From 97fff70e80067444720f45e366008cf50fbf70cc Mon Sep 17 00:00:00 2001 From: Peter Verthez Date: Sun, 13 Oct 2002 14:18:46 +0000 Subject: [PATCH] Integration of libcharset into gedcom-parse. --- utf8/libcharset/.cvsignore | 1 + utf8/libcharset/config.charset | 466 +++++++++++++++++++++++++++++++++ utf8/libcharset/libcharset.h | 41 +++ utf8/libcharset/localcharset.c | 369 ++++++++++++++++++++++++++ utf8/libcharset/ref-add.sin | 31 +++ utf8/libcharset/ref-del.sin | 26 ++ 6 files changed, 934 insertions(+) create mode 100644 utf8/libcharset/.cvsignore create mode 100755 utf8/libcharset/config.charset create mode 100644 utf8/libcharset/libcharset.h create mode 100644 utf8/libcharset/localcharset.c create mode 100644 utf8/libcharset/ref-add.sin create mode 100644 utf8/libcharset/ref-del.sin diff --git a/utf8/libcharset/.cvsignore b/utf8/libcharset/.cvsignore new file mode 100644 index 0000000..70845e0 --- /dev/null +++ b/utf8/libcharset/.cvsignore @@ -0,0 +1 @@ +Makefile.in diff --git a/utf8/libcharset/config.charset b/utf8/libcharset/config.charset new file mode 100755 index 0000000..4f98b5b --- /dev/null +++ b/utf8/libcharset/config.charset @@ -0,0 +1,466 @@ +#! /bin/sh +# Output a system dependent table of character encoding aliases. +# +# Copyright (C) 2000-2002 Free Software Foundation, Inc. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU Library 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 +# Library General Public License for more details. +# +# You should have received a copy of the GNU Library General Public +# License along with this program; if not, write to the Free Software +# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, +# USA. +# +# 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 used by which systems a MIME name? +# ASCII, ANSI_X3.4-1968 glibc solaris freebsd +# ISO-8859-1 glibc aix hpux irix osf solaris freebsd yes +# ISO-8859-2 glibc aix hpux irix osf solaris freebsd yes +# ISO-8859-3 glibc solaris yes +# ISO-8859-4 osf solaris freebsd yes +# ISO-8859-5 glibc aix hpux irix osf solaris freebsd yes +# ISO-8859-6 glibc aix hpux solaris yes +# ISO-8859-7 glibc aix hpux irix osf solaris yes +# ISO-8859-8 glibc aix hpux osf solaris yes +# ISO-8859-9 glibc aix hpux irix osf solaris yes +# ISO-8859-13 glibc +# ISO-8859-14 glibc +# ISO-8859-15 glibc aix osf solaris freebsd +# KOI8-R glibc solaris freebsd yes +# KOI8-U glibc freebsd yes +# 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 dos +# CP869 dos +# CP874 woe32 dos +# CP922 aix +# CP932 aix woe32 dos +# CP943 aix +# CP949 osf woe32 dos +# CP950 woe32 dos +# CP1046 aix +# CP1124 aix +# CP1125 dos +# CP1129 aix +# CP1250 woe32 +# CP1251 glibc woe32 +# CP1252 aix woe32 +# CP1253 woe32 +# CP1254 woe32 +# CP1255 glibc woe32 +# CP1256 woe32 +# CP1257 woe32 +# GB2312 glibc aix hpux irix solaris freebsd yes +# EUC-JP glibc aix hpux irix osf solaris freebsd yes +# EUC-KR glibc aix hpux irix osf solaris freebsd yes +# EUC-TW glibc aix hpux irix osf solaris +# BIG5 glibc aix hpux osf solaris freebsd yes +# BIG5-HKSCS glibc solaris +# GBK glibc aix osf solaris woe32 dos +# GB18030 glibc solaris +# SHIFT_JIS hpux osf solaris freebsd yes +# JOHAB glibc solaris woe32 +# TIS-620 glibc aix hpux osf solaris +# VISCII glibc yes +# TCVN5712-1 glibc +# GEORGIAN-PS 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 glibc aix hpux osf solaris yes +# +# 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. + # 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 "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 "ISO8859-15 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" + ;; + beos*) + # BeOS has 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 " + echo "# and Bruno Haible ." + 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_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/utf8/libcharset/libcharset.h b/utf8/libcharset/libcharset.h new file mode 100644 index 0000000..9ca9573 --- /dev/null +++ b/utf8/libcharset/libcharset.h @@ -0,0 +1,41 @@ +/* Copyright (C) 2000-2001 Free Software Foundation, Inc. + This file is part of the GNU CHARSET Library. + + The GNU CHARSET Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Library General Public License as + published by the Free Software Foundation; either version 2 of the + License, or (at your option) any later version. + + The GNU CHARSET Library 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 + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public License + along with the GNU CHARSET Library; see the file COPYING.LIB. If not, + write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, + Boston, MA 02111-1307, USA. */ + +#ifndef _LIBCHARSET_H +#define _LIBCHARSET_H + + +#ifdef __cplusplus +extern "C" { +#endif + + +/* Determine the current locale's character encoding, and canonicalize it + into one of the canonical names listed in config.charset. + 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); + + +#ifdef __cplusplus +} +#endif + + +#endif /* _LIBCHARSET_H */ diff --git a/utf8/libcharset/localcharset.c b/utf8/libcharset/localcharset.c new file mode 100644 index 0000000..2b1564e --- /dev/null +++ b/utf8/libcharset/localcharset.c @@ -0,0 +1,369 @@ +/* Determine a canonical name for the current locale's character encoding. + + Copyright (C) 2000-2002 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify it + under the terms of the GNU Library 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 + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public + License along with this program; if not, write to the Free Software + Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, + USA. */ + +/* Written by Bruno Haible . */ + +#ifdef HAVE_CONFIG_H +# include +#endif + +#if HAVE_STDDEF_H +# include +#endif + +#include +#if HAVE_STRING_H +# include +#else +# include +#endif +#if HAVE_STDLIB_H +# include +#endif + +#if defined _WIN32 || defined __WIN32__ +# undef WIN32 /* avoid warning on mingw32 */ +# define WIN32 +#endif + +#if defined __EMX__ +/* Assume EMX program runs on OS/2, even if compiled under DOS. */ +# define OS2 +#endif + +#if !defined WIN32 +# if HAVE_LANGINFO_CODESET +# include +# else +# if HAVE_SETLOCALE +# include +# endif +# endif +#elif defined WIN32 +# define WIN32_LEAN_AND_MEAN +# include +#endif +#if defined OS2 +# define INCL_DOS +# include +#endif + +#if defined _WIN32 || defined __WIN32__ || defined __EMX__ || defined __DJGPP__ + /* Win32, OS/2, DOS */ +# define ISSLASH(C) ((C) == '/' || (C) == '\\') +#endif + +#ifndef DIRECTORY_SEPARATOR +# define DIRECTORY_SEPARATOR '/' +#endif + +#ifndef ISSLASH +# define ISSLASH(C) ((C) == DIRECTORY_SEPARATOR) +#endif + +#ifdef HAVE_GETC_UNLOCKED +# undef getc +# define getc getc_unlocked +#endif + +#ifdef __cplusplus +/* When compiling with "gcc -x c++", produce a function with C linkage. */ +extern "C" const char * locale_charset (void); +#endif + +/* The following static variable is declared 'volatile' to avoid a + possible multithread problem in the function get_charset_aliases. If we + are running in a threaded environment, and if two threads initialize + 'charset_aliases' simultaneously, both will produce the same value, + and everything will be ok if the two assignments to 'charset_aliases' + are atomic. But I don't know what will happen if the two assignments mix. */ +#if __STDC__ != 1 +# define volatile /* empty */ +#endif +/* Pointer to the contents of the charset.alias file, if it has already been + read, else NULL. Its format is: + ALIAS_1 '\0' CANONICAL_1 '\0' ... ALIAS_n '\0' CANONICAL_n '\0' '\0' */ +static const char * volatile charset_aliases; + +/* Return a pointer to the contents of the charset.alias file. */ +static const char * +get_charset_aliases () +{ + const char *cp; + + cp = charset_aliases; + if (cp == NULL) + { +#if !defined WIN32 + FILE *fp; + const char *dir = LIBDIR; + const char *base = "charset.alias"; + char *file_name; + + /* 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); + } + } + + if (file_name == NULL || (fp = fopen (file_name, "r")) == NULL) + /* Out of memory or file not found, treat it as empty. */ + cp = ""; + else + { + /* Parse the file's contents. */ + int c; + char buf1[50+1]; + char buf2[50+1]; + char *res_ptr = NULL; + size_t res_size = 0; + size_t l1, l2; + + for (;;) + { + 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); + 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; + 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; + } + } + + if (file_name != NULL) + free (file_name); + +#else + + /* 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. */ + +# if defined WIN32 + cp = "CP936" "\0" "GBK" "\0" + "CP1361" "\0" "JOHAB" "\0" + "CP20127" "\0" "ASCII" "\0" + "CP20866" "\0" "KOI8-R" "\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"; +# endif +#endif + + charset_aliases = cp; + } + + return cp; +} + +/* Determine the current locale's character encoding, and canonicalize it + into one of the canonical names listed in config.charset. + The result must not be freed; it is statically allocated. + If the canonical name cannot be determined, the result is a non-canonical + name. */ + +#ifdef STATIC +STATIC +#endif +const char * +locale_charset () +{ + const char *codeset; + const char *aliases; + +#if !(defined WIN32 || defined OS2) + +# if HAVE_LANGINFO_CODESET + + /* Most systems support nl_langinfo (CODESET) nowadays. */ + codeset = nl_langinfo (CODESET); + +# else + + /* On old systems which lack it, use setlocale or getenv. */ + const char *locale = NULL; + + /* But most old systems don't have a complete set of locales. Some + (like SunOS 4 or DJGPP) have only the C locale. Therefore we don't + use setlocale here; it would return "C" when it doesn't support the + locale name the user has set. */ +# if HAVE_SETLOCALE && 0 + locale = setlocale (LC_CTYPE, NULL); +# endif + if (locale == NULL || locale[0] == '\0') + { + locale = getenv ("LC_ALL"); + if (locale == NULL || locale[0] == '\0') + { + 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, + you set it to "language_COUNTRY.charset". In any case, we resolve it + through the charset.alias file. */ + codeset = locale; + +# endif + +#elif defined WIN32 + + static char buf[2 + 10 + 1]; + + /* Woe32 has a function returning the locale's codepage as a number. */ + sprintf (buf, "CP%u", GetACP ()); + codeset = buf; + +#elif defined OS2 + + const char *locale; + static char buf[2 + 10 + 1]; + ULONG cp[3]; + ULONG cplen; + + /* Allow user to override the codeset, as set in the operating system, + with standard language environment variables. */ + locale = getenv ("LC_ALL"); + if (locale == NULL || locale[0] == '\0') + { + 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 (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; + } + } + + /* Resolve through the charset.alias file. */ + codeset = locale; + } + else + { + /* OS/2 has a function returning the locale's codepage as a number. */ + if (DosQueryCp (sizeof (cp), cp, &cplen)) + codeset = ""; + else + { + sprintf (buf, "CP%u", cp[0]); + codeset = buf; + } + } + +#endif + + if (codeset == NULL) + /* The canonical name cannot be determined. */ + codeset = ""; + + /* Resolve alias. */ + for (aliases = get_charset_aliases (); + *aliases != '\0'; + aliases += strlen (aliases) + 1, aliases += strlen (aliases) + 1) + if (strcmp (codeset, aliases) == 0 + || (aliases[0] == '*' && aliases[1] == '\0')) + { + codeset = aliases + strlen (aliases) + 1; + break; + } + + /* Don't return an empty string. GNU libc and GNU libiconv interpret + the empty string as denoting "the locale's character encoding", + thus GNU libiconv would call this function a second time. */ + if (codeset[0] == '\0') + codeset = "ASCII"; + + return codeset; +} diff --git a/utf8/libcharset/ref-add.sin b/utf8/libcharset/ref-add.sin new file mode 100644 index 0000000..8986029 --- /dev/null +++ b/utf8/libcharset/ref-add.sin @@ -0,0 +1,31 @@ +# Add this package to a list of references stored in a text file. +# +# Copyright (C) 2000 Free Software Foundation, Inc. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU Library 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 +# Library General Public License for more details. +# +# You should have received a copy of the GNU Library General Public +# License along with this program; if not, write to the Free Software +# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, +# USA. +# +# Written by Bruno Haible . +# +/^# Packages using this file: / { + s/# Packages using this file:// + ta + :a + s/ @PACKAGE@ / @PACKAGE@ / + tb + s/ $/ @PACKAGE@ / + :b + s/^/# Packages using this file:/ +} diff --git a/utf8/libcharset/ref-del.sin b/utf8/libcharset/ref-del.sin new file mode 100644 index 0000000..3a55797 --- /dev/null +++ b/utf8/libcharset/ref-del.sin @@ -0,0 +1,26 @@ +# Remove this package from a list of references stored in a text file. +# +# Copyright (C) 2000 Free Software Foundation, Inc. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU Library 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 +# Library General Public License for more details. +# +# You should have received a copy of the GNU Library General Public +# License along with this program; if not, write to the Free Software +# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, +# USA. +# +# Written by Bruno Haible . +# +/^# Packages using this file: / { + s/# Packages using this file:// + s/ @PACKAGE@ / / + s/^/# Packages using this file:/ +} -- 2.30.2