Daiki Ueno wrote:
> KO Myung-Hun <kom...@gmail.com> writes:
>
>>> For example, it says:
>>>
>>> If the output character set is ommited from the LANG variable, the
>>> default codepage is ALWAYS taken from the operating system (e.g. the
>>> codepage setting from locale.alias is always ignored, so "russian"
>>> stays just for "ru_RU" and not for "ru_RU.ISO-8859-5"); you may want
>>> to set it just if you want to override the active OS/2 codepage.
>>
>> This patch does not change any behaviors of OS/2 port of gettext.
>> Because this patch embeds charset aliases into localcharset.c instead of
>> using charset.alias file, and fixes the problem a locale instead of a
>> charset if a charset is not specified is returned.
>
> Thanks for checking, looks safe then. One question is: where did you
> take the mapping data? I found this chart:
> http://www.borgendale.com/locale.htm
>
I used CODEPAGE and COUNTRY parts of OS/2 command references.
> I'm not sure how authoritative it is, but there are some differences
> from yours: ar_AA, bg_BG, lt_LT, lv_LV, and zh_CN.
>
Owing to you, I've found that I omitted ar_AA and comments for code page
lists. Thanks.
And the differences of others is because cp915, cp921 and cp1381 are not
supported by libiconv. In these cases, I picked up code pages from
config.charset.
Finally, I changed a code page for bg_BG from cp1251 to cp855 which is
etc code page.
--
KO Myung-Hun
Using Mozilla SeaMonkey 2.7.2
Under OS/2 Warp 4 for Korean with FixPak #15
In VirtualBox v4.1.32 on Intel Core i7-3615QM 2.30GHz with 8GB RAM
Korean OS/2 User Community : http://www.ecomstation.co.kr
From c300b50a741bc01352ffdbe71738af6741ee0a95 Mon Sep 17 00:00:00 2001
From: KO Myung-Hun <k...@chollian.net>
Date: Thu, 23 Feb 2012 22:37:21 +0900
Subject: [PATCH] Fix character encoding aliases for OS/2
On OS/2, a charset is not specified generally. For examples, set LANG
just to ko_KR for Korean. So charset-to-charset mapping is not useful
in thise case. Instead use locale-to-charset mapping.
And embed aliases to avoid the troubles finding a separate file like
Windows.
* lib/config.charset: Remove os2* from case "$os" in
* lib/localcharset.c (get_charset_aliases): Use embedded encoding
aliases on OS/2.
---
lib/config.charset | 4 +---
lib/localcharset.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 66 insertions(+), 4 deletions(-)
diff --git a/lib/config.charset b/lib/config.charset
index 4e4c7ed..3e6c88f 100644
--- a/lib/config.charset
+++ b/lib/config.charset
@@ -348,12 +348,10 @@ case "$os" in
#echo "sun_eu_greek ?" # what is this?
echo "UTF-8 UTF-8"
;;
- freebsd* | os2*)
+ 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.
- # 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
diff --git a/lib/localcharset.c b/lib/localcharset.c
index 1c17af0..3a4c87d 100644
--- a/lib/localcharset.c
+++ b/lib/localcharset.c
@@ -128,7 +128,7 @@ get_charset_aliases (void)
cp = charset_aliases;
if (cp == NULL)
{
-#if !(defined DARWIN7 || defined VMS || defined WINDOWS_NATIVE || defined
__CYGWIN__)
+#if !(defined DARWIN7 || defined VMS || defined WINDOWS_NATIVE || defined
__CYGWIN__ || defined OS2)
const char *dir;
const char *base = "charset.alias";
char *file_name;
@@ -342,6 +342,70 @@ get_charset_aliases (void)
"CP54936" "\0" "GB18030" "\0"
"CP65001" "\0" "UTF-8" "\0";
# endif
+# if defined OS2
+ /* 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. */
+
+ /* On OS/2, a charset is not specified generally. For examples, set LANG
+ just to ko_KR for Korean. So charset-to-charset mapping is not useful
+ in thise case. Instead use locale-to-charset mapping. */
+
+ /* Pri, Alt, Etc */
+ cp = "ar_AA" "\0" "CP864" "\0" /* 864, 850, 437 */
+ "bg_BG" "\0" "CP855" "\0" /* 915, 850, 855 */
+ "ca_ES" "\0" "CP850" "\0" /* */
+ "cs_SZ" "\0" "CP852" "\0" /* 852, 850 */
+ "da_DK" "\0" "CP850" "\0" /* 850, 865, 1004 */
+ "de_AT" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "de_CH" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "de_DE" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "el_GR" "\0" "CP869" "\0" /* 869, 850, 813 */
+ "en_AU" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "en_CA" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "en_GB" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "en_IE" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "en_NZ" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "en_US" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "en_ZA" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "es_ES" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "es_LA" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "et_EE" "\0" "CP922" "\0" /* 922, 850 */
+ "fi_FI" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "fr_BE" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "fr_CA" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "fr_CH" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "fr_FR" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "hr_HR" "\0" "CP852" "\0" /* 852, 850 */
+ "hu_HU" "\0" "CP852" "\0" /* 852, 850, 1004 */
+ "is_IS" "\0" "CP850" "\0" /* 850, 861, 1004 */
+ "it_CH" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "it_IT" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "iw_IL" "\0" "CP862" "\0" /* 862, 850, 437 */
+ "ja_JP" "\0" "CP943" "\0" /* 943, 850, 942 */
+ "ko_KR" "\0" "CP949" "\0" /* 949, 850, 944 */
+ "lt_LT" "\0" "ISO-8859-13" "\0" /* 921, 850 */
+ "lv_LV" "\0" "ISO-8859-13" "\0" /* 921, 850 */
+ "mk_MK" "\0" "CP855" "\0" /* 855, 850, 915 */
+ "nl_BE" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "nl_NL" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "no_NO" "\0" "CP850" "\0" /* 850, 865, 1004 */
+ "pl_PL" "\0" "CP852" "\0" /* 852, 850 */
+ "pt_BR" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "pt_PT" "\0" "CP850" "\0" /* 850, 860, 1004 */
+ "ro_RO" "\0" "CP852" "\0" /* 852, 850, 1004 */
+ "ru_RU" "\0" "CP866" "\0" /* 866, 850, 915 */
+ "sh_BA" "\0" "CP852" "\0" /* 852, 850 */
+ "sk_SK" "\0" "CP852" "\0" /* 852, 850 */
+ "sl_SI" "\0" "CP852" "\0" /* 852, 850 */
+ "sq_AL" "\0" "CP850" "\0" /* 850, 437 */
+ "sr_SP" "\0" "CP855" "\0" /* 855, 850, 915 */
+ "sv_SE" "\0" "CP850" "\0" /* 850, 437, 1004 */
+ "th_TH" "\0" "CP874" "\0" /* 874, 850 */
+ "tr_TR" "\0" "CP857" "\0" /* 857, 850, 1004 */
+ "zh_CN" "\0" "GB2312" "\0" /* 1381, 850, 946 */
+ "zh_TW" "\0" "CP950" "\0"; /* 950, 850, 948 */
+# endif
#endif
charset_aliases = cp;
--
1.8.5.2
