upstream-mirrors/gnulib
1
0
Fork 0
mirror of https://https.git.savannah.gnu.org/git/gnulib.git synced 2026-05-13 15:13:36 +00:00
Code Activity

localcharset: Move mapping tables into the code.

Browse Source 
* lib/localcharset.h: Document the GNU canonical names for character
encodings here.
* lib/localcharset.c: Don't include <fcntl.h>, <unistd.h>,
relocatable.h, configmake.h.
(O_NOFOLLOW, ISSLASH, DIRECTORY_SEPARATOR, getc, volatile): Remove
macros.
(charset_aliases): Remove variable.
(get_charset_aliases): Remove function.
(struct table_entry): New type.
(alias_table, locale_table): New constants.
(locale_charset): Use the alias_table or locale_table to get the
canonicalized encoding name.
* lib/config.charset: Remove file.
* lib/ref-add.sin: Remove file.
* lib/ref-del.sin: Remove file.
* m4/localcharset.m4 (gl_LOCALCHARSET): Don't require gl_FCNTL_O_FLAGS,
AC_CANONICAL_HOST, gl_GLIBC21. Don't check for getc_unlocked.
* modules/localcharset (Notice): Remove.
(Files): Remove config.charset, ref-add.sin, ref-del.sin, fcntl-o.m4,
glibc21.m4.
(Depends-on): Remove configmake.
(configure.ac): Define LOCALCHARSET_TESTS_ENVIRONMENT to empty.
(Makefile.am): Simplify.
* build-aux/prefix-gnulib-mk: Remove special code for the removed files.
This commit is contained in:
Bruno Haible
2018-05-19 17:17:32 +02:00
parent 9d70137bfe
commit bb5cc1c59c
10 changed files with 812 additions and 1043 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
ChangeLog
View File

@@ -1,3 +1,31 @@
2018-05-19 Bruno Haible <bruno@clisp.org>
localcharset: Move mapping tables into the code. Use a binary search.
* lib/localcharset.h: Document the GNU canonical names for character
encodings here.
* lib/localcharset.c: Don't include <fcntl.h>, <unistd.h>,
relocatable.h, configmake.h.
(O_NOFOLLOW, ISSLASH, DIRECTORY_SEPARATOR, getc, volatile): Remove
macros.
(charset_aliases): Remove variable.
(get_charset_aliases): Remove function.
(struct table_entry): New type.
(alias_table, locale_table): New constants.
(locale_charset): Use the alias_table or locale_table to get the
canonicalized encoding name.
* lib/config.charset: Remove file.
* lib/ref-add.sin: Remove file.
* lib/ref-del.sin: Remove file.
* m4/localcharset.m4 (gl_LOCALCHARSET): Don't require gl_FCNTL_O_FLAGS,
AC_CANONICAL_HOST, gl_GLIBC21. Don't check for getc_unlocked.
* modules/localcharset (Notice): Remove.
(Files): Remove config.charset, ref-add.sin, ref-del.sin, fcntl-o.m4,
glibc21.m4.
(Depends-on): Remove configmake.
(configure.ac): Define LOCALCHARSET_TESTS_ENVIRONMENT to empty.
(Makefile.am): Simplify.
* build-aux/prefix-gnulib-mk: Remove special code for the removed files.
2018-05-19 Bruno Haible <bruno@clisp.org>
localcharset: Add a manual test.

9
build-aux/prefix-gnulib-mk
View File

@@ -146,15 +146,6 @@ sub prefix ($)
s{^([\w.]+\s*\+?=)(.*)$}
{prefix_assignment($1, $2)}gem;
# These three guys escape all the other regular rules.
# Require the leading white space to avoid inserting the prefix
# on a line like this:
# charset_alias = $(DESTDIR)$(libdir)/charset.alias
# With $(libdir), it would be erroneous.
s{(\s)(charset\.alias|ref-add\.sed|ref-del\.sed)}{$1$prefix$2}g;
# Unfortunately, as a result we sometimes have lib/lib.
s{($prefix){2}}{$1}g;
# $(srcdir)/ is actually $(top_srcdir)/$prefix/.
# The trailing slash is required to avoid matching this rule:
# test '$(srcdir)' = . || rm -f $(top_builddir)/GNUmakefile

1
lib/.cvsignore
View File

@@ -1,7 +1,6 @@
.deps
Makefile
alloca.h
charset.alias
fnmatch.h
fts.h
getdate.c

540
lib/config.charset
View File

@@ -1,540 +0,0 @@
#! /bin/sh
# Output a system dependent table of character encoding aliases.
#
# Copyright (C) 2000-2004, 2006-2018 Free Software Foundation, Inc.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2, or (at your option)
# any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, see <https://www.gnu.org/licenses/>.
#
# The table consists of lines of the form
# ALIAS CANONICAL
#
# ALIAS is the (system dependent) result of "nl_langinfo (CODESET)".
# ALIAS is compared in a case sensitive way.
#
# CANONICAL is the GNU canonical name for this character encoding.
# It must be an encoding supported by libiconv. Support by GNU libc is
# also desirable. CANONICAL is case insensitive. Usually an upper case
# MIME charset name is preferred.
# The current list of GNU canonical charset names is as follows.
#
# name MIME? used by which systems
# (darwin = Mac OS X, woe32 = native Windows)
#
# ASCII, ANSI_X3.4-1968 glibc solaris freebsd netbsd darwin cygwin
# ISO-8859-1 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin
# ISO-8859-2 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin
# ISO-8859-3 Y glibc solaris cygwin
# ISO-8859-4 Y osf solaris freebsd netbsd openbsd darwin
# ISO-8859-5 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin
# ISO-8859-6 Y glibc aix hpux solaris cygwin
# ISO-8859-7 Y glibc aix hpux irix osf solaris netbsd openbsd darwin cygwin
# ISO-8859-8 Y glibc aix hpux osf solaris cygwin
# ISO-8859-9 Y glibc aix hpux irix osf solaris darwin cygwin
# ISO-8859-13 glibc netbsd openbsd darwin cygwin
# ISO-8859-14 glibc cygwin
# ISO-8859-15 glibc aix osf solaris freebsd netbsd openbsd darwin cygwin
# KOI8-R Y glibc solaris freebsd netbsd openbsd darwin
# KOI8-U Y glibc freebsd netbsd openbsd darwin cygwin
# KOI8-T glibc
# CP437 dos
# CP775 dos
# CP850 aix osf dos
# CP852 dos
# CP855 dos
# CP856 aix
# CP857 dos
# CP861 dos
# CP862 dos
# CP864 dos
# CP865 dos
# CP866 freebsd netbsd openbsd darwin dos
# CP869 dos
# CP874 woe32 dos
# CP922 aix
# CP932 aix cygwin woe32 dos
# CP943 aix
# CP949 osf darwin woe32 dos
# CP950 woe32 dos
# CP1046 aix
# CP1124 aix
# CP1125 dos
# CP1129 aix
# CP1131 darwin
# CP1250 woe32
# CP1251 glibc solaris netbsd openbsd darwin cygwin woe32
# CP1252 aix woe32
# CP1253 woe32
# CP1254 woe32
# CP1255 glibc woe32
# CP1256 woe32
# CP1257 woe32
# GB2312 Y glibc aix hpux irix solaris freebsd netbsd darwin
# EUC-JP Y glibc aix hpux irix osf solaris freebsd netbsd darwin
# EUC-KR Y glibc aix hpux irix osf solaris freebsd netbsd darwin cygwin
# EUC-TW glibc aix hpux irix osf solaris netbsd
# BIG5 Y glibc aix hpux osf solaris freebsd netbsd darwin cygwin
# BIG5-HKSCS glibc solaris darwin
# GBK glibc aix osf solaris darwin cygwin woe32 dos
# GB18030 glibc solaris netbsd darwin
# SHIFT_JIS Y hpux osf solaris freebsd netbsd darwin
# JOHAB glibc solaris woe32
# TIS-620 glibc aix hpux osf solaris cygwin
# VISCII Y glibc
# TCVN5712-1 glibc
# ARMSCII-8 glibc darwin
# GEORGIAN-PS glibc cygwin
# PT154 glibc
# HP-ROMAN8 hpux
# HP-ARABIC8 hpux
# HP-GREEK8 hpux
# HP-HEBREW8 hpux
# HP-TURKISH8 hpux
# HP-KANA8 hpux
# DEC-KANJI osf
# DEC-HANYU osf
# UTF-8 Y glibc aix hpux osf solaris netbsd darwin cygwin
#
# Note: Names which are not marked as being a MIME name should not be used in
# Internet protocols for information interchange (mail, news, etc.).
#
# Note: ASCII and ANSI_X3.4-1968 are synonymous canonical names. Applications
# must understand both names and treat them as equivalent.
#
# The first argument passed to this file is the canonical host specification,
# CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM
# or
# CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM
host="$1"
os=`echo "$host" | sed -e 's/^[^-]*-[^-]*-\(.*\)$/\1/'`
echo "# This file contains a table of character encoding aliases,"
echo "# suitable for operating system '${os}'."
echo "# It was automatically generated from config.charset."
# List of references, updated during installation:
echo "# Packages using this file: "
case "$os" in
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.
;;
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*)
# FreeBSD 4.2 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 "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*)
# 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

1037
lib/localcharset.c
View File

File diff suppressed because it is too large Load Diff

96
lib/localcharset.h
View File

@@ -25,12 +25,106 @@ extern "C" {
/* Determine the current locale's character encoding, and canonicalize it
into one of the canonical names listed in config.charset.
into one of the canonical names listed below.
The result must not be freed; it is statically allocated.
If the canonical name cannot be determined, the result is a non-canonical
name. */
extern const char * locale_charset (void);
/* About GNU canonical names for character encodings:
Every canonical name must be supported by GNU libiconv. Support by GNU libc
is also desirable.
The name is case insensitive. Usually an upper case MIME charset name is
preferred.
The current list of these GNU canonical names is:
name MIME? used by which systems
(darwin = Mac OS X, windows = native Windows)
ASCII, ANSI_X3.4-1968 glibc solaris freebsd netbsd darwin cygwin
ISO-8859-1 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin
ISO-8859-2 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin
ISO-8859-3 Y glibc solaris cygwin
ISO-8859-4 Y osf solaris freebsd netbsd openbsd darwin
ISO-8859-5 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin
ISO-8859-6 Y glibc aix hpux solaris cygwin
ISO-8859-7 Y glibc aix hpux irix osf solaris netbsd openbsd darwin cygwin
ISO-8859-8 Y glibc aix hpux osf solaris cygwin
ISO-8859-9 Y glibc aix hpux irix osf solaris darwin cygwin
ISO-8859-13 glibc netbsd openbsd darwin cygwin
ISO-8859-14 glibc cygwin
ISO-8859-15 glibc aix osf solaris freebsd netbsd openbsd darwin cygwin
KOI8-R Y glibc solaris freebsd netbsd openbsd darwin
KOI8-U Y glibc freebsd netbsd openbsd darwin cygwin
KOI8-T glibc
CP437 dos
CP775 dos
CP850 aix osf dos
CP852 dos
CP855 dos
CP856 aix
CP857 dos
CP861 dos
CP862 dos
CP864 dos
CP865 dos
CP866 freebsd netbsd openbsd darwin dos
CP869 dos
CP874 windows dos
CP922 aix
CP932 aix cygwin windows dos
CP943 aix
CP949 osf darwin windows dos
CP950 windows dos
CP1046 aix
CP1124 aix
CP1125 dos
CP1129 aix
CP1131 darwin
CP1250 windows
CP1251 glibc solaris netbsd openbsd darwin cygwin windows
CP1252 aix windows
CP1253 windows
CP1254 windows
CP1255 glibc windows
CP1256 windows
CP1257 windows
GB2312 Y glibc aix hpux irix solaris freebsd netbsd darwin
EUC-JP Y glibc aix hpux irix osf solaris freebsd netbsd darwin
EUC-KR Y glibc aix hpux irix osf solaris freebsd netbsd darwin cygwin
EUC-TW glibc aix hpux irix osf solaris netbsd
BIG5 Y glibc aix hpux osf solaris freebsd netbsd darwin cygwin
BIG5-HKSCS glibc solaris darwin
GBK glibc aix osf solaris darwin cygwin windows dos
GB18030 glibc solaris netbsd darwin
SHIFT_JIS Y hpux osf solaris freebsd netbsd darwin
JOHAB glibc solaris windows
TIS-620 glibc aix hpux osf solaris cygwin
VISCII Y glibc
TCVN5712-1 glibc
ARMSCII-8 glibc darwin
GEORGIAN-PS glibc cygwin
PT154 glibc
HP-ROMAN8 hpux
HP-ARABIC8 hpux
HP-GREEK8 hpux
HP-HEBREW8 hpux
HP-TURKISH8 hpux
HP-KANA8 hpux
DEC-KANJI osf
DEC-HANYU osf
UTF-8 Y glibc aix hpux osf solaris netbsd darwin cygwin
Note: Names which are not marked as being a MIME name should not be used in
Internet protocols for information interchange (mail, news, etc.).
Note: ASCII and ANSI_X3.4-1968 are synonymous canonical names. Applications
must understand both names and treat them as equivalent.
*/
#ifdef __cplusplus
}

29
lib/ref-add.sin
View File

@@ -1,29 +0,0 @@
# Add this package to a list of references stored in a text file.
#
# Copyright (C) 2000, 2009-2018 Free Software Foundation, Inc.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2, or (at your option)
# any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, see <https://www.gnu.org/licenses/>.
#
# Written by Bruno Haible <haible@clisp.cons.org>.
#
/^# Packages using this file: / {
s/# Packages using this file://
ta
:a
s/ @PACKAGE@ / @PACKAGE@ /
tb
s/ $/ @PACKAGE@ /
:b
s/^/# Packages using this file:/
}

24
lib/ref-del.sin
View File

@@ -1,24 +0,0 @@
# Remove this package from a list of references stored in a text file.
#
# Copyright (C) 2000, 2009-2018 Free Software Foundation, Inc.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2, or (at your option)
# any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, see <https://www.gnu.org/licenses/>.
#
# Written by Bruno Haible <haible@clisp.cons.org>.
#
/^# Packages using this file: / {
s/# Packages using this file://
s/ @PACKAGE@ / /
s/^/# Packages using this file:/
}

8
m4/localcharset.m4
View File

@@ -1,4 +1,4 @@
# localcharset.m4 serial 7
# localcharset.m4 serial 8
dnl Copyright (C) 2002, 2004, 2006, 2009-2018 Free Software Foundation, Inc.
dnl This file is free software; the Free Software Foundation
dnl gives unlimited permission to copy and/or distribute it,
@@ -8,10 +8,4 @@ AC_DEFUN([gl_LOCALCHARSET],
[
dnl Prerequisites of lib/localcharset.c.
AC_REQUIRE([AM_LANGINFO_CODESET])
AC_REQUIRE([gl_FCNTL_O_FLAGS])
AC_CHECK_DECLS_ONCE([getc_unlocked])
dnl Prerequisites of the lib/Makefile.am snippet.
AC_REQUIRE([AC_CANONICAL_HOST])
AC_REQUIRE([gl_GLIBC21])
])

83
modules/localcharset
View File

@@ -1,100 +1,23 @@
Description:
Return current locale's character encoding.
Notice:
If your package's tests make use of the locale_charset() function directly or
indirectly, you may need to define the CHARSETALIASDIR environment variable,
so that "make check" works before "make install". In Makefile.am syntax:
TESTS_ENVIRONMENT += @LOCALCHARSET_TESTS_ENVIRONMENT@
Files:
lib/localcharset.h
lib/localcharset.c
lib/config.charset
lib/ref-add.sin
lib/ref-del.sin
m4/codeset.m4
m4/fcntl-o.m4
m4/glibc21.m4
m4/localcharset.m4
Depends-on:
configmake
extensions
configure.ac:
gl_LOCALCHARSET
LOCALCHARSET_TESTS_ENVIRONMENT="CHARSETALIASDIR=\"\$(abs_top_builddir)/$gl_source_base\""
dnl For backward compatibility. Some packages still use this.
LOCALCHARSET_TESTS_ENVIRONMENT=
AC_SUBST([LOCALCHARSET_TESTS_ENVIRONMENT])
Makefile.am:
lib_SOURCES += localcharset.h localcharset.c
# We need the following in order to install a simple file in $(libdir)
# which is shared with other installed packages. We use a list of referencing
# packages so that "make uninstall" will remove the file if and only if it
# is not used by another installed package.
# On systems with glibc-2.1 or newer, the file is redundant, therefore we
# avoid installing it.
all-local: charset.alias ref-add.sed ref-del.sed
charset_alias = $(DESTDIR)$(libdir)/charset.alias
charset_tmp = $(DESTDIR)$(libdir)/charset.tmp
install-exec-local: install-exec-localcharset
install-exec-localcharset: all-local
if test $(GLIBC21) = no; then \
case '$(host_os)' in \
darwin[56]*) \
need_charset_alias=true ;; \
darwin* | cygwin* | mingw* | pw32* | cegcc*) \
need_charset_alias=false ;; \
*) \
need_charset_alias=true ;; \
esac ; \
else \
need_charset_alias=false ; \
fi ; \
if $$need_charset_alias; then \
$(mkinstalldirs) $(DESTDIR)$(libdir) ; \
fi ; \
if test -f $(charset_alias); then \
sed -f ref-add.sed $(charset_alias) > $(charset_tmp) ; \
$(INSTALL_DATA) $(charset_tmp) $(charset_alias) ; \
rm -f $(charset_tmp) ; \
else \
if $$need_charset_alias; then \
sed -f ref-add.sed charset.alias > $(charset_tmp) ; \
$(INSTALL_DATA) $(charset_tmp) $(charset_alias) ; \
rm -f $(charset_tmp) ; \
fi ; \
fi
uninstall-local: uninstall-localcharset
uninstall-localcharset: all-local
if test -f $(charset_alias); then \
sed -f ref-del.sed $(charset_alias) > $(charset_tmp); \
if grep '^# Packages using this file: $$' $(charset_tmp) \
> /dev/null; then \
rm -f $(charset_alias); \
else \
$(INSTALL_DATA) $(charset_tmp) $(charset_alias); \
fi; \
rm -f $(charset_tmp); \
fi
charset.alias: config.charset
$(AM_V_GEN)rm -f t-$@ $@ && \
$(SHELL) $(srcdir)/config.charset '$(host)' > t-$@ && \
mv t-$@ $@
SUFFIXES += .sed .sin
.sin.sed:
$(AM_V_GEN)rm -f t-$@ $@ && \
sed -e '/^#/d' -e 's/@''PACKAGE''@/$(PACKAGE)/g' $< > t-$@ && \
mv t-$@ $@
CLEANFILES += charset.alias ref-add.sed ref-del.sed
lib_SOURCES += localcharset.c
Include:
"localcharset.h"