merge UTF-8 and UTF-16 encodings with or without BOM, with BOM automatically detected and handled
This commit is contained in:
@@ -33,58 +33,55 @@ var supportedFileTypeSeparators = map[string]rune{
|
||||
}
|
||||
|
||||
var supportedFileEncodings = map[string]encoding.Encoding{
|
||||
"utf-8": unicode.UTF8, // UTF-8
|
||||
"utf-8-bom": unicode.UTF8BOM, // UTF-8 with BOM
|
||||
"utf-16le": unicode.UTF16(unicode.LittleEndian, unicode.UseBOM), // UTF-16 Little Endian
|
||||
"utf-16be": unicode.UTF16(unicode.BigEndian, unicode.UseBOM), // UTF-16 Big Endian
|
||||
"utf-16le-bom": unicode.UTF16(unicode.LittleEndian, unicode.ExpectBOM), // UTF-16 Little Endian with BOM
|
||||
"utf-16be-bom": unicode.UTF16(unicode.BigEndian, unicode.ExpectBOM), // UTF-16 Big Endian with BOM
|
||||
"cp437": charmap.CodePage437, // OEM United States (CP-437)
|
||||
"cp863": charmap.CodePage863, // OEM Canadian French (CP-863)
|
||||
"cp037": charmap.CodePage037, // IBM EBCDIC US/Canada (CP-037)
|
||||
"cp1047": charmap.CodePage1047, // IBM EBCDIC Open Systems (CP-1047)
|
||||
"cp1140": charmap.CodePage1140, // IBM EBCDIC US/Canada with Euro (CP-1140)
|
||||
"iso-8859-1": charmap.ISO8859_1, // Western European (ISO-8859-1)
|
||||
"cp850": charmap.CodePage850, // Western European (CP-850)
|
||||
"cp858": charmap.CodePage858, // Western European with Euro (CP-858)
|
||||
"windows-1252": charmap.Windows1252, // Western European (Windows-1252)
|
||||
"iso-8859-15": charmap.ISO8859_15, // Western European (ISO-8859-15)
|
||||
"iso-8859-4": charmap.ISO8859_4, // North European (ISO-8859-4)
|
||||
"iso-8859-10": charmap.ISO8859_10, // North European (ISO-8859-10)
|
||||
"cp865": charmap.CodePage865, // North European (CP-865)
|
||||
"iso-8859-2": charmap.ISO8859_2, // Central European (ISO-8859-2)
|
||||
"cp852": charmap.CodePage852, // Central European (CP-852)
|
||||
"windows-1250": charmap.Windows1250, // Central European (Windows-1250)
|
||||
"iso-8859-14": charmap.ISO8859_14, // Celtic (ISO-8859-14)
|
||||
"iso-8859-3": charmap.ISO8859_3, // South European (ISO-8859-3)
|
||||
"cp860": charmap.CodePage860, // Portuguese (CP-860)
|
||||
"iso-8859-7": charmap.ISO8859_7, // Greek (ISO-8859-7)
|
||||
"windows-1253": charmap.Windows1253, // Greek (Windows-1253)
|
||||
"iso-8859-9": charmap.ISO8859_9, // Turkish (ISO-8859-9)
|
||||
"windows-1254": charmap.Windows1254, // Turkish (Windows-1254)
|
||||
"iso-8859-13": charmap.ISO8859_13, // Baltic (ISO-8859-13)
|
||||
"windows-1257": charmap.Windows1257, // Baltic (Windows-1257)
|
||||
"iso-8859-16": charmap.ISO8859_16, // South-Eastern European (ISO-8859-16)
|
||||
"iso-8859-5": charmap.ISO8859_5, // Cyrillic (ISO-8859-5)
|
||||
"cp855": charmap.CodePage855, // Cyrillic (CP-855)
|
||||
"cp866": charmap.CodePage866, // Cyrillic (CP-866)
|
||||
"windows-1251": charmap.Windows1251, // Cyrillic (Windows-1251)
|
||||
"koi8r": charmap.KOI8R, // Cyrillic (KOI8-R)
|
||||
"koi8u": charmap.KOI8U, // Cyrillic (KOI8-U)
|
||||
"iso-8859-6": charmap.ISO8859_6, // Arabic (ISO-8859-6)
|
||||
"windows-1256": charmap.Windows1256, // Arabic (Windows-1256)
|
||||
"iso-8859-8": charmap.ISO8859_8, // Hebrew (ISO-8859-8)
|
||||
"cp862": charmap.CodePage862, // Hebrew (CP-862)
|
||||
"windows-1255": charmap.Windows1255, // Hebrew (Windows-1255)
|
||||
"windows-874": charmap.Windows874, // Thai (Windows-874)
|
||||
"windows-1258": charmap.Windows1258, // Vietnamese (Windows-1258)
|
||||
"gb18030": simplifiedchinese.GB18030, // Chinese (Simplified, GB18030)
|
||||
"gbk": simplifiedchinese.GBK, // Chinese (Simplified, GBK)
|
||||
"big5": traditionalchinese.Big5, // Chinese (Traditional, Big5)
|
||||
"euc-kr": korean.EUCKR, // Korean (EUC-KR)
|
||||
"euc-jp": japanese.EUCJP, // Japanese (EUC-JP)
|
||||
"iso-2022-jp": japanese.ISO2022JP, // Japanese (ISO-2022-JP)
|
||||
"shift_jis": japanese.ShiftJIS, // Japanese (Shift JIS)
|
||||
"utf-8": unicode.UTF8BOM, // UTF-8
|
||||
"utf-16le": unicode.UTF16(unicode.LittleEndian, unicode.UseBOM), // UTF-16 Little Endian
|
||||
"utf-16be": unicode.UTF16(unicode.BigEndian, unicode.UseBOM), // UTF-16 Big Endian
|
||||
"cp437": charmap.CodePage437, // OEM United States (CP-437)
|
||||
"cp863": charmap.CodePage863, // OEM Canadian French (CP-863)
|
||||
"cp037": charmap.CodePage037, // IBM EBCDIC US/Canada (CP-037)
|
||||
"cp1047": charmap.CodePage1047, // IBM EBCDIC Open Systems (CP-1047)
|
||||
"cp1140": charmap.CodePage1140, // IBM EBCDIC US/Canada with Euro (CP-1140)
|
||||
"iso-8859-1": charmap.ISO8859_1, // Western European (ISO-8859-1)
|
||||
"cp850": charmap.CodePage850, // Western European (CP-850)
|
||||
"cp858": charmap.CodePage858, // Western European with Euro (CP-858)
|
||||
"windows-1252": charmap.Windows1252, // Western European (Windows-1252)
|
||||
"iso-8859-15": charmap.ISO8859_15, // Western European (ISO-8859-15)
|
||||
"iso-8859-4": charmap.ISO8859_4, // North European (ISO-8859-4)
|
||||
"iso-8859-10": charmap.ISO8859_10, // North European (ISO-8859-10)
|
||||
"cp865": charmap.CodePage865, // North European (CP-865)
|
||||
"iso-8859-2": charmap.ISO8859_2, // Central European (ISO-8859-2)
|
||||
"cp852": charmap.CodePage852, // Central European (CP-852)
|
||||
"windows-1250": charmap.Windows1250, // Central European (Windows-1250)
|
||||
"iso-8859-14": charmap.ISO8859_14, // Celtic (ISO-8859-14)
|
||||
"iso-8859-3": charmap.ISO8859_3, // South European (ISO-8859-3)
|
||||
"cp860": charmap.CodePage860, // Portuguese (CP-860)
|
||||
"iso-8859-7": charmap.ISO8859_7, // Greek (ISO-8859-7)
|
||||
"windows-1253": charmap.Windows1253, // Greek (Windows-1253)
|
||||
"iso-8859-9": charmap.ISO8859_9, // Turkish (ISO-8859-9)
|
||||
"windows-1254": charmap.Windows1254, // Turkish (Windows-1254)
|
||||
"iso-8859-13": charmap.ISO8859_13, // Baltic (ISO-8859-13)
|
||||
"windows-1257": charmap.Windows1257, // Baltic (Windows-1257)
|
||||
"iso-8859-16": charmap.ISO8859_16, // South-Eastern European (ISO-8859-16)
|
||||
"iso-8859-5": charmap.ISO8859_5, // Cyrillic (ISO-8859-5)
|
||||
"cp855": charmap.CodePage855, // Cyrillic (CP-855)
|
||||
"cp866": charmap.CodePage866, // Cyrillic (CP-866)
|
||||
"windows-1251": charmap.Windows1251, // Cyrillic (Windows-1251)
|
||||
"koi8r": charmap.KOI8R, // Cyrillic (KOI8-R)
|
||||
"koi8u": charmap.KOI8U, // Cyrillic (KOI8-U)
|
||||
"iso-8859-6": charmap.ISO8859_6, // Arabic (ISO-8859-6)
|
||||
"windows-1256": charmap.Windows1256, // Arabic (Windows-1256)
|
||||
"iso-8859-8": charmap.ISO8859_8, // Hebrew (ISO-8859-8)
|
||||
"cp862": charmap.CodePage862, // Hebrew (CP-862)
|
||||
"windows-1255": charmap.Windows1255, // Hebrew (Windows-1255)
|
||||
"windows-874": charmap.Windows874, // Thai (Windows-874)
|
||||
"windows-1258": charmap.Windows1258, // Vietnamese (Windows-1258)
|
||||
"gb18030": simplifiedchinese.GB18030, // Chinese (Simplified, GB18030)
|
||||
"gbk": simplifiedchinese.GBK, // Chinese (Simplified, GBK)
|
||||
"big5": traditionalchinese.Big5, // Chinese (Traditional, Big5)
|
||||
"euc-kr": korean.EUCKR, // Korean (EUC-KR)
|
||||
"euc-jp": japanese.EUCJP, // Japanese (EUC-JP)
|
||||
"iso-2022-jp": japanese.ISO2022JP, // Japanese (ISO-2022-JP)
|
||||
"shift_jis": japanese.ShiftJIS, // Japanese (Shift JIS)
|
||||
}
|
||||
|
||||
var customTransactionTypeNameMapping = map[models.TransactionType]string{
|
||||
|
||||
Reference in New Issue
Block a user