This module contains the Charset enum used by encoder and decoder.
Types
Charset = enum csUnknown, csUtf8 = "utf-8", csIbm866 = "ibm866", csIso8859_2 = "iso-8859-2", csIso8859_3 = "iso-8859-3", csIso8859_4 = "iso-8859-4", csIso8859_5 = "iso-8859-5", csIso8859_6 = "iso-8859-6", csIso8859_7 = "iso-8859-7", csIso8859_8 = "iso-8859-8", csIso8859_8i = "iso-8859-8-i", csIso8859_10 = "iso-8859-10", csIso8859_13 = "iso-8859-13", csIso8859_14 = "iso-8859-14", csIso8859_15 = "iso-8859-15", csIso8859_16 = "iso-8859-16", csKoi8r = "koi8-r", csKoi8u = "koi8-u", csMacintosh = "macintosh", csWindows874 = "windows-874", csWindows1250 = "windows-1250", csWindows1251 = "windows-1251", csWindows1252 = "windows-1252", csWindows1253 = "windows-1253", csWindows1254 = "windows-1254", csWindows1255 = "windows-1255", csWindows1256 = "windows-1256", csWindows1257 = "windows-1257", csWindows1258 = "windows-1258", csXMacCyrillic = "x-mac-cyrillic", csGbk = "gbk", csGb18030 = "gb18030", csBig5 = "Big5", csEucJP = "euc-jp", csIso2022JP = "iso-2022-jp", csShiftJIS = "shift_jis", csEucKR = "euc-kr", csReplacement = "replacement", csUtf16be = "utf-16be", csUtf16le = "utf-16le", csXUserDefined = "x-user-defined"
Consts
DefaultCharset = csUtf8
Procs
proc getCharset(s: string): Charset {....raises: [], tags: [], forbids: [].}
-
Return a Charset from the label s. This function is equivalent to the standard "get an encoding from a string label" algorithm:
https://encoding.spec.whatwg.org/#concept-encoding-get
On failure, csUnknown is returned.
proc getLocaleCharset(s: string): Charset {....raises: [], tags: [], forbids: [].}
- Extract a charset from a locale. e.g. returns EUC_JP for the string LC_ALL=ja_JP.EUC_JP.