gettext.c 5.36 KB
Newer Older
1 2 3 4
/*
 * Copyright (c) 2010 Ævar Arnfjörð Bjarmason
 */

5
#include "cache.h"
6
#include "exec-cmd.h"
7
#include "gettext.h"
8 9
#include "strbuf.h"
#include "utf8.h"
10
#include "config.h"
11

12 13 14 15 16 17 18 19 20 21 22
#ifndef NO_GETTEXT
#	include <locale.h>
#	include <libintl.h>
#	ifdef HAVE_LIBCHARSET_H
#		include <libcharset.h>
#	else
#		include <langinfo.h>
#		define locale_charset() nl_langinfo(CODESET)
#	endif
#endif

23 24
static const char *charset;

25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
/*
 * Guess the user's preferred languages from the value in LANGUAGE environment
 * variable and LC_MESSAGES locale category if NO_GETTEXT is not defined.
 *
 * The result can be a colon-separated list like "ko:ja:en".
 */
const char *get_preferred_languages(void)
{
	const char *retval;

	retval = getenv("LANGUAGE");
	if (retval && *retval)
		return retval;

#ifndef NO_GETTEXT
	retval = setlocale(LC_MESSAGES, NULL);
	if (retval && *retval &&
		strcmp(retval, "C") &&
		strcmp(retval, "POSIX"))
		return retval;
#endif

	return NULL;
}

50 51 52
int use_gettext_poison(void)
{
	static int poison_requested = -1;
53 54 55 56
	if (poison_requested == -1) {
		const char *v = getenv("GIT_TEST_GETTEXT_POISON");
		poison_requested = v && strlen(v) ? 1 : 0;
	}
57 58
	return poison_requested;
}
59 60

#ifndef NO_GETTEXT
61 62 63 64 65 66 67 68 69 70 71
static int test_vsnprintf(const char *fmt, ...)
{
	char buf[26];
	int ret;
	va_list ap;
	va_start(ap, fmt);
	ret = vsnprintf(buf, sizeof(buf), fmt, ap);
	va_end(ap);
	return ret;
}

72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140
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

141
	   The vsnprintf bug has been fixed since glibc 2.17.
142 143 144 145 146 147 148 149 150 151 152 153 154

	   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);
155 156 157
	/* the string is taken from v0.99.6~1 */
	if (test_vsnprintf("%.*s", 13, "David_K\345gedal") < 0)
		setlocale(LC_CTYPE, "C");
158 159 160 161
}

void git_setup_gettext(void)
{
162
	const char *podir = getenv(GIT_TEXT_DOMAIN_DIR_ENVIRONMENT);
163
	char *p = NULL;
164 165

	if (!podir)
166
		podir = p = system_path(GIT_LOCALE_PATH);
167

168 169
	use_gettext_poison(); /* getenv() reentrancy paranoia */

170 171
	if (!is_directory(podir)) {
		free(p);
172
		return;
173
	}
174

175 176
	bindtextdomain("git", podir);
	setlocale(LC_MESSAGES, "");
Jeff King's avatar
Jeff King committed
177
	setlocale(LC_TIME, "");
178 179
	init_gettext_charset("git");
	textdomain("git");
180 181

	free(p);
182
}
183 184 185 186 187 188

/* return the number of columns of string 's' in current locale */
int gettext_width(const char *s)
{
	static int is_utf8 = -1;
	if (is_utf8 == -1)
189
		is_utf8 = is_utf8_locale();
190 191 192

	return is_utf8 ? utf8_strwidth(s) : strlen(s);
}
193
#endif
194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212

int is_utf8_locale(void)
{
#ifdef NO_GETTEXT
	if (!charset) {
		const char *env = getenv("LC_ALL");
		if (!env || !*env)
			env = getenv("LC_CTYPE");
		if (!env || !*env)
			env = getenv("LANG");
		if (!env)
			env = "";
		if (strchr(env, '.'))
			env = strchr(env, '.') + 1;
		charset = xstrdup(env);
	}
#endif
	return is_encoding_utf8(charset);
}