Untabify.
diff --git a/libcharset/lib/ChangeLog b/libcharset/lib/ChangeLog
index 375d23f..af3607b 100644
--- a/libcharset/lib/ChangeLog
+++ b/libcharset/lib/ChangeLog
@@ -1,3 +1,8 @@
+2009-12-12 Bruno Haible <bruno@clisp.org>
+
+ * config.charset: Untabify.
+ * localcharset.c: Untabify.
+
2009-10-18 Bruno Haible <bruno@clisp.org>
Avoid symlink attack in localcharset module.
diff --git a/libcharset/lib/config.charset b/libcharset/lib/config.charset
old mode 100755
new mode 100644
index 21d55a4..82d2e8d
--- a/libcharset/lib/config.charset
+++ b/libcharset/lib/config.charset
@@ -124,561 +124,561 @@
# List of references, updated during installation:
echo "# Packages using this file: "
case "$os" in
- linux-gnulibc1*)
- # Linux libc5 doesn't have nl_langinfo(CODESET); therefore
- # localcharset.c falls back to using the full locale name
- # from the environment variables.
- echo "C ASCII"
- echo "POSIX ASCII"
- for l in af af_ZA ca ca_ES da da_DK de de_AT de_BE de_CH de_DE de_LU \
- en en_AU en_BW en_CA en_DK en_GB en_IE en_NZ en_US en_ZA \
- en_ZW es es_AR es_BO es_CL es_CO es_DO es_EC es_ES es_GT \
- es_HN es_MX es_PA es_PE es_PY es_SV es_US es_UY es_VE et \
- et_EE eu eu_ES fi fi_FI fo fo_FO fr fr_BE fr_CA fr_CH fr_FR \
- fr_LU ga ga_IE gl gl_ES id id_ID in in_ID is is_IS it it_CH \
- it_IT kl kl_GL nl nl_BE nl_NL no no_NO pt pt_BR pt_PT sv \
- sv_FI sv_SE; do
- echo "$l ISO-8859-1"
- echo "$l.iso-8859-1 ISO-8859-1"
- echo "$l.iso-8859-15 ISO-8859-15"
- echo "$l.iso-8859-15@euro ISO-8859-15"
- echo "$l@euro ISO-8859-15"
- echo "$l.cp-437 CP437"
- echo "$l.cp-850 CP850"
- echo "$l.cp-1252 CP1252"
- echo "$l.cp-1252@euro CP1252"
- #echo "$l.atari-st ATARI-ST" # not a commonly used encoding
- echo "$l.utf-8 UTF-8"
- echo "$l.utf-8@euro UTF-8"
- done
- for l in cs cs_CZ hr hr_HR hu hu_HU pl pl_PL ro ro_RO sk sk_SK sl \
- sl_SI sr sr_CS sr_YU; do
- echo "$l ISO-8859-2"
- echo "$l.iso-8859-2 ISO-8859-2"
- echo "$l.cp-852 CP852"
- echo "$l.cp-1250 CP1250"
- echo "$l.utf-8 UTF-8"
- done
- for l in mk mk_MK ru ru_RU; do
- echo "$l ISO-8859-5"
- echo "$l.iso-8859-5 ISO-8859-5"
- echo "$l.koi8-r KOI8-R"
- echo "$l.cp-866 CP866"
- echo "$l.cp-1251 CP1251"
- echo "$l.utf-8 UTF-8"
- done
- for l in ar ar_SA; do
- echo "$l ISO-8859-6"
- echo "$l.iso-8859-6 ISO-8859-6"
- echo "$l.cp-864 CP864"
- #echo "$l.cp-868 CP868" # not a commonly used encoding
- echo "$l.cp-1256 CP1256"
- echo "$l.utf-8 UTF-8"
- done
- for l in el el_GR gr gr_GR; do
- echo "$l ISO-8859-7"
- echo "$l.iso-8859-7 ISO-8859-7"
- echo "$l.cp-869 CP869"
- echo "$l.cp-1253 CP1253"
- echo "$l.cp-1253@euro CP1253"
- echo "$l.utf-8 UTF-8"
- echo "$l.utf-8@euro UTF-8"
- done
- for l in he he_IL iw iw_IL; do
- echo "$l ISO-8859-8"
- echo "$l.iso-8859-8 ISO-8859-8"
- echo "$l.cp-862 CP862"
- echo "$l.cp-1255 CP1255"
- echo "$l.utf-8 UTF-8"
- done
- for l in tr tr_TR; do
- echo "$l ISO-8859-9"
- echo "$l.iso-8859-9 ISO-8859-9"
- echo "$l.cp-857 CP857"
- echo "$l.cp-1254 CP1254"
- echo "$l.utf-8 UTF-8"
- done
- for l in lt lt_LT lv lv_LV; do
- #echo "$l BALTIC" # not a commonly used encoding, wrong encoding name
- echo "$l ISO-8859-13"
- done
- for l in ru_UA uk uk_UA; do
- echo "$l KOI8-U"
- done
- for l in zh zh_CN; do
- #echo "$l GB_2312-80" # not a commonly used encoding, wrong encoding name
- echo "$l GB2312"
- done
- for l in ja ja_JP ja_JP.EUC; do
- echo "$l EUC-JP"
- done
- for l in ko ko_KR; do
- echo "$l EUC-KR"
- done
- for l in th th_TH; do
- echo "$l TIS-620"
- done
- for l in fa fa_IR; do
- #echo "$l ISIRI-3342" # a broken encoding
- echo "$l.utf-8 UTF-8"
- done
- ;;
- linux* | *-gnu*)
- # With glibc-2.1 or newer, we don't need any canonicalization,
- # because glibc has iconv and both glibc and libiconv support all
- # GNU canonical names directly. Therefore, the Makefile does not
- # need to install the alias file at all.
- # The following applies only to glibc-2.0.x and older libcs.
- echo "ISO_646.IRV:1983 ASCII"
- ;;
- aix*)
- echo "ISO8859-1 ISO-8859-1"
- echo "ISO8859-2 ISO-8859-2"
- echo "ISO8859-5 ISO-8859-5"
- echo "ISO8859-6 ISO-8859-6"
- echo "ISO8859-7 ISO-8859-7"
- echo "ISO8859-8 ISO-8859-8"
- echo "ISO8859-9 ISO-8859-9"
- echo "ISO8859-15 ISO-8859-15"
- echo "IBM-850 CP850"
- echo "IBM-856 CP856"
- echo "IBM-921 ISO-8859-13"
- echo "IBM-922 CP922"
- echo "IBM-932 CP932"
- echo "IBM-943 CP943"
- echo "IBM-1046 CP1046"
- echo "IBM-1124 CP1124"
- echo "IBM-1129 CP1129"
- echo "IBM-1252 CP1252"
- echo "IBM-eucCN GB2312"
- echo "IBM-eucJP EUC-JP"
- echo "IBM-eucKR EUC-KR"
- echo "IBM-eucTW EUC-TW"
- echo "big5 BIG5"
- echo "GBK GBK"
- echo "TIS-620 TIS-620"
- echo "UTF-8 UTF-8"
- ;;
- hpux*)
- echo "iso88591 ISO-8859-1"
- echo "iso88592 ISO-8859-2"
- echo "iso88595 ISO-8859-5"
- echo "iso88596 ISO-8859-6"
- echo "iso88597 ISO-8859-7"
- echo "iso88598 ISO-8859-8"
- echo "iso88599 ISO-8859-9"
- echo "iso885915 ISO-8859-15"
- echo "roman8 HP-ROMAN8"
- echo "arabic8 HP-ARABIC8"
- echo "greek8 HP-GREEK8"
- echo "hebrew8 HP-HEBREW8"
- echo "turkish8 HP-TURKISH8"
- echo "kana8 HP-KANA8"
- echo "tis620 TIS-620"
- echo "big5 BIG5"
- echo "eucJP EUC-JP"
- echo "eucKR EUC-KR"
- echo "eucTW EUC-TW"
- echo "hp15CN GB2312"
- #echo "ccdc ?" # what is this?
- echo "SJIS SHIFT_JIS"
- echo "utf8 UTF-8"
- ;;
- irix*)
- echo "ISO8859-1 ISO-8859-1"
- echo "ISO8859-2 ISO-8859-2"
- echo "ISO8859-5 ISO-8859-5"
- echo "ISO8859-7 ISO-8859-7"
- echo "ISO8859-9 ISO-8859-9"
- echo "eucCN GB2312"
- echo "eucJP EUC-JP"
- echo "eucKR EUC-KR"
- echo "eucTW EUC-TW"
- ;;
- osf*)
- echo "ISO8859-1 ISO-8859-1"
- echo "ISO8859-2 ISO-8859-2"
- echo "ISO8859-4 ISO-8859-4"
- echo "ISO8859-5 ISO-8859-5"
- echo "ISO8859-7 ISO-8859-7"
- echo "ISO8859-8 ISO-8859-8"
- echo "ISO8859-9 ISO-8859-9"
- echo "ISO8859-15 ISO-8859-15"
- echo "cp850 CP850"
- echo "big5 BIG5"
- echo "dechanyu DEC-HANYU"
- echo "dechanzi GB2312"
- echo "deckanji DEC-KANJI"
- echo "deckorean EUC-KR"
- echo "eucJP EUC-JP"
- echo "eucKR EUC-KR"
- echo "eucTW EUC-TW"
- echo "GBK GBK"
- echo "KSC5601 CP949"
- echo "sdeckanji EUC-JP"
- echo "SJIS SHIFT_JIS"
- echo "TACTIS TIS-620"
- echo "UTF-8 UTF-8"
- ;;
- solaris*)
- echo "646 ASCII"
- echo "ISO8859-1 ISO-8859-1"
- echo "ISO8859-2 ISO-8859-2"
- echo "ISO8859-3 ISO-8859-3"
- echo "ISO8859-4 ISO-8859-4"
- echo "ISO8859-5 ISO-8859-5"
- echo "ISO8859-6 ISO-8859-6"
- echo "ISO8859-7 ISO-8859-7"
- echo "ISO8859-8 ISO-8859-8"
- echo "ISO8859-9 ISO-8859-9"
- echo "ISO8859-15 ISO-8859-15"
- echo "koi8-r KOI8-R"
- echo "ansi-1251 CP1251"
- echo "BIG5 BIG5"
- echo "Big5-HKSCS BIG5-HKSCS"
- echo "gb2312 GB2312"
- echo "GBK GBK"
- echo "GB18030 GB18030"
- echo "cns11643 EUC-TW"
- echo "5601 EUC-KR"
- echo "ko_KR.johap92 JOHAB"
- echo "eucJP EUC-JP"
- echo "PCK SHIFT_JIS"
- echo "TIS620.2533 TIS-620"
- #echo "sun_eu_greek ?" # what is this?
- echo "UTF-8 UTF-8"
- ;;
- freebsd* | os2*)
- # FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore
- # localcharset.c falls back to using the full locale name
- # from the environment variables.
- # Likewise for OS/2. OS/2 has XFree86 just like FreeBSD. Just
- # reuse FreeBSD's locale data for OS/2.
- echo "C ASCII"
- echo "US-ASCII ASCII"
- for l in la_LN lt_LN; do
- echo "$l.ASCII ASCII"
- done
- for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
- fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT la_LN \
- lt_LN nl_BE nl_NL no_NO pt_PT sv_SE; do
- echo "$l.ISO_8859-1 ISO-8859-1"
- echo "$l.DIS_8859-15 ISO-8859-15"
- done
- for l in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI; do
- echo "$l.ISO_8859-2 ISO-8859-2"
- done
- for l in la_LN lt_LT; do
- echo "$l.ISO_8859-4 ISO-8859-4"
- done
- for l in ru_RU ru_SU; do
- echo "$l.KOI8-R KOI8-R"
- echo "$l.ISO_8859-5 ISO-8859-5"
- echo "$l.CP866 CP866"
- done
- echo "uk_UA.KOI8-U KOI8-U"
- echo "zh_TW.BIG5 BIG5"
- echo "zh_TW.Big5 BIG5"
- echo "zh_CN.EUC GB2312"
- echo "ja_JP.EUC EUC-JP"
- echo "ja_JP.SJIS SHIFT_JIS"
- echo "ja_JP.Shift_JIS SHIFT_JIS"
- echo "ko_KR.EUC EUC-KR"
- ;;
- netbsd*)
- echo "646 ASCII"
- echo "ISO8859-1 ISO-8859-1"
- echo "ISO8859-2 ISO-8859-2"
- echo "ISO8859-4 ISO-8859-4"
- echo "ISO8859-5 ISO-8859-5"
- echo "ISO8859-7 ISO-8859-7"
- echo "ISO8859-13 ISO-8859-13"
- echo "ISO8859-15 ISO-8859-15"
- echo "eucCN GB2312"
- echo "eucJP EUC-JP"
- echo "eucKR EUC-KR"
- echo "eucTW EUC-TW"
- echo "BIG5 BIG5"
- echo "SJIS SHIFT_JIS"
- ;;
- openbsd*)
- echo "646 ASCII"
- echo "ISO8859-1 ISO-8859-1"
- echo "ISO8859-2 ISO-8859-2"
- echo "ISO8859-4 ISO-8859-4"
- echo "ISO8859-5 ISO-8859-5"
- echo "ISO8859-7 ISO-8859-7"
- echo "ISO8859-13 ISO-8859-13"
- echo "ISO8859-15 ISO-8859-15"
- ;;
- darwin[56]*)
- # Darwin 6.8 doesn't have nl_langinfo(CODESET); therefore
- # localcharset.c falls back to using the full locale name
- # from the environment variables.
- echo "C ASCII"
- for l in en_AU en_CA en_GB en_US la_LN; do
- echo "$l.US-ASCII ASCII"
- done
- for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
- fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT nl_BE \
- nl_NL no_NO pt_PT sv_SE; do
- echo "$l ISO-8859-1"
- echo "$l.ISO8859-1 ISO-8859-1"
- echo "$l.ISO8859-15 ISO-8859-15"
- done
- for l in la_LN; do
- echo "$l.ISO8859-1 ISO-8859-1"
- echo "$l.ISO8859-15 ISO-8859-15"
- done
- for l in cs_CZ hr_HR hu_HU la_LN pl_PL sl_SI; do
- echo "$l.ISO8859-2 ISO-8859-2"
- done
- for l in la_LN lt_LT; do
- echo "$l.ISO8859-4 ISO-8859-4"
- done
- for l in ru_RU; do
- echo "$l.KOI8-R KOI8-R"
- echo "$l.ISO8859-5 ISO-8859-5"
- echo "$l.CP866 CP866"
- done
- for l in bg_BG; do
- echo "$l.CP1251 CP1251"
- done
- echo "uk_UA.KOI8-U KOI8-U"
- echo "zh_TW.BIG5 BIG5"
- echo "zh_TW.Big5 BIG5"
- echo "zh_CN.EUC GB2312"
- echo "ja_JP.EUC EUC-JP"
- echo "ja_JP.SJIS SHIFT_JIS"
- echo "ko_KR.EUC EUC-KR"
- ;;
- darwin*)
- # Darwin 7.5 has nl_langinfo(CODESET), but sometimes its value is
- # useless:
- # - It returns the empty string when LANG is set to a locale of the
- # form ll_CC, although ll_CC/LC_CTYPE is a symlink to an UTF-8
- # LC_CTYPE file.
- # - The environment variables LANG, LC_CTYPE, LC_ALL are not set by
- # the system; nl_langinfo(CODESET) returns "US-ASCII" in this case.
- # - The documentation says:
- # "... all code that calls BSD system routines should ensure
- # that the const *char parameters of these routines are in UTF-8
- # encoding. All BSD system functions expect their string
- # parameters to be in UTF-8 encoding and nothing else."
- # It also says
- # "An additional caveat is that string parameters for files,
- # paths, and other file-system entities must be in canonical
- # UTF-8. In a canonical UTF-8 Unicode string, all decomposable
- # characters are decomposed ..."
- # but this is not true: You can pass non-decomposed UTF-8 strings
- # to file system functions, and it is the OS which will convert
- # them to decomposed UTF-8 before accessing the file system.
- # - The Apple Terminal application displays UTF-8 by default.
- # - However, other applications are free to use different encodings:
- # - xterm uses ISO-8859-1 by default.
- # - TextEdit uses MacRoman by default.
- # We prefer UTF-8 over decomposed UTF-8-MAC because one should
- # minimize the use of decomposed Unicode. Unfortunately, through the
- # Darwin file system, decomposed UTF-8 strings are leaked into user
- # space nevertheless.
- # Then there are also the locales with encodings other than US-ASCII
- # and UTF-8. These locales can be occasionally useful to users (e.g.
- # when grepping through ISO-8859-1 encoded text files), when all their
- # file names are in US-ASCII.
- echo "ISO8859-1 ISO-8859-1"
- echo "ISO8859-2 ISO-8859-2"
- echo "ISO8859-4 ISO-8859-4"
- echo "ISO8859-5 ISO-8859-5"
- echo "ISO8859-7 ISO-8859-7"
- echo "ISO8859-9 ISO-8859-9"
- echo "ISO8859-13 ISO-8859-13"
- echo "ISO8859-15 ISO-8859-15"
- echo "KOI8-R KOI8-R"
- echo "KOI8-U KOI8-U"
- echo "CP866 CP866"
- echo "CP949 CP949"
- echo "CP1131 CP1131"
- echo "CP1251 CP1251"
- echo "eucCN GB2312"
- echo "GB2312 GB2312"
- echo "eucJP EUC-JP"
- echo "eucKR EUC-KR"
- echo "Big5 BIG5"
- echo "Big5HKSCS BIG5-HKSCS"
- echo "GBK GBK"
- echo "GB18030 GB18030"
- echo "SJIS SHIFT_JIS"
- echo "ARMSCII-8 ARMSCII-8"
- echo "PT154 PT154"
- #echo "ISCII-DEV ?"
- echo "* UTF-8"
- ;;
- beos* | haiku*)
- # BeOS and Haiku have a single locale, and it has UTF-8 encoding.
- echo "* UTF-8"
- ;;
- msdosdjgpp*)
- # DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore
- # localcharset.c falls back to using the full locale name
- # from the environment variables.
- echo "#"
- echo "# The encodings given here may not all be correct."
- echo "# If you find that the encoding given for your language and"
- echo "# country is not the one your DOS machine actually uses, just"
- echo "# correct it in this file, and send a mail to"
- echo "# Juan Manuel Guerrero <juan.guerrero@gmx.de>"
- echo "# and Bruno Haible <bruno@clisp.org>."
- echo "#"
- echo "C ASCII"
- # ISO-8859-1 languages
- echo "ca CP850"
- echo "ca_ES CP850"
- echo "da CP865" # not CP850 ??
- echo "da_DK CP865" # not CP850 ??
- echo "de CP850"
- echo "de_AT CP850"
- echo "de_CH CP850"
- echo "de_DE CP850"
- echo "en CP850"
- echo "en_AU CP850" # not CP437 ??
- echo "en_CA CP850"
- echo "en_GB CP850"
- echo "en_NZ CP437"
- echo "en_US CP437"
- echo "en_ZA CP850" # not CP437 ??
- echo "es CP850"
- echo "es_AR CP850"
- echo "es_BO CP850"
- echo "es_CL CP850"
- echo "es_CO CP850"
- echo "es_CR CP850"
- echo "es_CU CP850"
- echo "es_DO CP850"
- echo "es_EC CP850"
- echo "es_ES CP850"
- echo "es_GT CP850"
- echo "es_HN CP850"
- echo "es_MX CP850"
- echo "es_NI CP850"
- echo "es_PA CP850"
- echo "es_PY CP850"
- echo "es_PE CP850"
- echo "es_SV CP850"
- echo "es_UY CP850"
- echo "es_VE CP850"
- echo "et CP850"
- echo "et_EE CP850"
- echo "eu CP850"
- echo "eu_ES CP850"
- echo "fi CP850"
- echo "fi_FI CP850"
- echo "fr CP850"
- echo "fr_BE CP850"
- echo "fr_CA CP850"
- echo "fr_CH CP850"
- echo "fr_FR CP850"
- echo "ga CP850"
- echo "ga_IE CP850"
- echo "gd CP850"
- echo "gd_GB CP850"
- echo "gl CP850"
- echo "gl_ES CP850"
- echo "id CP850" # not CP437 ??
- echo "id_ID CP850" # not CP437 ??
- echo "is CP861" # not CP850 ??
- echo "is_IS CP861" # not CP850 ??
- echo "it CP850"
- echo "it_CH CP850"
- echo "it_IT CP850"
- echo "lt CP775"
- echo "lt_LT CP775"
- echo "lv CP775"
- echo "lv_LV CP775"
- echo "nb CP865" # not CP850 ??
- echo "nb_NO CP865" # not CP850 ??
- echo "nl CP850"
- echo "nl_BE CP850"
- echo "nl_NL CP850"
- echo "nn CP865" # not CP850 ??
- echo "nn_NO CP865" # not CP850 ??
- echo "no CP865" # not CP850 ??
- echo "no_NO CP865" # not CP850 ??
- echo "pt CP850"
- echo "pt_BR CP850"
- echo "pt_PT CP850"
- echo "sv CP850"
- echo "sv_SE CP850"
- # ISO-8859-2 languages
- echo "cs CP852"
- echo "cs_CZ CP852"
- echo "hr CP852"
- echo "hr_HR CP852"
- echo "hu CP852"
- echo "hu_HU CP852"
- echo "pl CP852"
- echo "pl_PL CP852"
- echo "ro CP852"
- echo "ro_RO CP852"
- echo "sk CP852"
- echo "sk_SK CP852"
- echo "sl CP852"
- echo "sl_SI CP852"
- echo "sq CP852"
- echo "sq_AL CP852"
- echo "sr CP852" # CP852 or CP866 or CP855 ??
- echo "sr_CS CP852" # CP852 or CP866 or CP855 ??
- echo "sr_YU CP852" # CP852 or CP866 or CP855 ??
- # ISO-8859-3 languages
- echo "mt CP850"
- echo "mt_MT CP850"
- # ISO-8859-5 languages
- echo "be CP866"
- echo "be_BE CP866"
- echo "bg CP866" # not CP855 ??
- echo "bg_BG CP866" # not CP855 ??
- echo "mk CP866" # not CP855 ??
- echo "mk_MK CP866" # not CP855 ??
- echo "ru CP866"
- echo "ru_RU CP866"
- echo "uk CP1125"
- echo "uk_UA CP1125"
- # ISO-8859-6 languages
- echo "ar CP864"
- echo "ar_AE CP864"
- echo "ar_DZ CP864"
- echo "ar_EG CP864"
- echo "ar_IQ CP864"
- echo "ar_IR CP864"
- echo "ar_JO CP864"
- echo "ar_KW CP864"
- echo "ar_MA CP864"
- echo "ar_OM CP864"
- echo "ar_QA CP864"
- echo "ar_SA CP864"
- echo "ar_SY CP864"
- # ISO-8859-7 languages
- echo "el CP869"
- echo "el_GR CP869"
- # ISO-8859-8 languages
- echo "he CP862"
- echo "he_IL CP862"
- # ISO-8859-9 languages
- echo "tr CP857"
- echo "tr_TR CP857"
- # Japanese
- echo "ja CP932"
- echo "ja_JP CP932"
- # Chinese
- echo "zh_CN GBK"
- echo "zh_TW CP950" # not CP938 ??
- # Korean
- echo "kr CP949" # not CP934 ??
- echo "kr_KR CP949" # not CP934 ??
- # Thai
- echo "th CP874"
- echo "th_TH CP874"
- # Other
- echo "eo CP850"
- echo "eo_EO CP850"
- ;;
+ linux-gnulibc1*)
+ # Linux libc5 doesn't have nl_langinfo(CODESET); therefore
+ # localcharset.c falls back to using the full locale name
+ # from the environment variables.
+ echo "C ASCII"
+ echo "POSIX ASCII"
+ for l in af af_ZA ca ca_ES da da_DK de de_AT de_BE de_CH de_DE de_LU \
+ en en_AU en_BW en_CA en_DK en_GB en_IE en_NZ en_US en_ZA \
+ en_ZW es es_AR es_BO es_CL es_CO es_DO es_EC es_ES es_GT \
+ es_HN es_MX es_PA es_PE es_PY es_SV es_US es_UY es_VE et \
+ et_EE eu eu_ES fi fi_FI fo fo_FO fr fr_BE fr_CA fr_CH fr_FR \
+ fr_LU ga ga_IE gl gl_ES id id_ID in in_ID is is_IS it it_CH \
+ it_IT kl kl_GL nl nl_BE nl_NL no no_NO pt pt_BR pt_PT sv \
+ sv_FI sv_SE; do
+ echo "$l ISO-8859-1"
+ echo "$l.iso-8859-1 ISO-8859-1"
+ echo "$l.iso-8859-15 ISO-8859-15"
+ echo "$l.iso-8859-15@euro ISO-8859-15"
+ echo "$l@euro ISO-8859-15"
+ echo "$l.cp-437 CP437"
+ echo "$l.cp-850 CP850"
+ echo "$l.cp-1252 CP1252"
+ echo "$l.cp-1252@euro CP1252"
+ #echo "$l.atari-st ATARI-ST" # not a commonly used encoding
+ echo "$l.utf-8 UTF-8"
+ echo "$l.utf-8@euro UTF-8"
+ done
+ for l in cs cs_CZ hr hr_HR hu hu_HU pl pl_PL ro ro_RO sk sk_SK sl \
+ sl_SI sr sr_CS sr_YU; do
+ echo "$l ISO-8859-2"
+ echo "$l.iso-8859-2 ISO-8859-2"
+ echo "$l.cp-852 CP852"
+ echo "$l.cp-1250 CP1250"
+ echo "$l.utf-8 UTF-8"
+ done
+ for l in mk mk_MK ru ru_RU; do
+ echo "$l ISO-8859-5"
+ echo "$l.iso-8859-5 ISO-8859-5"
+ echo "$l.koi8-r KOI8-R"
+ echo "$l.cp-866 CP866"
+ echo "$l.cp-1251 CP1251"
+ echo "$l.utf-8 UTF-8"
+ done
+ for l in ar ar_SA; do
+ echo "$l ISO-8859-6"
+ echo "$l.iso-8859-6 ISO-8859-6"
+ echo "$l.cp-864 CP864"
+ #echo "$l.cp-868 CP868" # not a commonly used encoding
+ echo "$l.cp-1256 CP1256"
+ echo "$l.utf-8 UTF-8"
+ done
+ for l in el el_GR gr gr_GR; do
+ echo "$l ISO-8859-7"
+ echo "$l.iso-8859-7 ISO-8859-7"
+ echo "$l.cp-869 CP869"
+ echo "$l.cp-1253 CP1253"
+ echo "$l.cp-1253@euro CP1253"
+ echo "$l.utf-8 UTF-8"
+ echo "$l.utf-8@euro UTF-8"
+ done
+ for l in he he_IL iw iw_IL; do
+ echo "$l ISO-8859-8"
+ echo "$l.iso-8859-8 ISO-8859-8"
+ echo "$l.cp-862 CP862"
+ echo "$l.cp-1255 CP1255"
+ echo "$l.utf-8 UTF-8"
+ done
+ for l in tr tr_TR; do
+ echo "$l ISO-8859-9"
+ echo "$l.iso-8859-9 ISO-8859-9"
+ echo "$l.cp-857 CP857"
+ echo "$l.cp-1254 CP1254"
+ echo "$l.utf-8 UTF-8"
+ done
+ for l in lt lt_LT lv lv_LV; do
+ #echo "$l BALTIC" # not a commonly used encoding, wrong encoding name
+ echo "$l ISO-8859-13"
+ done
+ for l in ru_UA uk uk_UA; do
+ echo "$l KOI8-U"
+ done
+ for l in zh zh_CN; do
+ #echo "$l GB_2312-80" # not a commonly used encoding, wrong encoding name
+ echo "$l GB2312"
+ done
+ for l in ja ja_JP ja_JP.EUC; do
+ echo "$l EUC-JP"
+ done
+ for l in ko ko_KR; do
+ echo "$l EUC-KR"
+ done
+ for l in th th_TH; do
+ echo "$l TIS-620"
+ done
+ for l in fa fa_IR; do
+ #echo "$l ISIRI-3342" # a broken encoding
+ echo "$l.utf-8 UTF-8"
+ done
+ ;;
+ linux* | *-gnu*)
+ # With glibc-2.1 or newer, we don't need any canonicalization,
+ # because glibc has iconv and both glibc and libiconv support all
+ # GNU canonical names directly. Therefore, the Makefile does not
+ # need to install the alias file at all.
+ # The following applies only to glibc-2.0.x and older libcs.
+ echo "ISO_646.IRV:1983 ASCII"
+ ;;
+ aix*)
+ echo "ISO8859-1 ISO-8859-1"
+ echo "ISO8859-2 ISO-8859-2"
+ echo "ISO8859-5 ISO-8859-5"
+ echo "ISO8859-6 ISO-8859-6"
+ echo "ISO8859-7 ISO-8859-7"
+ echo "ISO8859-8 ISO-8859-8"
+ echo "ISO8859-9 ISO-8859-9"
+ echo "ISO8859-15 ISO-8859-15"
+ echo "IBM-850 CP850"
+ echo "IBM-856 CP856"
+ echo "IBM-921 ISO-8859-13"
+ echo "IBM-922 CP922"
+ echo "IBM-932 CP932"
+ echo "IBM-943 CP943"
+ echo "IBM-1046 CP1046"
+ echo "IBM-1124 CP1124"
+ echo "IBM-1129 CP1129"
+ echo "IBM-1252 CP1252"
+ echo "IBM-eucCN GB2312"
+ echo "IBM-eucJP EUC-JP"
+ echo "IBM-eucKR EUC-KR"
+ echo "IBM-eucTW EUC-TW"
+ echo "big5 BIG5"
+ echo "GBK GBK"
+ echo "TIS-620 TIS-620"
+ echo "UTF-8 UTF-8"
+ ;;
+ hpux*)
+ echo "iso88591 ISO-8859-1"
+ echo "iso88592 ISO-8859-2"
+ echo "iso88595 ISO-8859-5"
+ echo "iso88596 ISO-8859-6"
+ echo "iso88597 ISO-8859-7"
+ echo "iso88598 ISO-8859-8"
+ echo "iso88599 ISO-8859-9"
+ echo "iso885915 ISO-8859-15"
+ echo "roman8 HP-ROMAN8"
+ echo "arabic8 HP-ARABIC8"
+ echo "greek8 HP-GREEK8"
+ echo "hebrew8 HP-HEBREW8"
+ echo "turkish8 HP-TURKISH8"
+ echo "kana8 HP-KANA8"
+ echo "tis620 TIS-620"
+ echo "big5 BIG5"
+ echo "eucJP EUC-JP"
+ echo "eucKR EUC-KR"
+ echo "eucTW EUC-TW"
+ echo "hp15CN GB2312"
+ #echo "ccdc ?" # what is this?
+ echo "SJIS SHIFT_JIS"
+ echo "utf8 UTF-8"
+ ;;
+ irix*)
+ echo "ISO8859-1 ISO-8859-1"
+ echo "ISO8859-2 ISO-8859-2"
+ echo "ISO8859-5 ISO-8859-5"
+ echo "ISO8859-7 ISO-8859-7"
+ echo "ISO8859-9 ISO-8859-9"
+ echo "eucCN GB2312"
+ echo "eucJP EUC-JP"
+ echo "eucKR EUC-KR"
+ echo "eucTW EUC-TW"
+ ;;
+ osf*)
+ echo "ISO8859-1 ISO-8859-1"
+ echo "ISO8859-2 ISO-8859-2"
+ echo "ISO8859-4 ISO-8859-4"
+ echo "ISO8859-5 ISO-8859-5"
+ echo "ISO8859-7 ISO-8859-7"
+ echo "ISO8859-8 ISO-8859-8"
+ echo "ISO8859-9 ISO-8859-9"
+ echo "ISO8859-15 ISO-8859-15"
+ echo "cp850 CP850"
+ echo "big5 BIG5"
+ echo "dechanyu DEC-HANYU"
+ echo "dechanzi GB2312"
+ echo "deckanji DEC-KANJI"
+ echo "deckorean EUC-KR"
+ echo "eucJP EUC-JP"
+ echo "eucKR EUC-KR"
+ echo "eucTW EUC-TW"
+ echo "GBK GBK"
+ echo "KSC5601 CP949"
+ echo "sdeckanji EUC-JP"
+ echo "SJIS SHIFT_JIS"
+ echo "TACTIS TIS-620"
+ echo "UTF-8 UTF-8"
+ ;;
+ solaris*)
+ echo "646 ASCII"
+ echo "ISO8859-1 ISO-8859-1"
+ echo "ISO8859-2 ISO-8859-2"
+ echo "ISO8859-3 ISO-8859-3"
+ echo "ISO8859-4 ISO-8859-4"
+ echo "ISO8859-5 ISO-8859-5"
+ echo "ISO8859-6 ISO-8859-6"
+ echo "ISO8859-7 ISO-8859-7"
+ echo "ISO8859-8 ISO-8859-8"
+ echo "ISO8859-9 ISO-8859-9"
+ echo "ISO8859-15 ISO-8859-15"
+ echo "koi8-r KOI8-R"
+ echo "ansi-1251 CP1251"
+ echo "BIG5 BIG5"
+ echo "Big5-HKSCS BIG5-HKSCS"
+ echo "gb2312 GB2312"
+ echo "GBK GBK"
+ echo "GB18030 GB18030"
+ echo "cns11643 EUC-TW"
+ echo "5601 EUC-KR"
+ echo "ko_KR.johap92 JOHAB"
+ echo "eucJP EUC-JP"
+ echo "PCK SHIFT_JIS"
+ echo "TIS620.2533 TIS-620"
+ #echo "sun_eu_greek ?" # what is this?
+ echo "UTF-8 UTF-8"
+ ;;
+ freebsd* | os2*)
+ # FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore
+ # localcharset.c falls back to using the full locale name
+ # from the environment variables.
+ # Likewise for OS/2. OS/2 has XFree86 just like FreeBSD. Just
+ # reuse FreeBSD's locale data for OS/2.
+ echo "C ASCII"
+ echo "US-ASCII ASCII"
+ for l in la_LN lt_LN; do
+ echo "$l.ASCII ASCII"
+ done
+ for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
+ fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT la_LN \
+ lt_LN nl_BE nl_NL no_NO pt_PT sv_SE; do
+ echo "$l.ISO_8859-1 ISO-8859-1"
+ echo "$l.DIS_8859-15 ISO-8859-15"
+ done
+ for l in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI; do
+ echo "$l.ISO_8859-2 ISO-8859-2"
+ done
+ for l in la_LN lt_LT; do
+ echo "$l.ISO_8859-4 ISO-8859-4"
+ done
+ for l in ru_RU ru_SU; do
+ echo "$l.KOI8-R KOI8-R"
+ echo "$l.ISO_8859-5 ISO-8859-5"
+ echo "$l.CP866 CP866"
+ done
+ echo "uk_UA.KOI8-U KOI8-U"
+ echo "zh_TW.BIG5 BIG5"
+ echo "zh_TW.Big5 BIG5"
+ echo "zh_CN.EUC GB2312"
+ echo "ja_JP.EUC EUC-JP"
+ echo "ja_JP.SJIS SHIFT_JIS"
+ echo "ja_JP.Shift_JIS SHIFT_JIS"
+ echo "ko_KR.EUC EUC-KR"
+ ;;
+ netbsd*)
+ echo "646 ASCII"
+ echo "ISO8859-1 ISO-8859-1"
+ echo "ISO8859-2 ISO-8859-2"
+ echo "ISO8859-4 ISO-8859-4"
+ echo "ISO8859-5 ISO-8859-5"
+ echo "ISO8859-7 ISO-8859-7"
+ echo "ISO8859-13 ISO-8859-13"
+ echo "ISO8859-15 ISO-8859-15"
+ echo "eucCN GB2312"
+ echo "eucJP EUC-JP"
+ echo "eucKR EUC-KR"
+ echo "eucTW EUC-TW"
+ echo "BIG5 BIG5"
+ echo "SJIS SHIFT_JIS"
+ ;;
+ openbsd*)
+ echo "646 ASCII"
+ echo "ISO8859-1 ISO-8859-1"
+ echo "ISO8859-2 ISO-8859-2"
+ echo "ISO8859-4 ISO-8859-4"
+ echo "ISO8859-5 ISO-8859-5"
+ echo "ISO8859-7 ISO-8859-7"
+ echo "ISO8859-13 ISO-8859-13"
+ echo "ISO8859-15 ISO-8859-15"
+ ;;
+ darwin[56]*)
+ # Darwin 6.8 doesn't have nl_langinfo(CODESET); therefore
+ # localcharset.c falls back to using the full locale name
+ # from the environment variables.
+ echo "C ASCII"
+ for l in en_AU en_CA en_GB en_US la_LN; do
+ echo "$l.US-ASCII ASCII"
+ done
+ for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
+ fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT nl_BE \
+ nl_NL no_NO pt_PT sv_SE; do
+ echo "$l ISO-8859-1"
+ echo "$l.ISO8859-1 ISO-8859-1"
+ echo "$l.ISO8859-15 ISO-8859-15"
+ done
+ for l in la_LN; do
+ echo "$l.ISO8859-1 ISO-8859-1"
+ echo "$l.ISO8859-15 ISO-8859-15"
+ done
+ for l in cs_CZ hr_HR hu_HU la_LN pl_PL sl_SI; do
+ echo "$l.ISO8859-2 ISO-8859-2"
+ done
+ for l in la_LN lt_LT; do
+ echo "$l.ISO8859-4 ISO-8859-4"
+ done
+ for l in ru_RU; do
+ echo "$l.KOI8-R KOI8-R"
+ echo "$l.ISO8859-5 ISO-8859-5"
+ echo "$l.CP866 CP866"
+ done
+ for l in bg_BG; do
+ echo "$l.CP1251 CP1251"
+ done
+ echo "uk_UA.KOI8-U KOI8-U"
+ echo "zh_TW.BIG5 BIG5"
+ echo "zh_TW.Big5 BIG5"
+ echo "zh_CN.EUC GB2312"
+ echo "ja_JP.EUC EUC-JP"
+ echo "ja_JP.SJIS SHIFT_JIS"
+ echo "ko_KR.EUC EUC-KR"
+ ;;
+ darwin*)
+ # Darwin 7.5 has nl_langinfo(CODESET), but sometimes its value is
+ # useless:
+ # - It returns the empty string when LANG is set to a locale of the
+ # form ll_CC, although ll_CC/LC_CTYPE is a symlink to an UTF-8
+ # LC_CTYPE file.
+ # - The environment variables LANG, LC_CTYPE, LC_ALL are not set by
+ # the system; nl_langinfo(CODESET) returns "US-ASCII" in this case.
+ # - The documentation says:
+ # "... all code that calls BSD system routines should ensure
+ # that the const *char parameters of these routines are in UTF-8
+ # encoding. All BSD system functions expect their string
+ # parameters to be in UTF-8 encoding and nothing else."
+ # It also says
+ # "An additional caveat is that string parameters for files,
+ # paths, and other file-system entities must be in canonical
+ # UTF-8. In a canonical UTF-8 Unicode string, all decomposable
+ # characters are decomposed ..."
+ # but this is not true: You can pass non-decomposed UTF-8 strings
+ # to file system functions, and it is the OS which will convert
+ # them to decomposed UTF-8 before accessing the file system.
+ # - The Apple Terminal application displays UTF-8 by default.
+ # - However, other applications are free to use different encodings:
+ # - xterm uses ISO-8859-1 by default.
+ # - TextEdit uses MacRoman by default.
+ # We prefer UTF-8 over decomposed UTF-8-MAC because one should
+ # minimize the use of decomposed Unicode. Unfortunately, through the
+ # Darwin file system, decomposed UTF-8 strings are leaked into user
+ # space nevertheless.
+ # Then there are also the locales with encodings other than US-ASCII
+ # and UTF-8. These locales can be occasionally useful to users (e.g.
+ # when grepping through ISO-8859-1 encoded text files), when all their
+ # file names are in US-ASCII.
+ echo "ISO8859-1 ISO-8859-1"
+ echo "ISO8859-2 ISO-8859-2"
+ echo "ISO8859-4 ISO-8859-4"
+ echo "ISO8859-5 ISO-8859-5"
+ echo "ISO8859-7 ISO-8859-7"
+ echo "ISO8859-9 ISO-8859-9"
+ echo "ISO8859-13 ISO-8859-13"
+ echo "ISO8859-15 ISO-8859-15"
+ echo "KOI8-R KOI8-R"
+ echo "KOI8-U KOI8-U"
+ echo "CP866 CP866"
+ echo "CP949 CP949"
+ echo "CP1131 CP1131"
+ echo "CP1251 CP1251"
+ echo "eucCN GB2312"
+ echo "GB2312 GB2312"
+ echo "eucJP EUC-JP"
+ echo "eucKR EUC-KR"
+ echo "Big5 BIG5"
+ echo "Big5HKSCS BIG5-HKSCS"
+ echo "GBK GBK"
+ echo "GB18030 GB18030"
+ echo "SJIS SHIFT_JIS"
+ echo "ARMSCII-8 ARMSCII-8"
+ echo "PT154 PT154"
+ #echo "ISCII-DEV ?"
+ echo "* UTF-8"
+ ;;
+ beos* | haiku*)
+ # BeOS and Haiku have a single locale, and it has UTF-8 encoding.
+ echo "* UTF-8"
+ ;;
+ msdosdjgpp*)
+ # DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore
+ # localcharset.c falls back to using the full locale name
+ # from the environment variables.
+ echo "#"
+ echo "# The encodings given here may not all be correct."
+ echo "# If you find that the encoding given for your language and"
+ echo "# country is not the one your DOS machine actually uses, just"
+ echo "# correct it in this file, and send a mail to"
+ echo "# Juan Manuel Guerrero <juan.guerrero@gmx.de>"
+ echo "# and Bruno Haible <bruno@clisp.org>."
+ echo "#"
+ echo "C ASCII"
+ # ISO-8859-1 languages
+ echo "ca CP850"
+ echo "ca_ES CP850"
+ echo "da CP865" # not CP850 ??
+ echo "da_DK CP865" # not CP850 ??
+ echo "de CP850"
+ echo "de_AT CP850"
+ echo "de_CH CP850"
+ echo "de_DE CP850"
+ echo "en CP850"
+ echo "en_AU CP850" # not CP437 ??
+ echo "en_CA CP850"
+ echo "en_GB CP850"
+ echo "en_NZ CP437"
+ echo "en_US CP437"
+ echo "en_ZA CP850" # not CP437 ??
+ echo "es CP850"
+ echo "es_AR CP850"
+ echo "es_BO CP850"
+ echo "es_CL CP850"
+ echo "es_CO CP850"
+ echo "es_CR CP850"
+ echo "es_CU CP850"
+ echo "es_DO CP850"
+ echo "es_EC CP850"
+ echo "es_ES CP850"
+ echo "es_GT CP850"
+ echo "es_HN CP850"
+ echo "es_MX CP850"
+ echo "es_NI CP850"
+ echo "es_PA CP850"
+ echo "es_PY CP850"
+ echo "es_PE CP850"
+ echo "es_SV CP850"
+ echo "es_UY CP850"
+ echo "es_VE CP850"
+ echo "et CP850"
+ echo "et_EE CP850"
+ echo "eu CP850"
+ echo "eu_ES CP850"
+ echo "fi CP850"
+ echo "fi_FI CP850"
+ echo "fr CP850"
+ echo "fr_BE CP850"
+ echo "fr_CA CP850"
+ echo "fr_CH CP850"
+ echo "fr_FR CP850"
+ echo "ga CP850"
+ echo "ga_IE CP850"
+ echo "gd CP850"
+ echo "gd_GB CP850"
+ echo "gl CP850"
+ echo "gl_ES CP850"
+ echo "id CP850" # not CP437 ??
+ echo "id_ID CP850" # not CP437 ??
+ echo "is CP861" # not CP850 ??
+ echo "is_IS CP861" # not CP850 ??
+ echo "it CP850"
+ echo "it_CH CP850"
+ echo "it_IT CP850"
+ echo "lt CP775"
+ echo "lt_LT CP775"
+ echo "lv CP775"
+ echo "lv_LV CP775"
+ echo "nb CP865" # not CP850 ??
+ echo "nb_NO CP865" # not CP850 ??
+ echo "nl CP850"
+ echo "nl_BE CP850"
+ echo "nl_NL CP850"
+ echo "nn CP865" # not CP850 ??
+ echo "nn_NO CP865" # not CP850 ??
+ echo "no CP865" # not CP850 ??
+ echo "no_NO CP865" # not CP850 ??
+ echo "pt CP850"
+ echo "pt_BR CP850"
+ echo "pt_PT CP850"
+ echo "sv CP850"
+ echo "sv_SE CP850"
+ # ISO-8859-2 languages
+ echo "cs CP852"
+ echo "cs_CZ CP852"
+ echo "hr CP852"
+ echo "hr_HR CP852"
+ echo "hu CP852"
+ echo "hu_HU CP852"
+ echo "pl CP852"
+ echo "pl_PL CP852"
+ echo "ro CP852"
+ echo "ro_RO CP852"
+ echo "sk CP852"
+ echo "sk_SK CP852"
+ echo "sl CP852"
+ echo "sl_SI CP852"
+ echo "sq CP852"
+ echo "sq_AL CP852"
+ echo "sr CP852" # CP852 or CP866 or CP855 ??
+ echo "sr_CS CP852" # CP852 or CP866 or CP855 ??
+ echo "sr_YU CP852" # CP852 or CP866 or CP855 ??
+ # ISO-8859-3 languages
+ echo "mt CP850"
+ echo "mt_MT CP850"
+ # ISO-8859-5 languages
+ echo "be CP866"
+ echo "be_BE CP866"
+ echo "bg CP866" # not CP855 ??
+ echo "bg_BG CP866" # not CP855 ??
+ echo "mk CP866" # not CP855 ??
+ echo "mk_MK CP866" # not CP855 ??
+ echo "ru CP866"
+ echo "ru_RU CP866"
+ echo "uk CP1125"
+ echo "uk_UA CP1125"
+ # ISO-8859-6 languages
+ echo "ar CP864"
+ echo "ar_AE CP864"
+ echo "ar_DZ CP864"
+ echo "ar_EG CP864"
+ echo "ar_IQ CP864"
+ echo "ar_IR CP864"
+ echo "ar_JO CP864"
+ echo "ar_KW CP864"
+ echo "ar_MA CP864"
+ echo "ar_OM CP864"
+ echo "ar_QA CP864"
+ echo "ar_SA CP864"
+ echo "ar_SY CP864"
+ # ISO-8859-7 languages
+ echo "el CP869"
+ echo "el_GR CP869"
+ # ISO-8859-8 languages
+ echo "he CP862"
+ echo "he_IL CP862"
+ # ISO-8859-9 languages
+ echo "tr CP857"
+ echo "tr_TR CP857"
+ # Japanese
+ echo "ja CP932"
+ echo "ja_JP CP932"
+ # Chinese
+ echo "zh_CN GBK"
+ echo "zh_TW CP950" # not CP938 ??
+ # Korean
+ echo "kr CP949" # not CP934 ??
+ echo "kr_KR CP949" # not CP934 ??
+ # Thai
+ echo "th CP874"
+ echo "th_TH CP874"
+ # Other
+ echo "eo CP850"
+ echo "eo_EO CP850"
+ ;;
esac
diff --git a/libcharset/lib/localcharset.c b/libcharset/lib/localcharset.c
index e808967..5f13f84 100644
--- a/libcharset/lib/localcharset.c
+++ b/libcharset/lib/localcharset.c
@@ -130,214 +130,214 @@
char *file_name;
/* Make it possible to override the charset.alias location. This is
- necessary for running the testsuite before "make install". */
+ necessary for running the testsuite before "make install". */
dir = getenv ("CHARSETALIASDIR");
if (dir == NULL || dir[0] == '\0')
- dir = relocate (LIBDIR);
+ dir = relocate (LIBDIR);
/* Concatenate dir and base into freshly allocated file_name. */
{
- size_t dir_len = strlen (dir);
- size_t base_len = strlen (base);
- int add_slash = (dir_len > 0 && !ISSLASH (dir[dir_len - 1]));
- file_name = (char *) malloc (dir_len + add_slash + base_len + 1);
- if (file_name != NULL)
- {
- memcpy (file_name, dir, dir_len);
- if (add_slash)
- file_name[dir_len] = DIRECTORY_SEPARATOR;
- memcpy (file_name + dir_len + add_slash, base, base_len + 1);
- }
+ size_t dir_len = strlen (dir);
+ size_t base_len = strlen (base);
+ int add_slash = (dir_len > 0 && !ISSLASH (dir[dir_len - 1]));
+ file_name = (char *) malloc (dir_len + add_slash + base_len + 1);
+ if (file_name != NULL)
+ {
+ memcpy (file_name, dir, dir_len);
+ if (add_slash)
+ file_name[dir_len] = DIRECTORY_SEPARATOR;
+ memcpy (file_name + dir_len + add_slash, base, base_len + 1);
+ }
}
if (file_name == NULL)
- /* Out of memory. Treat the file as empty. */
- cp = "";
+ /* Out of memory. Treat the file as empty. */
+ cp = "";
else
- {
- int fd;
+ {
+ int fd;
- /* Open the file. Reject symbolic links on platforms that support
- O_NOFOLLOW. This is a security feature. Without it, an attacker
- could retrieve parts of the contents (namely, the tail of the
- first line that starts with "* ") of an arbitrary file by placing
- a symbolic link to that file under the name "charset.alias" in
- some writable directory and defining the environment variable
- CHARSETALIASDIR to point to that directory. */
- fd = open (file_name,
- O_RDONLY | (HAVE_WORKING_O_NOFOLLOW ? O_NOFOLLOW : 0));
- if (fd < 0)
- /* File not found. Treat it as empty. */
- cp = "";
- else
- {
- FILE *fp;
+ /* Open the file. Reject symbolic links on platforms that support
+ O_NOFOLLOW. This is a security feature. Without it, an attacker
+ could retrieve parts of the contents (namely, the tail of the
+ first line that starts with "* ") of an arbitrary file by placing
+ a symbolic link to that file under the name "charset.alias" in
+ some writable directory and defining the environment variable
+ CHARSETALIASDIR to point to that directory. */
+ fd = open (file_name,
+ O_RDONLY | (HAVE_WORKING_O_NOFOLLOW ? O_NOFOLLOW : 0));
+ if (fd < 0)
+ /* File not found. Treat it as empty. */
+ cp = "";
+ else
+ {
+ FILE *fp;
- fp = fdopen (fd, "r");
- if (fp == NULL)
- {
- /* Out of memory. Treat the file as empty. */
- close (fd);
- cp = "";
- }
- else
- {
- /* Parse the file's contents. */
- char *res_ptr = NULL;
- size_t res_size = 0;
+ fp = fdopen (fd, "r");
+ if (fp == NULL)
+ {
+ /* Out of memory. Treat the file as empty. */
+ close (fd);
+ cp = "";
+ }
+ else
+ {
+ /* Parse the file's contents. */
+ char *res_ptr = NULL;
+ size_t res_size = 0;
- for (;;)
- {
- int c;
- char buf1[50+1];
- char buf2[50+1];
- size_t l1, l2;
- char *old_res_ptr;
+ for (;;)
+ {
+ int c;
+ char buf1[50+1];
+ char buf2[50+1];
+ size_t l1, l2;
+ char *old_res_ptr;
- c = getc (fp);
- if (c == EOF)
- break;
- if (c == '\n' || c == ' ' || c == '\t')
- continue;
- if (c == '#')
- {
- /* Skip comment, to end of line. */
- do
- c = getc (fp);
- while (!(c == EOF || c == '\n'));
- if (c == EOF)
- break;
- continue;
- }
- ungetc (c, fp);
- if (fscanf (fp, "%50s %50s", buf1, buf2) < 2)
- break;
- l1 = strlen (buf1);
- l2 = strlen (buf2);
- old_res_ptr = res_ptr;
- if (res_size == 0)
- {
- res_size = l1 + 1 + l2 + 1;
- res_ptr = (char *) malloc (res_size + 1);
- }
- else
- {
- res_size += l1 + 1 + l2 + 1;
- res_ptr = (char *) realloc (res_ptr, res_size + 1);
- }
- if (res_ptr == NULL)
- {
- /* Out of memory. */
- res_size = 0;
- if (old_res_ptr != NULL)
- free (old_res_ptr);
- break;
- }
- strcpy (res_ptr + res_size - (l2 + 1) - (l1 + 1), buf1);
- strcpy (res_ptr + res_size - (l2 + 1), buf2);
- }
- fclose (fp);
- if (res_size == 0)
- cp = "";
- else
- {
- *(res_ptr + res_size) = '\0';
- cp = res_ptr;
- }
- }
- }
+ c = getc (fp);
+ if (c == EOF)
+ break;
+ if (c == '\n' || c == ' ' || c == '\t')
+ continue;
+ if (c == '#')
+ {
+ /* Skip comment, to end of line. */
+ do
+ c = getc (fp);
+ while (!(c == EOF || c == '\n'));
+ if (c == EOF)
+ break;
+ continue;
+ }
+ ungetc (c, fp);
+ if (fscanf (fp, "%50s %50s", buf1, buf2) < 2)
+ break;
+ l1 = strlen (buf1);
+ l2 = strlen (buf2);
+ old_res_ptr = res_ptr;
+ if (res_size == 0)
+ {
+ res_size = l1 + 1 + l2 + 1;
+ res_ptr = (char *) malloc (res_size + 1);
+ }
+ else
+ {
+ res_size += l1 + 1 + l2 + 1;
+ res_ptr = (char *) realloc (res_ptr, res_size + 1);
+ }
+ if (res_ptr == NULL)
+ {
+ /* Out of memory. */
+ res_size = 0;
+ if (old_res_ptr != NULL)
+ free (old_res_ptr);
+ break;
+ }
+ strcpy (res_ptr + res_size - (l2 + 1) - (l1 + 1), buf1);
+ strcpy (res_ptr + res_size - (l2 + 1), buf2);
+ }
+ fclose (fp);
+ if (res_size == 0)
+ cp = "";
+ else
+ {
+ *(res_ptr + res_size) = '\0';
+ cp = res_ptr;
+ }
+ }
+ }
- free (file_name);
- }
+ free (file_name);
+ }
#else
# if defined DARWIN7
/* To avoid the trouble of installing a file that is shared by many
- GNU packages -- many packaging systems have problems with this --,
- simply inline the aliases here. */
+ GNU packages -- many packaging systems have problems with this --,
+ simply inline the aliases here. */
cp = "ISO8859-1" "\0" "ISO-8859-1" "\0"
- "ISO8859-2" "\0" "ISO-8859-2" "\0"
- "ISO8859-4" "\0" "ISO-8859-4" "\0"
- "ISO8859-5" "\0" "ISO-8859-5" "\0"
- "ISO8859-7" "\0" "ISO-8859-7" "\0"
- "ISO8859-9" "\0" "ISO-8859-9" "\0"
- "ISO8859-13" "\0" "ISO-8859-13" "\0"
- "ISO8859-15" "\0" "ISO-8859-15" "\0"
- "KOI8-R" "\0" "KOI8-R" "\0"
- "KOI8-U" "\0" "KOI8-U" "\0"
- "CP866" "\0" "CP866" "\0"
- "CP949" "\0" "CP949" "\0"
- "CP1131" "\0" "CP1131" "\0"
- "CP1251" "\0" "CP1251" "\0"
- "eucCN" "\0" "GB2312" "\0"
- "GB2312" "\0" "GB2312" "\0"
- "eucJP" "\0" "EUC-JP" "\0"
- "eucKR" "\0" "EUC-KR" "\0"
- "Big5" "\0" "BIG5" "\0"
- "Big5HKSCS" "\0" "BIG5-HKSCS" "\0"
- "GBK" "\0" "GBK" "\0"
- "GB18030" "\0" "GB18030" "\0"
- "SJIS" "\0" "SHIFT_JIS" "\0"
- "ARMSCII-8" "\0" "ARMSCII-8" "\0"
- "PT154" "\0" "PT154" "\0"
- /*"ISCII-DEV" "\0" "?" "\0"*/
- "*" "\0" "UTF-8" "\0";
+ "ISO8859-2" "\0" "ISO-8859-2" "\0"
+ "ISO8859-4" "\0" "ISO-8859-4" "\0"
+ "ISO8859-5" "\0" "ISO-8859-5" "\0"
+ "ISO8859-7" "\0" "ISO-8859-7" "\0"
+ "ISO8859-9" "\0" "ISO-8859-9" "\0"
+ "ISO8859-13" "\0" "ISO-8859-13" "\0"
+ "ISO8859-15" "\0" "ISO-8859-15" "\0"
+ "KOI8-R" "\0" "KOI8-R" "\0"
+ "KOI8-U" "\0" "KOI8-U" "\0"
+ "CP866" "\0" "CP866" "\0"
+ "CP949" "\0" "CP949" "\0"
+ "CP1131" "\0" "CP1131" "\0"
+ "CP1251" "\0" "CP1251" "\0"
+ "eucCN" "\0" "GB2312" "\0"
+ "GB2312" "\0" "GB2312" "\0"
+ "eucJP" "\0" "EUC-JP" "\0"
+ "eucKR" "\0" "EUC-KR" "\0"
+ "Big5" "\0" "BIG5" "\0"
+ "Big5HKSCS" "\0" "BIG5-HKSCS" "\0"
+ "GBK" "\0" "GBK" "\0"
+ "GB18030" "\0" "GB18030" "\0"
+ "SJIS" "\0" "SHIFT_JIS" "\0"
+ "ARMSCII-8" "\0" "ARMSCII-8" "\0"
+ "PT154" "\0" "PT154" "\0"
+ /*"ISCII-DEV" "\0" "?" "\0"*/
+ "*" "\0" "UTF-8" "\0";
# endif
# if defined VMS
/* To avoid the troubles of an extra file charset.alias_vms in the
- sources of many GNU packages, simply inline the aliases here. */
+ sources of many GNU packages, simply inline the aliases here. */
/* The list of encodings is taken from the OpenVMS 7.3-1 documentation
- "Compaq C Run-Time Library Reference Manual for OpenVMS systems"
- section 10.7 "Handling Different Character Sets". */
+ "Compaq C Run-Time Library Reference Manual for OpenVMS systems"
+ section 10.7 "Handling Different Character Sets". */
cp = "ISO8859-1" "\0" "ISO-8859-1" "\0"
- "ISO8859-2" "\0" "ISO-8859-2" "\0"
- "ISO8859-5" "\0" "ISO-8859-5" "\0"
- "ISO8859-7" "\0" "ISO-8859-7" "\0"
- "ISO8859-8" "\0" "ISO-8859-8" "\0"
- "ISO8859-9" "\0" "ISO-8859-9" "\0"
- /* Japanese */
- "eucJP" "\0" "EUC-JP" "\0"
- "SJIS" "\0" "SHIFT_JIS" "\0"
- "DECKANJI" "\0" "DEC-KANJI" "\0"
- "SDECKANJI" "\0" "EUC-JP" "\0"
- /* Chinese */
- "eucTW" "\0" "EUC-TW" "\0"
- "DECHANYU" "\0" "DEC-HANYU" "\0"
- "DECHANZI" "\0" "GB2312" "\0"
- /* Korean */
- "DECKOREAN" "\0" "EUC-KR" "\0";
+ "ISO8859-2" "\0" "ISO-8859-2" "\0"
+ "ISO8859-5" "\0" "ISO-8859-5" "\0"
+ "ISO8859-7" "\0" "ISO-8859-7" "\0"
+ "ISO8859-8" "\0" "ISO-8859-8" "\0"
+ "ISO8859-9" "\0" "ISO-8859-9" "\0"
+ /* Japanese */
+ "eucJP" "\0" "EUC-JP" "\0"
+ "SJIS" "\0" "SHIFT_JIS" "\0"
+ "DECKANJI" "\0" "DEC-KANJI" "\0"
+ "SDECKANJI" "\0" "EUC-JP" "\0"
+ /* Chinese */
+ "eucTW" "\0" "EUC-TW" "\0"
+ "DECHANYU" "\0" "DEC-HANYU" "\0"
+ "DECHANZI" "\0" "GB2312" "\0"
+ /* Korean */
+ "DECKOREAN" "\0" "EUC-KR" "\0";
# endif
# if defined WIN32_NATIVE || defined __CYGWIN__
/* To avoid the troubles of installing a separate file in the same
- directory as the DLL and of retrieving the DLL's directory at
- runtime, simply inline the aliases here. */
+ directory as the DLL and of retrieving the DLL's directory at
+ runtime, simply inline the aliases here. */
cp = "CP936" "\0" "GBK" "\0"
- "CP1361" "\0" "JOHAB" "\0"
- "CP20127" "\0" "ASCII" "\0"
- "CP20866" "\0" "KOI8-R" "\0"
- "CP20936" "\0" "GB2312" "\0"
- "CP21866" "\0" "KOI8-RU" "\0"
- "CP28591" "\0" "ISO-8859-1" "\0"
- "CP28592" "\0" "ISO-8859-2" "\0"
- "CP28593" "\0" "ISO-8859-3" "\0"
- "CP28594" "\0" "ISO-8859-4" "\0"
- "CP28595" "\0" "ISO-8859-5" "\0"
- "CP28596" "\0" "ISO-8859-6" "\0"
- "CP28597" "\0" "ISO-8859-7" "\0"
- "CP28598" "\0" "ISO-8859-8" "\0"
- "CP28599" "\0" "ISO-8859-9" "\0"
- "CP28605" "\0" "ISO-8859-15" "\0"
- "CP38598" "\0" "ISO-8859-8" "\0"
- "CP51932" "\0" "EUC-JP" "\0"
- "CP51936" "\0" "GB2312" "\0"
- "CP51949" "\0" "EUC-KR" "\0"
- "CP51950" "\0" "EUC-TW" "\0"
- "CP54936" "\0" "GB18030" "\0"
- "CP65001" "\0" "UTF-8" "\0";
+ "CP1361" "\0" "JOHAB" "\0"
+ "CP20127" "\0" "ASCII" "\0"
+ "CP20866" "\0" "KOI8-R" "\0"
+ "CP20936" "\0" "GB2312" "\0"
+ "CP21866" "\0" "KOI8-RU" "\0"
+ "CP28591" "\0" "ISO-8859-1" "\0"
+ "CP28592" "\0" "ISO-8859-2" "\0"
+ "CP28593" "\0" "ISO-8859-3" "\0"
+ "CP28594" "\0" "ISO-8859-4" "\0"
+ "CP28595" "\0" "ISO-8859-5" "\0"
+ "CP28596" "\0" "ISO-8859-6" "\0"
+ "CP28597" "\0" "ISO-8859-7" "\0"
+ "CP28598" "\0" "ISO-8859-8" "\0"
+ "CP28599" "\0" "ISO-8859-9" "\0"
+ "CP28605" "\0" "ISO-8859-15" "\0"
+ "CP38598" "\0" "ISO-8859-8" "\0"
+ "CP51932" "\0" "EUC-JP" "\0"
+ "CP51936" "\0" "GB2312" "\0"
+ "CP51949" "\0" "EUC-KR" "\0"
+ "CP51950" "\0" "EUC-TW" "\0"
+ "CP54936" "\0" "GB18030" "\0"
+ "CP65001" "\0" "UTF-8" "\0";
# endif
#endif
@@ -381,34 +381,34 @@
locale = getenv ("LC_ALL");
if (locale == NULL || locale[0] == '\0')
- {
- locale = getenv ("LC_CTYPE");
- if (locale == NULL || locale[0] == '\0')
- locale = getenv ("LANG");
- }
+ {
+ locale = getenv ("LC_CTYPE");
+ if (locale == NULL || locale[0] == '\0')
+ locale = getenv ("LANG");
+ }
if (locale != NULL && locale[0] != '\0')
- {
- /* If the locale name contains an encoding after the dot, return
- it. */
- const char *dot = strchr (locale, '.');
+ {
+ /* If the locale name contains an encoding after the dot, return
+ it. */
+ const char *dot = strchr (locale, '.');
- if (dot != NULL)
- {
- const char *modifier;
+ if (dot != NULL)
+ {
+ const char *modifier;
- dot++;
- /* Look for the possible @... trailer and remove it, if any. */
- modifier = strchr (dot, '@');
- if (modifier == NULL)
- return dot;
- if (modifier - dot < sizeof (buf))
- {
- memcpy (buf, dot, modifier - dot);
- buf [modifier - dot] = '\0';
- return buf;
- }
- }
- }
+ dot++;
+ /* Look for the possible @... trailer and remove it, if any. */
+ modifier = strchr (dot, '@');
+ if (modifier == NULL)
+ return dot;
+ if (modifier - dot < sizeof (buf))
+ {
+ memcpy (buf, dot, modifier - dot);
+ buf [modifier - dot] = '\0';
+ return buf;
+ }
+ }
+ }
/* Woe32 has a function returning the locale's codepage as a number. */
sprintf (buf, "CP%u", GetACP ());
@@ -432,11 +432,11 @@
{
locale = getenv ("LC_ALL");
if (locale == NULL || locale[0] == '\0')
- {
- locale = getenv ("LC_CTYPE");
- if (locale == NULL || locale[0] == '\0')
- locale = getenv ("LANG");
- }
+ {
+ locale = getenv ("LC_CTYPE");
+ if (locale == NULL || locale[0] == '\0')
+ locale = getenv ("LANG");
+ }
}
/* On some old systems, one used to set locale = "iso8859_1". On others,
@@ -468,7 +468,7 @@
{
locale = getenv ("LC_CTYPE");
if (locale == NULL || locale[0] == '\0')
- locale = getenv ("LANG");
+ locale = getenv ("LANG");
}
if (locale != NULL && locale[0] != '\0')
{
@@ -476,21 +476,21 @@
const char *dot = strchr (locale, '.');
if (dot != NULL)
- {
- const char *modifier;
+ {
+ const char *modifier;
- dot++;
- /* Look for the possible @... trailer and remove it, if any. */
- modifier = strchr (dot, '@');
- if (modifier == NULL)
- return dot;
- if (modifier - dot < sizeof (buf))
- {
- memcpy (buf, dot, modifier - dot);
- buf [modifier - dot] = '\0';
- return buf;
- }
- }
+ dot++;
+ /* Look for the possible @... trailer and remove it, if any. */
+ modifier = strchr (dot, '@');
+ if (modifier == NULL)
+ return dot;
+ if (modifier - dot < sizeof (buf))
+ {
+ memcpy (buf, dot, modifier - dot);
+ buf [modifier - dot] = '\0';
+ return buf;
+ }
+ }
/* Resolve through the charset.alias file. */
codeset = locale;
@@ -499,12 +499,12 @@
{
/* OS/2 has a function returning the locale's codepage as a number. */
if (DosQueryCp (sizeof (cp), cp, &cplen))
- codeset = "";
+ codeset = "";
else
- {
- sprintf (buf, "CP%u", cp[0]);
- codeset = buf;
- }
+ {
+ sprintf (buf, "CP%u", cp[0]);
+ codeset = buf;
+ }
}
#endif
@@ -518,10 +518,10 @@
*aliases != '\0';
aliases += strlen (aliases) + 1, aliases += strlen (aliases) + 1)
if (strcmp (codeset, aliases) == 0
- || (aliases[0] == '*' && aliases[1] == '\0'))
+ || (aliases[0] == '*' && aliases[1] == '\0'))
{
- codeset = aliases + strlen (aliases) + 1;
- break;
+ codeset = aliases + strlen (aliases) + 1;
+ break;
}
/* Don't return an empty string. GNU libc and GNU libiconv interpret