2 # This file describes dependencies between encodings, CES, CCS, etc.
3 # File relates only to UCS-based conversions and is needed for automatic
4 # generation of C source files and C header files.
6 # This configuration file consists of sections, each section consists of
9 # Use only normalized names.
13 # The first section named "ENCODINGS" describes:
14 # 1. CES converter corresponding for each enoding;
15 # 2. Each encoding's aliases;
16 # 3. CCS tables corresponding for each enoding.
20 # ISO-10646-UCS-2. Big Endian, NBSP is always interpreted as NBSP (BOM isn't supported).
24 ALIASES: ucs2 iso_10646_ucs_2 iso10646_ucs_2 iso_10646_ucs2 iso10646_ucs2 iso10646ucs2 csUnicode
27 # Big Endian version of ISO-10646-UCS-2 (in fact, equivalent to ucs_2).
28 # Big Endian, NBSP is always interpreted as NBSP (BOM isn't supported).
35 # Little Endian version of ISO-10646-UCS-2.
36 # Little Endian, NBSP is always interpreted as NBSP (BOM isn't supported).
43 # ISO-10646-UCS-2 in system byte order.
44 # NBSP is always interpreted as NBSP (BOM isn't supported).
45 # NOTE: Dont delete and rename this since it is used as widechar's
46 # encoding when sizeof(wchar_t) == 2
48 ENCODING: ucs_2_internal
50 ALIASES: ucs2_internal ucs_2internal ucs2internal
53 # ISO-10646-UCS-4. Big Endian, NBSP is always interpreted as NBSP (BOM isn't supported).
57 ALIASES: ucs4 iso_10646_ucs_4 iso10646_ucs_4 iso_10646_ucs4 iso10646_ucs4 iso10646ucs4
60 # Big Endian version of ISO-10646-UCS-4 (in fact, equivalent to ucs_4).
61 # Big Endian, NBSP is always interpreted as NBSP (BOM isn't supported).
68 # Little Endian version of ISO-10646-UCS-4.
69 # Little Endian, NBSP is always interpreted as NBSP (BOM isn't supported).
76 # ISO-10646-UCS-4 in system byte order.
77 # NBSP is always interpreted as NBSP (BOM isn't supported).
78 # NOTE: Dont delete and rename this since it is used as widechar's
79 # encoding when sizeof(wchar_t) == 4
81 ENCODING: ucs_4_internal
83 ALIASES: ucs4_internal ucs_4internal ucs4internal
93 # RFC 2781 UTF-16. The very first NBSP code in stream is interpreted as BOM.
100 # Big Endian version of RFC 2781 UTF-16.
101 # NBSP is always interpreted as NBSP (BOM isn't supported).
108 # Little Endian version of RFC 2781 UTF-16.
109 # NBSP is always interpreted as NBSP (BOM isn't supported).
120 ALIASES: ansi_x3.4_1968 ansi_x3.4_1986 iso_646.irv:1991 ascii iso646_us us ibm367 cp367 csascii
128 ALIASES: cskoi8r koi8r koi8
131 # Obsoleted Ukrainian
155 # ISO IR 111/ECMA Cyrillic.
160 ALIASES: ecma_cyrillic koi8_e koi8e csiso111ecmacyrillic
163 # ISO 8859-1:1987 - Latin 1, West European
168 ALIASES: iso8859_1 iso88591 iso_8859_1:1987 iso_ir_100 latin1 l1 ibm819 cp819 csisolatin1
171 # ISO 8859-2:1987 - Latin 2, East European
176 ALIASES: iso8859_2 iso88592 iso_8859_2:1987 iso_ir_101 latin2 l2 csisolatin2
179 # ISO 8859-3:1988 - Latin 3, South European
184 ALIASES: iso_8859_3:1988 iso_ir_109 iso8859_3 latin3 l3 csisolatin3 iso88593
187 # ISO 8859-4:1988 - Latin 4, North European
192 ALIASES: iso8859_4 iso88594 iso_8859_4:1988 iso_ir_110 latin4 l4 csisolatin4
195 # ISO 8859-5:1988 - Cyrillic
200 ALIASES: iso8859_5 iso88595 iso_8859_5:1988 iso_ir_144 cyrillic csisolatincyrillic
203 # ISO i8859-6:1987 - Arabic
208 ALIASES: iso_8859_6:1987 iso_ir_127 iso8859_6 ecma_114 asmo_708 arabic csisolatinarabic iso88596
211 # ISO 8859-7:1987 - Greek
216 ALIASES: iso_8859_7:1987 iso_ir_126 iso8859_7 elot_928 ecma_118 greek greek8 csisolatingreek iso88597
219 # ISO 8859-8:1988 - Hebrew
224 ALIASES: iso_8859_8:1988 iso_ir_138 iso8859_8 hebrew csisolatinhebrew iso88598
227 # ISO 8859-9:1989 - Latin 5, Turkish
232 ALIASES: iso_8859_9:1989 iso_ir_148 iso8859_9 latin5 l5 csisolatin5 iso88599
235 # ISO 8859-10:1992 - Latin 6, Nordic
237 ENCODING: iso_8859_10
240 ALIASES: iso_8859_10:1992 iso_ir_157 iso885910 latin6 l6 csisolatin6 iso8859_10
245 ENCODING: iso_8859_11
248 ALIASES: iso8859_11 iso885911
251 # ISO 8859-13:1998 - Latin 7, Baltic Rim
253 ENCODING: iso_8859_13
256 ALIASES: iso_8859_13:1998 iso8859_13 iso885913
259 # ISO 8859-14:1998 - Latin 8, Celtic
261 ENCODING: iso_8859_14
264 ALIASES: iso_8859_14:1998 iso885914 iso8859_14
267 # ISO 8859-15:1998 - Latin 9, West Europe, successor of Latin 1
269 ENCODING: iso_8859_15
272 ALIASES: iso885915 iso_8859_15:1998 iso8859_15
283 # Win-1251 - Cyrillic
339 # Win-1258 - Vietnamese7 that supports Cyrillic
347 # big5 - an encoding for Traditional Chinese
352 ALIASES: csbig5 big_five bigfive cn_big5 cp950
355 # IBM 775 - an updated version of CP 437 that supports balitic languages.
360 ALIASES: ibm775 cspc775baltic
363 # IBM 850 - an updated version of CP 437 where several Latin 1 characters have been
364 # added instead of some less-often used characters like line-drawing and greek ones.
369 ALIASES: ibm850 850 cspc850multilingual
372 # IBM 852 - an updated version of CP 437 where several Latin 2 characters have been added
373 # instead of some less-often used characters like line-drawing and greek ones.
378 ALIASES: ibm852 852 cspcp852
381 # IBM 855 - an updated version of CP 437 that supports Cyrillic.
386 ALIASES: ibm855 855 csibm855
389 # IBM 866 - an updated version of CP 855 which followes the more logical Russian alphabet
390 # ordering of the alternativny variant that is preferred by many Russian users.
395 ALIASES: 866 IBM866 CSIBM866
398 # EUC-JP - The EUC for Japanese
402 CCS: jis_x0208_1990 jis_x0201_1976 jis_x0212_1990
406 # EUC-KR - The EUC for Korean
414 # EUC-TW - The EUC for Traditional Chinese
418 CCS: cns11643_plane1 cns11643_plane2 cns11643_plane14
425 # This section is named "CES_DEPENDENCIES" and describes dependencies
426 # between CES converters (some CES converters may use another CES converters).
428 SECTION CES_DEPENDENCIES
437 USED_CES: table us_ascii