Expand description
§Murdoch-Charsets
murdoch-charsets provides API for name of character sets defined by Internet Assigned Numbers Authority (IANA).
In all settings, murdoch-charset provides CharacterSet traits and InvalidCharacterSetNameError.
§Default Setting
By default, murdoch-charsets provides types corresponding character sets defined by IANA,
and CharacterSetEnum to hold any of them.
§Custom Character-Sets
You can customize the character sets by using no_charset feature
[dependencies]
murdoch-charsets = { features = [ "no_charset" ] }then murdoch-charsets exports character_sets! macro.
character_sets!(
UnicodeCharacterSet,
UTF_8, // character-set type/variant name
None, // preferred_mime_name
"UTF-8", // name
["UTF8", "UTF_8",], // aliases
["UTF-8", "UTF8", "UTF_8",], // uppercase set of names (for FromStr)
UTF_16,
None,
"UTF-16",
["UTF16", "UTF_16",],
["UTF-16", "UTF16", "UTF_16",],
UTF_32,
None,
"UTF-32",
["UTF32", "UTF_32",],
["UTF-32", "UTF32", "UTF_32",],
);By calling the macro as above, the following types and implementations of traits (Debug,
Display, Copy, Clone, PartialEq, Eq, FromStr, AsRef<str>, AsRef<[u8]>) are generated.
pub struct UTF_8;
pub struct UTF_16;
pub struct UTF_32;
pub enum UnicodeCharacterSet
{
UTF_8,
UTF_16,
UTF_32,
}Structs§
- ADOBE_
STANDARD_ ENCODING - ADOBE_
SYMBOL_ ENCODING - AMIGA_
1251 - ANSI_
X3_ 110_ 1983 - ASMO_
449 - BIG5
- BIG5_
HKSCS - BOCU_1
- BRF
- BS_4730
- BS_
VIEWDATA - CESU_8
- CP50220
- CP51932
- CSA_
Z243_ 4_ 1985_ 1 - CSA_
Z243_ 4_ 1985_ 2 - CSA_
Z243_ 4_ 1985_ GR - CSN_
369103 - DEC_MCS
- DIN_
66003 - DK_US
- DS_2089
- EBCDIC_
AT_ DE - EBCDIC_
AT_ DE_ A - EBCDIC_
CA_ FR - EBCDIC_
DK_ NO - EBCDIC_
DK_ NO_ A - EBCDIC_
ES - EBCDIC_
ES_ A - EBCDIC_
ES_ S - EBCDIC_
FI_ SE - EBCDIC_
FI_ SE_ A - EBCDIC_
FR - EBCDIC_
IT - EBCDIC_
PT - EBCDIC_
UK - EBCDIC_
US - ECMA_
CYRILLIC - ES
- ES2
- EUC_KR
- EXTENDED_
UNIX_ CODE_ FIXED_ WIDTH_ FOR_ JAPANESE - EXTENDED_
UNIX_ CODE_ PACKED_ FORMAT_ FOR_ JAPANESE - GB2312
- GB18030
- GBK
- GB_
1988_ 80 - GB_
2312_ 80 - GOST_
19768_ 74 - GREEK7
- GREE
K7_ OLD - GREEK_
CCITT - HP_
DESKTOP - HP_
LEGAL - HP_
MATH8 - HP_
PI_ FONT - HP_
ROMA N8 - HZ_
GB_ 2312 - IBM00858
- IBM00924
- IBM01140
- IBM01141
- IBM01142
- IBM01143
- IBM01144
- IBM01145
- IBM01146
- IBM01147
- IBM01148
- IBM01149
- IBM037
- IBM038
- IBM273
- IBM274
- IBM275
- IBM277
- IBM278
- IBM280
- IBM281
- IBM284
- IBM285
- IBM290
- IBM297
- IBM420
- IBM423
- IBM424
- IBM437
- IBM500
- IBM775
- IBM850
- IBM851
- IBM852
- IBM855
- IBM857
- IBM860
- IBM861
- IBM862
- IBM863
- IBM864
- IBM865
- IBM866
- IBM868
- IBM869
- IBM870
- IBM871
- IBM880
- IBM891
- IBM903
- IBM904
- IBM905
- IBM918
- IBM1026
- IBM1047
- IBM_
SYMBOLS - IBM_
THAI - IEC_
P27_ 1 - INIS
- INIS_8
- INIS_
CYRILLIC - INVARIANT
- ISO_
646_ BASIC_ 1983 - ISO_
646_ IRV_ 1983 - ISO_
5427 - ISO_
2022_ CN - ISO_
2022_ CN_ EXT - ISO_
2022_ JP - ISO_
2022_ JP_ 2 - ISO_
2022_ KR - ISO_
2033_ 1983 - ISO_
5427_ 1981 - ISO_
5428_ 1980 - ISO_
6937_ 2_ 25 - ISO_
6937_ 2_ ADD - ISO_
8859_ 1_ 1987 - ISO_
8859_ 1_ WINDOWS_ 3_ 0_ LATIN_ 1 - ISO_
8859_ 1_ WINDOWS_ 3_ 1_ LATIN_ 1 - ISO_
8859_ 2_ 1987 - ISO_
8859_ 2_ WINDOWS_ LATIN_ 2 - ISO_
8859_ 3_ 1988 - ISO_
8859_ 4_ 1988 - ISO_
8859_ 5_ 1988 - ISO_
8859_ 6_ 1987 - ISO_
8859_ 6_ E - ISO_
8859_ 6_ I - ISO_
8859_ 7_ 1987 - ISO_
8859_ 8_ 1988 - ISO_
8859_ 8_ E - ISO_
8859_ 8_ I - ISO_
8859_ 9_ 1989 - ISO_
8859_ 9_ WINDOWS_ LATIN_ 5 - ISO_
8859_ 10 - ISO_
8859_ 13 - ISO_
8859_ 14 - ISO_
8859_ 15 - ISO_
8859_ 16 - ISO_
8859_ SUPP - ISO_
10367_ BOX - ISO_
10646_ J_ 1 - ISO_
10646_ UCS_ 2 - ISO_
10646_ UCS_ 4 - ISO_
10646_ UCS_ BASIC - ISO_
10646_ UNICODE_ LATI N1 - ISO_
10646_ UTF_ 1 - ISO_
11548_ 1 - ISO_
IR_ 90 - ISO_
UNICODE_ IBM_ 1261 - ISO_
UNICODE_ IBM_ 1264 - ISO_
UNICODE_ IBM_ 1265 - ISO_
UNICODE_ IBM_ 1268 - ISO_
UNICODE_ IBM_ 1276 - IT
- Invalid
Character SetName Error - JIS_
C6220_ 1969_ JP - JIS_
C6220_ 1969_ RO - JIS_
C6226_ 1978 - JIS_
C6226_ 1983 - JIS_
C6229_ 1984_ A - JIS_
C6229_ 1984_ B - JIS_
C6229_ 1984_ B_ ADD - JIS_
C6229_ 1984_ HAND - JIS_
C6229_ 1984_ HAND_ ADD - JIS_
C6229_ 1984_ KANA - JIS_
ENCODING - JIS_
X0201 - JIS_
X0212_ 1990 - JUS_
I_ B1_ 002 - JUS_
I_ B1_ 003_ MAC - JUS_
I_ B1_ 003_ SERB - KOI7_
SWITCHED - KOI8_R
- KOI8_U
- KSC5636
- KS_
C_ 5601_ 1987 - KZ_1048
- LATIN_
GREEK - LATIN_
GREEK_ 1 - LATIN_
LAP - MACINTOSH
- MICROSOFT_
PUBLISHING - MNEM
- MNEMONIC
- MSZ_
7795_ 3 - NATS_
DANO - NATS_
DANO_ ADD - NATS_
SEFI - NATS_
SEFI_ ADD - NC_
NC00_ 10_ 81 - NF_
Z_ 62_ 010 - NF_
Z_ 62_ 010_ 1973 - NS_
4551_ 1 - NS_
4551_ 2 - OSD_
EBCDIC_ DF03_ IRV - OSD_
EBCDIC_ DF04_ 1 - OSD_
EBCDIC_ DF04_ 15 - PC8_
DANISH_ NORWEGIAN - PC8_
TURKISH - PT
- PT2
- PTCP154
- SCSU
- SEN_
850200_ B - SEN_
850200_ C - SHIFT_
JIS - TIS_620
- TSCII
- T_
61_ 7BIT - T_
61_ 8BIT - T_
101_ G2 - UNICODE_
1_ 1 - UNICODE_
1_ 1_ UTF_ 7 - UNKNOWN_
8BIT - US_
ASCII - US_DK
- UTF_7
- UTF_8
- UTF_16
- UTF_32
- UTF_
16BE - UTF_
16LE - UTF_
32BE - UTF_
32LE - VENTURA_
INTERNATIONAL - VENTURA_
MATH - VENTURA_
US - VIDEOTEX_
SUPPL - VIQR
- VISCII
- WINDOWS_
31J - WINDOWS_
874 - WINDOWS_
1250 - WINDOWS_
1251 - WINDOWS_
1252 - WINDOWS_
1253 - WINDOWS_
1254 - WINDOWS_
1255 - WINDOWS_
1256 - WINDOWS_
1257 - WINDOWS_
1258