[PATCH 0/6] Gettext poison rework

@@ -2398,7 +2398,8 @@ XGETTEXT_FLAGS_C = $(XGETTEXT_FLAGS) --language=C \
 XGETTEXT_FLAGS_SH = $(XGETTEXT_FLAGS) --language=Shell \
 	--keyword=gettextln --keyword=eval_gettextln
 XGETTEXT_FLAGS_PERL = $(XGETTEXT_FLAGS) --keyword=__ --language=Perl
-LOCALIZED_C := $(C_OBJ:o=c) $(LIB_H) $(GENERATED_H)
+C_OBJ_NOTESTS:= $(filter-out test-%,$(C_OBJ))
+LOCALIZED_C := $(C_OBJ_NOTESTS:o=c) $(LIB_H) $(GENERATED_H)
 LOCALIZED_SH := $(SCRIPT_SH)
 LOCALIZED_PERL := $(SCRIPT_PERL)
 

@@ -2409,7 +2409,7 @@ LOCALIZED_SH += t/t0200/test.sh
 LOCALIZED_PERL += t/t0200/test.perl
 endif
 
-po/git.pot: $(LOCALIZED_C)
+po/git.pot: $(LOCALIZED_C) $(LOCALIZED_SH) $(LOCALIZED_PERL)
 	$(QUIET_XGETTEXT)$(XGETTEXT) -o$@+ $(XGETTEXT_FLAGS_C) $(LOCALIZED_C)
 	$(QUIET_XGETTEXT)$(XGETTEXT) -o$@+ --join-existing $(XGETTEXT_FLAGS_SH) \
 		$(LOCALIZED_SH)

@@ -258,11 +258,6 @@ all::
 # Define HAVE_DEV_TTY if your system can open /dev/tty to interact with the
 # user.
 #
-# Define GETTEXT_POISON if you are debugging the choice of strings marked
-# for translation.  In a GETTEXT_POISON build, you can turn all strings marked
-# for translation into gibberish by setting the GIT_GETTEXT_POISON variable
-# (to any value) in your environment.
-#
 # Define JSMIN to point to JavaScript minifier that functions as
 # a filter to have gitweb.js minified.
 #

@@ -376,6 +371,8 @@ MSGFMT = msgfmt
 PTHREAD_LIBS = -lpthread
 PTHREAD_CFLAGS =
 GCOV = gcov
+PODEBUG = podebug
+PODEBUG_OPTS = --rewrite=unicode
 
 export TCL_PATH TCLTK_PATH
 

@@ -1594,9 +1591,6 @@ endif
 ifdef NO_SYMLINK_HEAD
 	BASIC_CFLAGS += -DNO_SYMLINK_HEAD
 endif
-ifdef GETTEXT_POISON
-	BASIC_CFLAGS += -DGETTEXT_POISON
-endif
 ifdef NO_GETTEXT
 	BASIC_CFLAGS += -DNO_GETTEXT
 	USE_GETTEXT_SCHEME ?= fallthrough

@@ -2403,19 +2397,28 @@ LOCALIZED_C := $(C_OBJ_NOTESTS:o=c) $(LIB_H) $(GENERATED_H)
 LOCALIZED_SH := $(SCRIPT_SH)
 LOCALIZED_PERL := $(SCRIPT_PERL)
 
-ifdef XGETTEXT_INCLUDE_TESTS
-LOCALIZED_C += t/t0200/test.c
-LOCALIZED_SH += t/t0200/test.sh
-LOCALIZED_PERL += t/t0200/test.perl
-endif
+LOCALIZED_C_TESTS += t/t0200/test.c $(TEST_OBJS:o=c)
+LOCALIZED_SH_TESTS += t/t0200/test.sh
+LOCALIZED_PERL_TESTS += t/t0200/test.perl
 
-po/git.pot: $(LOCALIZED_C) $(LOCALIZED_SH) $(LOCALIZED_PERL)
-	$(QUIET_XGETTEXT)$(XGETTEXT) -o$@+ $(XGETTEXT_FLAGS_C) $(LOCALIZED_C)
-	$(QUIET_XGETTEXT)$(XGETTEXT) -o$@+ --join-existing $(XGETTEXT_FLAGS_SH) \
+po/git.pot+: $(LOCALIZED_C) $(LOCALIZED_SH) $(LOCALIZED_PERL)
+	$(QUIET_XGETTEXT)$(XGETTEXT) -o$@ $(XGETTEXT_FLAGS_C) $(LOCALIZED_C)
+	$(QUIET_XGETTEXT)$(XGETTEXT) -o$@ --join-existing $(XGETTEXT_FLAGS_SH) \
 		$(LOCALIZED_SH)
-	$(QUIET_XGETTEXT)$(XGETTEXT) -o$@+ --join-existing $(XGETTEXT_FLAGS_PERL) \
+	$(QUIET_XGETTEXT)$(XGETTEXT) -o$@ --join-existing $(XGETTEXT_FLAGS_PERL) \
 		$(LOCALIZED_PERL)
-	mv $@+ $@
+
+po/git.pot: po/git.pot+
+	mv $< $@
+
+t/test.po: po/git.pot+ $(LOCALIZED_C_TESTS) $(LOCALIZED_SH_TESTS) $(LOCALIZED_PERL_TESTS)
+	cp $< $@t
+	$(QUIET_XGETTEXT)$(XGETTEXT) -o$@t --join-existing $(XGETTEXT_FLAGS_C) $(LOCALIZED_C_TESTS)
+	$(QUIET_XGETTEXT)$(XGETTEXT) -o$@t --join-existing $(XGETTEXT_FLAGS_SH) \
+		$(LOCALIZED_SH_TESTS)
+	$(QUIET_XGETTEXT)$(XGETTEXT) -o$@t --join-existing $(XGETTEXT_FLAGS_PERL) \
+		$(LOCALIZED_PERL_TESTS)
+	$(PODEBUG) $(PODEBUG_OPTS) $@t -o $@
 
 pot: po/git.pot
 

@@ -2429,6 +2432,11 @@ endif
 po/build/locale/%/LC_MESSAGES/git.mo: po/%.po
 	$(QUIET_MSGFMT)mkdir -p $(dir $@) && $(MSGFMT) -o $@ $<
 
+po/build/pseudo-locale/$(L)/LC_MESSAGES/git.mo: t/test.po
+	$(QUIET_MSGFMT)mkdir -p $(dir $@) && $(MSGFMT) -o $@ $<
+
+pseudo-locale: po/build/pseudo-locale/$(L)/LC_MESSAGES/git.mo
+
 FIND_SOURCE_FILES = ( git ls-files '*.[hcS]' 2>/dev/null || \
 			$(FIND) . \( -name .git -type d -prune \) \
 				-o \( -name '*.[hcS]' -type f -print \) )

@@ -2498,7 +2506,6 @@ ifdef GIT_TEST_CMP_USE_COPIED_CONTEXT
 	@echo GIT_TEST_CMP_USE_COPIED_CONTEXT=YesPlease >>$@
 endif
 	@echo NO_GETTEXT=\''$(subst ','\'',$(subst ','\'',$(NO_GETTEXT)))'\' >>$@
-	@echo GETTEXT_POISON=\''$(subst ','\'',$(subst ','\'',$(GETTEXT_POISON)))'\' >>$@
 ifdef GIT_PERF_REPEAT_COUNT
 	@echo GIT_PERF_REPEAT_COUNT=\''$(subst ','\'',$(subst ','\'',$(GIT_PERF_REPEAT_COUNT)))'\' >>$@
 endif

@@ -16,16 +16,6 @@
 #	endif
 #endif
 
-#ifdef GETTEXT_POISON
-int use_gettext_poison(void)
-{
-	static int poison_requested = -1;
-	if (poison_requested == -1)
-		poison_requested = getenv("GIT_GETTEXT_POISON") ? 1 : 0;
-	return poison_requested;
-}
-#endif
-
 #ifndef NO_GETTEXT
 static void init_gettext_charset(const char *domain)
 {

@@ -36,22 +36,14 @@ static inline void git_setup_gettext(void)
 }
 #endif
 
-#ifdef GETTEXT_POISON
-extern int use_gettext_poison(void);
-#else
-#define use_gettext_poison() 0
-#endif
-
 static inline FORMAT_PRESERVING(1) const char *_(const char *msgid)
 {
-	return use_gettext_poison() ? "# GETTEXT POISON #" : gettext(msgid);
+	return gettext(msgid);
 }
 
 static inline FORMAT_PRESERVING(1) FORMAT_PRESERVING(2)
 const char *Q_(const char *msgid, const char *plu, unsigned long n)
 {
-	if (use_gettext_poison())
-		return "# GETTEXT POISON #";
 	return ngettext(msgid, plu, n);
 }
 

@@ -24,9 +24,6 @@ then
 elif test -n "$GIT_INTERNAL_GETTEXT_TEST_FALLBACKS"
 then
 	: no probing necessary
-elif test -n "$GIT_GETTEXT_POISON"
-then
-	GIT_INTERNAL_GETTEXT_SH_SCHEME=poison
 elif type gettext.sh >/dev/null 2>&1
 then
 	# GNU libintl's gettext.sh

@@ -55,17 +52,6 @@ gettext_without_eval_gettext)
 		)
 	}
 	;;
-poison)
-	# Emit garbage so that tests that incorrectly rely on translatable
-	# strings will fail.
-	gettext () {
-		printf "%s" "# GETTEXT POISON #"
-	}
-
-	eval_gettext () {
-		printf "%s" "# GETTEXT POISON #"
-	}
-	;;
 *)
 	gettext () {
 		printf "%s" "$1"

@@ -1 +1,2 @@
 /build
+/git.pot+

@@ -270,16 +270,15 @@ something in the test suite might still depend on the US English
 version of the strings, e.g. to grep some error message or other
 output.
 
-To smoke out issues like these Git can be compiled with gettext poison
-support, at the top-level:
+To smoke out issues like these, we can use a podebug [1] utility
+to generate a pseudotranslation. At top level:
 
-    make GETTEXT_POISON=YesPlease
+    # Assume locale "vi_VN.UTF-8" is supported by system
+    make pseudo-locale L=vi
+    make GETTEXT_POISON=vi_VN.UTF-8 test
 
 That'll give you a git which emits gibberish on every call to
-gettext. It's obviously not meant to be installed, but you should run
-the test suite with it:
-
-    cd t && prove -j 9 ./t[0-9]*.sh
+gettext.
 
 If tests break with it you should inspect them manually and see if
 what you're translating is sane, i.e. that you're not translating

@@ -290,3 +289,5 @@ test_cmp calls with test_i18ncmp. If that's not enough you can skip
 the whole test by making it depend on the C_LOCALE_OUTPUT
 prerequisite. See existing test files with this prerequisite for
 examples.
+
+[1] http://translate.sourceforge.net/wiki/toolkit/podebug

@@ -1,3 +1,4 @@
 /trash directory*
 /test-results
 /.prove
+/test.po*

@@ -5,7 +5,12 @@
 
 . ./test-lib.sh
 
-GIT_TEXTDOMAINDIR="$GIT_BUILD_DIR/po/build/locale"
+if test -n "$GETTEXT_POISON"
+then
+	GIT_TEXTDOMAINDIR="$GIT_BUILD_DIR/po/build/pseudo-locale"
+else
+	GIT_TEXTDOMAINDIR="$GIT_BUILD_DIR/po/build/locale"
+fi
 GIT_PO_PATH="$GIT_BUILD_DIR/po"
 export GIT_TEXTDOMAINDIR GIT_PO_PATH
 

@@ -36,6 +36,7 @@ test_expect_success GETTEXT 'sanity: $TEXTDOMAINDIR exists without NO_GETTEXT=Ye
 '
 
 test_expect_success GETTEXT 'sanity: Icelandic locale was compiled' '
+    test -n "$GETTEXT_POISON" ||
     test -f "$TEXTDOMAINDIR/is/LC_MESSAGES/git.mo"
 '
 

@@ -1,36 +0,0 @@
-#!/bin/sh
-#
-# Copyright (c) 2010 Ævar Arnfjörð Bjarmason
-#
-
-test_description='Gettext Shell poison'
-
-. ./lib-gettext.sh
-
-test_expect_success GETTEXT_POISON "sanity: \$GIT_INTERNAL_GETTEXT_SH_SCHEME is set (to $GIT_INTERNAL_GETTEXT_SH_SCHEME)" '
-    test -n "$GIT_INTERNAL_GETTEXT_SH_SCHEME"
-'
-
-test_expect_success GETTEXT_POISON 'sanity: $GIT_INTERNAL_GETTEXT_SH_SCHEME" is poison' '
-    test "$GIT_INTERNAL_GETTEXT_SH_SCHEME" = "poison"
-'
-
-test_expect_success GETTEXT_POISON 'gettext: our gettext() fallback has poison semantics' '
-    printf "# GETTEXT POISON #" >expect &&
-    gettext "test" >actual &&
-    test_cmp expect actual &&
-    printf "# GETTEXT POISON #" >expect &&
-    gettext "test more words" >actual &&
-    test_cmp expect actual
-'
-
-test_expect_success GETTEXT_POISON 'eval_gettext: our eval_gettext() fallback has poison semantics' '
-    printf "# GETTEXT POISON #" >expect &&
-    eval_gettext "test" >actual &&
-    test_cmp expect actual &&
-    printf "# GETTEXT POISON #" >expect &&
-    eval_gettext "test more words" >actual &&
-    test_cmp expect actual
-'
-
-test_done

@@ -626,7 +626,7 @@ test -z "$NO_GETTEXT" && test_set_prereq GETTEXT
 # Can we rely on git's output in the C locale?
 if test -n "$GETTEXT_POISON"
 then
-	GIT_GETTEXT_POISON=YesPlease
+	GIT_GETTEXT_POISON=$GETTEXT_POISON
 	export GIT_GETTEXT_POISON
 	test_set_prereq GETTEXT_POISON
 else

@@ -15,7 +15,15 @@ else
 	export GIT_TEMPLATE_DIR
 fi
 GITPERLLIB='@@BUILD_DIR@@/perl/blib/lib'
-GIT_TEXTDOMAINDIR='@@BUILD_DIR@@/po/build/locale'
+if test -n "$GIT_GETTEXT_POISON"
+then
+	GIT_TEXTDOMAINDIR='@@BUILD_DIR@@/po/build/pseudo-locale'
+	LANG=$GIT_GETTEXT_POISON
+	unset LC_ALL
+	export LANG
+else
+	GIT_TEXTDOMAINDIR='@@BUILD_DIR@@/po/build/locale'
+fi
 PATH='@@BUILD_DIR@@/bin-wrappers:'"$PATH"
 export GIT_EXEC_PATH GITPERLLIB PATH GIT_TEXTDOMAINDIR
 

@@ -48,6 +48,7 @@ int main(int argc, char **argv)
 	struct timeval now;
 	const char *x;
 
+	git_setup_gettext();
 	x = getenv("TEST_DATE_NOW");
 	if (x) {
 		now.tv_sec = atoi(x);

@@ -22,6 +22,7 @@ int main(int argc, char *argv[])
 	void *from_buf, *data_buf, *out_buf;
 	unsigned long from_size, data_size, out_size;
 
+	git_setup_gettext();
 	if (argc != 5 || (strcmp(argv[1], "-d") && strcmp(argv[1], "-p"))) {
 		fprintf(stderr, "Usage: %s\n", usage_str);
 		return 1;

@@ -56,7 +56,10 @@ static int dump_cache_tree(struct cache_tree *it,
 
 int main(int ac, char **av)
 {
-	struct cache_tree *another = cache_tree();
+	struct cache_tree *another;
+
+	git_setup_gettext();
+	another = cache_tree();
 	if (read_cache() < 0)
 		die("unable to read index file");
 	cache_tree_update(another, active_cache, active_nr, WRITE_TREE_DRY_RUN);

@@ -5,6 +5,7 @@ int main(int argc, const char **argv)
 	struct cache_header hdr;
 	int version;
 
+	git_setup_gettext();
 	memset(&hdr,0,sizeof(hdr));
 	if (read(0, &hdr, sizeof(hdr)) != sizeof(hdr))
 		return 0;

@@ -6,6 +6,7 @@ int main(int ac, char **av)
 	unsigned char hash1[20], hash2[20], shifted[20];
 	struct tree *one, *two;
 
+	git_setup_gettext();
 	if (get_sha1(av[1], hash1))
 		die("cannot parse %s as an object name", av[1]);
 	if (get_sha1(av[2], hash2))

@@ -27,6 +27,7 @@ int main(int argc, const char **argv)
 	struct line *line, *p = NULL, *lines = NULL;
 	struct strbuf sb = STRBUF_INIT;
 
+	git_setup_gettext();
 	for (;;) {
 		if (strbuf_getwholeline(&sb, stdin, '\n'))
 			break;

@@ -81,6 +81,7 @@ int main(int argc, const char **argv)
 	};
 	int i;
 
+	git_setup_gettext();
 	argc = parse_options(argc, argv, prefix, options, usage, 0);
 
 	printf("boolean: %d\n", boolean);

@@ -2,6 +2,7 @@
 
 int main(int argc, char **argv)
 {
+	git_setup_gettext();
 	if (argc == 3 && !strcmp(argv[1], "normalize_path_copy")) {
 		char *buf = xmalloc(PATH_MAX + 1);
 		int rv = normalize_path_copy(buf, argv[2]);

@@ -47,6 +47,7 @@ static int run_revision_walk(void)
 
 int main(int argc, char **argv)
 {
+	git_setup_gettext();
 	if (argc < 2)
 		return 1;
 

@@ -6,7 +6,9 @@ static struct lock_file index_lock;
 
 int main(int ac, char **av)
 {
-	int fd = hold_locked_index(&index_lock, 1);
+	int fd;
+	git_setup_gettext();
+	fd = hold_locked_index(&index_lock, 1);
 	if (read_cache() < 0)
 		die("unable to read index file");
 	active_cache_tree = NULL;

@@ -7,6 +7,7 @@ int main(int ac, char **av)
 	unsigned bufsz = 8192;
 	char *buffer;
 
+	git_setup_gettext();
 	if (ac == 2)
 		bufsz = strtoul(av[1], NULL, 10) * 1024 * 1024;
 

@@ -6,6 +6,7 @@ int main(int argc, const char **argv)
 	struct child_process cp;
 	int nogit = 0;
 
+	git_setup_gettext();
 	setup_git_directory_gently(&nogit);
 	if (nogit)
 		die("No git repo found");

@@ -195,6 +195,7 @@
 /test-sigchain
 /test-subprocess
 /test-svn-fe
+/untranslated.log
 /common-cmds.h
 *.tar.gz
 *.dsc

@@ -17,6 +17,12 @@ fi
 GITPERLLIB='@@BUILD_DIR@@/perl/blib/lib'
 if test -n "$GIT_GETTEXT_POISON"
 then
+	if test -x /usr/lib/preloadable_libintl.so
+	then
+		GETTEXT_LOG_UNTRANSLATED=@@BUILD_DIR@@/untranslated.log
+		LD_PRELOAD="/usr/lib/preloadable_libintl.so $LD_PRELOAD"
+		export LD_PRELOAD GETTEXT_LOG_UNTRANSLATED
+	fi
 	GIT_TEXTDOMAINDIR='@@BUILD_DIR@@/po/build/pseudo-locale'
 	LANG=$GIT_GETTEXT_POISON
 	unset LC_ALL

@@ -33,50 +33,50 @@ int main(int argc, const char **argv)
 {
 	const char *prefix = "prefix/";
 	const char *usage[] = {
-		"test-parse-options <options>",
+		N_("test-parse-options <options>"),
 		NULL
 	};
 	struct option options[] = {
-		OPT_BOOL(0, "yes", &boolean, "get a boolean"),
-		OPT_BOOL('D', "no-doubt", &boolean, "begins with 'no-'"),
+		OPT_BOOL(0, "yes", &boolean, N_("get a boolean")),
+		OPT_BOOL('D', "no-doubt", &boolean, N_("begins with 'no-'")),
 		{ OPTION_SET_INT, 'B', "no-fear", &boolean, NULL,
-		  "be brave", PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 },
-		OPT_COUNTUP('b', "boolean", &boolean, "increment by one"),
+		  N_("be brave"), PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 },
+		OPT_COUNTUP('b', "boolean", &boolean, N_("increment by one")),
 		OPT_BIT('4', "or4", &boolean,
-			"bitwise-or boolean with ...0100", 4),
-		OPT_NEGBIT(0, "neg-or4", &boolean, "same as --no-or4", 4),
+			N_("bitwise-or boolean with ...0100"), 4),
+		OPT_NEGBIT(0, "neg-or4", &boolean, N_("same as --no-or4"), 4),
 		OPT_GROUP(""),
-		OPT_INTEGER('i', "integer", &integer, "get a integer"),
-		OPT_INTEGER('j', NULL, &integer, "get a integer, too"),
-		OPT_SET_INT(0, "set23", &integer, "set integer to 23", 23),
-		OPT_DATE('t', NULL, &timestamp, "get timestamp of <time>"),
-		OPT_CALLBACK('L', "length", &integer, "str",
-			"get length of <str>", length_callback),
-		OPT_FILENAME('F', "file", &file, "set file to <file>"),
-		OPT_GROUP("String options"),
-		OPT_STRING('s', "string", &string, "string", "get a string"),
-		OPT_STRING(0, "string2", &string, "str", "get another string"),
-		OPT_STRING(0, "st", &string, "st", "get another string (pervert ordering)"),
-		OPT_STRING('o', NULL, &string, "str", "get another string"),
+		OPT_INTEGER('i', "integer", &integer, N_("get a integer")),
+		OPT_INTEGER('j', NULL, &integer, N_("get a integer, too")),
+		OPT_SET_INT(0, "set23", &integer, N_("set integer to 23"), 23),
+		OPT_DATE('t', NULL, &timestamp, N_("get timestamp of <time>")),
+		OPT_CALLBACK('L', "length", &integer, N_("str"),
+			N_("get length of <str>"), length_callback),
+		OPT_FILENAME('F', "file", &file, N_("set file to <file>")),
+		OPT_GROUP(N_("String options")),
+		OPT_STRING('s', "string", &string, N_("string"), N_("get a string")),
+		OPT_STRING(0, "string2", &string, N_("str"), N_("get another string")),
+		OPT_STRING(0, "st", &string, N_("st"), N_("get another string (pervert ordering)")),
+		OPT_STRING('o', NULL, &string, N_("str"), N_("get another string")),
 		OPT_NOOP_NOARG(0, "obsolete"),
 		OPT_SET_PTR(0, "default-string", &string,
-			"set string to default", (unsigned long)"default"),
-		OPT_STRING_LIST(0, "list", &list, "str", "add str to list"),
-		OPT_GROUP("Magic arguments"),
-		OPT_ARGUMENT("quux", "means --quux"),
-		OPT_NUMBER_CALLBACK(&integer, "set integer to NUM",
+			N_("set string to default"), (unsigned long)"default"),
+		OPT_STRING_LIST(0, "list", &list, N_("str"), N_("add str to list")),
+		OPT_GROUP(N_("Magic arguments")),
+		OPT_ARGUMENT("quux", N_("means --quux")),
+		OPT_NUMBER_CALLBACK(&integer, N_("set integer to NUM"),
 			number_callback),
-		{ OPTION_COUNTUP, '+', NULL, &boolean, NULL, "same as -b",
+		{ OPTION_COUNTUP, '+', NULL, &boolean, NULL, N_("same as -b"),
 		  PARSE_OPT_NOARG | PARSE_OPT_NONEG | PARSE_OPT_NODASH },
 		{ OPTION_COUNTUP, 0, "ambiguous", &ambiguous, NULL,
-		  "positive ambiguity", PARSE_OPT_NOARG | PARSE_OPT_NONEG },
+		  N_("positive ambiguity"), PARSE_OPT_NOARG | PARSE_OPT_NONEG },
 		{ OPTION_COUNTUP, 0, "no-ambiguous", &ambiguous, NULL,
-		  "negative ambiguity", PARSE_OPT_NOARG | PARSE_OPT_NONEG },
-		OPT_GROUP("Standard options"),
+		  N_("negative ambiguity"), PARSE_OPT_NOARG | PARSE_OPT_NONEG },
+		OPT_GROUP(N_("Standard options")),
 		OPT__ABBREV(&abbrev),
-		OPT__VERBOSE(&verbose, "be verbose"),
-		OPT__DRY_RUN(&dry_run, "dry run"),
-		OPT__QUIET(&quiet, "be quiet"),
+		OPT__VERBOSE(&verbose, N_("be verbose")),
+		OPT__DRY_RUN(&dry_run, N_("dry run")),
+		OPT__QUIET(&quiet, N_("be quiet")),
 		OPT_END(),
 	};
 	int i;