From 04efb3a4a3995015ba739372336e5e4286b96413 Mon Sep 17 00:00:00 2001 From: ftrvxmtrx Date: Thu, 1 Jan 2015 11:20:23 +0100 Subject: tcs: update charsets. Fixes issue #214 --- sys/src/cmd/tcs/alias.txt | 2 +- sys/src/cmd/tcs/charsets.awk | 57 +- sys/src/cmd/tcs/charsets.txt | 1868 --------------------------- sys/src/cmd/tcs/charsets.xml | 2865 ++++++++++++++++++++++++++++++++++++++++++ sys/src/cmd/tcs/mkfile | 8 +- 5 files changed, 2897 insertions(+), 1903 deletions(-) delete mode 100644 sys/src/cmd/tcs/charsets.txt create mode 100644 sys/src/cmd/tcs/charsets.xml (limited to 'sys/src/cmd/tcs') diff --git a/sys/src/cmd/tcs/alias.txt b/sys/src/cmd/tcs/alias.txt index 8aa98345a..b3fa6ff03 100644 --- a/sys/src/cmd/tcs/alias.txt +++ b/sys/src/cmd/tcs/alias.txt @@ -9,7 +9,7 @@ iso_8859-8 8859-8 iso_8859-9 8859-9 iso_8859-10 8859-10 iso_8859-15 8859-15 -ascii ascii +us-ascii ascii atari av big5 big5 diff --git a/sys/src/cmd/tcs/charsets.awk b/sys/src/cmd/tcs/charsets.awk index e822f80e8..d6caefcd5 100755 --- a/sys/src/cmd/tcs/charsets.awk +++ b/sys/src/cmd/tcs/charsets.awk @@ -1,36 +1,33 @@ #!/bin/awk -f -# makes a table of character sets from http://www.iana.org/assignments/character-sets +# makes a table of character sets from http://www.iana.org/assignments/character-sets/character-sets.xml # and tcs.txt -BEGIN{ - if(ARGC != 3){ - print "Usage: " ARGV[0] " charsets.txt tcs.txt" - exit 1 - } - while(getline/, /<\/name>/ { + gsub(/[<>\/]+/, " ") + i = 0 + name = tolower($2) + names[name] = name + alias[name i] = name + nalias[name] = ++i + next } -{ - tcs = $1 - if(tcs in names){ - name = names[tcs] - for(i=0; i/, /<\/alias>/ { + gsub(/[<>\/]+/, " ") + a = tolower($2) + names[a] = name + alias[name i] = a + nalias[name] = ++i + next +} + +END { + while(getline 1999) is -intended for vendor specific coded character sets. - - Assigned MIB enum Numbers - ------------------------- - 0-2 Reserved - 3-999 Set By Standards Organizations - 1000-1999 Unicode / 10646 - 2000-2999 Vendor - -The aliases that start with "cs" have been added for use with the -IANA-CHARSET-MIB as originally defined in RFC3808, and as currently -maintained by IANA at http://www.iana.org/assignments/ianacharset-mib. -Note that the ianacharset-mib needs to be kept in sync with this -registry. These aliases that start with "cs" contain the standard -numbers along with suggestive names in order to facilitate applications -that want to display the names in user interfaces. The "cs" stands -for character set and is provided for applications that need a lower -case first letter but want to use mixed case thereafter that cannot -contain any special characters, such as underbar ("_") and dash ("-"). - -If the character set is from an ISO standard, its cs alias is the ISO -standard number or name. If the character set is not from an ISO -standard, but is registered with ISO (IPSJ/ITSCJ is the current ISO -Registration Authority), the ISO Registry number is specified as -ISOnnn followed by letters suggestive of the name or standards number -of the code set. When a national or international standard is -revised, the year of revision is added to the cs alias of the new -character set entry in the IANA Registry in order to distinguish the -revised character set from the original character set. - - -Character Set Reference -------------- --------- - -Name: ANSI_X3.4-1968 [RFC1345,KXS2] -MIBenum: 3 -Source: ECMA registry -Alias: iso-ir-6 -Alias: ANSI_X3.4-1986 -Alias: ISO_646.irv:1991 -Alias: ASCII -Alias: ISO646-US -Alias: US-ASCII (preferred MIME name) -Alias: us -Alias: IBM367 -Alias: cp367 -Alias: csASCII - -Name: ISO-10646-UTF-1 -MIBenum: 27 -Source: Universal Transfer Format (1), this is the multibyte - encoding, that subsets ASCII-7. It does not have byte - ordering issues. -Alias: csISO10646UTF1 - -Name: ISO_646.basic:1983 [RFC1345,KXS2] -MIBenum: 28 -Source: ECMA registry -Alias: ref -Alias: csISO646basic1983 - -Name: INVARIANT [RFC1345,KXS2] -MIBenum: 29 -Alias: csINVARIANT - -Name: ISO_646.irv:1983 [RFC1345,KXS2] -MIBenum: 30 -Source: ECMA registry -Alias: iso-ir-2 -Alias: irv -Alias: csISO2IntlRefVersion - -Name: BS_4730 [RFC1345,KXS2] -MIBenum: 20 -Source: ECMA registry -Alias: iso-ir-4 -Alias: ISO646-GB -Alias: gb -Alias: uk -Alias: csISO4UnitedKingdom - -Name: NATS-SEFI [RFC1345,KXS2] -MIBenum: 31 -Source: ECMA registry -Alias: iso-ir-8-1 -Alias: csNATSSEFI - -Name: NATS-SEFI-ADD [RFC1345,KXS2] -MIBenum: 32 -Source: ECMA registry -Alias: iso-ir-8-2 -Alias: csNATSSEFIADD - -Name: NATS-DANO [RFC1345,KXS2] -MIBenum: 33 -Source: ECMA registry -Alias: iso-ir-9-1 -Alias: csNATSDANO - -Name: NATS-DANO-ADD [RFC1345,KXS2] -MIBenum: 34 -Source: ECMA registry -Alias: iso-ir-9-2 -Alias: csNATSDANOADD - -Name: SEN_850200_B [RFC1345,KXS2] -MIBenum: 35 -Source: ECMA registry -Alias: iso-ir-10 -Alias: FI -Alias: ISO646-FI -Alias: ISO646-SE -Alias: se -Alias: csISO10Swedish - -Name: SEN_850200_C [RFC1345,KXS2] -MIBenum: 21 -Source: ECMA registry -Alias: iso-ir-11 -Alias: ISO646-SE2 -Alias: se2 -Alias: csISO11SwedishForNames - -Name: KS_C_5601-1987 [RFC1345,KXS2] -MIBenum: 36 -Source: ECMA registry -Alias: iso-ir-149 -Alias: KS_C_5601-1989 -Alias: KSC_5601 -Alias: korean -Alias: csKSC56011987 - -Name: ISO-2022-KR (preferred MIME name) [RFC1557,Choi] -MIBenum: 37 -Source: RFC-1557 (see also KS_C_5601-1987) -Alias: csISO2022KR - -Name: EUC-KR (preferred MIME name) [RFC1557,Choi] -MIBenum: 38 -Source: RFC-1557 (see also KS_C_5861-1992) -Alias: csEUCKR - -Name: ISO-2022-JP (preferred MIME name) [RFC1468,Murai] -MIBenum: 39 -Source: RFC-1468 (see also RFC-2237) -Alias: csISO2022JP - -Name: ISO-2022-JP-2 (preferred MIME name) [RFC1554,Ohta] -MIBenum: 40 -Source: RFC-1554 -Alias: csISO2022JP2 - -Name: ISO-2022-CN [RFC1922] -MIBenum: 104 -Source: RFC-1922 - -Name: ISO-2022-CN-EXT [RFC1922] -MIBenum: 105 -Source: RFC-1922 - -Name: JIS_C6220-1969-jp [RFC1345,KXS2] -MIBenum: 41 -Source: ECMA registry -Alias: JIS_C6220-1969 -Alias: iso-ir-13 -Alias: katakana -Alias: x0201-7 -Alias: csISO13JISC6220jp - -Name: JIS_C6220-1969-ro [RFC1345,KXS2] -MIBenum: 42 -Source: ECMA registry -Alias: iso-ir-14 -Alias: jp -Alias: ISO646-JP -Alias: csISO14JISC6220ro - -Name: IT [RFC1345,KXS2] -MIBenum: 22 -Source: ECMA registry -Alias: iso-ir-15 -Alias: ISO646-IT -Alias: csISO15Italian - -Name: PT [RFC1345,KXS2] -MIBenum: 43 -Source: ECMA registry -Alias: iso-ir-16 -Alias: ISO646-PT -Alias: csISO16Portuguese - -Name: ES [RFC1345,KXS2] -MIBenum: 23 -Source: ECMA registry -Alias: iso-ir-17 -Alias: ISO646-ES -Alias: csISO17Spanish - -Name: greek7-old [RFC1345,KXS2] -MIBenum: 44 -Source: ECMA registry -Alias: iso-ir-18 -Alias: csISO18Greek7Old - -Name: latin-greek [RFC1345,KXS2] -MIBenum: 45 -Source: ECMA registry -Alias: iso-ir-19 -Alias: csISO19LatinGreek - -Name: DIN_66003 [RFC1345,KXS2] -MIBenum: 24 -Source: ECMA registry -Alias: iso-ir-21 -Alias: de -Alias: ISO646-DE -Alias: csISO21German - -Name: NF_Z_62-010_(1973) [RFC1345,KXS2] -MIBenum: 46 -Source: ECMA registry -Alias: iso-ir-25 -Alias: ISO646-FR1 -Alias: csISO25French - -Name: Latin-greek-1 [RFC1345,KXS2] -MIBenum: 47 -Source: ECMA registry -Alias: iso-ir-27 -Alias: csISO27LatinGreek1 - -Name: ISO_5427 [RFC1345,KXS2] -MIBenum: 48 -Source: ECMA registry -Alias: iso-ir-37 -Alias: csISO5427Cyrillic - -Name: JIS_C6226-1978 [RFC1345,KXS2] -MIBenum: 49 -Source: ECMA registry -Alias: iso-ir-42 -Alias: csISO42JISC62261978 - -Name: BS_viewdata [RFC1345,KXS2] -MIBenum: 50 -Source: ECMA registry -Alias: iso-ir-47 -Alias: csISO47BSViewdata - -Name: INIS [RFC1345,KXS2] -MIBenum: 51 -Source: ECMA registry -Alias: iso-ir-49 -Alias: csISO49INIS - -Name: INIS-8 [RFC1345,KXS2] -MIBenum: 52 -Source: ECMA registry -Alias: iso-ir-50 -Alias: csISO50INIS8 - -Name: INIS-cyrillic [RFC1345,KXS2] -MIBenum: 53 -Source: ECMA registry -Alias: iso-ir-51 -Alias: csISO51INISCyrillic - -Name: ISO_5427:1981 [RFC1345,KXS2] -MIBenum: 54 -Source: ECMA registry -Alias: iso-ir-54 -Alias: ISO5427Cyrillic1981 - -Name: ISO_5428:1980 [RFC1345,KXS2] -MIBenum: 55 -Source: ECMA registry -Alias: iso-ir-55 -Alias: csISO5428Greek - -Name: GB_1988-80 [RFC1345,KXS2] -MIBenum: 56 -Source: ECMA registry -Alias: iso-ir-57 -Alias: cn -Alias: ISO646-CN -Alias: csISO57GB1988 - -Name: GB_2312-80 [RFC1345,KXS2] -MIBenum: 57 -Source: ECMA registry -Alias: iso-ir-58 -Alias: chinese -Alias: csISO58GB231280 - -Name: NS_4551-1 [RFC1345,KXS2] -MIBenum: 25 -Source: ECMA registry -Alias: iso-ir-60 -Alias: ISO646-NO -Alias: no -Alias: csISO60DanishNorwegian -Alias: csISO60Norwegian1 - -Name: NS_4551-2 [RFC1345,KXS2] -MIBenum: 58 -Source: ECMA registry -Alias: ISO646-NO2 -Alias: iso-ir-61 -Alias: no2 -Alias: csISO61Norwegian2 - -Name: NF_Z_62-010 [RFC1345,KXS2] -MIBenum: 26 -Source: ECMA registry -Alias: iso-ir-69 -Alias: ISO646-FR -Alias: fr -Alias: csISO69French - -Name: videotex-suppl [RFC1345,KXS2] -MIBenum: 59 -Source: ECMA registry -Alias: iso-ir-70 -Alias: csISO70VideotexSupp1 - -Name: PT2 [RFC1345,KXS2] -MIBenum: 60 -Source: ECMA registry -Alias: iso-ir-84 -Alias: ISO646-PT2 -Alias: csISO84Portuguese2 - -Name: ES2 [RFC1345,KXS2] -MIBenum: 61 -Source: ECMA registry -Alias: iso-ir-85 -Alias: ISO646-ES2 -Alias: csISO85Spanish2 - -Name: MSZ_7795.3 [RFC1345,KXS2] -MIBenum: 62 -Source: ECMA registry -Alias: iso-ir-86 -Alias: ISO646-HU -Alias: hu -Alias: csISO86Hungarian - -Name: JIS_C6226-1983 [RFC1345,KXS2] -MIBenum: 63 -Source: ECMA registry -Alias: iso-ir-87 -Alias: x0208 -Alias: JIS_X0208-1983 -Alias: csISO87JISX0208 - -Name: greek7 [RFC1345,KXS2] -MIBenum: 64 -Source: ECMA registry -Alias: iso-ir-88 -Alias: csISO88Greek7 - -Name: ASMO_449 [RFC1345,KXS2] -MIBenum: 65 -Source: ECMA registry -Alias: ISO_9036 -Alias: arabic7 -Alias: iso-ir-89 -Alias: csISO89ASMO449 - -Name: iso-ir-90 [RFC1345,KXS2] -MIBenum: 66 -Source: ECMA registry -Alias: csISO90 - -Name: JIS_C6229-1984-a [RFC1345,KXS2] -MIBenum: 67 -Source: ECMA registry -Alias: iso-ir-91 -Alias: jp-ocr-a -Alias: csISO91JISC62291984a - -Name: JIS_C6229-1984-b [RFC1345,KXS2] -MIBenum: 68 -Source: ECMA registry -Alias: iso-ir-92 -Alias: ISO646-JP-OCR-B -Alias: jp-ocr-b -Alias: csISO92JISC62991984b - -Name: JIS_C6229-1984-b-add [RFC1345,KXS2] -MIBenum: 69 -Source: ECMA registry -Alias: iso-ir-93 -Alias: jp-ocr-b-add -Alias: csISO93JIS62291984badd - -Name: JIS_C6229-1984-hand [RFC1345,KXS2] -MIBenum: 70 -Source: ECMA registry -Alias: iso-ir-94 -Alias: jp-ocr-hand -Alias: csISO94JIS62291984hand - -Name: JIS_C6229-1984-hand-add [RFC1345,KXS2] -MIBenum: 71 -Source: ECMA registry -Alias: iso-ir-95 -Alias: jp-ocr-hand-add -Alias: csISO95JIS62291984handadd - -Name: JIS_C6229-1984-kana [RFC1345,KXS2] -MIBenum: 72 -Source: ECMA registry -Alias: iso-ir-96 -Alias: csISO96JISC62291984kana - -Name: ISO_2033-1983 [RFC1345,KXS2] -MIBenum: 73 -Source: ECMA registry -Alias: iso-ir-98 -Alias: e13b -Alias: csISO2033 - -Name: ANSI_X3.110-1983 [RFC1345,KXS2] -MIBenum: 74 -Source: ECMA registry -Alias: iso-ir-99 -Alias: CSA_T500-1983 -Alias: NAPLPS -Alias: csISO99NAPLPS - -Name: ISO_8859-1:1987 [RFC1345,KXS2] -MIBenum: 4 -Source: ECMA registry -Alias: iso-ir-100 -Alias: ISO_8859-1 -Alias: ISO-8859-1 (preferred MIME name) -Alias: latin1 -Alias: l1 -Alias: IBM819 -Alias: CP819 -Alias: csISOLatin1 - -Name: ISO_8859-2:1987 [RFC1345,KXS2] -MIBenum: 5 -Source: ECMA registry -Alias: iso-ir-101 -Alias: ISO_8859-2 -Alias: ISO-8859-2 (preferred MIME name) -Alias: latin2 -Alias: l2 -Alias: csISOLatin2 - -Name: T.61-7bit [RFC1345,KXS2] -MIBenum: 75 -Source: ECMA registry -Alias: iso-ir-102 -Alias: csISO102T617bit - -Name: T.61-8bit [RFC1345,KXS2] -MIBenum: 76 -Alias: T.61 -Source: ECMA registry -Alias: iso-ir-103 -Alias: csISO103T618bit - -Name: ISO_8859-3:1988 [RFC1345,KXS2] -MIBenum: 6 -Source: ECMA registry -Alias: iso-ir-109 -Alias: ISO_8859-3 -Alias: ISO-8859-3 (preferred MIME name) -Alias: latin3 -Alias: l3 -Alias: csISOLatin3 - -Name: ISO_8859-4:1988 [RFC1345,KXS2] -MIBenum: 7 -Source: ECMA registry -Alias: iso-ir-110 -Alias: ISO_8859-4 -Alias: ISO-8859-4 (preferred MIME name) -Alias: latin4 -Alias: l4 -Alias: csISOLatin4 - -Name: ECMA-cyrillic -MIBenum: 77 -Source: ISO registry (formerly ECMA registry) - http://www.itscj.ipsj.jp/ISO-IR/111.pdf -Alias: iso-ir-111 -Alias: KOI8-E -Alias: csISO111ECMACyrillic - -Name: CSA_Z243.4-1985-1 [RFC1345,KXS2] -MIBenum: 78 -Source: ECMA registry -Alias: iso-ir-121 -Alias: ISO646-CA -Alias: csa7-1 -Alias: ca -Alias: csISO121Canadian1 - -Name: CSA_Z243.4-1985-2 [RFC1345,KXS2] -MIBenum: 79 -Source: ECMA registry -Alias: iso-ir-122 -Alias: ISO646-CA2 -Alias: csa7-2 -Alias: csISO122Canadian2 - -Name: CSA_Z243.4-1985-gr [RFC1345,KXS2] -MIBenum: 80 -Source: ECMA registry -Alias: iso-ir-123 -Alias: csISO123CSAZ24341985gr - -Name: ISO_8859-6:1987 [RFC1345,KXS2] -MIBenum: 9 -Source: ECMA registry -Alias: iso-ir-127 -Alias: ISO_8859-6 -Alias: ISO-8859-6 (preferred MIME name) -Alias: ECMA-114 -Alias: ASMO-708 -Alias: arabic -Alias: csISOLatinArabic - -Name: ISO_8859-6-E [RFC1556,IANA] -MIBenum: 81 -Source: RFC1556 -Alias: csISO88596E -Alias: ISO-8859-6-E (preferred MIME name) - -Name: ISO_8859-6-I [RFC1556,IANA] -MIBenum: 82 -Source: RFC1556 -Alias: csISO88596I -Alias: ISO-8859-6-I (preferred MIME name) - -Name: ISO_8859-7:1987 [RFC1947,RFC1345,KXS2] -MIBenum: 10 -Source: ECMA registry -Alias: iso-ir-126 -Alias: ISO_8859-7 -Alias: ISO-8859-7 (preferred MIME name) -Alias: ELOT_928 -Alias: ECMA-118 -Alias: greek -Alias: greek8 -Alias: csISOLatinGreek - -Name: T.101-G2 [RFC1345,KXS2] -MIBenum: 83 -Source: ECMA registry -Alias: iso-ir-128 -Alias: csISO128T101G2 - -Name: ISO_8859-8:1988 [RFC1345,KXS2] -MIBenum: 11 -Source: ECMA registry -Alias: iso-ir-138 -Alias: ISO_8859-8 -Alias: ISO-8859-8 (preferred MIME name) -Alias: hebrew -Alias: csISOLatinHebrew - -Name: ISO_8859-8-E [RFC1556,Nussbacher] -MIBenum: 84 -Source: RFC1556 -Alias: csISO88598E -Alias: ISO-8859-8-E (preferred MIME name) - -Name: ISO_8859-8-I [RFC1556,Nussbacher] -MIBenum: 85 -Source: RFC1556 -Alias: csISO88598I -Alias: ISO-8859-8-I (preferred MIME name) - -Name: CSN_369103 [RFC1345,KXS2] -MIBenum: 86 -Source: ECMA registry -Alias: iso-ir-139 -Alias: csISO139CSN369103 - -Name: JUS_I.B1.002 [RFC1345,KXS2] -MIBenum: 87 -Source: ECMA registry -Alias: iso-ir-141 -Alias: ISO646-YU -Alias: js -Alias: yu -Alias: csISO141JUSIB1002 - -Name: ISO_6937-2-add [RFC1345,KXS2] -MIBenum: 14 -Source: ECMA registry and ISO 6937-2:1983 -Alias: iso-ir-142 -Alias: csISOTextComm - -Name: IEC_P27-1 [RFC1345,KXS2] -MIBenum: 88 -Source: ECMA registry -Alias: iso-ir-143 -Alias: csISO143IECP271 - -Name: ISO_8859-5:1988 [RFC1345,KXS2] -MIBenum: 8 -Source: ECMA registry -Alias: iso-ir-144 -Alias: ISO_8859-5 -Alias: ISO-8859-5 (preferred MIME name) -Alias: cyrillic -Alias: csISOLatinCyrillic - -Name: JUS_I.B1.003-serb [RFC1345,KXS2] -MIBenum: 89 -Source: ECMA registry -Alias: iso-ir-146 -Alias: serbian -Alias: csISO146Serbian - -Name: JUS_I.B1.003-mac [RFC1345,KXS2] -MIBenum: 90 -Source: ECMA registry -Alias: macedonian -Alias: iso-ir-147 -Alias: csISO147Macedonian - -Name: ISO_8859-9:1989 [RFC1345,KXS2] -MIBenum: 12 -Source: ECMA registry -Alias: iso-ir-148 -Alias: ISO_8859-9 -Alias: ISO-8859-9 (preferred MIME name) -Alias: latin5 -Alias: l5 -Alias: csISOLatin5 - -Name: greek-ccitt [RFC1345,KXS2] -MIBenum: 91 -Source: ECMA registry -Alias: iso-ir-150 -Alias: csISO150 -Alias: csISO150GreekCCITT - -Name: NC_NC00-10:81 [RFC1345,KXS2] -MIBenum: 92 -Source: ECMA registry -Alias: cuba -Alias: iso-ir-151 -Alias: ISO646-CU -Alias: csISO151Cuba - -Name: ISO_6937-2-25 [RFC1345,KXS2] -MIBenum: 93 -Source: ECMA registry -Alias: iso-ir-152 -Alias: csISO6937Add - -Name: GOST_19768-74 [RFC1345,KXS2] -MIBenum: 94 -Source: ECMA registry -Alias: ST_SEV_358-88 -Alias: iso-ir-153 -Alias: csISO153GOST1976874 - -Name: ISO_8859-supp [RFC1345,KXS2] -MIBenum: 95 -Source: ECMA registry -Alias: iso-ir-154 -Alias: latin1-2-5 -Alias: csISO8859Supp - -Name: ISO_10367-box [RFC1345,KXS2] -MIBenum: 96 -Source: ECMA registry -Alias: iso-ir-155 -Alias: csISO10367Box - -Name: ISO-8859-10 (preferred MIME name) [RFC1345,KXS2] -MIBenum: 13 -Source: ECMA registry -Alias: iso-ir-157 -Alias: l6 -Alias: ISO_8859-10:1992 -Alias: csISOLatin6 -Alias: latin6 - -Name: latin-lap [RFC1345,KXS2] -MIBenum: 97 -Source: ECMA registry -Alias: lap -Alias: iso-ir-158 -Alias: csISO158Lap - -Name: JIS_X0212-1990 [RFC1345,KXS2] -MIBenum: 98 -Source: ECMA registry -Alias: x0212 -Alias: iso-ir-159 -Alias: csISO159JISX02121990 - -Name: DS_2089 [RFC1345,KXS2] -MIBenum: 99 -Source: Danish Standard, DS 2089, February 1974 -Alias: DS2089 -Alias: ISO646-DK -Alias: dk -Alias: csISO646Danish - -Name: us-dk [RFC1345,KXS2] -MIBenum: 100 -Alias: csUSDK - -Name: dk-us [RFC1345,KXS2] -MIBenum: 101 -Alias: csDKUS - -Name: JIS_X0201 [RFC1345,KXS2] -MIBenum: 15 -Source: JIS X 0201-1976. One byte only, this is equivalent to - JIS/Roman (similar to ASCII) plus eight-bit half-width - Katakana -Alias: X0201 -Alias: csHalfWidthKatakana - -Name: KSC5636 [RFC1345,KXS2] -MIBenum: 102 -Alias: ISO646-KR -Alias: csKSC5636 - -Name: ISO-10646-UCS-2 -MIBenum: 1000 -Source: the 2-octet Basic Multilingual Plane, aka Unicode - this needs to specify network byte order: the standard - does not specify (it is a 16-bit integer space) -Alias: csUnicode - -Name: ISO-10646-UCS-4 -MIBenum: 1001 -Source: the full code space. (same comment about byte order, - these are 31-bit numbers. -Alias: csUCS4 - -Name: DEC-MCS [RFC1345,KXS2] -MIBenum: 2008 -Source: VAX/VMS User's Manual, - Order Number: AI-Y517A-TE, April 1986. -Alias: dec -Alias: csDECMCS - -Name: hp-roman8 [HP-PCL5,RFC1345,KXS2] -MIBenum: 2004 -Source: LaserJet IIP Printer User's Manual, - HP part no 33471-90901, Hewlet-Packard, June 1989. -Alias: roman8 -Alias: r8 -Alias: csHPRoman8 - -Name: macintosh [RFC1345,KXS2] -MIBenum: 2027 -Source: The Unicode Standard ver1.0, ISBN 0-201-56788-1, Oct 1991 -Alias: mac -Alias: csMacintosh - -Name: IBM037 [RFC1345,KXS2] -MIBenum: 2028 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp037 -Alias: ebcdic-cp-us -Alias: ebcdic-cp-ca -Alias: ebcdic-cp-wt -Alias: ebcdic-cp-nl -Alias: csIBM037 - -Name: IBM038 [RFC1345,KXS2] -MIBenum: 2029 -Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990 -Alias: EBCDIC-INT -Alias: cp038 -Alias: csIBM038 - -Name: IBM273 [RFC1345,KXS2] -MIBenum: 2030 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: CP273 -Alias: csIBM273 - -Name: IBM274 [RFC1345,KXS2] -MIBenum: 2031 -Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990 -Alias: EBCDIC-BE -Alias: CP274 -Alias: csIBM274 - -Name: IBM275 [RFC1345,KXS2] -MIBenum: 2032 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: EBCDIC-BR -Alias: cp275 -Alias: csIBM275 - -Name: IBM277 [RFC1345,KXS2] -MIBenum: 2033 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: EBCDIC-CP-DK -Alias: EBCDIC-CP-NO -Alias: csIBM277 - -Name: IBM278 [RFC1345,KXS2] -MIBenum: 2034 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: CP278 -Alias: ebcdic-cp-fi -Alias: ebcdic-cp-se -Alias: csIBM278 - -Name: IBM280 [RFC1345,KXS2] -MIBenum: 2035 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: CP280 -Alias: ebcdic-cp-it -Alias: csIBM280 - -Name: IBM281 [RFC1345,KXS2] -MIBenum: 2036 -Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990 -Alias: EBCDIC-JP-E -Alias: cp281 -Alias: csIBM281 - -Name: IBM284 [RFC1345,KXS2] -MIBenum: 2037 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: CP284 -Alias: ebcdic-cp-es -Alias: csIBM284 - -Name: IBM285 [RFC1345,KXS2] -MIBenum: 2038 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: CP285 -Alias: ebcdic-cp-gb -Alias: csIBM285 - -Name: IBM290 [RFC1345,KXS2] -MIBenum: 2039 -Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990 -Alias: cp290 -Alias: EBCDIC-JP-kana -Alias: csIBM290 - -Name: IBM297 [RFC1345,KXS2] -MIBenum: 2040 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp297 -Alias: ebcdic-cp-fr -Alias: csIBM297 - -Name: IBM420 [RFC1345,KXS2] -MIBenum: 2041 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990, - IBM NLS RM p 11-11 -Alias: cp420 -Alias: ebcdic-cp-ar1 -Alias: csIBM420 - -Name: IBM423 [RFC1345,KXS2] -MIBenum: 2042 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp423 -Alias: ebcdic-cp-gr -Alias: csIBM423 - -Name: IBM424 [RFC1345,KXS2] -MIBenum: 2043 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp424 -Alias: ebcdic-cp-he -Alias: csIBM424 - -Name: IBM437 [RFC1345,KXS2] -MIBenum: 2011 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp437 -Alias: 437 -Alias: csPC8CodePage437 - -Name: IBM500 [RFC1345,KXS2] -MIBenum: 2044 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: CP500 -Alias: ebcdic-cp-be -Alias: ebcdic-cp-ch -Alias: csIBM500 - -Name: IBM775 [HP-PCL5] -MIBenum: 2087 -Source: HP PCL 5 Comparison Guide (P/N 5021-0329) pp B-13, 1996 -Alias: cp775 -Alias: csPC775Baltic - -Name: IBM850 [RFC1345,KXS2] -MIBenum: 2009 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp850 -Alias: 850 -Alias: csPC850Multilingual - -Name: IBM851 [RFC1345,KXS2] -MIBenum: 2045 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp851 -Alias: 851 -Alias: csIBM851 - -Name: IBM852 [RFC1345,KXS2] -MIBenum: 2010 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp852 -Alias: 852 -Alias: csPCp852 - -Name: IBM855 [RFC1345,KXS2] -MIBenum: 2046 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp855 -Alias: 855 -Alias: csIBM855 - -Name: IBM857 [RFC1345,KXS2] -MIBenum: 2047 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp857 -Alias: 857 -Alias: csIBM857 - -Name: IBM860 [RFC1345,KXS2] -MIBenum: 2048 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp860 -Alias: 860 -Alias: csIBM860 - -Name: IBM861 [RFC1345,KXS2] -MIBenum: 2049 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp861 -Alias: 861 -Alias: cp-is -Alias: csIBM861 - -Name: IBM862 [RFC1345,KXS2] -MIBenum: 2013 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp862 -Alias: 862 -Alias: csPC862LatinHebrew - -Name: IBM863 [RFC1345,KXS2] -MIBenum: 2050 -Source: IBM Keyboard layouts and code pages, PN 07G4586 June 1991 -Alias: cp863 -Alias: 863 -Alias: csIBM863 - -Name: IBM864 [RFC1345,KXS2] -MIBenum: 2051 -Source: IBM Keyboard layouts and code pages, PN 07G4586 June 1991 -Alias: cp864 -Alias: csIBM864 - -Name: IBM865 [RFC1345,KXS2] -MIBenum: 2052 -Source: IBM DOS 3.3 Ref (Abridged), 94X9575 (Feb 1987) -Alias: cp865 -Alias: 865 -Alias: csIBM865 - -Name: IBM866 [Pond] -MIBenum: 2086 -Source: IBM NLDG Volume 2 (SE09-8002-03) August 1994 -Alias: cp866 -Alias: 866 -Alias: csIBM866 - -Name: IBM868 [RFC1345,KXS2] -MIBenum: 2053 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: CP868 -Alias: cp-ar -Alias: csIBM868 - -Name: IBM869 [RFC1345,KXS2] -MIBenum: 2054 -Source: IBM Keyboard layouts and code pages, PN 07G4586 June 1991 -Alias: cp869 -Alias: 869 -Alias: cp-gr -Alias: csIBM869 - -Name: IBM870 [RFC1345,KXS2] -MIBenum: 2055 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: CP870 -Alias: ebcdic-cp-roece -Alias: ebcdic-cp-yu -Alias: csIBM870 - -Name: IBM871 [RFC1345,KXS2] -MIBenum: 2056 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: CP871 -Alias: ebcdic-cp-is -Alias: csIBM871 - -Name: IBM880 [RFC1345,KXS2] -MIBenum: 2057 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp880 -Alias: EBCDIC-Cyrillic -Alias: csIBM880 - -Name: IBM891 [RFC1345,KXS2] -MIBenum: 2058 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp891 -Alias: csIBM891 - -Name: IBM903 [RFC1345,KXS2] -MIBenum: 2059 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp903 -Alias: csIBM903 - -Name: IBM904 [RFC1345,KXS2] -MIBenum: 2060 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: cp904 -Alias: 904 -Alias: csIBBM904 - -Name: IBM905 [RFC1345,KXS2] -MIBenum: 2061 -Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990 -Alias: CP905 -Alias: ebcdic-cp-tr -Alias: csIBM905 - -Name: IBM918 [RFC1345,KXS2] -MIBenum: 2062 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: CP918 -Alias: ebcdic-cp-ar2 -Alias: csIBM918 - -Name: IBM1026 [RFC1345,KXS2] -MIBenum: 2063 -Source: IBM NLS RM Vol2 SE09-8002-01, March 1990 -Alias: CP1026 -Alias: csIBM1026 - -Name: EBCDIC-AT-DE [RFC1345,KXS2] -MIBenum: 2064 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csIBMEBCDICATDE - -Name: EBCDIC-AT-DE-A [RFC1345,KXS2] -MIBenum: 2065 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICATDEA - -Name: EBCDIC-CA-FR [RFC1345,KXS2] -MIBenum: 2066 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICCAFR - -Name: EBCDIC-DK-NO [RFC1345,KXS2] -MIBenum: 2067 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICDKNO - -Name: EBCDIC-DK-NO-A [RFC1345,KXS2] -MIBenum: 2068 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICDKNOA - -Name: EBCDIC-FI-SE [RFC1345,KXS2] -MIBenum: 2069 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICFISE - -Name: EBCDIC-FI-SE-A [RFC1345,KXS2] -MIBenum: 2070 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICFISEA - -Name: EBCDIC-FR [RFC1345,KXS2] -MIBenum: 2071 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICFR - -Name: EBCDIC-IT [RFC1345,KXS2] -MIBenum: 2072 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICIT - -Name: EBCDIC-PT [RFC1345,KXS2] -MIBenum: 2073 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICPT - -Name: EBCDIC-ES [RFC1345,KXS2] -MIBenum: 2074 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICES - -Name: EBCDIC-ES-A [RFC1345,KXS2] -MIBenum: 2075 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICESA - -Name: EBCDIC-ES-S [RFC1345,KXS2] -MIBenum: 2076 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICESS - -Name: EBCDIC-UK [RFC1345,KXS2] -MIBenum: 2077 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICUK - -Name: EBCDIC-US [RFC1345,KXS2] -MIBenum: 2078 -Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 -Alias: csEBCDICUS - -Name: UNKNOWN-8BIT [RFC1428] -MIBenum: 2079 -Alias: csUnknown8BiT - -Name: MNEMONIC [RFC1345,KXS2] -MIBenum: 2080 -Source: RFC 1345, also known as "mnemonic+ascii+38" -Alias: csMnemonic - -Name: MNEM [RFC1345,KXS2] -MIBenum: 2081 -Source: RFC 1345, also known as "mnemonic+ascii+8200" -Alias: csMnem - -Name: VISCII [RFC1456] -MIBenum: 2082 -Source: RFC 1456 -Alias: csVISCII - -Name: VIQR [RFC1456] -MIBenum: 2083 -Source: RFC 1456 -Alias: csVIQR - -Name: KOI8-R (preferred MIME name) [RFC1489] -MIBenum: 2084 -Source: RFC 1489, based on GOST-19768-74, ISO-6937/8, - INIS-Cyrillic, ISO-5427. -Alias: csKOI8R - -Name: KOI8-U [RFC2319] -MIBenum: 2088 -Source: RFC 2319 - -Name: IBM00858 -MIBenum: 2089 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM00858) [Mahdi] -Alias: CCSID00858 -Alias: CP00858 -Alias: PC-Multilingual-850+euro - -Name: IBM00924 -MIBenum: 2090 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM00924) [Mahdi] -Alias: CCSID00924 -Alias: CP00924 -Alias: ebcdic-Latin9--euro - -Name: IBM01140 -MIBenum: 2091 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01140) [Mahdi] -Alias: CCSID01140 -Alias: CP01140 -Alias: ebcdic-us-37+euro - -Name: IBM01141 -MIBenum: 2092 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01141) [Mahdi] -Alias: CCSID01141 -Alias: CP01141 -Alias: ebcdic-de-273+euro - -Name: IBM01142 -MIBenum: 2093 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01142) [Mahdi] -Alias: CCSID01142 -Alias: CP01142 -Alias: ebcdic-dk-277+euro -Alias: ebcdic-no-277+euro - -Name: IBM01143 -MIBenum: 2094 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01143) [Mahdi] -Alias: CCSID01143 -Alias: CP01143 -Alias: ebcdic-fi-278+euro -Alias: ebcdic-se-278+euro - -Name: IBM01144 -MIBenum: 2095 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01144) [Mahdi] -Alias: CCSID01144 -Alias: CP01144 -Alias: ebcdic-it-280+euro - -Name: IBM01145 -MIBenum: 2096 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01145) [Mahdi] -Alias: CCSID01145 -Alias: CP01145 -Alias: ebcdic-es-284+euro - -Name: IBM01146 -MIBenum: 2097 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01146) [Mahdi] -Alias: CCSID01146 -Alias: CP01146 -Alias: ebcdic-gb-285+euro - -Name: IBM01147 -MIBenum: 2098 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01147) [Mahdi] -Alias: CCSID01147 -Alias: CP01147 -Alias: ebcdic-fr-297+euro - -Name: IBM01148 -MIBenum: 2099 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01148) [Mahdi] -Alias: CCSID01148 -Alias: CP01148 -Alias: ebcdic-international-500+euro - -Name: IBM01149 -MIBenum: 2100 -Source: IBM See (http://www.iana.org/assignments/charset-reg/IBM01149) [Mahdi] -Alias: CCSID01149 -Alias: CP01149 -Alias: ebcdic-is-871+euro - -Name: Big5-HKSCS [Yick] -MIBenum: 2101 -Source: See (http://www.iana.org/assignments/charset-reg/Big5-HKSCS) -Alias: None - -Name: IBM1047 [Robrigado] -MIBenum: 2102 -Source: IBM1047 (EBCDIC Latin 1/Open Systems) -http://www-1.ibm.com/servers/eserver/iseries/software/globalization/pdf/cp01047z.pdf -Alias: IBM-1047 - -Name: PTCP154 [Uskov] -MIBenum: 2103 -Source: See (http://www.iana.org/assignments/charset-reg/PTCP154) -Alias: csPTCP154 -Alias: PT154 -Alias: CP154 -Alias: Cyrillic-Asian - -Name: Amiga-1251 -MIBenum: 2104 -Source: See (http://www.amiga.ultranet.ru/Amiga-1251.html) -Alias: Ami1251 -Alias: Amiga1251 -Alias: Ami-1251 -(Aliases are provided for historical reasons and should not be used) - [Malyshev] - -Name: KOI7-switched -MIBenum: 2105 -Source: See -Aliases: None - -Name: UNICODE-1-1 [RFC1641] -MIBenum: 1010 -Source: RFC 1641 -Alias: csUnicode11 - -Name: SCSU -MIBenum: 1011 -Source: SCSU See (http://www.iana.org/assignments/charset-reg/SCSU) [Scherer] -Alias: None - -Name: UTF-7 [RFC2152] -MIBenum: 1012 -Source: RFC 2152 -Alias: None - -Name: UTF-16BE [RFC2781] -MIBenum: 1013 -Source: RFC 2781 -Alias: None - -Name: UTF-16LE [RFC2781] -MIBenum: 1014 -Source: RFC 2781 -Alias: None - -Name: UTF-16 [RFC2781] -MIBenum: 1015 -Source: RFC 2781 -Alias: None - -Name: CESU-8 [Phipps] -MIBenum: 1016 -Source: -Alias: csCESU-8 - -Name: UTF-32 [Davis] -MIBenum: 1017 -Source: -Alias: None - -Name: UTF-32BE [Davis] -MIBenum: 1018 -Source: -Alias: None - -Name: UTF-32LE [Davis] -MIBenum: 1019 -Source: -Alias: None - -Name: BOCU-1 [Scherer] -MIBenum: 1020 -Source: http://www.unicode.org/notes/tn6/ -Alias: csBOCU-1 - -Name: UNICODE-1-1-UTF-7 [RFC1642] -MIBenum: 103 -Source: RFC 1642 -Alias: csUnicode11UTF7 - -Name: UTF-8 [RFC3629] -MIBenum: 106 -Source: RFC 3629 -Alias: None - -Name: ISO-8859-13 -MIBenum: 109 -Source: ISO See (http://www.iana.org/assignments/charset-reg/iso-8859-13)[Tumasonis] -Alias: None - -Name: ISO-8859-14 -MIBenum: 110 -Source: ISO See (http://www.iana.org/assignments/charset-reg/iso-8859-14) [Simonsen] -Alias: iso-ir-199 -Alias: ISO_8859-14:1998 -Alias: ISO_8859-14 -Alias: latin8 -Alias: iso-celtic -Alias: l8 - -Name: ISO-8859-15 -MIBenum: 111 -Source: ISO - Please see: -Alias: ISO_8859-15 -Alias: Latin-9 - -Name: ISO-8859-16 -MIBenum: 112 -Source: ISO -Alias: iso-ir-226 -Alias: ISO_8859-16:2001 -Alias: ISO_8859-16 -Alias: latin10 -Alias: l10 - -Name: GBK -MIBenum: 113 -Source: Chinese IT Standardization Technical Committee - Please see: -Alias: CP936 -Alias: MS936 -Alias: windows-936 - -Name: GB18030 -MIBenum: 114 -Source: Chinese IT Standardization Technical Committee - Please see: -Alias: None - -Name: OSD_EBCDIC_DF04_15 -MIBenum: 115 -Source: Fujitsu-Siemens standard mainframe EBCDIC encoding - Please see: -Alias: None - -Name: OSD_EBCDIC_DF03_IRV -MIBenum: 116 -Source: Fujitsu-Siemens standard mainframe EBCDIC encoding - Please see: -Alias: None - -Name: OSD_EBCDIC_DF04_1 -MIBenum: 117 -Source: Fujitsu-Siemens standard mainframe EBCDIC encoding - Please see: -Alias: None - -Name: JIS_Encoding -MIBenum: 16 -Source: JIS X 0202-1991. Uses ISO 2022 escape sequences to - shift code sets as documented in JIS X 0202-1991. -Alias: csJISEncoding - -Name: Shift_JIS (preferred MIME name) -MIBenum: 17 -Source: This charset is an extension of csHalfWidthKatakana by - adding graphic characters in JIS X 0208. The CCS's are - JIS X0201:1997 and JIS X0208:1997. The - complete definition is shown in Appendix 1 of JIS - X0208:1997. - This charset can be used for the top-level media type "text". -Alias: MS_Kanji -Alias: csShiftJIS - -Name: Extended_UNIX_Code_Packed_Format_for_Japanese -MIBenum: 18 -Source: Standardized by OSF, UNIX International, and UNIX Systems - Laboratories Pacific. Uses ISO 2022 rules to select - code set 0: US-ASCII (a single 7-bit byte set) - code set 1: JIS X0208-1990 (a double 8-bit byte set) - restricted to A0-FF in both bytes - code set 2: Half Width Katakana (a single 7-bit byte set) - requiring SS2 as the character prefix - code set 3: JIS X0212-1990 (a double 7-bit byte set) - restricted to A0-FF in both bytes - requiring SS3 as the character prefix -Alias: csEUCPkdFmtJapanese -Alias: EUC-JP (preferred MIME name) - -Name: Extended_UNIX_Code_Fixed_Width_for_Japanese -MIBenum: 19 -Source: Used in Japan. Each character is 2 octets. - code set 0: US-ASCII (a single 7-bit byte set) - 1st byte = 00 - 2nd byte = 20-7E - code set 1: JIS X0208-1990 (a double 7-bit byte set) - restricted to A0-FF in both bytes - code set 2: Half Width Katakana (a single 7-bit byte set) - 1st byte = 00 - 2nd byte = A0-FF - code set 3: JIS X0212-1990 (a double 7-bit byte set) - restricted to A0-FF in - the first byte - and 21-7E in the second byte -Alias: csEUCFixWidJapanese - -Name: ISO-10646-UCS-Basic -MIBenum: 1002 -Source: ASCII subset of Unicode. Basic Latin = collection 1 - See ISO 10646, Appendix A -Alias: csUnicodeASCII - -Name: ISO-10646-Unicode-Latin1 -MIBenum: 1003 -Source: ISO Latin-1 subset of Unicode. Basic Latin and Latin-1 - Supplement = collections 1 and 2. See ISO 10646, - Appendix A. See RFC 1815. -Alias: csUnicodeLatin1 -Alias: ISO-10646 - -Name: ISO-10646-J-1 -Source: ISO 10646 Japanese, see RFC 1815. - -Name: ISO-Unicode-IBM-1261 -MIBenum: 1005 -Source: IBM Latin-2, -3, -5, Extended Presentation Set, GCSGID: 1261 -Alias: csUnicodeIBM1261 - -Name: ISO-Unicode-IBM-1268 -MIBenum: 1006 -Source: IBM Latin-4 Extended Presentation Set, GCSGID: 1268 -Alias: csUnicodeIBM1268 - -Name: ISO-Unicode-IBM-1276 -MIBenum: 1007 -Source: IBM Cyrillic Greek Extended Presentation Set, GCSGID: 1276 -Alias: csUnicodeIBM1276 - -Name: ISO-Unicode-IBM-1264 -MIBenum: 1008 -Source: IBM Arabic Presentation Set, GCSGID: 1264 -Alias: csUnicodeIBM1264 - -Name: ISO-Unicode-IBM-1265 -MIBenum: 1009 -Source: IBM Hebrew Presentation Set, GCSGID: 1265 -Alias: csUnicodeIBM1265 - -Name: ISO-8859-1-Windows-3.0-Latin-1 [HP-PCL5] -MIBenum: 2000 -Source: Extended ISO 8859-1 Latin-1 for Windows 3.0. - PCL Symbol Set id: 9U -Alias: csWindows30Latin1 - -Name: ISO-8859-1-Windows-3.1-Latin-1 [HP-PCL5] -MIBenum: 2001 -Source: Extended ISO 8859-1 Latin-1 for Windows 3.1. - PCL Symbol Set id: 19U -Alias: csWindows31Latin1 - -Name: ISO-8859-2-Windows-Latin-2 [HP-PCL5] -MIBenum: 2002 -Source: Extended ISO 8859-2. Latin-2 for Windows 3.1. - PCL Symbol Set id: 9E -Alias: csWindows31Latin2 - -Name: ISO-8859-9-Windows-Latin-5 [HP-PCL5] -MIBenum: 2003 -Source: Extended ISO 8859-9. Latin-5 for Windows 3.1 - PCL Symbol Set id: 5T -Alias: csWindows31Latin5 - -Name: Adobe-Standard-Encoding [Adobe] -MIBenum: 2005 -Source: PostScript Language Reference Manual - PCL Symbol Set id: 10J -Alias: csAdobeStandardEncoding - -Name: Ventura-US [HP-PCL5] -MIBenum: 2006 -Source: Ventura US. ASCII plus characters typically used in - publishing, like pilcrow, copyright, registered, trade mark, - section, dagger, and double dagger in the range A0 (hex) - to FF (hex). - PCL Symbol Set id: 14J -Alias: csVenturaUS - -Name: Ventura-International [HP-PCL5] -MIBenum: 2007 -Source: Ventura International. ASCII plus coded characters similar - to Roman8. - PCL Symbol Set id: 13J -Alias: csVenturaInternational - -Name: PC8-Danish-Norwegian [HP-PCL5] -MIBenum: 2012 -Source: PC Danish Norwegian - 8-bit PC set for Danish Norwegian - PCL Symbol Set id: 11U -Alias: csPC8DanishNorwegian - -Name: PC8-Turkish [HP-PCL5] -MIBenum: 2014 -Source: PC Latin Turkish. PCL Symbol Set id: 9T -Alias: csPC8Turkish - -Name: IBM-Symbols [IBM-CIDT] -MIBenum: 2015 -Source: Presentation Set, CPGID: 259 -Alias: csIBMSymbols - -Name: IBM-Thai [IBM-CIDT] -MIBenum: 2016 -Source: Presentation Set, CPGID: 838 -Alias: csIBMThai - -Name: HP-Legal [HP-PCL5] -MIBenum: 2017 -Source: PCL 5 Comparison Guide, Hewlett-Packard, - HP part number 5961-0510, October 1992 - PCL Symbol Set id: 1U -Alias: csHPLegal - -Name: HP-Pi-font [HP-PCL5] -MIBenum: 2018 -Source: PCL 5 Comparison Guide, Hewlett-Packard, - HP part number 5961-0510, October 1992 - PCL Symbol Set id: 15U -Alias: csHPPiFont - -Name: HP-Math8 [HP-PCL5] -MIBenum: 2019 -Source: PCL 5 Comparison Guide, Hewlett-Packard, - HP part number 5961-0510, October 1992 - PCL Symbol Set id: 8M -Alias: csHPMath8 - -Name: Adobe-Symbol-Encoding [Adobe] -MIBenum: 2020 -Source: PostScript Language Reference Manual - PCL Symbol Set id: 5M -Alias: csHPPSMath - -Name: HP-DeskTop [HP-PCL5] -MIBenum: 2021 -Source: PCL 5 Comparison Guide, Hewlett-Packard, - HP part number 5961-0510, October 1992 - PCL Symbol Set id: 7J -Alias: csHPDesktop - -Name: Ventura-Math [HP-PCL5] -MIBenum: 2022 -Source: PCL 5 Comparison Guide, Hewlett-Packard, - HP part number 5961-0510, October 1992 - PCL Symbol Set id: 6M -Alias: csVenturaMath - -Name: Microsoft-Publishing [HP-PCL5] -MIBenum: 2023 -Source: PCL 5 Comparison Guide, Hewlett-Packard, - HP part number 5961-0510, October 1992 - PCL Symbol Set id: 6J -Alias: csMicrosoftPublishing - -Name: Windows-31J -MIBenum: 2024 -Source: Windows Japanese. A further extension of Shift_JIS - to include NEC special characters (Row 13), NEC - selection of IBM extensions (Rows 89 to 92), and IBM - extensions (Rows 115 to 119). The CCS's are - JIS X0201:1997, JIS X0208:1997, and these extensions. - This charset can be used for the top-level media type "text", - but it is of limited or specialized use (see RFC2278). - PCL Symbol Set id: 19K -Alias: csWindows31J - -Name: GB2312 (preferred MIME name) -MIBenum: 2025 -Source: Chinese for People's Republic of China (PRC) mixed one byte, - two byte set: - 20-7E = one byte ASCII - A1-FE = two byte PRC Kanji - See GB 2312-80 - PCL Symbol Set Id: 18C -Alias: csGB2312 - -Name: Big5 (preferred MIME name) -MIBenum: 2026 -Source: Chinese for Taiwan Multi-byte set. - PCL Symbol Set Id: 18T -Alias: csBig5 - -Name: windows-1250 -MIBenum: 2250 -Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1250) [Lazhintseva] -Alias: None - -Name: windows-1251 -MIBenum: 2251 -Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1251) [Lazhintseva] -Alias: None - -Name: windows-1252 -MIBenum: 2252 -Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1252) [Wendt] -Alias: None - -Name: windows-1253 -MIBenum: 2253 -Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1253) [Lazhintseva] -Alias: None - -Name: windows-1254 -MIBenum: 2254 -Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1254) [Lazhintseva] -Alias: None - -Name: windows-1255 -MIBenum: 2255 -Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1255) [Lazhintseva] -Alias: None - -Name: windows-1256 -MIBenum: 2256 -Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1256) [Lazhintseva] -Alias: None - -Name: windows-1257 -MIBenum: 2257 -Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1257) [Lazhintseva] -Alias: None - -Name: windows-1258 -MIBenum: 2258 -Source: Microsoft (http://www.iana.org/assignments/charset-reg/windows-1258) [Lazhintseva] -Alias: None - -Name: TIS-620 -MIBenum: 2259 -Source: Thai Industrial Standards Institute (TISI) [Tantsetthi] - -Name: HZ-GB-2312 -MIBenum: 2085 -Source: RFC 1842, RFC 1843 [RFC1842, RFC1843] - - -REFERENCES ----------- - -[RFC1345] Simonsen, K., "Character Mnemonics & Character Sets", - RFC 1345, Rationel Almen Planlaegning, Rationel Almen - Planlaegning, June 1992. - -[RFC1428] Vaudreuil, G., "Transition of Internet Mail from - Just-Send-8 to 8bit-SMTP/MIME", RFC1428, CNRI, February - 1993. - -[RFC1456] Vietnamese Standardization Working Group, "Conventions for - Encoding the Vietnamese Language VISCII: VIetnamese - Standard Code for Information Interchange VIQR: VIetnamese - Quoted-Readable Specification Revision 1.1", RFC 1456, May - 1993. - -[RFC1468] Murai, J., Crispin, M., and E. van der Poel, "Japanese - Character Encoding for Internet Messages", RFC 1468, - Keio University, Panda Programming, June 1993. - -[RFC1489] Chernov, A., "Registration of a Cyrillic Character Set", - RFC1489, RELCOM Development Team, July 1993. - -[RFC1554] Ohta, M., and K. Handa, "ISO-2022-JP-2: Multilingual - Extension of ISO-2022-JP", RFC1554, Tokyo Institute of - Technology, ETL, December 1993. - -[RFC1556] Nussbacher, H., "Handling of Bi-directional Texts in MIME", - RFC1556, Israeli Inter-University, December 1993. - -[RFC1557] Choi, U., Chon, K., and H. Park, "Korean Character Encoding - for Internet Messages", KAIST, Solvit Chosun Media, - December 1993. - -[RFC1641] Goldsmith, D., and M. Davis, "Using Unicode with MIME", - RFC1641, Taligent, Inc., July 1994. - -[RFC1642] Goldsmith, D., and M. Davis, "UTF-7", RFC1642, Taligent, - Inc., July 1994. - -[RFC1815] Ohta, M., "Character Sets ISO-10646 and ISO-10646-J-1", - RFC 1815, Tokyo Institute of Technology, July 1995. - - -[Adobe] Adobe Systems Incorporated, PostScript Language Reference - Manual, second edition, Addison-Wesley Publishing Company, - Inc., 1990. - -[ECMA Registry] ISO-IR: International Register of Escape Sequences - http://www.itscj.ipsj.or.jp/ISO-IE/ Note: The current - registration authority is IPSJ/ITSCJ, Japan. - -[HP-PCL5] Hewlett-Packard Company, "HP PCL 5 Comparison Guide", - (P/N 5021-0329) pp B-13, 1996. - -[IBM-CIDT] IBM Corporation, "ABOUT TYPE: IBM's Technical Reference - for Core Interchange Digitized Type", Publication number - S544-3708-01 - -[RFC1842] Wei, Y., J. Li, and Y. Jiang, "ASCII Printable - Characters-Based Chinese Character Encoding for Internet - Messages", RFC 1842, Harvard University, Rice University, - University of Maryland, August 1995. - -[RFC1843] Lee, F., "HZ - A Data Format for Exchanging Files of - Arbitrarily Mixed Chinese and ASCII Characters", RFC 1843, - Stanford University, August 1995. - -[RFC2152] Goldsmith, D., M. Davis, "UTF-7: A Mail-Safe Transformation - Format of Unicode", RFC 2152, Apple Computer, Inc., - Taligent Inc., May 1997. - -[RFC2279] Yergeau, F., "UTF-8, A Transformation Format of ISO 10646", - RFC 2279, Alis Technologies, January, 1998. - -[RFC2781] Hoffman, P., Yergeau, F., "UTF-16, an encoding of ISO 10646", - RFC 2781, February 2000. - -[RFC3629] Yergeau, F., "UTF-8, a transformation format of ISO 10646", - RFC3629, November 2003. - -PEOPLE ------- - -[KXS2] Keld Simonsen - -[Choi] Woohyong Choi - -[Davis] Mark Davis, , April 2002. - -[Lazhintseva] Katya Lazhintseva, , May 1996. - -[Mahdi] Tamer Mahdi, , August 2000. - -[Malyshev] Michael Malyshev, , January 2004 - -[Murai] Jun Murai - -[Nussbacher] Hank Nussbacher, - -[Ohta] Masataka Ohta, , July 1995. - -[Phipps] Toby Phipps, , March 2002. - -[Pond] Rick Pond, , March 1997. - -[Robrigado] Reuel Robrigado, , September 2002. - -[Scherer] Markus Scherer, , August 2000, - September 2002. - -[Simonsen] Keld Simonsen, , August 2000. - -[Tantsetthi] Trin Tantsetthi, , September 1998. - -[Tumasonis] Vladas Tumasonis, , August 2000. - -[Uskov] Alexander Uskov, , September 2002. - -[Wendt] Chris Wendt, , December 1999. - -[Yick] Nicky Yick, , October 2000. - -[] - - - - - - - diff --git a/sys/src/cmd/tcs/charsets.xml b/sys/src/cmd/tcs/charsets.xml new file mode 100644 index 000000000..ccd52f0a7 --- /dev/null +++ b/sys/src/cmd/tcs/charsets.xml @@ -0,0 +1,2865 @@ + + + + + 2013-12-20 + Character Sets + Character Sets + + Expert Review + Primary Expert Ned Freed and Secondary Expert Martin Dürst + These are the official names for character sets that may be used in +the Internet and may be referred to in Internet documentation. These +names are expressed in ANSI_X3.4-1968 which is commonly called +US-ASCII or simply ASCII. The character set most commonly use in the +Internet and used especially in protocol standards is US-ASCII, this +is strongly encouraged. The use of the name US-ASCII is also +encouraged. + +The character set names may be up to 40 characters taken from the +printable characters of US-ASCII. However, no distinction is made +between use of upper and lower case letters. + +The MIBenum value is a unique value for use in MIBs to identify coded +character sets. + +The value space for MIBenum values has been divided into three +regions. The first region (3-999) consists of coded character sets +that have been standardized by some standard setting organization. +This region is intended for standards that do not have subset +implementations. The second region (1000-1999) is for the Unicode and +ISO/IEC 10646 coded character sets together with a specification of a +(set of) sub-repertoires that may occur. The third region (>1999) is +intended for vendor specific coded character sets. + + Assigned MIB enum Numbers + ------------------------- + 0-2 Reserved + 3-999 Set By Standards Organizations + 1000-1999 Unicode / 10646 + 2000-2999 Vendor + +The aliases that start with "cs" have been added for use with the +IANA-CHARSET-MIB as originally defined in , and as currently +maintained by IANA at . +Note that the ianacharset-mib needs to be kept in sync with this +registry. These aliases that start with "cs" contain the standard +numbers along with suggestive names in order to facilitate applications +that want to display the names in user interfaces. The "cs" stands +for character set and is provided for applications that need a lower +case first letter but want to use mixed case thereafter that cannot +contain any special characters, such as underbar ("_") and dash ("-"). + +If the character set is from an ISO standard, its cs alias is the ISO +standard number or name. If the character set is not from an ISO +standard, but is registered with ISO (IPSJ/ITSCJ is the current ISO +Registration Authority), the ISO Registry number is specified as +ISOnnn followed by letters suggestive of the name or standards number +of the code set. When a national or international standard is +revised, the year of revision is added to the cs alias of the new +character set entry in the IANA Registry in order to distinguish the +revised character set from the original character set. + + + US-ASCII + + 3 + ANSI X3.4-1986 + iso-ir-6 + ANSI_X3.4-1968 + ANSI_X3.4-1986 + ISO_646.irv:1991 + ISO646-US + US-ASCII + us + IBM367 + cp367 + csASCII + US-ASCII + + + ISO_8859-1:1987 + + + 4 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-100 + ISO_8859-1 + ISO-8859-1 + latin1 + l1 + IBM819 + CP819 + csISOLatin1 + ISO-8859-1 +
+ + ISO_8859-2:1987 + + + 5 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-101 + ISO_8859-2 + ISO-8859-2 + latin2 + l2 + csISOLatin2 + ISO-8859-2 +
+ + ISO_8859-3:1988 + + + 6 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-109 + ISO_8859-3 + ISO-8859-3 + latin3 + l3 + csISOLatin3 + ISO-8859-3 +
+ + ISO_8859-4:1988 + + + 7 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-110 + ISO_8859-4 + ISO-8859-4 + latin4 + l4 + csISOLatin4 + ISO-8859-4 +
+ + ISO_8859-5:1988 + + + 8 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-144 + ISO_8859-5 + ISO-8859-5 + cyrillic + csISOLatinCyrillic + ISO-8859-5 +
+ + ISO_8859-6:1987 + + + 9 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-127 + ISO_8859-6 + ISO-8859-6 + ECMA-114 + ASMO-708 + arabic + csISOLatinArabic + ISO-8859-6 +
+ + ISO_8859-7:1987 + + + + 10 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-126 + ISO_8859-7 + ISO-8859-7 + ELOT_928 + ECMA-118 + greek + greek8 + csISOLatinGreek + ISO-8859-7 +
+ + ISO_8859-8:1988 + + + 11 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-138 + ISO_8859-8 + ISO-8859-8 + hebrew + csISOLatinHebrew + ISO-8859-8 +
+ + ISO_8859-9:1989 + + + 12 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-148 + ISO_8859-9 + ISO-8859-9 + latin5 + l5 + csISOLatin5 + ISO-8859-9 +
+ + ISO-8859-10 + + + 13 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-157 + l6 + ISO_8859-10:1992 + csISOLatin6 + latin6 + ISO-8859-10 +
+ + ISO_6937-2-add + + + 14 + + ISO-IR: International Register of Escape Sequences and ISO 6937-2:1983
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-142 + csISOTextComm +
+ + JIS_X0201 + + + 15 + JIS X 0201-1976. One byte only, this is equivalent to +JIS/Roman (similar to ASCII) plus eight-bit half-width +Katakana + X0201 + csHalfWidthKatakana + + + JIS_Encoding + 16 + JIS X 0202-1991. Uses ISO 2022 escape sequences to +shift code sets as documented in JIS X 0202-1991. + csJISEncoding + + + Shift_JIS + 17 + This charset is an extension of csHalfWidthKatakana by +adding graphic characters in JIS X 0208. The CCS's are +JIS X0201:1997 and JIS X0208:1997. The +complete definition is shown in Appendix 1 of JIS +X0208:1997. +This charset can be used for the top-level media type "text". + MS_Kanji + csShiftJIS + Shift_JIS + + + Extended_UNIX_Code_Packed_Format_for_Japanese + 18 + Standardized by OSF, UNIX International, and UNIX Systems +Laboratories Pacific. Uses ISO 2022 rules to select +code set 0: US-ASCII (a single 7-bit byte set) +code set 1: JIS X0208-1990 (a double 8-bit byte set) +restricted to A0-FF in both bytes +code set 2: Half Width Katakana (a single 7-bit byte set) +requiring SS2 as the character prefix +code set 3: JIS X0212-1990 (a double 7-bit byte set) +restricted to A0-FF in both bytes +requiring SS3 as the character prefix + csEUCPkdFmtJapanese + EUC-JP + EUC-JP + + + Extended_UNIX_Code_Fixed_Width_for_Japanese + 19 + Used in Japan. Each character is 2 octets. +code set 0: US-ASCII (a single 7-bit byte set) +1st byte = 00 +2nd byte = 20-7E +code set 1: JIS X0208-1990 (a double 7-bit byte set) +restricted to A0-FF in both bytes +code set 2: Half Width Katakana (a single 7-bit byte set) +1st byte = 00 +2nd byte = A0-FF +code set 3: JIS X0212-1990 (a double 7-bit byte set) +restricted to A0-FF in +the first byte +and 21-7E in the second byte + csEUCFixWidJapanese + + + BS_4730 + + + 20 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-4 + ISO646-GB + gb + uk + csISO4UnitedKingdom +
+ + SEN_850200_C + + + 21 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-11 + ISO646-SE2 + se2 + csISO11SwedishForNames +
+ + IT + + + 22 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-15 + ISO646-IT + csISO15Italian +
+ + ES + + + 23 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-17 + ISO646-ES + csISO17Spanish +
+ + DIN_66003 + + + 24 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-21 + de + ISO646-DE + csISO21German +
+ + NS_4551-1 + + + 25 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-60 + ISO646-NO + no + csISO60DanishNorwegian + csISO60Norwegian1 +
+ + NF_Z_62-010 + + + 26 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-69 + ISO646-FR + fr + csISO69French +
+ + ISO-10646-UTF-1 + 27 + Universal Transfer Format (1), this is the multibyte +encoding, that subsets ASCII-7. It does not have byte +ordering issues. + csISO10646UTF1 + + + ISO_646.basic:1983 + + + 28 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ ref + csISO646basic1983 +
+ + INVARIANT + + + 29 + csINVARIANT + + + ISO_646.irv:1983 + + + 30 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-2 + irv + csISO2IntlRefVersion +
+ + NATS-SEFI + + + 31 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-8-1 + csNATSSEFI +
+ + NATS-SEFI-ADD + + + 32 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-8-2 + csNATSSEFIADD +
+ + NATS-DANO + + + 33 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-9-1 + csNATSDANO +
+ + NATS-DANO-ADD + + + 34 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-9-2 + csNATSDANOADD +
+ + SEN_850200_B + + + 35 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-10 + FI + ISO646-FI + ISO646-SE + se + csISO10Swedish +
+ + KS_C_5601-1987 + + + 36 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-149 + KS_C_5601-1989 + KSC_5601 + korean + csKSC56011987 +
+ + ISO-2022-KR + + + 37 + (see also KS_C_5601-1987) + csISO2022KR + ISO-2022-KR + + + EUC-KR + + + 38 + (see also KS_C_5861-1992) + csEUCKR + EUC-KR + + + ISO-2022-JP + + + 39 + (see also ) + csISO2022JP + ISO-2022-JP + + + ISO-2022-JP-2 + + + 40 + + + + csISO2022JP2 + ISO-2022-JP-2 + + + JIS_C6220-1969-jp + + + 41 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ JIS_C6220-1969 + iso-ir-13 + katakana + x0201-7 + csISO13JISC6220jp +
+ + JIS_C6220-1969-ro + + + 42 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-14 + jp + ISO646-JP + csISO14JISC6220ro +
+ + PT + + + 43 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-16 + ISO646-PT + csISO16Portuguese +
+ + greek7-old + + + 44 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-18 + csISO18Greek7Old +
+ + latin-greek + + + 45 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-19 + csISO19LatinGreek +
+ + NF_Z_62-010_(1973) + + + 46 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-25 + ISO646-FR1 + csISO25French +
+ + Latin-greek-1 + + + 47 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-27 + csISO27LatinGreek1 +
+ + ISO_5427 + + + 48 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-37 + csISO5427Cyrillic +
+ + JIS_C6226-1978 + + + 49 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-42 + csISO42JISC62261978 +
+ + BS_viewdata + + + 50 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-47 + csISO47BSViewdata +
+ + INIS + + + 51 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-49 + csISO49INIS +
+ + INIS-8 + + + 52 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-50 + csISO50INIS8 +
+ + INIS-cyrillic + + + 53 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-51 + csISO51INISCyrillic +
+ + ISO_5427:1981 + + + 54 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-54 + ISO5427Cyrillic1981 + csISO54271981 +
+ + ISO_5428:1980 + + + 55 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-55 + csISO5428Greek +
+ + GB_1988-80 + + + 56 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-57 + cn + ISO646-CN + csISO57GB1988 +
+ + GB_2312-80 + + + 57 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-58 + chinese + csISO58GB231280 +
+ + NS_4551-2 + + + 58 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ ISO646-NO2 + iso-ir-61 + no2 + csISO61Norwegian2 +
+ + videotex-suppl + + + 59 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-70 + csISO70VideotexSupp1 +
+ + PT2 + + + 60 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-84 + ISO646-PT2 + csISO84Portuguese2 +
+ + ES2 + + + 61 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-85 + ISO646-ES2 + csISO85Spanish2 +
+ + MSZ_7795.3 + + + 62 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-86 + ISO646-HU + hu + csISO86Hungarian +
+ + JIS_C6226-1983 + + + 63 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-87 + x0208 + JIS_X0208-1983 + csISO87JISX0208 +
+ + greek7 + + + 64 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-88 + csISO88Greek7 +
+ + ASMO_449 + + + 65 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ ISO_9036 + arabic7 + iso-ir-89 + csISO89ASMO449 +
+ + iso-ir-90 + + + 66 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ csISO90 +
+ + JIS_C6229-1984-a + + + 67 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-91 + jp-ocr-a + csISO91JISC62291984a +
+ + JIS_C6229-1984-b + + + 68 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-92 + ISO646-JP-OCR-B + jp-ocr-b + csISO92JISC62991984b +
+ + JIS_C6229-1984-b-add + + + 69 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-93 + jp-ocr-b-add + csISO93JIS62291984badd +
+ + JIS_C6229-1984-hand + + + 70 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-94 + jp-ocr-hand + csISO94JIS62291984hand +
+ + JIS_C6229-1984-hand-add + + + 71 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-95 + jp-ocr-hand-add + csISO95JIS62291984handadd +
+ + JIS_C6229-1984-kana + + + 72 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-96 + csISO96JISC62291984kana +
+ + ISO_2033-1983 + + + 73 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-98 + e13b + csISO2033 +
+ + ANSI_X3.110-1983 + + + 74 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-99 + CSA_T500-1983 + NAPLPS + csISO99NAPLPS +
+ + T.61-7bit + + + 75 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-102 + csISO102T617bit +
+ + T.61-8bit + + + 76 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ T.61 + iso-ir-103 + csISO103T618bit +
+ + ECMA-cyrillic + 77 + ISO registry + (formerly ECMA + registry) + iso-ir-111 + KOI8-E + csISO111ECMACyrillic + + + CSA_Z243.4-1985-1 + + + 78 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-121 + ISO646-CA + csa7-1 + csa71 + ca + csISO121Canadian1 +
+ + CSA_Z243.4-1985-2 + + + 79 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-122 + ISO646-CA2 + csa7-2 + csa72 + csISO122Canadian2 +
+ + CSA_Z243.4-1985-gr + + + 80 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-123 + csISO123CSAZ24341985gr +
+ + ISO_8859-6-E + + + 81 + + + + csISO88596E + ISO-8859-6-E + ISO-8859-6-E + + + ISO_8859-6-I + + + 82 + + + + csISO88596I + ISO-8859-6-I + ISO-8859-6-I + + + T.101-G2 + + + 83 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-128 + csISO128T101G2 +
+ + ISO_8859-8-E + + + 84 + + + + csISO88598E + ISO-8859-8-E + ISO-8859-8-E + + + ISO_8859-8-I + + + 85 + + + + csISO88598I + ISO-8859-8-I + ISO-8859-8-I + + + CSN_369103 + + + 86 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-139 + csISO139CSN369103 +
+ + JUS_I.B1.002 + + + 87 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-141 + ISO646-YU + js + yu + csISO141JUSIB1002 +
+ + IEC_P27-1 + + + 88 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-143 + csISO143IECP271 +
+ + JUS_I.B1.003-serb + + + 89 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-146 + serbian + csISO146Serbian +
+ + JUS_I.B1.003-mac + + + 90 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ macedonian + iso-ir-147 + csISO147Macedonian +
+ + greek-ccitt + + + 91 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-150 + csISO150 + csISO150GreekCCITT +
+ + NC_NC00-10:81 + + + 92 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ cuba + iso-ir-151 + ISO646-CU + csISO151Cuba +
+ + ISO_6937-2-25 + + + 93 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-152 + csISO6937Add +
+ + GOST_19768-74 + + + 94 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ ST_SEV_358-88 + iso-ir-153 + csISO153GOST1976874 +
+ + ISO_8859-supp + + + 95 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-154 + latin1-2-5 + csISO8859Supp +
+ + ISO_10367-box + + + 96 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ iso-ir-155 + csISO10367Box +
+ + latin-lap + + + 97 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ lap + iso-ir-158 + csISO158Lap +
+ + JIS_X0212-1990 + + + 98 + + ISO-IR: International Register of Escape Sequences
+ Note: The current registration authority is IPSJ/ITSCJ, Japan. +
+ x0212 + iso-ir-159 + csISO159JISX02121990 +
+ + DS_2089 + + + 99 + Danish Standard, DS 2089, February 1974 + DS2089 + ISO646-DK + dk + csISO646Danish + + + us-dk + + + 100 + csUSDK + + + dk-us + + + 101 + csDKUS + + + KSC5636 + + + 102 + ISO646-KR + csKSC5636 + + + UNICODE-1-1-UTF-7 + + 103 + + + + csUnicode11UTF7 + + + ISO-2022-CN + + 104 + + + + csISO2022CN + + + ISO-2022-CN-EXT + + 105 + + + + csISO2022CNEXT + + + UTF-8 + + 106 + + + + csUTF8 + + + ISO-8859-13 + 109 + ISO See + csISO885913 + + + ISO-8859-14 + 110 + ISO See + iso-ir-199 + ISO_8859-14:1998 + ISO_8859-14 + latin8 + iso-celtic + l8 + csISO885914 + + + ISO-8859-15 + 111 + ISO +Please see: + ISO_8859-15 + Latin-9 + csISO885915 + + + ISO-8859-16 + 112 + ISO + iso-ir-226 + ISO_8859-16:2001 + ISO_8859-16 + latin10 + l10 + csISO885916 + + + GBK + 113 + Chinese IT Standardization Technical Committee +Please see: + CP936 + MS936 + windows-936 + csGBK + + + GB18030 + 114 + Chinese IT Standardization Technical Committee +Please see: + csGB18030 + + + OSD_EBCDIC_DF04_15 + 115 + Fujitsu-Siemens standard mainframe EBCDIC encoding +Please see: + csOSDEBCDICDF0415 + + + OSD_EBCDIC_DF03_IRV + 116 + Fujitsu-Siemens standard mainframe EBCDIC encoding +Please see: + csOSDEBCDICDF03IRV + + + OSD_EBCDIC_DF04_1 + 117 + Fujitsu-Siemens standard mainframe EBCDIC encoding +Please see: + csOSDEBCDICDF041 + + + ISO-11548-1 + 118 + See + ISO_11548-1 + ISO_TR_11548-1 + csISO115481 + + + KZ-1048 + 119 + See + STRK1048-2002 + RK1048 + csKZ1048 + + + ISO-10646-UCS-2 + 1000 + the 2-octet Basic Multilingual Plane, aka Unicode +this needs to specify network byte order: the standard +does not specify (it is a 16-bit integer space) + csUnicode + + + ISO-10646-UCS-4 + 1001 + the full code space. (same comment about byte order, +these are 31-bit numbers. + csUCS4 + + + ISO-10646-UCS-Basic + 1002 + ASCII subset of Unicode. Basic Latin = collection 1 +See ISO 10646, Appendix A + csUnicodeASCII + + + ISO-10646-Unicode-Latin1 + 1003 + ISO Latin-1 subset of Unicode. Basic Latin and Latin-1 +Supplement = collections 1 and 2. See ISO 10646, +Appendix A. See . + csUnicodeLatin1 + ISO-10646 + + + ISO-10646-J-1 + 1004 + ISO 10646 Japanese, see . + csUnicodeJapanese + + + ISO-Unicode-IBM-1261 + 1005 + IBM Latin-2, -3, -5, Extended Presentation Set, GCSGID: 1261 + csUnicodeIBM1261 + + + ISO-Unicode-IBM-1268 + 1006 + IBM Latin-4 Extended Presentation Set, GCSGID: 1268 + csUnicodeIBM1268 + + + ISO-Unicode-IBM-1276 + 1007 + IBM Cyrillic Greek Extended Presentation Set, GCSGID: 1276 + csUnicodeIBM1276 + + + ISO-Unicode-IBM-1264 + 1008 + IBM Arabic Presentation Set, GCSGID: 1264 + csUnicodeIBM1264 + + + ISO-Unicode-IBM-1265 + 1009 + IBM Hebrew Presentation Set, GCSGID: 1265 + csUnicodeIBM1265 + + + UNICODE-1-1 + + 1010 + + + + csUnicode11 + + + SCSU + 1011 + SCSU See + csSCSU + + + UTF-7 + + 1012 + + + + csUTF7 + + + UTF-16BE + + 1013 + + + + csUTF16BE + + + UTF-16LE + + 1014 + + + + csUTF16LE + + + UTF-16 + + 1015 + + + + csUTF16 + + + CESU-8 + + 1016 + + + + csCESU8 + csCESU-8 + + + UTF-32 + + 1017 + + + + csUTF32 + + + UTF-32BE + + 1018 + + + + csUTF32BE + + + UTF-32LE + + 1019 + + + + csUTF32LE + + + BOCU-1 + + 1020 + + + + csBOCU1 + csBOCU-1 + + + ISO-8859-1-Windows-3.0-Latin-1 + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2000 + Extended ISO 8859-1 Latin-1 for Windows 3.0. +PCL Symbol Set id: 9U + csWindows30Latin1 + + + ISO-8859-1-Windows-3.1-Latin-1 + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2001 + Extended ISO 8859-1 Latin-1 for Windows 3.1. +PCL Symbol Set id: 19U + csWindows31Latin1 + + + ISO-8859-2-Windows-Latin-2 + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2002 + Extended ISO 8859-2. Latin-2 for Windows 3.1. +PCL Symbol Set id: 9E + csWindows31Latin2 + + + ISO-8859-9-Windows-Latin-5 + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2003 + Extended ISO 8859-9. Latin-5 for Windows 3.1 +PCL Symbol Set id: 5T + csWindows31Latin5 + + + hp-roman8 + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + + + 2004 + LaserJet IIP Printer User's Manual, +HP part no 33471-90901, Hewlet-Packard, June 1989. + roman8 + r8 + csHPRoman8 + + + Adobe-Standard-Encoding + Adobe Systems Incorporated, PostScript Language Reference +Manual, second edition, Addison-Wesley Publishing Company, +Inc., 1990. + 2005 + PostScript Language Reference Manual +PCL Symbol Set id: 10J + csAdobeStandardEncoding + + + Ventura-US + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2006 + Ventura US. ASCII plus characters typically used in +publishing, like pilcrow, copyright, registered, trade mark, +section, dagger, and double dagger in the range A0 (hex) +to FF (hex). +PCL Symbol Set id: 14J + csVenturaUS + + + Ventura-International + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2007 + Ventura International. ASCII plus coded characters similar +to Roman8. +PCL Symbol Set id: 13J + csVenturaInternational + + + DEC-MCS + + + 2008 + VAX/VMS User's Manual, +Order Number: AI-Y517A-TE, April 1986. + dec + csDECMCS + + + IBM850 + + + 2009 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp850 + 850 + csPC850Multilingual + + + PC8-Danish-Norwegian + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2012 + PC Danish Norwegian +8-bit PC set for Danish Norwegian +PCL Symbol Set id: 11U + csPC8DanishNorwegian + + + IBM862 + + + 2013 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp862 + 862 + csPC862LatinHebrew + + + PC8-Turkish + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2014 + PC Latin Turkish. PCL Symbol Set id: 9T + csPC8Turkish + + + IBM-Symbols + IBM Corporation, "ABOUT TYPE: IBM's Technical Reference +for Core Interchange Digitized Type", Publication number +S544-3708-01 + 2015 + Presentation Set, CPGID: 259 + csIBMSymbols + + + IBM-Thai + IBM Corporation, "ABOUT TYPE: IBM's Technical Reference +for Core Interchange Digitized Type", Publication number +S544-3708-01 + 2016 + Presentation Set, CPGID: 838 + csIBMThai + + + HP-Legal + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2017 + PCL 5 Comparison Guide, Hewlett-Packard, +HP part number 5961-0510, October 1992 +PCL Symbol Set id: 1U + csHPLegal + + + HP-Pi-font + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2018 + PCL 5 Comparison Guide, Hewlett-Packard, +HP part number 5961-0510, October 1992 +PCL Symbol Set id: 15U + csHPPiFont + + + HP-Math8 + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2019 + PCL 5 Comparison Guide, Hewlett-Packard, +HP part number 5961-0510, October 1992 +PCL Symbol Set id: 8M + csHPMath8 + + + Adobe-Symbol-Encoding + Adobe Systems Incorporated, PostScript Language Reference +Manual, second edition, Addison-Wesley Publishing Company, +Inc., 1990. + 2020 + PostScript Language Reference Manual +PCL Symbol Set id: 5M + csHPPSMath + + + HP-DeskTop + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2021 + PCL 5 Comparison Guide, Hewlett-Packard, +HP part number 5961-0510, October 1992 +PCL Symbol Set id: 7J + csHPDesktop + + + Ventura-Math + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2022 + PCL 5 Comparison Guide, Hewlett-Packard, +HP part number 5961-0510, October 1992 +PCL Symbol Set id: 6M + csVenturaMath + + + Microsoft-Publishing + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2023 + PCL 5 Comparison Guide, Hewlett-Packard, +HP part number 5961-0510, October 1992 +PCL Symbol Set id: 6J + csMicrosoftPublishing + + + Windows-31J + 2024 + Windows Japanese. A further extension of Shift_JIS +to include NEC special characters (Row 13), NEC +selection of IBM extensions (Rows 89 to 92), and IBM +extensions (Rows 115 to 119). The CCS's are +JIS X0201:1997, JIS X0208:1997, and these extensions. +This charset can be used for the top-level media type "text", +but it is of limited or specialized use (see ). +PCL Symbol Set id: 19K + csWindows31J + + + GB2312 + 2025 + Chinese for People's Republic of China (PRC) mixed one byte, +two byte set: +20-7E = one byte ASCII +A1-FE = two byte PRC Kanji +See GB 2312-80 +PCL Symbol Set Id: 18C + csGB2312 + GB2312 + + + Big5 + 2026 + Chinese for Taiwan Multi-byte set. +PCL Symbol Set Id: 18T + csBig5 + Big5 + + + macintosh + + + 2027 + The Unicode Standard ver1.0, ISBN 0-201-56788-1, Oct 1991 + mac + csMacintosh + + + IBM037 + + + 2028 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp037 + ebcdic-cp-us + ebcdic-cp-ca + ebcdic-cp-wt + ebcdic-cp-nl + csIBM037 + + + IBM038 + + + 2029 + IBM 3174 Character Set Ref, GA27-3831-02, March 1990 + EBCDIC-INT + cp038 + csIBM038 + + + IBM273 + + + 2030 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + CP273 + csIBM273 + + + IBM274 + + + 2031 + IBM 3174 Character Set Ref, GA27-3831-02, March 1990 + EBCDIC-BE + CP274 + csIBM274 + + + IBM275 + + + 2032 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + EBCDIC-BR + cp275 + csIBM275 + + + IBM277 + + + 2033 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + EBCDIC-CP-DK + EBCDIC-CP-NO + csIBM277 + + + IBM278 + + + 2034 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + CP278 + ebcdic-cp-fi + ebcdic-cp-se + csIBM278 + + + IBM280 + + + 2035 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + CP280 + ebcdic-cp-it + csIBM280 + + + IBM281 + + + 2036 + IBM 3174 Character Set Ref, GA27-3831-02, March 1990 + EBCDIC-JP-E + cp281 + csIBM281 + + + IBM284 + + + 2037 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + CP284 + ebcdic-cp-es + csIBM284 + + + IBM285 + + + 2038 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + CP285 + ebcdic-cp-gb + csIBM285 + + + IBM290 + + + 2039 + IBM 3174 Character Set Ref, GA27-3831-02, March 1990 + cp290 + EBCDIC-JP-kana + csIBM290 + + + IBM297 + + + 2040 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp297 + ebcdic-cp-fr + csIBM297 + + + IBM420 + + + 2041 + IBM NLS RM Vol2 SE09-8002-01, March 1990, +IBM NLS RM p 11-11 + cp420 + ebcdic-cp-ar1 + csIBM420 + + + IBM423 + + + 2042 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp423 + ebcdic-cp-gr + csIBM423 + + + IBM424 + + + 2043 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp424 + ebcdic-cp-he + csIBM424 + + + IBM437 + + + 2011 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp437 + 437 + csPC8CodePage437 + + + IBM500 + + + 2044 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + CP500 + ebcdic-cp-be + ebcdic-cp-ch + csIBM500 + + + IBM851 + + + 2045 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp851 + 851 + csIBM851 + + + IBM852 + + + 2010 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp852 + 852 + csPCp852 + + + IBM855 + + + 2046 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp855 + 855 + csIBM855 + + + IBM857 + + + 2047 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp857 + 857 + csIBM857 + + + IBM860 + + + 2048 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp860 + 860 + csIBM860 + + + IBM861 + + + 2049 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp861 + 861 + cp-is + csIBM861 + + + IBM863 + + + 2050 + IBM Keyboard layouts and code pages, PN 07G4586 June 1991 + cp863 + 863 + csIBM863 + + + IBM864 + + + 2051 + IBM Keyboard layouts and code pages, PN 07G4586 June 1991 + cp864 + csIBM864 + + + IBM865 + + + 2052 + IBM DOS 3.3 Ref (Abridged), 94X9575 (Feb 1987) + cp865 + 865 + csIBM865 + + + IBM868 + + + 2053 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + CP868 + cp-ar + csIBM868 + + + IBM869 + + + 2054 + IBM Keyboard layouts and code pages, PN 07G4586 June 1991 + cp869 + 869 + cp-gr + csIBM869 + + + IBM870 + + + 2055 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + CP870 + ebcdic-cp-roece + ebcdic-cp-yu + csIBM870 + + + IBM871 + + + 2056 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + CP871 + ebcdic-cp-is + csIBM871 + + + IBM880 + + + 2057 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp880 + EBCDIC-Cyrillic + csIBM880 + + + IBM891 + + + 2058 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp891 + csIBM891 + + + IBM903 + + + 2059 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp903 + csIBM903 + + + IBM904 + + + 2060 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + cp904 + 904 + csIBBM904 + + + IBM905 + + + 2061 + IBM 3174 Character Set Ref, GA27-3831-02, March 1990 + CP905 + ebcdic-cp-tr + csIBM905 + + + IBM918 + + + 2062 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + CP918 + ebcdic-cp-ar2 + csIBM918 + + + IBM1026 + + + 2063 + IBM NLS RM Vol2 SE09-8002-01, March 1990 + CP1026 + csIBM1026 + + + EBCDIC-AT-DE + + + 2064 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csIBMEBCDICATDE + + + EBCDIC-AT-DE-A + + + 2065 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICATDEA + + + EBCDIC-CA-FR + + + 2066 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICCAFR + + + EBCDIC-DK-NO + + + 2067 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICDKNO + + + EBCDIC-DK-NO-A + + + 2068 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICDKNOA + + + EBCDIC-FI-SE + + + 2069 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICFISE + + + EBCDIC-FI-SE-A + + + 2070 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICFISEA + + + EBCDIC-FR + + + 2071 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICFR + + + EBCDIC-IT + + + 2072 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICIT + + + EBCDIC-PT + + + 2073 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICPT + + + EBCDIC-ES + + + 2074 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICES + + + EBCDIC-ES-A + + + 2075 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICESA + + + EBCDIC-ES-S + + + 2076 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICESS + + + EBCDIC-UK + + + 2077 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICUK + + + EBCDIC-US + + + 2078 + IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987 + csEBCDICUS + + + UNKNOWN-8BIT + + 2079 + csUnknown8BiT + + + MNEMONIC + + + 2080 + , also known as "mnemonic+ascii+38" + csMnemonic + + + MNEM + + + 2081 + , also known as "mnemonic+ascii+8200" + csMnem + + + VISCII + + 2082 + + + + csVISCII + + + VIQR + + 2083 + + + + csVIQR + + + KOI8-R + + 2084 + , based on GOST-19768-74, ISO-6937/8, +INIS-Cyrillic, ISO-5427. + csKOI8R + KOI8-R + + + HZ-GB-2312 + 2085 + , + + + IBM866 + + 2086 + IBM NLDG Volume 2 (SE09-8002-03) August 1994 + cp866 + 866 + csIBM866 + + + IBM775 + Hewlett-Packard Company, "HP PCL 5 Comparison Guide", +(P/N 5021-0329) pp B-13, 1996. + 2087 + HP PCL 5 Comparison Guide (P/N 5021-0329) pp B-13, 1996 + cp775 + csPC775Baltic + + + KOI8-U + + 2088 + + + + csKOI8U + + + IBM00858 + 2089 + IBM See + CCSID00858 + CP00858 + PC-Multilingual-850+euro + csIBM00858 + + + IBM00924 + 2090 + IBM See + CCSID00924 + CP00924 + ebcdic-Latin9--euro + csIBM00924 + + + IBM01140 + 2091 + IBM See + CCSID01140 + CP01140 + ebcdic-us-37+euro + csIBM01140 + + + IBM01141 + 2092 + IBM See + CCSID01141 + CP01141 + ebcdic-de-273+euro + csIBM01141 + + + IBM01142 + 2093 + IBM See + CCSID01142 + CP01142 + ebcdic-dk-277+euro + ebcdic-no-277+euro + csIBM01142 + + + IBM01143 + 2094 + IBM See + CCSID01143 + CP01143 + ebcdic-fi-278+euro + ebcdic-se-278+euro + csIBM01143 + + + IBM01144 + 2095 + IBM See + CCSID01144 + CP01144 + ebcdic-it-280+euro + csIBM01144 + + + IBM01145 + 2096 + IBM See + CCSID01145 + CP01145 + ebcdic-es-284+euro + csIBM01145 + + + IBM01146 + 2097 + IBM See + CCSID01146 + CP01146 + ebcdic-gb-285+euro + csIBM01146 + + + IBM01147 + 2098 + IBM See + CCSID01147 + CP01147 + ebcdic-fr-297+euro + csIBM01147 + + + IBM01148 + 2099 + IBM See + CCSID01148 + CP01148 + ebcdic-international-500+euro + csIBM01148 + + + IBM01149 + 2100 + IBM See + CCSID01149 + CP01149 + ebcdic-is-871+euro + csIBM01149 + + + Big5-HKSCS + + 2101 + See + csBig5HKSCS + + + IBM1047 + + 2102 + IBM1047 (EBCDIC Latin 1/Open Systems) + + IBM-1047 + csIBM1047 + + + PTCP154 + + 2103 + See + csPTCP154 + PT154 + CP154 + Cyrillic-Asian + + + Amiga-1251 + 2104 + See + Ami1251 + Amiga1251 + Ami-1251 + csAmiga1251 +(Aliases are provided for historical reasons and should not be used) [Malyshev] + + + KOI7-switched + 2105 + See + csKOI7switched + + + BRF + 2106 + See + csBRF + + + TSCII + 2107 + See + csTSCII + + + CP51932 + 2108 + See + csCP51932 + + + windows-874 + 2109 + See + cswindows874 + + + windows-1250 + 2250 + Microsoft + cswindows1250 + + + windows-1251 + 2251 + Microsoft + cswindows1251 + + + windows-1252 + 2252 + Microsoft + cswindows1252 + + + windows-1253 + 2253 + Microsoft + cswindows1253 + + + windows-1254 + 2254 + Microsoft + cswindows1254 + + + windows-1255 + 2255 + Microsoft + cswindows1255 + + + windows-1256 + 2256 + Microsoft + cswindows1256 + + + windows-1257 + 2257 + Microsoft + cswindows1257 + + + windows-1258 + 2258 + Microsoft + cswindows1258 + + + TIS-620 + 2259 + Thai Industrial Standards Institute (TISI) + csTIS620 + ISO-8859-11 + + + CP50220 + 2260 + See + csCP50220 + +
+ + + Alexander Uskov + mailto:auskov&idc.kz + 2002-09 + + + Alexei Veremeev + mailto:Alexey.Veremeev&oracle.com + 2006-12-07 + + + Chris Wendt + mailto:christw&microsoft.com + 1999-12 + + + Hank Nussbacher + mailto:hank&vm.tau.ac.il + + + Internet Assigned Numbers Authority + mailto:iana&iana.org + + + Jun Murai + mailto:jun&wide.ad.jp + + + Katya Lazhintseva + mailto:katyal&microsoft.com + 1996-05 + + + Keld Simonsen + mailto:Keld.Simonsen&dkuug.dk + + + Keld Simonsen + mailto:Keld.Simonsen&rap.dk + 2000-08 + + + Kuppuswamy Kalyanasundaram + mailto:kalyan.geo&yahoo.com + 2007-05-14 + + + Mark Davis + mailto:mark&unicode.org + 2002-04 + + + Markus Scherer + mailto:markus.scherer&jtcsv.com + 2002-09 + + + Masataka Ohta + mailto:mohta&cc.titech.ac.jp + 1995-07 + + + Nicky Yick + mailto:cliac&itsd.gcn.gov.hk + 2000-10 + + + Reuel Robrigado + mailto:reuelr&ca.ibm.com + 2002-09 + + + Rick Pond + mailto:rickpond&vnet.ibm.com + 1997-03 + + + Sairan M. Kikkarin + mailto:sairan&sci.kz + 2006-12-07 + + + Samuel Thibault + mailto:samuel.thibault&ens-lyon.org + 2006-12-07 + + + Shawn Steele + mailto:Shawn.Steele&microsoft.com + 2010-11-04 + + + Tamer Mahdi + mailto:tamer&ca.ibm.com + 2000-08 + + + Toby Phipps + mailto:tphipps&peoplesoft.com + 2002-03 + + + Trin Tantsetthi + mailto:trin&mozart.inet.co.th + 1998-09 + + + Vladas Tumasonis + mailto:vladas.tumasonis&maf.vu.lt + 2000-08 + + + Woohyong Choi + mailto:whchoi&cosmos.kaist.ac.kr + + + Yui Naruse + mailto:naruse&airemix.jp + 2011-09-23 + + +
diff --git a/sys/src/cmd/tcs/mkfile b/sys/src/cmd/tcs/mkfile index 677b59422..435e0f687 100644 --- a/sys/src/cmd/tcs/mkfile +++ b/sys/src/cmd/tcs/mkfile @@ -34,11 +34,11 @@ tcs.$O: alias.h conv%.$O: conv.h conv_ksc.$O: ksc.h -charsets.txt: - hget http://www.iana.org/assignments/character-sets | sed 's/ //' >$target +charsets.xml: + hget http://www.iana.org/assignments/character-sets/character-sets.xml >$target -alias.h: charsets.awk charsets.txt alias.txt - ./charsets.awk charsets.txt alias.txt >$target +alias.h: charsets.awk charsets.xml alias.txt + ./charsets.awk charsets.xml alias.txt >$target clean:V: rm -f *.[$OS] [$OS].out y.tab.? y.debug y.output alias.h $TARG -- cgit v1.2.3