Merge branch 'jk/archive-tar-filter'

* jk/archive-tar-filter:
  upload-archive: allow user to turn off filters
  archive: provide builtin .tar.gz filter
  archive: implement configurable tar filters
  archive: refactor file extension format-guessing
  archive: move file extension format-guessing lower
  archive: pass archiver struct to write_archive callback
  archive: refactor list of archive formats
  archive-tar: don't reload default config options
  archive: reorder option parsing and config reading

Documentation/git-archive.txt

@@ -101,6 +101,25 @@ tar.umask::
 	details.  If `--remote` is used then only the configuration of
 	the remote repository takes effect.
 
+tar.<format>.command::
+	This variable specifies a shell command through which the tar
+	output generated by `git archive` should be piped. The command
+	is executed using the shell with the generated tar file on its
+	standard input, and should produce the final output on its
+	standard output. Any compression-level options will be passed
+	to the command (e.g., "-9"). An output file with the same
+	extension as `<format>` will be use this format if no other
+	format is given.
++
+The "tar.gz" and "tgz" formats are defined automatically and default to
+`gzip -cn`. You may override them with custom commands.
+
+tar.<format>.remote::
+	If true, enable `<format>` for use by remote clients via
+	linkgit:git-upload-archive[1]. Defaults to false for
+	user-defined formats, but true for the "tar.gz" and "tgz"
+	formats.
+
 ATTRIBUTES
 ----------
 
@@ -133,6 +152,14 @@ git archive --format=tar --prefix=git-1.4.0/ v1.4.0 | gzip >git-1.4.0.tar.gz::
 
 	Create a compressed tarball for v1.4.0 release.
 
+git archive --format=tar.gz --prefix=git-1.4.0/ v1.4.0 >git-1.4.0.tar.gz::
+
+	Same as above, but using the builtin tar.gz handling.
+
+git archive --prefix=git-1.4.0/ -o git-1.4.0.tar.gz v1.4.0::
+
+	Same as above, but the format is inferred from the output file.
+
 git archive --format=tar --prefix=git-1.4.0/ v1.4.0{caret}\{tree\} | gzip >git-1.4.0.tar.gz::
 
 	Create a compressed tarball for v1.4.0 release, but without a
@@ -149,6 +176,12 @@ git archive -o latest.zip HEAD::
 	commit on the current branch. Note that the output format is
 	inferred by the extension of the output file.
 
+git config tar.tar.xz.command "xz -c"::
+
+	Configure a "tar.xz" format for making LZMA-compressed tarfiles.
+	You can use it specifying `--format=tar.xz`, or by creating an
+	output file like `-o foo.tar.xz`.
+
 
 SEE ALSO
 --------

archive-tar.c

@@ -4,6 +4,7 @@
 #include "cache.h"
 #include "tar.h"
 #include "archive.h"
+#include "run-command.h"
 
 #define RECORDSIZE	(512)
 #define BLOCKSIZE	(RECORDSIZE * 20)
@@ -13,6 +14,9 @@ static unsigned long offset;
 
 static int tar_umask = 002;
 
+static int write_tar_filter_archive(const struct archiver *ar,
+				    struct archiver_args *args);
+
 /* writes out the whole block, but only if it is full */
 static void write_if_needed(void)
 {
@@ -220,6 +224,67 @@ static int write_global_extended_header(struct archiver_args *args)
 	return err;
 }
 
+static struct archiver **tar_filters;
+static int nr_tar_filters;
+static int alloc_tar_filters;
+
+static struct archiver *find_tar_filter(const char *name, int len)
+{
+	int i;
+	for (i = 0; i < nr_tar_filters; i++) {
+		struct archiver *ar = tar_filters[i];
+		if (!strncmp(ar->name, name, len) && !ar->name[len])
+			return ar;
+	}
+	return NULL;
+}
+
+static int tar_filter_config(const char *var, const char *value, void *data)
+{
+	struct archiver *ar;
+	const char *dot;
+	const char *name;
+	const char *type;
+	int namelen;
+
+	if (prefixcmp(var, "tar."))
+		return 0;
+	dot = strrchr(var, '.');
+	if (dot == var + 9)
+		return 0;
+
+	name = var + 4;
+	namelen = dot - name;
+	type = dot + 1;
+
+	ar = find_tar_filter(name, namelen);
+	if (!ar) {
+		ar = xcalloc(1, sizeof(*ar));
+		ar->name = xmemdupz(name, namelen);
+		ar->write_archive = write_tar_filter_archive;
+		ar->flags = ARCHIVER_WANT_COMPRESSION_LEVELS;
+		ALLOC_GROW(tar_filters, nr_tar_filters + 1, alloc_tar_filters);
+		tar_filters[nr_tar_filters++] = ar;
+	}
+
+	if (!strcmp(type, "command")) {
+		if (!value)
+			return config_error_nonbool(var);
+		free(ar->data);
+		ar->data = xstrdup(value);
+		return 0;
+	}
+	if (!strcmp(type, "remote")) {
+		if (git_config_bool(var, value))
+			ar->flags |= ARCHIVER_REMOTE;
+		else
+			ar->flags &= ~ARCHIVER_REMOTE;
+		return 0;
+	}
+
+	return 0;
+}
+
 static int git_tar_config(const char *var, const char *value, void *cb)
 {
 	if (!strcmp(var, "tar.umask")) {
@@ -231,15 +296,15 @@ static int git_tar_config(const char *var, const char *value, void *cb)
 		}
 		return 0;
 	}
-	return git_default_config(var, value, cb);
+
+	return tar_filter_config(var, value, cb);
 }
 
-int write_tar_archive(struct archiver_args *args)
+static int write_tar_archive(const struct archiver *ar,
+			     struct archiver_args *args)
 {
 	int err = 0;
 
-	git_config(git_tar_config, NULL);
-
 	if (args->commit_sha1)
 		err = write_global_extended_header(args);
 	if (!err)
@@ -248,3 +313,65 @@ int write_tar_archive(struct archiver_args *args)
 		write_trailer();
 	return err;
 }
+
+static int write_tar_filter_archive(const struct archiver *ar,
+				    struct archiver_args *args)
+{
+	struct strbuf cmd = STRBUF_INIT;
+	struct child_process filter;
+	const char *argv[2];
+	int r;
+
+	if (!ar->data)
+		die("BUG: tar-filter archiver called with no filter defined");
+
+	strbuf_addstr(&cmd, ar->data);
+	if (args->compression_level >= 0)
+		strbuf_addf(&cmd, " -%d", args->compression_level);
+
+	memset(&filter, 0, sizeof(filter));
+	argv[0] = cmd.buf;
+	argv[1] = NULL;
+	filter.argv = argv;
+	filter.use_shell = 1;
+	filter.in = -1;
+
+	if (start_command(&filter) < 0)
+		die_errno("unable to start '%s' filter", argv[0]);
+	close(1);
+	if (dup2(filter.in, 1) < 0)
+		die_errno("unable to redirect descriptor");
+	close(filter.in);
+
+	r = write_tar_archive(ar, args);
+
+	close(1);
+	if (finish_command(&filter) != 0)
+		die("'%s' filter reported error", argv[0]);
+
+	strbuf_release(&cmd);
+	return r;
+}
+
+static struct archiver tar_archiver = {
+	"tar",
+	write_tar_archive,
+	ARCHIVER_REMOTE
+};
+
+void init_tar_archiver(void)
+{
+	int i;
+	register_archiver(&tar_archiver);
+
+	tar_filter_config("tar.tgz.command", "gzip -cn", NULL);
+	tar_filter_config("tar.tgz.remote", "true", NULL);
+	tar_filter_config("tar.tar.gz.command", "gzip -cn", NULL);
+	tar_filter_config("tar.tar.gz.remote", "true", NULL);
+	git_config(git_tar_config, NULL);
+	for (i = 0; i < nr_tar_filters; i++) {
+		/* omit any filters that never had a command configured */
+		if (tar_filters[i]->data)
+			register_archiver(tar_filters[i]);
+	}
+}

archive-zip.c

@@ -261,7 +261,8 @@ static void dos_time(time_t *time, int *dos_date, int *dos_time)
 	*dos_time = t->tm_sec / 2 + t->tm_min * 32 + t->tm_hour * 2048;
 }
 
-int write_zip_archive(struct archiver_args *args)
+static int write_zip_archive(const struct archiver *ar,
+			     struct archiver_args *args)
 {
 	int err;
 
@@ -278,3 +279,14 @@ int write_zip_archive(struct archiver_args *args)
 
 	return err;
 }
+
+static struct archiver zip_archiver = {
+	"zip",
+	write_zip_archive,
+	ARCHIVER_WANT_COMPRESSION_LEVELS|ARCHIVER_REMOTE
+};
+
+void init_zip_archiver(void)
+{
+	register_archiver(&zip_archiver);
+}

archive.c

@@ -14,16 +14,15 @@ static char const * const archive_usage[] = {
 	NULL
 };
 
-#define USES_ZLIB_COMPRESSION 1
-
-static const struct archiver {
-	const char *name;
-	write_archive_fn_t write_archive;
-	unsigned int flags;
-} archivers[] = {
-	{ "tar", write_tar_archive },
-	{ "zip", write_zip_archive, USES_ZLIB_COMPRESSION },
-};
+static const struct archiver **archivers;
+static int nr_archivers;
+static int alloc_archivers;
+
+void register_archiver(struct archiver *ar)
+{
+	ALLOC_GROW(archivers, nr_archivers + 1, alloc_archivers);
+	archivers[nr_archivers++] = ar;
+}
 
 static void format_subst(const struct commit *commit,
                          const char *src, size_t len,
@@ -208,9 +207,9 @@ static const struct archiver *lookup_archiver(const char *name)
 	if (!name)
 		return NULL;
 
-	for (i = 0; i < ARRAY_SIZE(archivers); i++) {
-		if (!strcmp(name, archivers[i].name))
-			return &archivers[i];
+	for (i = 0; i < nr_archivers; i++) {
+		if (!strcmp(name, archivers[i]->name))
+			return archivers[i];
 	}
 	return NULL;
 }
@@ -299,9 +298,10 @@ static void parse_treeish_arg(const char **argv,
 	  PARSE_OPT_NOARG | PARSE_OPT_NONEG | PARSE_OPT_HIDDEN, NULL, (p) }
 
 static int parse_archive_args(int argc, const char **argv,
-		const struct archiver **ar, struct archiver_args *args)
+		const struct archiver **ar, struct archiver_args *args,
+		const char *name_hint, int is_remote)
 {
-	const char *format = "tar";
+	const char *format = NULL;
 	const char *base = NULL;
 	const char *remote = NULL;
 	const char *exec = NULL;
@@ -355,21 +355,27 @@ static int parse_archive_args(int argc, const char **argv,
 		base = "";
 
 	if (list) {
-		for (i = 0; i < ARRAY_SIZE(archivers); i++)
-			printf("%s\n", archivers[i].name);
+		for (i = 0; i < nr_archivers; i++)
+			if (!is_remote || archivers[i]->flags & ARCHIVER_REMOTE)
+				printf("%s\n", archivers[i]->name);
 		exit(0);
 	}
 
+	if (!format && name_hint)
+		format = archive_format_from_filename(name_hint);
+	if (!format)
+		format = "tar";
+
 	/* We need at least one parameter -- tree-ish */
 	if (argc < 1)
 		usage_with_options(archive_usage, opts);
 	*ar = lookup_archiver(format);
-	if (!*ar)
+	if (!*ar || (is_remote && !((*ar)->flags & ARCHIVER_REMOTE)))
 		die("Unknown archive format '%s'", format);
 
 	args->compression_level = Z_DEFAULT_COMPRESSION;
 	if (compression_level != -1) {
-		if ((*ar)->flags & USES_ZLIB_COMPRESSION)
+		if ((*ar)->flags & ARCHIVER_WANT_COMPRESSION_LEVELS)
 			args->compression_level = compression_level;
 		else {
 			die("Argument not supported for format '%s': -%d",
@@ -385,19 +391,55 @@ static int parse_archive_args(int argc, const char **argv,
 }
 
 int write_archive(int argc, const char **argv, const char *prefix,
-		int setup_prefix)
+		  int setup_prefix, const char *name_hint, int remote)
 {
+	int nongit = 0;
 	const struct archiver *ar = NULL;
 	struct archiver_args args;
 
-	argc = parse_archive_args(argc, argv, &ar, &args);
 	if (setup_prefix && prefix == NULL)
-		prefix = setup_git_directory();
+		prefix = setup_git_directory_gently(&nongit);
+
+	git_config(git_default_config, NULL);
+	init_tar_archiver();
+	init_zip_archiver();
+
+	argc = parse_archive_args(argc, argv, &ar, &args, name_hint, remote);
+	if (nongit) {
+		/*
+		 * We know this will die() with an error, so we could just
+		 * die ourselves; but its error message will be more specific
+		 * than what we could write here.
+		 */
+		setup_git_directory();
+	}
 
 	parse_treeish_arg(argv, &args, prefix);
 	parse_pathspec_arg(argv + 1, &args);
 
-	git_config(git_default_config, NULL);
+	return ar->write_archive(ar, &args);
+}
 
-	return ar->write_archive(&args);
+static int match_extension(const char *filename, const char *ext)
+{
+	int prefixlen = strlen(filename) - strlen(ext);
+
+	/*
+	 * We need 1 character for the '.', and 1 character to ensure that the
+	 * prefix is non-empty (k.e., we don't match .tar.gz with no actual
+	 * filename).
+	 */
+	if (prefixlen < 2 || filename[prefixlen-1] != '.')
+		return 0;
+	return !strcmp(filename + prefixlen, ext);
+}
+
+const char *archive_format_from_filename(const char *filename)
+{
+	int i;
+
+	for (i = 0; i < nr_archivers; i++)
+		if (match_extension(filename, archivers[i]->name))
+			return archivers[i]->name;
+	return NULL;
 }

archive.h

@@ -14,17 +14,24 @@ struct archiver_args {
 	int compression_level;
 };
 
-typedef int (*write_archive_fn_t)(struct archiver_args *);
+#define ARCHIVER_WANT_COMPRESSION_LEVELS 1
+#define ARCHIVER_REMOTE 2
+struct archiver {
+	const char *name;
+	int (*write_archive)(const struct archiver *, struct archiver_args *);
+	unsigned flags;
+	void *data;
+};
+extern void register_archiver(struct archiver *);
 
-typedef int (*write_archive_entry_fn_t)(struct archiver_args *args, const unsigned char *sha1, const char *path, size_t pathlen, unsigned int mode, void *buffer, unsigned long size);
+extern void init_tar_archiver(void);
+extern void init_zip_archiver(void);
 
-/*
- * Archive-format specific backends.
- */
-extern int write_tar_archive(struct archiver_args *);
-extern int write_zip_archive(struct archiver_args *);
+typedef int (*write_archive_entry_fn_t)(struct archiver_args *args, const unsigned char *sha1, const char *path, size_t pathlen, unsigned int mode, void *buffer, unsigned long size);
 
 extern int write_archive_entries(struct archiver_args *args, write_archive_entry_fn_t write_entry);
-extern int write_archive(int argc, const char **argv, const char *prefix, int setup_prefix);
+extern int write_archive(int argc, const char **argv, const char *prefix, int setup_prefix, const char *name_hint, int remote);
+
+const char *archive_format_from_filename(const char *filename);
 
 #endif	/* ARCHIVE_H */

builtin/archive.c

@@ -24,7 +24,8 @@ static void create_output_file(const char *output_file)
 }
 
 static int run_remote_archiver(int argc, const char **argv,
-			       const char *remote, const char *exec)
+			       const char *remote, const char *exec,
+			       const char *name_hint)
 {
 	char buf[LARGE_PACKET_MAX];
 	int fd[2], i, len, rv;
@@ -37,6 +38,17 @@ static int run_remote_archiver(int argc, const char **argv,
 	transport = transport_get(_remote, _remote->url[0]);
 	transport_connect(transport, "git-upload-archive", exec, fd);
 
+	/*
+	 * Inject a fake --format field at the beginning of the
+	 * arguments, with the format inferred from our output
+	 * filename. This way explicit --format options can override
+	 * it.
+	 */
+	if (name_hint) {
+		const char *format = archive_format_from_filename(name_hint);
+		if (format)
+			packet_write(fd[1], "argument --format=%s\n", format);
+	}
 	for (i = 1; i < argc; i++)
 		packet_write(fd[1], "argument %s\n", argv[i]);
 	packet_flush(fd[1]);
@@ -63,17 +75,6 @@ static int run_remote_archiver(int argc, const char **argv,
 	return !!rv;
 }
 
-static const char *format_from_name(const char *filename)
-{
-	const char *ext = strrchr(filename, '.');
-	if (!ext)
-		return NULL;
-	ext++;
-	if (!strcasecmp(ext, "zip"))
-		return "--format=zip";
-	return NULL;
-}
-
 #define PARSE_OPT_KEEP_ALL ( PARSE_OPT_KEEP_DASHDASH | 	\
 			     PARSE_OPT_KEEP_ARGV0 | 	\
 			     PARSE_OPT_KEEP_UNKNOWN |	\
@@ -84,7 +85,6 @@ int cmd_archive(int argc, const char **argv, const char *prefix)
 	const char *exec = "git-upload-archive";
 	const char *output = NULL;
 	const char *remote = NULL;
-	const char *format_option = NULL;
 	struct option local_opts[] = {
 		OPT_STRING('o', "output", &output, "file",
 			"write the archive to this file"),
@@ -98,32 +98,13 @@ int cmd_archive(int argc, const char **argv, const char *prefix)
 	argc = parse_options(argc, argv, prefix, local_opts, NULL,
 			     PARSE_OPT_KEEP_ALL);
 
-	if (output) {
+	if (output)
 		create_output_file(output);
-		format_option = format_from_name(output);
-	}
-
-	/*
-	 * We have enough room in argv[] to muck it in place, because
-	 * --output must have been given on the original command line
-	 * if we get to this point, and parse_options() must have eaten
-	 * it, i.e. we can add back one element to the array.
-	 *
-	 * We add a fake --format option at the beginning, with the
-	 * format inferred from our output filename.  This way explicit
-	 * --format options can override it, and the fake option is
-	 * inserted before any "--" that might have been given.
-	 */
-	if (format_option) {
-		memmove(argv + 2, argv + 1, sizeof(*argv) * argc);
-		argv[1] = format_option;
-		argv[++argc] = NULL;
-	}
 
 	if (remote)
-		return run_remote_archiver(argc, argv, remote, exec);
+		return run_remote_archiver(argc, argv, remote, exec, output);
 
 	setvbuf(stderr, NULL, _IOLBF, BUFSIZ);
 
-	return write_archive(argc, argv, prefix, 1);
+	return write_archive(argc, argv, prefix, 1, output, 0);
 }

builtin/upload-archive.c

@@ -64,7 +64,7 @@ static int run_upload_archive(int argc, const char **argv, const char *prefix)
 	sent_argv[sent_argc] = NULL;
 
 	/* parse all options sent by the client */
-	return write_archive(sent_argc, sent_argv, prefix, 0);
+	return write_archive(sent_argc, sent_argv, prefix, 0, NULL, 1);
 }
 
 __attribute__((format (printf, 1, 2)))

t/t5000-tar-tree.sh

@@ -26,6 +26,8 @@ commit id embedding:
 
 . ./test-lib.sh
 UNZIP=${UNZIP:-unzip}
+GZIP=${GZIP:-gzip}
+GUNZIP=${GUNZIP:-gzip -d}
 
 SUBSTFORMAT=%H%n
 
@@ -252,4 +254,102 @@ test_expect_success 'git-archive --prefix=olde-' '
 	test -f h/olde-a/bin/sh
 '
 
+test_expect_success 'setup tar filters' '
+	git config tar.tar.foo.command "tr ab ba" &&
+	git config tar.bar.command "tr ab ba" &&
+	git config tar.bar.remote true
+'
+
+test_expect_success 'archive --list mentions user filter' '
+	git archive --list >output &&
+	grep "^tar\.foo\$" output &&
+	grep "^bar\$" output
+'
+
+test_expect_success 'archive --list shows only enabled remote filters' '
+	git archive --list --remote=. >output &&
+	! grep "^tar\.foo\$" output &&
+	grep "^bar\$" output
+'
+
+test_expect_success 'invoke tar filter by format' '
+	git archive --format=tar.foo HEAD >config.tar.foo &&
+	tr ab ba <config.tar.foo >config.tar &&
+	test_cmp b.tar config.tar &&
+	git archive --format=bar HEAD >config.bar &&
+	tr ab ba <config.bar >config.tar &&
+	test_cmp b.tar config.tar
+'
+
+test_expect_success 'invoke tar filter by extension' '
+	git archive -o config-implicit.tar.foo HEAD &&
+	test_cmp config.tar.foo config-implicit.tar.foo &&
+	git archive -o config-implicit.bar HEAD &&
+	test_cmp config.tar.foo config-implicit.bar
+'
+
+test_expect_success 'default output format remains tar' '
+	git archive -o config-implicit.baz HEAD &&
+	test_cmp b.tar config-implicit.baz
+'
+
+test_expect_success 'extension matching requires dot' '
+	git archive -o config-implicittar.foo HEAD &&
+	test_cmp b.tar config-implicittar.foo
+'
+
+test_expect_success 'only enabled filters are available remotely' '
+	test_must_fail git archive --remote=. --format=tar.foo HEAD \
+		>remote.tar.foo &&
+	git archive --remote=. --format=bar >remote.bar HEAD &&
+	test_cmp remote.bar config.bar
+'
+
+if $GZIP --version >/dev/null 2>&1; then
+	test_set_prereq GZIP
+else
+	say "Skipping some tar.gz tests because gzip not found"
+fi
+
+test_expect_success GZIP 'git archive --format=tgz' '
+	git archive --format=tgz HEAD >j.tgz
+'
+
+test_expect_success GZIP 'git archive --format=tar.gz' '
+	git archive --format=tar.gz HEAD >j1.tar.gz &&
+	test_cmp j.tgz j1.tar.gz
+'
+
+test_expect_success GZIP 'infer tgz from .tgz filename' '
+	git archive --output=j2.tgz HEAD &&
+	test_cmp j.tgz j2.tgz
+'
+
+test_expect_success GZIP 'infer tgz from .tar.gz filename' '
+	git archive --output=j3.tar.gz HEAD &&
+	test_cmp j.tgz j3.tar.gz
+'
+
+if $GUNZIP --version >/dev/null 2>&1; then
+	test_set_prereq GUNZIP
+else
+	say "Skipping some tar.gz tests because gunzip was not found"
+fi
+
+test_expect_success GZIP,GUNZIP 'extract tgz file' '
+	$GUNZIP -c <j.tgz >j.tar &&
+	test_cmp b.tar j.tar
+'
+
+test_expect_success GZIP 'remote tar.gz is allowed by default' '
+	git archive --remote=. --format=tar.gz HEAD >remote.tar.gz &&
+	test_cmp j.tgz remote.tar.gz
+'
+
+test_expect_success GZIP 'remote tar.gz can be disabled' '
+	git config tar.tar.gz.remote false &&
+	test_must_fail git archive --remote=. --format=tar.gz HEAD \
+		>remote.tar.gz
+'
+
 test_done