) { - converted += Common::String("..."); // Replace ...-symbol with ... + WideString result; + for (AnsiString::const_iterator i = str.begin(), end = str.end(); i != end; ++i) { + const byte c = *i; + if (c < 0x80 || c >= 0xA0) { + result += c; } else { - converted += c; + uint32 utf32 = _ansiToUTF32[c - 0x80]; + if (utf32) { + result += utf32; + } else { + // It's an invalid CP1252 character... + } } - index++; } - // using default os locale! - - /* setlocale(LC_CTYPE, ""); - size_t wideSize = mbstowcs(NULL, str.c_str(), 0) + 1; - wchar_t *wstr = new wchar_t[WideSize]; - mbstowcs(wstr, str.c_str(), WideSize); - WideString ResultString(wstr); - delete[] wstr; - return ResultString;*/ - return WideString(converted); + return result; } ////////////////////////////////////////////////////////////////////////// AnsiString StringUtil::wideToAnsi(const WideString &wstr) { - // using default os locale! - // TODO: This function gets called a lot, so warnings like these drown out the usefull information - /* setlocale(LC_CTYPE, ""); - size_t wideSize = wcstombs(NULL, wstr.c_str(), 0) + 1; - char *str = new char[WideSize]; - wcstombs(str, wstr.c_str(), WideSize); - AnsiString ResultString(str); - delete[] str; - return ResultString;*/ - return AnsiString(wstr); + AnsiString result; + for (WideString::const_iterator i = wstr.begin(), end = wstr.end(); i != end; ++i) { + const uint32 c = *i; + if (c < 0x80 || (c >= 0xA0 && c <= 0xFF)) { + result += c; + } else { + uint32 ansi = 0xFFFFFFFF; + for (uint j = 0; j < ARRAYSIZE(_ansiToUTF32); ++j) { + if (_ansiToUTF32[j] == c) { + ansi = j + 0x80; + break; + } + } + + if (ansi != 0xFFFFFFFF) { + result += ansi; + } else { + // There's no valid CP1252 code for this character... + } + } + } + return result; } ////////////////////////////////////////////////////////////////////////// @@ -256,12 +151,7 @@ bool StringUtil::isUtf8BOM(const byte *buffer, uint32 bufferSize) { ////////////////////////////////////////////////////////////////////////// int StringUtil::indexOf(const WideString &str, const WideString &toFind, size_t startFrom) { - const char *index = strstr(str.c_str(), toFind.c_str()); - if (index == nullptr) { - return -1; - } else { - return index - str.c_str(); - } + return str.find(toFind, startFrom); } Common::String StringUtil::encodeSetting(const Common::String &str) { @@ -282,5 +172,10 @@ AnsiString StringUtil::toString(int val) { return Common::String::format("%d", val); } +// Mapping of CP1252 characters 0x80...0x9F into UTF-32 +uint32 StringUtil::_ansiToUTF32[32] = { + 0x20AC, 0x0000, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0x02C6, 0x2030, 0x0160, 0x2039, 0x0152, 0x0000, 0x017D, 0x0000, + 0x0000, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x02DC, 0x2122, 0x0161, 0x203A, 0x0153, 0x0000, 0x017E, 0x0178 +}; } // End of namespace Wintermute |