diff options
author | Junio C Hamano <gitster@pobox.com> | 2021-01-16 08:48:46 +0300 |
---|---|---|
committer | Junio C Hamano <gitster@pobox.com> | 2021-01-16 08:48:46 +0300 |
commit | cf2870addaa747b7038ebfa0b580e92f0affd2d6 (patch) | |
tree | c52e4364e7c708f14e99b5e61f9c74361ffd95a9 | |
parent | eecc5f0775ebbd454f92e1da02f83bc43b5f3703 (diff) | |
parent | 9371c0e9dd54717894e3dd19d36aba06190cb8a0 (diff) |
Merge branch 'ab/gettext-charset-comment-fix'
Comments update.
* ab/gettext-charset-comment-fix:
gettext.c: remove/reword a mostly-useless comment
Makefile: remove a warning about old GETTEXT_POISON flag
-rw-r--r-- | Makefile | 3 | ||||
-rw-r--r-- | gettext.c | 94 |
2 files changed, 15 insertions, 82 deletions
@@ -1554,9 +1554,6 @@ endif ifdef NO_SYMLINK_HEAD BASIC_CFLAGS += -DNO_SYMLINK_HEAD endif -ifdef GETTEXT_POISON -$(warning The GETTEXT_POISON option has been removed in favor of runtime GIT_TEST_GETTEXT_POISON. See t/README!) -endif ifdef NO_GETTEXT BASIC_CFLAGS += -DNO_GETTEXT USE_GETTEXT_SCHEME ?= fallthrough @@ -87,88 +87,24 @@ static int test_vsnprintf(const char *fmt, ...) static void init_gettext_charset(const char *domain) { - /* - This trick arranges for messages to be emitted in the user's - requested encoding, but avoids setting LC_CTYPE from the - environment for the whole program. - - This primarily done to avoid a bug in vsnprintf in the GNU C - Library [1]. which triggered a "your vsnprintf is broken" error - on Git's own repository when inspecting v0.99.6~1 under a UTF-8 - locale. - - That commit contains a ISO-8859-1 encoded author name, which - the locale aware vsnprintf(3) won't interpolate in the format - argument, due to mismatch between the data encoding and the - locale. - - Even if it wasn't for that bug we wouldn't want to use LC_CTYPE at - this point, because it'd require auditing all the code that uses C - functions whose semantics are modified by LC_CTYPE. - - But only setting LC_MESSAGES as we do creates a problem, since - we declare the encoding of our PO files[2] the gettext - implementation will try to recode it to the user's locale, but - without LC_CTYPE it'll emit something like this on 'git init' - under the Icelandic locale: - - Bj? til t?ma Git lind ? /hlagh/.git/ - - Gettext knows about the encoding of our PO file, but we haven't - told it about the user's encoding, so all the non-US-ASCII - characters get encoded to question marks. - - But we're in luck! We can set LC_CTYPE from the environment - only while we call nl_langinfo and - bind_textdomain_codeset. That suffices to tell gettext what - encoding it should emit in, so it'll now say: - - Bjó til tóma Git lind í /hlagh/.git/ - - And the equivalent ISO-8859-1 string will be emitted under a - ISO-8859-1 locale. - - With this change way we get the advantages of setting LC_CTYPE - (talk to the user in his language/encoding), without the major - drawbacks (changed semantics for C functions we rely on). - - However foreign functions using other message catalogs that - aren't using our neat trick will still have a problem, e.g. if - we have to call perror(3): - - #include <stdio.h> - #include <locale.h> - #include <errno.h> - - int main(void) - { - setlocale(LC_MESSAGES, ""); - setlocale(LC_CTYPE, "C"); - errno = ENODEV; - perror("test"); - return 0; - } - - Running that will give you a message with question marks: - - $ LANGUAGE= LANG=de_DE.utf8 ./test - test: Kein passendes Ger?t gefunden - - The vsnprintf bug has been fixed since glibc 2.17. - - Then we could simply set LC_CTYPE from the environment, which would - make things like the external perror(3) messages work. - - See t/t0203-gettext-setlocale-sanity.sh's "gettext.c" tests for - regression tests. - - 1. http://sourceware.org/bugzilla/show_bug.cgi?id=6530 - 2. E.g. "Content-Type: text/plain; charset=UTF-8\n" in po/is.po - */ setlocale(LC_CTYPE, ""); charset = locale_charset(); bind_textdomain_codeset(domain, charset); - /* the string is taken from v0.99.6~1 */ + + /* + * Work around an old bug fixed in glibc 2.17 (released on + * 2012-12-24), at the cost of potentially making translated + * messages from external functions like perror() emitted in + * the wrong encoding. + * + * The bug affected e.g. git.git's own 7eb93c89651 ([PATCH] + * Simplify git script, 2005-09-07), which is the origin of + * the "David_K\345gedal" test string. + * + * See a much longer comment added to this file in 5e9637c6297 + * (i18n: add infrastructure for translating Git with gettext, + * 2011-11-18) for more details. + */ if (test_vsnprintf("%.*s", 13, "David_K\345gedal") < 0) setlocale(LC_CTYPE, "C"); } |