intl/config.charset

   1 #! /bin/sh
   2 # Output a system dependent table of character encoding aliases.
   3 #
   4 #   Copyright (C) 2000-2002 Free Software Foundation, Inc.
   5 #
   6 #   This program is free software; you can redistribute it and/or modify it
   7 #   under the terms of the GNU Library General Public License as published
   8 #   by the Free Software Foundation; either version 2, or (at your option)
   9 #   any later version.
  10 #
  11 #   This program is distributed in the hope that it will be useful,
  12 #   but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 #   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14 #   Library General Public License for more details.
  15 #
  16 #   You should have received a copy of the GNU Library General Public
  17 #   License along with this program; if not, write to the Free Software
  18 #   Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
  19 #   USA.
  20 #
  21 # The table consists of lines of the form
  22 #    ALIAS  CANONICAL
  23 #
  24 # ALIAS is the (system dependent) result of "nl_langinfo (CODESET)".
  25 # ALIAS is compared in a case sensitive way.
  26 #
  27 # CANONICAL is the GNU canonical name for this character encoding.
  28 # It must be an encoding supported by libiconv. Support by GNU libc is
  29 # also desirable. CANONICAL is case insensitive. Usually an upper case
  30 # MIME charset name is preferred.
  31 # The current list of GNU canonical charset names is as follows.
  32 #
  33 #       name                         used by which systems         a MIME name?
  34 #   ASCII, ANSI_X3.4-1968     glibc solaris freebsd
  35 #   ISO-8859-1                glibc aix hpux irix osf solaris freebsd   yes
  36 #   ISO-8859-2                glibc aix hpux irix osf solaris freebsd   yes
  37 #   ISO-8859-3                glibc solaris                             yes
  38 #   ISO-8859-4                osf solaris freebsd                       yes
  39 #   ISO-8859-5                glibc aix hpux irix osf solaris freebsd   yes
  40 #   ISO-8859-6                glibc aix hpux solaris                    yes
  41 #   ISO-8859-7                glibc aix hpux irix osf solaris           yes
  42 #   ISO-8859-8                glibc aix hpux osf solaris                yes
  43 #   ISO-8859-9                glibc aix hpux irix osf solaris           yes
  44 #   ISO-8859-13               glibc
  45 #   ISO-8859-14               glibc
  46 #   ISO-8859-15               glibc aix osf solaris freebsd
  47 #   KOI8-R                    glibc solaris freebsd                     yes
  48 #   KOI8-U                    glibc freebsd                             yes
  49 #   KOI8-T                    glibc
  50 #   CP437                     dos
  51 #   CP775                     dos
  52 #   CP850                     aix osf dos
  53 #   CP852                     dos
  54 #   CP855                     dos
  55 #   CP856                     aix
  56 #   CP857                     dos
  57 #   CP861                     dos
  58 #   CP862                     dos
  59 #   CP864                     dos
  60 #   CP865                     dos
  61 #   CP866                     freebsd dos
  62 #   CP869                     dos
  63 #   CP874                     woe32 dos
  64 #   CP922                     aix
  65 #   CP932                     aix woe32 dos
  66 #   CP943                     aix
  67 #   CP949                     osf woe32 dos
  68 #   CP950                     woe32 dos
  69 #   CP1046                    aix
  70 #   CP1124                    aix
  71 #   CP1125                    dos
  72 #   CP1129                    aix
  73 #   CP1250                    woe32
  74 #   CP1251                    glibc woe32
  75 #   CP1252                    aix woe32
  76 #   CP1253                    woe32
  77 #   CP1254                    woe32
  78 #   CP1255                    glibc woe32
  79 #   CP1256                    woe32
  80 #   CP1257                    woe32
  81 #   GB2312                    glibc aix hpux irix solaris freebsd       yes
  82 #   EUC-JP                    glibc aix hpux irix osf solaris freebsd   yes
  83 #   EUC-KR                    glibc aix hpux irix osf solaris freebsd   yes
  84 #   EUC-TW                    glibc aix hpux irix osf solaris
  85 #   BIG5                      glibc aix hpux osf solaris freebsd        yes
  86 #   BIG5-HKSCS                glibc solaris
  87 #   GBK                       glibc aix osf solaris woe32 dos
  88 #   GB18030                   glibc solaris
  89 #   SHIFT_JIS                 hpux osf solaris freebsd                  yes
  90 #   JOHAB                     glibc solaris woe32
  91 #   TIS-620                   glibc aix hpux osf solaris
  92 #   VISCII                    glibc                                     yes
  93 #   TCVN5712-1                glibc
  94 #   GEORGIAN-PS               glibc
  95 #   HP-ROMAN8                 hpux
  96 #   HP-ARABIC8                hpux
  97 #   HP-GREEK8                 hpux
  98 #   HP-HEBREW8                hpux
  99 #   HP-TURKISH8               hpux
 100 #   HP-KANA8                  hpux
 101 #   DEC-KANJI                 osf
 102 #   DEC-HANYU                 osf
 103 #   UTF-8                     glibc aix hpux osf solaris                yes
 104 #
 105 # Note: Names which are not marked as being a MIME name should not be used in
 106 # Internet protocols for information interchange (mail, news, etc.).
 107 #
 108 # Note: ASCII and ANSI_X3.4-1968 are synonymous canonical names. Applications
 109 # must understand both names and treat them as equivalent.
 110 #
 111 # The first argument passed to this file is the canonical host specification,
 112 #    CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM
 113 # or
 114 #    CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM
 115
 116 host="$1"
 117 os=`echo "$host" | sed -e 's/^[^-]*-[^-]*-\(.*\)$/\1/'`
 118 echo "# This file contains a table of character encoding aliases,"
 119 echo "# suitable for operating system '${os}'."
 120 echo "# It was automatically generated from config.charset."
 121 # List of references, updated during installation:
 122 echo "# Packages using this file: "
 123 case "$os" in
 124     linux* | *-gnu*)
 125         # With glibc-2.1 or newer, we don't need any canonicalization,
 126         # because glibc has iconv and both glibc and libiconv support all
 127         # GNU canonical names directly. Therefore, the Makefile does not
 128         # need to install the alias file at all.
 129         # The following applies only to glibc-2.0.x and older libcs.
 130         echo "ISO_646.IRV:1983 ASCII"
 131         ;;
 132     aix*)
 133         echo "ISO8859-1 ISO-8859-1"
 134         echo "ISO8859-2 ISO-8859-2"
 135         echo "ISO8859-5 ISO-8859-5"
 136         echo "ISO8859-6 ISO-8859-6"
 137         echo "ISO8859-7 ISO-8859-7"
 138         echo "ISO8859-8 ISO-8859-8"
 139         echo "ISO8859-9 ISO-8859-9"
 140         echo "ISO8859-15 ISO-8859-15"
 141         echo "IBM-850 CP850"
 142         echo "IBM-856 CP856"
 143         echo "IBM-921 ISO-8859-13"
 144         echo "IBM-922 CP922"
 145         echo "IBM-932 CP932"
 146         echo "IBM-943 CP943"
 147         echo "IBM-1046 CP1046"
 148         echo "IBM-1124 CP1124"
 149         echo "IBM-1129 CP1129"
 150         echo "IBM-1252 CP1252"
 151         echo "IBM-eucCN GB2312"
 152         echo "IBM-eucJP EUC-JP"
 153         echo "IBM-eucKR EUC-KR"
 154         echo "IBM-eucTW EUC-TW"
 155         echo "big5 BIG5"
 156         echo "GBK GBK"
 157         echo "TIS-620 TIS-620"
 158         echo "UTF-8 UTF-8"
 159         ;;
 160     hpux*)
 161         echo "iso88591 ISO-8859-1"
 162         echo "iso88592 ISO-8859-2"
 163         echo "iso88595 ISO-8859-5"
 164         echo "iso88596 ISO-8859-6"
 165         echo "iso88597 ISO-8859-7"
 166         echo "iso88598 ISO-8859-8"
 167         echo "iso88599 ISO-8859-9"
 168         echo "iso885915 ISO-8859-15"
 169         echo "roman8 HP-ROMAN8"
 170         echo "arabic8 HP-ARABIC8"
 171         echo "greek8 HP-GREEK8"
 172         echo "hebrew8 HP-HEBREW8"
 173         echo "turkish8 HP-TURKISH8"
 174         echo "kana8 HP-KANA8"
 175         echo "tis620 TIS-620"
 176         echo "big5 BIG5"
 177         echo "eucJP EUC-JP"
 178         echo "eucKR EUC-KR"
 179         echo "eucTW EUC-TW"
 180         echo "hp15CN GB2312"
 181         #echo "ccdc ?" # what is this?
 182         echo "SJIS SHIFT_JIS"
 183         echo "utf8 UTF-8"
 184         ;;
 185     irix*)
 186         echo "ISO8859-1 ISO-8859-1"
 187         echo "ISO8859-2 ISO-8859-2"
 188         echo "ISO8859-5 ISO-8859-5"
 189         echo "ISO8859-7 ISO-8859-7"
 190         echo "ISO8859-9 ISO-8859-9"
 191         echo "eucCN GB2312"
 192         echo "eucJP EUC-JP"
 193         echo "eucKR EUC-KR"
 194         echo "eucTW EUC-TW"
 195         ;;
 196     osf*)
 197         echo "ISO8859-1 ISO-8859-1"
 198         echo "ISO8859-2 ISO-8859-2"
 199         echo "ISO8859-4 ISO-8859-4"
 200         echo "ISO8859-5 ISO-8859-5"
 201         echo "ISO8859-7 ISO-8859-7"
 202         echo "ISO8859-8 ISO-8859-8"
 203         echo "ISO8859-9 ISO-8859-9"
 204         echo "ISO8859-15 ISO-8859-15"
 205         echo "cp850 CP850"
 206         echo "big5 BIG5"
 207         echo "dechanyu DEC-HANYU"
 208         echo "dechanzi GB2312"
 209         echo "deckanji DEC-KANJI"
 210         echo "deckorean EUC-KR"
 211         echo "eucJP EUC-JP"
 212         echo "eucKR EUC-KR"
 213         echo "eucTW EUC-TW"
 214         echo "GBK GBK"
 215         echo "KSC5601 CP949"
 216         echo "sdeckanji EUC-JP"
 217         echo "SJIS SHIFT_JIS"
 218         echo "TACTIS TIS-620"
 219         echo "UTF-8 UTF-8"
 220         ;;
 221     solaris*)
 222         echo "646 ASCII"
 223         echo "ISO8859-1 ISO-8859-1"
 224         echo "ISO8859-2 ISO-8859-2"
 225         echo "ISO8859-3 ISO-8859-3"
 226         echo "ISO8859-4 ISO-8859-4"
 227         echo "ISO8859-5 ISO-8859-5"
 228         echo "ISO8859-6 ISO-8859-6"
 229         echo "ISO8859-7 ISO-8859-7"
 230         echo "ISO8859-8 ISO-8859-8"
 231         echo "ISO8859-9 ISO-8859-9"
 232         echo "ISO8859-15 ISO-8859-15"
 233         echo "koi8-r KOI8-R"
 234         echo "BIG5 BIG5"
 235         echo "Big5-HKSCS BIG5-HKSCS"
 236         echo "gb2312 GB2312"
 237         echo "GBK GBK"
 238         echo "GB18030 GB18030"
 239         echo "cns11643 EUC-TW"
 240         echo "5601 EUC-KR"
 241         echo "ko_KR.johap92 JOHAB"
 242         echo "eucJP EUC-JP"
 243         echo "PCK SHIFT_JIS"
 244         echo "TIS620.2533 TIS-620"
 245         #echo "sun_eu_greek ?" # what is this?
 246         echo "UTF-8 UTF-8"
 247         ;;
 248     freebsd* | os2*)
 249         # FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore
 250         # localcharset.c falls back to using the full locale name
 251         # from the environment variables.
 252         # Likewise for OS/2. OS/2 has XFree86 just like FreeBSD. Just
 253         # reuse FreeBSD's locale data for OS/2.
 254         echo "C ASCII"
 255         echo "US-ASCII ASCII"
 256         for l in la_LN lt_LN; do
 257           echo "$l.ASCII ASCII"
 258         done
 259         for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
 260                  fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT la_LN \
 261                  lt_LN nl_BE nl_NL no_NO pt_PT sv_SE; do
 262           echo "$l.ISO_8859-1 ISO-8859-1"
 263           echo "$l.DIS_8859-15 ISO-8859-15"
 264         done
 265         for l in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI; do
 266           echo "$l.ISO_8859-2 ISO-8859-2"
 267         done
 268         for l in la_LN lt_LT; do
 269           echo "$l.ISO_8859-4 ISO-8859-4"
 270         done
 271         for l in ru_RU ru_SU; do
 272           echo "$l.KOI8-R KOI8-R"
 273           echo "$l.ISO_8859-5 ISO-8859-5"
 274           echo "$l.CP866 CP866"
 275         done
 276         echo "uk_UA.KOI8-U KOI8-U"
 277         echo "zh_TW.BIG5 BIG5"
 278         echo "zh_TW.Big5 BIG5"
 279         echo "zh_CN.EUC GB2312"
 280         echo "ja_JP.EUC EUC-JP"
 281         echo "ja_JP.SJIS SHIFT_JIS"
 282         echo "ja_JP.Shift_JIS SHIFT_JIS"
 283         echo "ko_KR.EUC EUC-KR"
 284         ;;
 285     netbsd*)
 286         echo "646 ASCII"
 287         echo "ISO8859-1 ISO-8859-1"
 288         echo "ISO8859-2 ISO-8859-2"
 289         echo "ISO8859-4 ISO-8859-4"
 290         echo "ISO8859-5 ISO-8859-5"
 291         echo "ISO8859-15 ISO-8859-15"
 292         echo "eucCN GB2312"
 293         echo "eucJP EUC-JP"
 294         echo "eucKR EUC-KR"
 295         echo "eucTW EUC-TW"
 296         echo "BIG5 BIG5"
 297         echo "SJIS SHIFT_JIS"
 298         ;;
 299     beos*)
 300         # BeOS has a single locale, and it has UTF-8 encoding.
 301         echo "* UTF-8"
 302         ;;
 303     msdosdjgpp*)
 304         # DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore
 305         # localcharset.c falls back to using the full locale name
 306         # from the environment variables.
 307         echo "#"
 308         echo "# The encodings given here may not all be correct."
 309         echo "# If you find that the encoding given for your language and"
 310         echo "# country is not the one your DOS machine actually uses, just"
 311         echo "# correct it in this file, and send a mail to"
 312         echo "# Juan Manuel Guerrero <st001906@hrz1.hrz.tu-darmstadt.de>"
 313         echo "# and Bruno Haible <bruno@clisp.org>."
 314         echo "#"
 315         echo "C ASCII"
 316         # ISO-8859-1 languages
 317         echo "ca CP850"
 318         echo "ca_ES CP850"
 319         echo "da CP865"    # not CP850 ??
 320         echo "da_DK CP865" # not CP850 ??
 321         echo "de CP850"
 322         echo "de_AT CP850"
 323         echo "de_CH CP850"
 324         echo "de_DE CP850"
 325         echo "en CP850"
 326         echo "en_AU CP850" # not CP437 ??
 327         echo "en_CA CP850"
 328         echo "en_GB CP850"
 329         echo "en_NZ CP437"
 330         echo "en_US CP437"
 331         echo "en_ZA CP850" # not CP437 ??
 332         echo "es CP850"
 333         echo "es_AR CP850"
 334         echo "es_BO CP850"
 335         echo "es_CL CP850"
 336         echo "es_CO CP850"
 337         echo "es_CR CP850"
 338         echo "es_CU CP850"
 339         echo "es_DO CP850"
 340         echo "es_EC CP850"
 341         echo "es_ES CP850"
 342         echo "es_GT CP850"
 343         echo "es_HN CP850"
 344         echo "es_MX CP850"
 345         echo "es_NI CP850"
 346         echo "es_PA CP850"
 347         echo "es_PY CP850"
 348         echo "es_PE CP850"
 349         echo "es_SV CP850"
 350         echo "es_UY CP850"
 351         echo "es_VE CP850"
 352         echo "et CP850"
 353         echo "et_EE CP850"
 354         echo "eu CP850"
 355         echo "eu_ES CP850"
 356         echo "fi CP850"
 357         echo "fi_FI CP850"
 358         echo "fr CP850"
 359         echo "fr_BE CP850"
 360         echo "fr_CA CP850"
 361         echo "fr_CH CP850"
 362         echo "fr_FR CP850"
 363         echo "ga CP850"
 364         echo "ga_IE CP850"
 365         echo "gd CP850"
 366         echo "gd_GB CP850"
 367         echo "gl CP850"
 368         echo "gl_ES CP850"
 369         echo "id CP850"    # not CP437 ??
 370         echo "id_ID CP850" # not CP437 ??
 371         echo "is CP861"    # not CP850 ??
 372         echo "is_IS CP861" # not CP850 ??
 373         echo "it CP850"
 374         echo "it_CH CP850"
 375         echo "it_IT CP850"
 376         echo "lt CP775"
 377         echo "lt_LT CP775"
 378         echo "lv CP775"
 379         echo "lv_LV CP775"
 380         echo "nb CP865"    # not CP850 ??
 381         echo "nb_NO CP865" # not CP850 ??
 382         echo "nl CP850"
 383         echo "nl_BE CP850"
 384         echo "nl_NL CP850"
 385         echo "nn CP865"    # not CP850 ??
 386         echo "nn_NO CP865" # not CP850 ??
 387         echo "no CP865"    # not CP850 ??
 388         echo "no_NO CP865" # not CP850 ??
 389         echo "pt CP850"
 390         echo "pt_BR CP850"
 391         echo "pt_PT CP850"
 392         echo "sv CP850"
 393         echo "sv_SE CP850"
 394         # ISO-8859-2 languages
 395         echo "cs CP852"
 396         echo "cs_CZ CP852"
 397         echo "hr CP852"
 398         echo "hr_HR CP852"
 399         echo "hu CP852"
 400         echo "hu_HU CP852"
 401         echo "pl CP852"
 402         echo "pl_PL CP852"
 403         echo "ro CP852"
 404         echo "ro_RO CP852"
 405         echo "sk CP852"
 406         echo "sk_SK CP852"
 407         echo "sl CP852"
 408         echo "sl_SI CP852"
 409         echo "sq CP852"
 410         echo "sq_AL CP852"
 411         echo "sr CP852"    # CP852 or CP866 or CP855 ??
 412         echo "sr_YU CP852" # CP852 or CP866 or CP855 ??
 413         # ISO-8859-3 languages
 414         echo "mt CP850"
 415         echo "mt_MT CP850"
 416         # ISO-8859-5 languages
 417         echo "be CP866"
 418         echo "be_BE CP866"
 419         echo "bg CP866"    # not CP855 ??
 420         echo "bg_BG CP866" # not CP855 ??
 421         echo "mk CP866"    # not CP855 ??
 422         echo "mk_MK CP866" # not CP855 ??
 423         echo "ru CP866"
 424         echo "ru_RU CP866"
 425         echo "uk CP1125"
 426         echo "uk_UA CP1125"
 427         # ISO-8859-6 languages
 428         echo "ar CP864"
 429         echo "ar_AE CP864"
 430         echo "ar_DZ CP864"
 431         echo "ar_EG CP864"
 432         echo "ar_IQ CP864"
 433         echo "ar_IR CP864"
 434         echo "ar_JO CP864"
 435         echo "ar_KW CP864"
 436         echo "ar_MA CP864"
 437         echo "ar_OM CP864"
 438         echo "ar_QA CP864"
 439         echo "ar_SA CP864"
 440         echo "ar_SY CP864"
 441         # ISO-8859-7 languages
 442         echo "el CP869"
 443         echo "el_GR CP869"
 444         # ISO-8859-8 languages
 445         echo "he CP862"
 446         echo "he_IL CP862"
 447         # ISO-8859-9 languages
 448         echo "tr CP857"
 449         echo "tr_TR CP857"
 450         # Japanese
 451         echo "ja CP932"
 452         echo "ja_JP CP932"
 453         # Chinese
 454         echo "zh_CN GBK"
 455         echo "zh_TW CP950" # not CP938 ??
 456         # Korean
 457         echo "kr CP949"    # not CP934 ??
 458         echo "kr_KR CP949" # not CP934 ??
 459         # Thai
 460         echo "th CP874"
 461         echo "th_TH CP874"
 462         # Other
 463         echo "eo CP850"
 464         echo "eo_EO CP850"
 465         ;;
 466 esac