COMMON: added method to convert text from various code pages to Unicode

2 files changed, 113 insertions, 0 deletions

diff --git a/common/ustr.cpp b/common/ustr.cpp
index cddfda7201..f314eb1df4 100644
--- a/common/ustr.cpp
+++ b/common/ustr.cpp
@@ -360,4 +360,107 @@ U32String convertUtf8ToUtf32(const String &str) {
 	return u32str;
 }
 
+uint32 g_windows1250ConversionTable[] = {0x20AC, 0x0081, 0x201A, 0x0083, 0x201E, 0x2026, 0x2020, 0x2021,
+										 0x0088, 0x2030, 0x0160, 0x2039, 0x015A, 0x0164, 0x017D, 0x0179,
+										 0x0090, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+										 0x0098, 0x2122, 0x0161, 0x203A, 0x015B, 0x0165, 0x017E, 0x017A,
+										 0x00A0, 0x02C7, 0x02D8, 0x0141, 0x00A4, 0x0104, 0x00A6, 0x00A7,
+										 0x00A8, 0x00A9, 0x015E, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x017B,
+										 0x00B0, 0x00B1, 0x02DB, 0x0142, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
+										 0x00B8, 0x0105, 0x015F, 0x00BB, 0x013D, 0x02DD, 0x013E, 0x017C,
+										 0x0154, 0x00C1, 0x00C2, 0x0102, 0x00C4, 0x0139, 0x0106, 0x00C7,
+										 0x010C, 0x00C9, 0x0118, 0x00CB, 0x011A, 0x00CD, 0x00CE, 0x010E,
+										 0x0110, 0x0143, 0x0147, 0x00D3, 0x00D4, 0x0150, 0x00D6, 0x00D7,
+										 0x0158, 0x016E, 0x00DA, 0x0170, 0x00DC, 0x00DD, 0x0162, 0x00DF,
+										 0x0155, 0x00E1, 0x00E2, 0x0103, 0x00E4, 0x013A, 0x0107, 0x00E7,
+										 0x010D, 0x00E9, 0x0119, 0x00EB, 0x011B, 0x00ED, 0x00EE, 0x010F,
+										 0x0111, 0x0144, 0x0148, 0x00F3, 0x00F4, 0x0151, 0x00F6, 0x00F7,
+										 0x0159, 0x016F, 0x00FA, 0x0171, 0x00FC, 0x00FD, 0x0163, 0x02D9};
+
+uint32 g_windows1251ConversionTable[] = {0x0402, 0x0403, 0x201A, 0x0453, 0x201E, 0x2026, 0x2020, 0x2021,
+										 0x20AC, 0x2030, 0x0409, 0x2039, 0x040A, 0x040C, 0x040B, 0x040F,
+										 0x0452, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+										 0x0098, 0x2122, 0x0459, 0x203A, 0x045A, 0x045C, 0x045B, 0x045F,
+										 0x00A0, 0x040E, 0x045E, 0x0408, 0x00A4, 0x0490, 0x00A6, 0x00A7,
+										 0x0401, 0x00A9, 0x0404, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x0407,
+										 0x00B0, 0x00B1, 0x0406, 0x0456, 0x0491, 0x00B5, 0x00B6, 0x00B7,
+										 0x0451, 0x2116, 0x0454, 0x00BB, 0x0458, 0x0405, 0x0455, 0x0457,
+										 0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417,
+										 0x0418, 0x0419, 0x041A, 0x041B, 0x041C, 0x041D, 0x041E, 0x041F,
+										 0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427,
+										 0x0428, 0x0429, 0x042A, 0x042B, 0x042C, 0x042D, 0x042E, 0x042F,
+										 0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437,
+										 0x0438, 0x0439, 0x043A, 0x043B, 0x043C, 0x043D, 0x043E, 0x043F,
+										 0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447,
+										 0x0448, 0x0449, 0x044A, 0x044B, 0x044C, 0x044D, 0x044E, 0x044F};
+
+uint32 g_windows1252ConversionTable[] = {0x20AC, 0x0081, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021,
+										 0x02C6, 0x2030, 0x0160, 0x2039, 0x0152, 0x008D, 0x017D, 0x008F,
+										 0x0090, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+										 0x02DC, 0x2122, 0x0161, 0x203A, 0x0153, 0x009D, 0x017E, 0x0178,
+										 0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
+										 0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
+										 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
+										 0x00B8, 0x00B9, 0x00BA, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF,
+										 0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
+										 0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF,
+										 0x00D0, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x00D7,
+										 0x00D8, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x00DD, 0x00DE, 0x00DF,
+										 0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7,
+										 0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF,
+										 0x00F0, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x00F7,
+										 0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x00FD, 0x00FE, 0x00FF};
+
+uint32 g_windows1255ConversionTable[] = {0x20AC, 0x0081, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021,
+										 0x02C6, 0x2030, 0x008A, 0x2039, 0x008C, 0x008D, 0x008E, 0x008F,
+										 0x0090, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+										 0x02DC, 0x2122, 0x009A, 0x203A, 0x009C, 0x009D, 0x009E, 0x009F,
+										 0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x20AA, 0x00A5, 0x00A6, 0x00A7,
+										 0x00A8, 0x00A9, 0x00D7, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
+										 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
+										 0x00B8, 0x00B9, 0x00F7, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF,
+										 0x05B0, 0x05B1, 0x05B2, 0x05B3, 0x05B4, 0x05B5, 0x05B6, 0x05B7,
+										 0x05B8, 0x05B9, 0x05BA, 0x05BB, 0x05BC, 0x05BD, 0x05BE, 0x05BF,
+										 0x05C0, 0x05C1, 0x05C2, 0x05C3, 0x05F0, 0x05F1, 0x05F2, 0x05F3,
+										 0x05F4, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x00DD, 0x00DE, 0x00DF,
+										 0x05D0, 0x05D1, 0x05D2, 0x05D3, 0x05D4, 0x05D5, 0x05D6, 0x05D7,
+										 0x05D8, 0x05D9, 0x05DA, 0x05DB, 0x05DC, 0x05DD, 0x05DE, 0x05DF,
+										 0x05E0, 0x05E1, 0x05E2, 0x05E3, 0x05E4, 0x05E5, 0x05E6, 0x05E7,
+										 0x05E8, 0x05E9, 0x05EA, 0x00FB, 0x00FC, 0x200E, 0x200F, 0x00FF};
+
+U32String convertToU32String(const char *str, uint codePage) {
+	const String string(str);
+	if (codePage == kAscii) {
+		return convertUtf8ToUtf32(string);
+	}
+
+	U32String unicodeString;
+	for (uint i = 0; i < string.size(); ++i) {
+		if ((byte)string[i] <= 0x7F) {
+			unicodeString += string[i];
+			continue;
+		}
+
+		byte index = string[i] - 0x80;
+
+		switch (codePage) {
+		case kWindows1250:
+			unicodeString += g_windows1250ConversionTable[index];
+			break;
+		case kWindows1251:
+			unicodeString += g_windows1251ConversionTable[index];
+			break;
+		case kWindows1252:
+			unicodeString += g_windows1252ConversionTable[index];
+			break;
+		case kWindows1255:
+			unicodeString += g_windows1255ConversionTable[index];
+			break;
+		default:
+			break;
+		}
+	}
+	return unicodeString;
+}
+
 } // End of namespace Common
diff --git a/common/ustr.h b/common/ustr.h
index 5be3c8b6e7..57657c9025 100644
--- a/common/ustr.h
+++ b/common/ustr.h
@@ -195,6 +195,16 @@ private:
 
 U32String convertUtf8ToUtf32(const String &str);
 
+enum {
+	kAscii,
+	kWindows1250,
+	kWindows1251,
+	kWindows1252,
+	kWindows1255
+};
+
+U32String convertToU32String(const char *str, uint codePage = kAscii);
+
 } // End of namespace Common
 
 #endif