gettext.c

   1 /*
   2  * Copyright (c) 2010 Ævar Arnfjörð Bjarmason
   3  */
   4
   5 #include "git-compat-util.h"
   6 #include "gettext.h"
   7
   8 #ifndef NO_GETTEXT
   9 #       include <locale.h>
  10 #       include <libintl.h>
  11 #       ifdef HAVE_LIBCHARSET_H
  12 #               include <libcharset.h>
  13 #       else
  14 #               include <langinfo.h>
  15 #               define locale_charset() nl_langinfo(CODESET)
  16 #       endif
  17 #endif
  18
  19 #ifdef GETTEXT_POISON
  20 int use_gettext_poison(void)
  21 {
  22         static int poison_requested = -1;
  23         if (poison_requested == -1)
  24                 poison_requested = getenv("GIT_GETTEXT_POISON") ? 1 : 0;
  25         return poison_requested;
  26 }
  27 #endif
  28
  29 #ifndef NO_GETTEXT
  30 static void init_gettext_charset(const char *domain)
  31 {
  32         const char *charset;
  33
  34         /*
  35            This trick arranges for messages to be emitted in the user's
  36            requested encoding, but avoids setting LC_CTYPE from the
  37            environment for the whole program.
  38
  39            This primarily done to avoid a bug in vsnprintf in the GNU C
  40            Library [1]. which triggered a "your vsnprintf is broken" error
  41            on Git's own repository when inspecting v0.99.6~1 under a UTF-8
  42            locale.
  43
  44            That commit contains a ISO-8859-1 encoded author name, which
  45            the locale aware vsnprintf(3) won't interpolate in the format
  46            argument, due to mismatch between the data encoding and the
  47            locale.
  48
  49            Even if it wasn't for that bug we wouldn't want to use LC_CTYPE at
  50            this point, because it'd require auditing all the code that uses C
  51            functions whose semantics are modified by LC_CTYPE.
  52
  53            But only setting LC_MESSAGES as we do creates a problem, since
  54            we declare the encoding of our PO files[2] the gettext
  55            implementation will try to recode it to the user's locale, but
  56            without LC_CTYPE it'll emit something like this on 'git init'
  57            under the Icelandic locale:
  58
  59                Bj? til t?ma Git lind ? /hlagh/.git/
  60
  61            Gettext knows about the encoding of our PO file, but we haven't
  62            told it about the user's encoding, so all the non-US-ASCII
  63            characters get encoded to question marks.
  64
  65            But we're in luck! We can set LC_CTYPE from the environment
  66            only while we call nl_langinfo and
  67            bind_textdomain_codeset. That suffices to tell gettext what
  68            encoding it should emit in, so it'll now say:
  69
  70                Bjó til tóma Git lind í /hlagh/.git/
  71
  72            And the equivalent ISO-8859-1 string will be emitted under a
  73            ISO-8859-1 locale.
  74
  75            With this change way we get the advantages of setting LC_CTYPE
  76            (talk to the user in his language/encoding), without the major
  77            drawbacks (changed semantics for C functions we rely on).
  78
  79            However foreign functions using other message catalogs that
  80            aren't using our neat trick will still have a problem, e.g. if
  81            we have to call perror(3):
  82
  83            #include <stdio.h>
  84            #include <locale.h>
  85            #include <errno.h>
  86
  87            int main(void)
  88            {
  89                    setlocale(LC_MESSAGES, "");
  90                    setlocale(LC_CTYPE, "C");
  91                    errno = ENODEV;
  92                    perror("test");
  93                    return 0;
  94            }
  95
  96            Running that will give you a message with question marks:
  97
  98            $ LANGUAGE= LANG=de_DE.utf8 ./test
  99            test: Kein passendes Ger?t gefunden
 100
 101            In the long term we should probably see about getting that
 102            vsnprintf bug in glibc fixed, and audit our code so it won't
 103            fall apart under a non-C locale.
 104
 105            Then we could simply set LC_CTYPE from the environment, which would
 106            make things like the external perror(3) messages work.
 107
 108            See t/t0203-gettext-setlocale-sanity.sh's "gettext.c" tests for
 109            regression tests.
 110
 111            1. http://sourceware.org/bugzilla/show_bug.cgi?id=6530
 112            2. E.g. "Content-Type: text/plain; charset=UTF-8\n" in po/is.po
 113         */
 114         setlocale(LC_CTYPE, "");
 115         charset = locale_charset();
 116         bind_textdomain_codeset(domain, charset);
 117         setlocale(LC_CTYPE, "C");
 118 }
 119
 120 void git_setup_gettext(void)
 121 {
 122         const char *podir = getenv("GIT_TEXTDOMAINDIR");
 123
 124         if (!podir)
 125                 podir = GIT_LOCALE_PATH;
 126         bindtextdomain("git", podir);
 127         setlocale(LC_MESSAGES, "");
 128         init_gettext_charset("git");
 129         textdomain("git");
 130 }
 131 #endif