home *** CD-ROM | disk | FTP | other *** search
Text File | 2000-09-24 | 18.5 KB | 209 lines | [TEXT/ToyS] |
- (*
-
- A list of encoding names registered in Cyclone for AppleScript.
- This list is based on Apple's <TextCommon.h> and "Programming With the Text Encoding Conversion Manager"
- (For Version 1.5).
- If you have any problems with names or you will have an encoding not listed here,
- you may use raw numbers in your scripts as well (in decimal form, AppleScript does not support hex).
- Some of these encodings are not supported by current version of Text Encoding Converter.
- Encodings marked with '*' are available with TEC 1.4.2/1.4.3.
- Encoding marked with '•' are new in TEC 1.5.
-
- Note that spaces and punctation chars are replaced with '_' in names for AppleScript compatibility.
-
- Cyclone 1.3 adds Internet name support via TECGetTextEncodingFromInternetName() call,
- inheriting all its features and limitations. Internet names are case-insensitive.
- Contrary to what TEC documentation says, the Internet name "UTF-16" is not supported by TEC 1.5,
- but Cyclone 1.3 checks for "UTF-16" and resolves it properly.
- I did not test these names extensively. If you find an Internet name which is not listed here,
- but works with TEC, drop me a line <mailto:tkukiel@mac.com>.
-
-
- Name: Code: Internet name: Comments:
-
- "Mac_Western" 0x00000000 "mac", "macintosh", "x-mac-roman" "same as Roman"*
- "Mac_Roman" 0x00000000 "mac", "macintosh", "x-mac-roman" "Western"*
- "Mac_Roman_Euro_Sign" 0x00000000 "mac", "macintosh", "x-mac-roman" ""*
- "Mac_Roman_Old" 0x00010000 - ""*
- "Mac_Japanese" 0x00000001 "x-mac-japanese" ""*
- "Mac_Japanese_Standard" 0x00000001 "x-mac-japanese" ""*
- "Mac_Japanese_Standard_No_Verticals" 0x00010001 - ""*
- "Mac_Japanese_Basic" 0x00020001 - ""*
- "Mac_Japanese_PostScript_Screen" 0x00030001 - ""*
- "Mac_Japanese_PostScript_Print" 0x00040001 - ""*
- "Mac_Japanese_Vert_At_Ku_Plus_Ten" 0x00050001 - ""*
- "Mac_Traditional_Chinese" 0x00000002 "x-mac-chinesetrad" ""*
- "Mac_Korean" 0x00000003 "x-mac-korean" ""*
- "Mac_Arabic" 0x00000004 "x-mac-arabic" ""*
- "Mac_Arabic_Standard" 0x00000004 "x-mac-arabic" ""*
- "Mac_Arabic_TrueType" 0x00010004 - ""*
- "Mac_Arabic_Thuluth" 0x00020004 - ""*
- "Mac_Arabic_AlBayan" 0x00030004 - ""*
- "Mac_Hebrew" 0x00000005 "x-mac-hebrew" ""*
- "Mac_Hebrew_Standard" 0x00000005 "x-mac-hebrew" ""*
- "Mac_Hebrew_Figure_Space" 0x00010005 - ""*
- "Mac_Greek" 0x00000006 "x-mac-greek" ""*
- "Mac_Cyrillic" 0x00000007 "x-mac-cyrillic" ""*
- "Mac_Cyrillic_Old_Standard" 0x00010007 - ""•
- "Mac_Cyrillic_Old_Ukrainian" 0x00020007 - ""•
- "Mac_Cyrillic_Euro_Sign" 0x00030007 - ""•
- "Mac_Devanagari" 0x00000009 "x-mac-devanagari" ""*
- "Mac_Gurmukhi" 0x0000000A "x-mac-gurmukhi" ""*
- "Mac_Gujarati" 0x0000000B "x-mac-gujarati" ""*
- "Mac_Oriya" 0x0000000C - ""
- "Mac_Bengali" 0x0000000D - ""
- "Mac_Tamil" 0x0000000E - ""
- "Mac_Telugu" 0x0000000F - ""
- "Mac_Kannada" 0x00000010 - ""
- "Mac_Malayalam" 0x00000011 - ""
- "Mac_Sinhalese" 0x00000012 - ""
- "Mac_Burmese" 0x00000013 - ""
- "Mac_Khmer" 0x00000014 - ""
- "Mac_Thai" 0x00000015 "x-mac-thai" ""*
- "Mac_Laotian" 0x00000016 - ""
- "Mac_Georgian" 0x00000017 - ""
- "Mac_Armenian" 0x00000018 - ""
- "Mac_Simplified_Chinese" 0x00000019 "x-mac-chinesesimp" ""*
- "Mac_Tibetan" 0x0000001A "x-mac-tibetan" ""•
- "Mac_Mongolian" 0x0000001B - ""
- "Mac_Ethiopic" 0x0000001C - ""
- "Mac_Central_European" 0x0000001D "x-mac-centraleurroman" ""*
- "Mac_Vietnamese" 0x0000001E - ""
- "Mac_Arabic_Extended" 0x0000001F - ""
- "Mac_Symbol" 0x00000021 "x-mac-symbol" ""*
- "Mac_Dingbats" 0x00000022 "x-mac-dingbats" ""*
- "Mac_Turkish" 0x00000023 "x-mac-turkish" ""*
- "Mac_Croatian" 0x00000024 "x-mac-croatian" ""*
- "Mac_Croatian_Euro_Sign" 0x00000024 "x-mac-croatian" ""*
- "Mac_Croatian_Old" 0x00010024 - ""*
- "Mac_Icelandic" 0x00000025 "x-mac-icelandic" ""*
- "Mac_Icelandic_Euro_Sign_Standard" 0x00000025 "x-mac-icelandic" ""*
- "Mac_Icelandic_Old_Standard" 0x00020025 - ""*
- "Mac_Icelandic_Old_TrueType" 0x00030025 - ""*
- "Mac_Icelandic_Euro_Sign_TrueType" 0x00050025 - ""*
- "Mac_Romanian" 0x00000026 "x-mac-romanian" ""*
- "Mac_Romanian_Euro_Sign" 0x00000026 "x-mac-romanian" ""*
- "Mac_Romanian_Old" 0x00010026 - ""*
- "Mac_Celtic" 0x00000027 - ""
- "Mac_Gaelic" 0x00000028 - ""
- "Mac_Farsi" 0x0000008C "x-mac-farsi" ""*
- "Mac_Farsi_Standard" 0x0000008C "x-mac-farsi" ""*
- "Mac_Farsi_TrueType" 0x0001008C - ""*
- "Mac_Ukrainian" 0x00000098 "x-mac-ukrainian" "in TEC 1.5 mapped to Mac_Cyrillic"*
- "Mac_Inuit" 0x000000EC - ""
- "Mac_VT100" 0x000000FC "x-mac-vt100" ""*
- "Mac_VT100_Euro_Sign" 0x000000FC "x-mac-vt100" ""*
- "Mac_VT100_Old" 0x000100FC - ""*
-
- "Unicode_1_1" 0x00000101 "UNICODE-1-1" "default Standard 16 Bit"*
- "Unicode_1_1_16_Bit" 0x00000101 "UNICODE-1-1" "same as Standard"*
- "Unicode_1_1_Standard" 0x00000101 "UNICODE-1-1" "16 Bit"*
- "Unicode_1_1_No_Compatibility" 0x00010101 - ""
- "Unicode_1_1_Canonical_Decomposition" 0x00020101 - ""
- "Unicode_1_1_No_Composed" 0x00030101 - ""
- "Unicode_1_1_No_Corporate" 0x00040101 - ""
-
- "Unicode_1_1_UTF_7" 0x04000101 "UNICODE-1-1-UTF-7" "7 Bit"*
- "Unicode_1_1_UTF_8" 0x08000101 "UNICODE-1-1-UTF-8" "8 Bit"*
-
- "Unicode" 0x00000103 "UNICODE-2-0" "default to Unicode 2.1 16 Bit"*
- "Unicode_2_0" 0x00000103 "UNICODE-2-0" "New location for Korean Hangul"*
- "Unicode_2_1" 0x00000103 "UNICODE-2-0", "UTF-16" "We treat both Unicode 2.0 and Unicode 2.1 as 2.1"*
- "Unicode_2_1_16 Bit" 0x00000103 "UNICODE-2-0", "UTF-16" "same as Standard"*
- "Unicode_2_1_Standard" 0x00000103 "UNICODE-2-0", "UTF-16" "16 Bit"*
- "Unicode_2_1_No_Compatibility" 0x00010103 - ""
- "Unicode_2_1_Canonical_Decomposition" 0x00020103 - ""•
- "Unicode_2_1_No_Composed" 0x00030103 - ""
- "Unicode_2_1_No_Corporate" 0x00040103 - ""
-
- "Unicode_2_1_UTF_7" 0x04000103 "UNICODE-2-0-UTF-7", "UTF-7" "7 Bit"*
- "Unicode_2_1_UTF_8" 0x08000103 "UNICODE-2-0-UTF-8", "UTF-8" "8 Bit"*
-
- "ISO_Latin_1" 0x00000201 "ISO-8859-1", "latin1" "ISO 8859-1"*
- "ISO_Latin_2" 0x00000202 "ISO-8859-2", "latin2" "ISO 8859-2"*
- "ISO_Latin_3" 0x00000203 "ISO-8859-3", "latin3" "ISO 8859-3"•
- "ISO_Latin_4" 0x00000204 "ISO-8859-4", "latin4" "ISO 8859-4"•
- "ISO_Latin_Cyrillic" 0x00000205 "ISO-8859-5", "cyrillic" "ISO 8859-5"*
- "ISO_Latin_Arabic" 0x00000206 "ISO-8859-6", "arabic" "ISO 8859-6, = ASMO 708, =DOS CP 708"*
- "ISO_Latin_Greek" 0x00000207 "ISO-8859-7", "greek" "ISO 8859-7"*
- "ISO_Latin_Hebrew" 0x00000208 "ISO-8859-8", "hebrew" "ISO 8859-8"*
- "ISO_Latin_5" 0x00000209 "ISO-8859-9", "latin5" "ISO 8859-9, Turkish"*
- "ISO_Latin_6" 0x0000020A - "ISO 8859-10"
- "ISO_Latin_7" 0x0000020D - "ISO 8859-13, Baltic Rim"
- "ISO_Latin_8" 0x0000020E - "ISO 8859-14, Celtic"
- "ISO_Latin_9" 0x0000020F, "ISO-8859-15", "latin9" "ISO 8859-15, 8859-1 changed for EURO & CP1252 letters"•
-
- "DOS_Latin_US" 0x00000400 "cp437" "CP 437"*
- "DOS_Greek" 0x00000405 - "CP 737 (formerly CP 437G)"
- "DOS_Baltic_Rim" 0x00000406 - "CP 775"
- "DOS_Latin_1" 0x00000410 "cp850" "CP 850 <Multilingual>"*
- "DOS_Greek_1" 0x00000411 - "CP 851"
- "DOS_Latin_2" 0x00000412 - "CP 852, Slavic"
- "DOS_Cyrillic" 0x00000413 - "CP 855, IBM Cyrillic"
- "DOS_Turkish" 0x00000414 - "CP 857, IBM Turkish"
- "DOS_Portuguese" 0x00000415 - "CP 860"
- "DOS_Icelandic" 0x00000416 - "CP 861"
- "DOS_Hebrew" 0x00000417 - "CP 862"
- "DOS_Canadian_French" 0x00000418 - "CP 863"
- "DOS_Arabic" 0x00000419 "cp864" "CP 864"*
- "DOS_Nordic" 0x0000041A - "CP 865"
- "DOS_Russian" 0x0000041B "cp866" "CP 866"
- "DOS_Greek_2" 0x0000041C - "CP 869, IBM Modern Greek"
- "DOS_Thai" 0x0000041D "cp874" "CP 874, also for Windows"*
- "DOS_Japanese" 0x00000420 - "CP 932, also for Windows; Shift-JIS with additions"*
- "DOS_Simplified_Chinese" 0x00000421 - "CP 936, also for Windows; was EUC-CN, now GBK (EUC-CN extended)"*
- "DOS_Korean" 0x00000422 - "CP 949, also for Windows; Unified Hangul Code (EUC-KR extended)"
- "DOS_Traditional_Chinese" 0x00000423 - "CP 950 also for Windows; Big-5"*
- "Win_Latin_1" 0x00000500 "windows-1252", "cp1252" "CP 1252"*
- "Win_ANSI" 0x00000500 "windows-1252", "cp1252" "CP 1252 (alternate name)"*
- "Win_Latin_2" 0x00000501 "windows-1250", "cp1250" "CP 1250 Central Europe"*
- "Win_Cyrillic" 0x00000502 "windows-1251", "cp1251" "CP 1251, Slavic Cyrillic"*
- "Win_Greek" 0x00000503 "windows-1253", "cp1253" "CP 1253"*
- "Win_Latin_5" 0x00000504 "windows-1254", "cp1254" "CP 1254, Turkish"*
- "Win_Hebrew" 0x00000505 "windows-1255", "cp1255" "CP 1255"*
- "Win_Arabic" 0x00000506 "windows-1256", "cp1256" "CP 1256"*
- "Win_Baltic_Rim" 0x00000507 "windows-1257", "cp1257" "CP 1257"•
- "Win_Vietnamese" 0x00000508 "windows-1258", "cp1258" "CP 1258"•
- "Win_Korean_Johab" 0x00000510 - "CP 1361, for Windows NT"
-
- "Western_ASCII" 0x00000600 "US-ASCII" ""*
- "Japanese_JIS_X0201_76" 0x00000620 - "JIS Roman and 1-byte katakana (halfwidth)"
- "Japanese_JIS_X0208_83" 0x00000621 - ""
- "Japanese_JIS_X0208_90" 0x00000622 "JIS_C6226-1983" ""*
- "Japanese_JIS_X0212_90" 0x00000623 - ""
- "Japanese_JIS_C6226_78" 0x00000624 - ""
- "Simplified_Chinese_GB_2312_80" 0x00000630 "csISO58GB231280" ""*
- "Chinese_GBK_95" 0x00000631 "X-GBK" "annex to GB 13000-93; for Windows 95; EUC-CN extended"*
- "Korean_KSC_5601_87" 0x00000640 "csKSC56011987" "same as KSC 5601-92 without Johab annex"*
- "Korean_KSC_5601_92_Johab" 0x00000641 - "KSC 5601-92 Johab annex"
- "CNS_11643_92_P1" 0x00000651 "x-cns11643-1" "CNS 11643-1992 plane 1"
- "CNS_11643_92_P2" 0x00000652 "x-cns11643-2" "CNS 11643-1992 plane 2"
- "CNS_11643_92_P3" 0x00000653 - "CNS 11643-1992 plane 3 (was plane 14 in 1986 version)"
-
- "Japanese_ISO_2022_JP" 0x00000820 "ISO-2022-JP" ""*
- "Japanese_ISO_2022_JP_2" 0x00000821 - ""
- "Simplified_Chinese_ISO_2022_CN" 0x00000830 "ISO-2022-CN" ""*
- "Simplified_Chinese_ISO_2022_CN_EXT" 0x00000831 - ""
- "Korean_ISO_2022_KR" 0x00000840 "ISO-2022-KR" "EUC collections begin at 0x900"*
- "Japanese_EUC" 0x00000920 "EUC-JP", "X-EUC-JP" "ISO 646, 1-byte katakana, JIS 208, JIS 212"*
- "Simplified_Chinese_EUC" 0x00000930 "GB2312", "X-EUC-CN" "ISO 646, GB 2312-80"*
- "Traditional_Chinese_EUC" 0x00000931 "X-EUC-TW" "ISO 646, CNS 11643-1992 Planes 1-16"*
- "Korean_EUC" 0x00000940 "EUC-KR" "ISO 646, KS C 5601-1987"*
-
- "Japanese_Shift_JIS" 0x00000A01 "Shift_JIS", "x-sjis", "x-shift-jis" "plain Shift-JIS"*
- "Cyrillic_KOI8_R" 0x00000A02 "KOI8-R" "Russian internet standard"*
-
- "Traditional_Chinese_Big_5" 0x00000A03 "Big5" ""*
- "Traditional_Chinese_Big_5_Basic" 0x00000A03 "Big5" ""*
- "Traditional_Chinese_Big_5_Standard" 0x00010A03 - ""
- "Traditional_Chinese_Big_5_ETen" 0x00020A03 - ""
-
- "Western_Mac_Mail" 0x00000A04 "x-mac-latin1" "Mac OS Roman permuted to align with ISO Latin-1"*
- "Simplified_Chinese_HZ_GB_2312" 0x00000A05 "HZ-GB-2312" "HZ (RFC 1842, for Chinese mail & news)"*
- "Western_Next_Step" 0x00000B01 "X-NEXTSTEP" "NextStep encoding"*
- "Western_EBCDIC_US" 0x00000C01 - "basic EBCDIC-US"
- "Western_EBCDIC_CP037" 0x00000C02 "cp037" "CP 037, extended EBCDIC (Latin-1 set) for US, Canada..."*
- "Multi_Run" 0x00000FFF - "Multi-encoding text with external run info"*
-
- *)
-