From 2321286298bf956a3fa8e91dd361b8cf4e81e6a0 Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Wed, 15 Jun 2011 18:31:28 -0400
Subject: archive: reorder option parsing and config reading

The archive command does three things during its
initialization phase:

  1. parse command-line options

  2. setup the git directory

  3. read config

During phase (1), if we see any options that do not require
a git directory (like "--list"), we handle them immediately
and exit, making it safe to abort step (2) if we are not in
a git directory.

Step (3) must come after step (2), since the git directory
may influence configuration.  However, this leaves no
possibility of configuration from step (3) impacting the
command-line options in step (1) (which is useful, for
example, for supporting user-configurable output formats).

Instead, let's reorder this to:

  1. setup the git directory, if it exists

  2. read config

  3. parse command-line options

  4. if we are not in a git repository, die

This should have the same external behavior, but puts
configuration before command-line parsing.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/archive.c b/archive.c
index 42f2d2f..2616676 100644
--- a/archive.c
+++ b/archive.c
@@ -387,17 +387,27 @@ 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 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);
+
+	argc = parse_archive_args(argc, argv, &ar, &args);
+	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(&args);
 }
-- 
cgit v0.10.2-6-g49f6


From 40e7629194c79e72009b5b8e98cce65921b0faf2 Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Tue, 21 Jun 2011 21:22:20 -0400
Subject: archive-tar: don't reload default config options

We load our own tar-specific config, and then chain to
git_default_config. This is pointless, as our caller should
already have loaded the default config. It also introduces a
needless inconsistency with the zip archiver, which does not
look at the config files at all (and therefore relies on the
caller to have loaded config).

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/archive-tar.c b/archive-tar.c
index cee06ce..1ab1a2c 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -231,7 +231,7 @@ static int git_tar_config(const char *var, const char *value, void *cb)
 		}
 		return 0;
 	}
-	return git_default_config(var, value, cb);
+	return 0;
 }
 
 int write_tar_archive(struct archiver_args *args)
-- 
cgit v0.10.2-6-g49f6


From 13e0f88d4aba326da9217c225d6ab5e642eb611d Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Tue, 21 Jun 2011 21:23:33 -0400
Subject: archive: refactor list of archive formats

Most of the tar and zip code was nicely split out into two
abstracted files which knew only about their specific
formats. The entry point to this code was a single "write
archive" function.

However, as these basic formats grow more complex (e.g., by
handling multiple file extensions and format names), a
static list of the entry point functions won't be enough.
Instead, let's provide a way for the tar and zip code to
tell the main archive code what they support by registering
archiver names and functions.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/archive-tar.c b/archive-tar.c
index 1ab1a2c..930375b 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -234,12 +234,10 @@ static int git_tar_config(const char *var, const char *value, void *cb)
 	return 0;
 }
 
-int write_tar_archive(struct archiver_args *args)
+static int write_tar_archive(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 +246,15 @@ int write_tar_archive(struct archiver_args *args)
 		write_trailer();
 	return err;
 }
+
+static struct archiver tar_archiver = {
+	"tar",
+	write_tar_archive,
+	0
+};
+
+void init_tar_archiver(void)
+{
+	register_archiver(&tar_archiver);
+	git_config(git_tar_config, NULL);
+}
diff --git a/archive-zip.c b/archive-zip.c
index cf28504..a776d83 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -261,7 +261,7 @@ 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(struct archiver_args *args)
 {
 	int err;
 
@@ -278,3 +278,14 @@ int write_zip_archive(struct archiver_args *args)
 
 	return err;
 }
+
+static struct archiver zip_archiver = {
+	"zip",
+	write_zip_archive,
+	ARCHIVER_WANT_COMPRESSION_LEVELS
+};
+
+void init_zip_archiver(void)
+{
+	register_archiver(&zip_archiver);
+}
diff --git a/archive.c b/archive.c
index 2616676..f0b4e85 100644
--- a/archive.c
+++ b/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;
 }
@@ -355,8 +354,8 @@ 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++)
+			printf("%s\n", archivers[i]->name);
 		exit(0);
 	}
 
@@ -369,7 +368,7 @@ static int parse_archive_args(int argc, const char **argv,
 
 	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",
@@ -395,6 +394,8 @@ int write_archive(int argc, const char **argv, const char *prefix,
 		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);
 	if (nongit) {
diff --git a/archive.h b/archive.h
index 038ac35..f39cede 100644
--- a/archive.h
+++ b/archive.h
@@ -14,15 +14,18 @@ struct archiver_args {
 	int compression_level;
 };
 
-typedef int (*write_archive_fn_t)(struct archiver_args *);
+#define ARCHIVER_WANT_COMPRESSION_LEVELS 1
+struct archiver {
+	const char *name;
+	int (*write_archive)(struct archiver_args *);
+	unsigned flags;
+};
+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);
-- 
cgit v0.10.2-6-g49f6


From 4d7c98986379b0ab93cbf9092b60dfb5ab1cee7c Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Tue, 21 Jun 2011 21:24:07 -0400
Subject: archive: pass archiver struct to write_archive callback

The current archivers are very static; when you are in the
write_tar_archive function, you know you are writing a tar.
However, to facilitate runtime-configurable archivers
that will share a common write function we need to tell the
function which archiver was used.

As a convenience, we also provide an opaque data pointer in
the archiver struct so that individual archivers can put
something useful there when they register themselves.
Technically they could just use the "name" field to look in
an internal map of names to data, but this is much simpler.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/archive-tar.c b/archive-tar.c
index 930375b..bed9a9b 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -234,7 +234,8 @@ static int git_tar_config(const char *var, const char *value, void *cb)
 	return 0;
 }
 
-static int write_tar_archive(struct archiver_args *args)
+static int write_tar_archive(const struct archiver *ar,
+			     struct archiver_args *args)
 {
 	int err = 0;
 
diff --git a/archive-zip.c b/archive-zip.c
index a776d83..42df660 100644
--- a/archive-zip.c
+++ b/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;
 }
 
-static int write_zip_archive(struct archiver_args *args)
+static int write_zip_archive(const struct archiver *ar,
+			     struct archiver_args *args)
 {
 	int err;
 
diff --git a/archive.c b/archive.c
index f0b4e85..a0a5beb 100644
--- a/archive.c
+++ b/archive.c
@@ -410,5 +410,5 @@ int write_archive(int argc, const char **argv, const char *prefix,
 	parse_treeish_arg(argv, &args, prefix);
 	parse_pathspec_arg(argv + 1, &args);
 
-	return ar->write_archive(&args);
+	return ar->write_archive(ar, &args);
 }
diff --git a/archive.h b/archive.h
index f39cede..b3cf219 100644
--- a/archive.h
+++ b/archive.h
@@ -17,8 +17,9 @@ struct archiver_args {
 #define ARCHIVER_WANT_COMPRESSION_LEVELS 1
 struct archiver {
 	const char *name;
-	int (*write_archive)(struct archiver_args *);
+	int (*write_archive)(const struct archiver *, struct archiver_args *);
 	unsigned flags;
+	void *data;
 };
 extern void register_archiver(struct archiver *);
 
-- 
cgit v0.10.2-6-g49f6


From 56baa61d011e9ed5199766fea89ea8c2c183f0ba Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Tue, 21 Jun 2011 21:24:48 -0400
Subject: archive: move file extension format-guessing lower

The process for guessing an archive output format based on
the filename is something like this:

  a. parse --output in cmd_archive; check the filename
     against a static set of mapping heuristics (right now
     it just matches ".zip" for zip files).

  b. if found, stick a fake "--format=zip" at the beginning
     of the arguments list (if the user did specify a
     --format manually, the later option will override our
     fake one)

  c. if it's a remote call, ship the arguments to the remote
     (including the fake), which will call write_archive on
     their end

  d. if it's local, ship the arguments to write_archive
     locally

There are two problems:

  1. The set of mappings is static and at too high a level.
     The write_archive level is going to check config for
     user-defined formats, some of which will specify
     extensions. We need to delay lookup until those are
     parsed, so we can match against them.

  2. For a remote archive call, our set of mappings (or
     formats) may not match the remote side's. This is OK in
     practice right now, because all versions of git
     understand "zip" and "tar". But as new formats are
     added, there is going to be a mismatch between what the
     client can do and what the remote server can do.

To fix (1), this patch refactors the location guessing to
happen at the write_archive level, instead of the
cmd_archive level. So instead of sticking a fake --format
field in the argv list, we actually pass a "name hint" down
the callchain; this hint is used at the appropriate time to
guess the format (if one hasn't been given already).

This patch leaves (2) unfixed. The name_hint is converted to
a "--format" option as before, and passed to the remote.
This means the local side's idea of how extensions map to
formats will take precedence.

Another option would be to pass the name hint to the remote
side and let the remote choose. This isn't a good idea for
two reasons:

  1. There's no room in the protocol for passing that
     information. We can pass a new argument, but older
     versions of git on the server will choke on it.

  2. Letting the remote side decide creates a silent
     inconsistency in user experience. Consider the case
     that the locally installed git knows about the "tar.gz"
     format, but a remote server doesn't.

     Running "git archive -o foo.tar.gz" will use the tar.gz
     format. If we use --remote, and the local side chooses
     the format, then we send "--format=tar.gz" to the
     remote, which will complain about the unknown format.
     But if we let the remote side choose the format, then
     it will realize that it doesn't know about "tar.gz" and
     output uncompressed tar without even issuing a warning.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/archive.c b/archive.c
index a0a5beb..7d0ca32 100644
--- a/archive.c
+++ b/archive.c
@@ -298,9 +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)
 {
-	const char *format = "tar";
+	const char *format = NULL;
 	const char *base = NULL;
 	const char *remote = NULL;
 	const char *exec = NULL;
@@ -359,6 +360,11 @@ static int parse_archive_args(int argc, const char **argv,
 		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);
@@ -384,7 +390,7 @@ 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 nongit = 0;
 	const struct archiver *ar = NULL;
@@ -397,7 +403,7 @@ int write_archive(int argc, const char **argv, const char *prefix,
 	init_tar_archiver();
 	init_zip_archiver();
 
-	argc = parse_archive_args(argc, argv, &ar, &args);
+	argc = parse_archive_args(argc, argv, &ar, &args, name_hint);
 	if (nongit) {
 		/*
 		 * We know this will die() with an error, so we could just
@@ -412,3 +418,14 @@ int write_archive(int argc, const char **argv, const char *prefix,
 
 	return ar->write_archive(ar, &args);
 }
+
+const char *archive_format_from_filename(const char *filename)
+{
+	const char *ext = strrchr(filename, '.');
+	if (!ext)
+		return NULL;
+	ext++;
+	if (!strcasecmp(ext, "zip"))
+		return "zip";
+	return NULL;
+}
diff --git a/archive.h b/archive.h
index b3cf219..202d528 100644
--- a/archive.h
+++ b/archive.h
@@ -29,6 +29,8 @@ extern void init_zip_archiver(void);
 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);
+
+const char *archive_format_from_filename(const char *filename);
 
 #endif	/* ARCHIVE_H */
diff --git a/builtin/archive.c b/builtin/archive.c
index b14eaba..2578cf5 100644
--- a/builtin/archive.c
+++ b/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);
 }
diff --git a/builtin/upload-archive.c b/builtin/upload-archive.c
index 73f788e..e6bb97d 100644
--- a/builtin/upload-archive.c
+++ b/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);
 }
 
 __attribute__((format (printf, 1, 2)))
-- 
cgit v0.10.2-6-g49f6


From 08716b3c11f4899c1be046eca735761b30ca686d Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Tue, 21 Jun 2011 21:25:25 -0400
Subject: archive: refactor file extension format-guessing

Git-archive will guess a format from the output filename if
no format is explicitly given.  The current function just
hardcodes "zip" to the zip format, and leaves everything
else NULL (which will default to tar). Since we are about
to add user-specified formats, we need to be more flexible.
The new rule is "if a filename ends with a dot and the name
of a format, it matches that format". For the existing "tar"
and "zip" formats, this is identical to the current
behavior. For new user-specified formats, this will do what
the user expects if they name their formats appropriately.

Because we will eventually start matching arbitrary
user-specified extensions that may include dots, the strrchr
search for the final dot is not sufficient. We need to do an
actual suffix match with each extension.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/archive.c b/archive.c
index 7d0ca32..41065a8 100644
--- a/archive.c
+++ b/archive.c
@@ -419,13 +419,26 @@ int write_archive(int argc, const char **argv, const char *prefix,
 	return ar->write_archive(ar, &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)
 {
-	const char *ext = strrchr(filename, '.');
-	if (!ext)
-		return NULL;
-	ext++;
-	if (!strcasecmp(ext, "zip"))
-		return "zip";
+	int i;
+
+	for (i = 0; i < nr_archivers; i++)
+		if (match_extension(filename, archivers[i]->name))
+			return archivers[i]->name;
 	return NULL;
 }
-- 
cgit v0.10.2-6-g49f6


From 767cf4579f0e34a3cfc6704d5c313842321dfafa Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Tue, 21 Jun 2011 21:26:31 -0400
Subject: archive: implement configurable tar filters

It's common to pipe the tar output produce by "git archive"
through gzip or some other compressor. Locally, this can
easily be done by using a shell pipe. When requesting a
remote archive, though, it cannot be done through the
upload-archive interface.

This patch allows configurable tar filters, so that one
could define a "tar.gz" format that automatically pipes tar
output through gzip.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Documentation/git-archive.txt b/Documentation/git-archive.txt
index 9c750e2..726bf63 100644
--- a/Documentation/git-archive.txt
+++ b/Documentation/git-archive.txt
@@ -101,6 +101,16 @@ 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.
+
 ATTRIBUTES
 ----------
 
@@ -149,6 +159,12 @@ 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
 --------
diff --git a/archive-tar.c b/archive-tar.c
index bed9a9b..5c30747 100644
--- a/archive-tar.c
+++ b/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 +224,60 @@ 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;
+	}
+
+	return 0;
+}
+
 static int git_tar_config(const char *var, const char *value, void *cb)
 {
 	if (!strcmp(var, "tar.umask")) {
@@ -231,7 +289,8 @@ static int git_tar_config(const char *var, const char *value, void *cb)
 		}
 		return 0;
 	}
-	return 0;
+
+	return tar_filter_config(var, value, cb);
 }
 
 static int write_tar_archive(const struct archiver *ar,
@@ -248,6 +307,45 @@ static int write_tar_archive(const struct archiver *ar,
 	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,
@@ -256,6 +354,13 @@ static struct archiver tar_archiver = {
 
 void init_tar_archiver(void)
 {
+	int i;
 	register_archiver(&tar_archiver);
+
 	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]);
+	}
 }
diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh
index cff1b3e..1f90692 100755
--- a/t/t5000-tar-tree.sh
+++ b/t/t5000-tar-tree.sh
@@ -252,4 +252,47 @@ 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"
+'
+
+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 remote user 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_done
-- 
cgit v0.10.2-6-g49f6


From 0e804e09938905ed4fe6984f832057267cc5d86f Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Tue, 21 Jun 2011 21:27:35 -0400
Subject: archive: provide builtin .tar.gz filter

This works exactly as if the user had configured it via:

  [tar "tgz"]
	command = gzip -cn
  [tar "tar.gz"]
	command = gzip -cn

but since it is so common, it's convenient to have it
builtin without the user needing to do anything.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Documentation/git-archive.txt b/Documentation/git-archive.txt
index 726bf63..8b0080a 100644
--- a/Documentation/git-archive.txt
+++ b/Documentation/git-archive.txt
@@ -110,6 +110,9 @@ tar.<format>.command::
 	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.
 
 ATTRIBUTES
 ----------
@@ -143,6 +146,14 @@ 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
diff --git a/archive-tar.c b/archive-tar.c
index 5c30747..f470ebe 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -357,6 +357,8 @@ void init_tar_archiver(void)
 	int i;
 	register_archiver(&tar_archiver);
 
+	tar_filter_config("tar.tgz.command", "gzip -cn", NULL);
+	tar_filter_config("tar.tar.gz.command", "gzip -cn", NULL);
 	git_config(git_tar_config, NULL);
 	for (i = 0; i < nr_tar_filters; i++) {
 		/* omit any filters that never had a command configured */
diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh
index 1f90692..070250e 100755
--- a/t/t5000-tar-tree.sh
+++ b/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
 
@@ -295,4 +297,40 @@ test_expect_success 'extension matching requires dot' '
 	test_cmp b.tar config-implicittar.foo
 '
 
+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_done
-- 
cgit v0.10.2-6-g49f6


From 7b97730b764cac823531ccd14669f9c5b45496dc Mon Sep 17 00:00:00 2001
From: Jeff King <peff@github.com>
Date: Tue, 21 Jun 2011 23:17:35 -0400
Subject: upload-archive: allow user to turn off filters

Some tar filters may be very expensive to run, so sites do
not want to expose them via upload-archive. This patch lets
users configure tar.<filter>.remote to turn them off.

By default, gzip filters are left on, as they are about as
expensive as creating zip archives.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Documentation/git-archive.txt b/Documentation/git-archive.txt
index 8b0080a..1320c87 100644
--- a/Documentation/git-archive.txt
+++ b/Documentation/git-archive.txt
@@ -114,6 +114,12 @@ tar.<format>.command::
 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
 ----------
 
diff --git a/archive-tar.c b/archive-tar.c
index f470ebe..20af005 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -274,6 +274,13 @@ static int tar_filter_config(const char *var, const char *value, void *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;
 }
@@ -349,7 +356,7 @@ static int write_tar_filter_archive(const struct archiver *ar,
 static struct archiver tar_archiver = {
 	"tar",
 	write_tar_archive,
-	0
+	ARCHIVER_REMOTE
 };
 
 void init_tar_archiver(void)
@@ -358,7 +365,9 @@ void init_tar_archiver(void)
 	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 */
diff --git a/archive-zip.c b/archive-zip.c
index 42df660..3c102a1 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -283,7 +283,7 @@ static int write_zip_archive(const struct archiver *ar,
 static struct archiver zip_archiver = {
 	"zip",
 	write_zip_archive,
-	ARCHIVER_WANT_COMPRESSION_LEVELS
+	ARCHIVER_WANT_COMPRESSION_LEVELS|ARCHIVER_REMOTE
 };
 
 void init_zip_archiver(void)
diff --git a/archive.c b/archive.c
index 41065a8..2a7a28e 100644
--- a/archive.c
+++ b/archive.c
@@ -299,7 +299,7 @@ static void parse_treeish_arg(const char **argv,
 
 static int parse_archive_args(int argc, const char **argv,
 		const struct archiver **ar, struct archiver_args *args,
-		const char *name_hint)
+		const char *name_hint, int is_remote)
 {
 	const char *format = NULL;
 	const char *base = NULL;
@@ -356,7 +356,8 @@ static int parse_archive_args(int argc, const char **argv,
 
 	if (list) {
 		for (i = 0; i < nr_archivers; i++)
-			printf("%s\n", archivers[i]->name);
+			if (!is_remote || archivers[i]->flags & ARCHIVER_REMOTE)
+				printf("%s\n", archivers[i]->name);
 		exit(0);
 	}
 
@@ -369,7 +370,7 @@ static int parse_archive_args(int argc, const char **argv,
 	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;
@@ -390,7 +391,7 @@ static int parse_archive_args(int argc, const char **argv,
 }
 
 int write_archive(int argc, const char **argv, const char *prefix,
-		  int setup_prefix, const char *name_hint)
+		  int setup_prefix, const char *name_hint, int remote)
 {
 	int nongit = 0;
 	const struct archiver *ar = NULL;
@@ -403,7 +404,7 @@ int write_archive(int argc, const char **argv, const char *prefix,
 	init_tar_archiver();
 	init_zip_archiver();
 
-	argc = parse_archive_args(argc, argv, &ar, &args, name_hint);
+	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
diff --git a/archive.h b/archive.h
index 202d528..2b0884f 100644
--- a/archive.h
+++ b/archive.h
@@ -15,6 +15,7 @@ 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 *);
@@ -29,7 +30,7 @@ extern void init_zip_archiver(void);
 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, const char *name_hint);
+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);
 
diff --git a/builtin/archive.c b/builtin/archive.c
index 2578cf5..883c009 100644
--- a/builtin/archive.c
+++ b/builtin/archive.c
@@ -106,5 +106,5 @@ int cmd_archive(int argc, const char **argv, const char *prefix)
 
 	setvbuf(stderr, NULL, _IOLBF, BUFSIZ);
 
-	return write_archive(argc, argv, prefix, 1, output);
+	return write_archive(argc, argv, prefix, 1, output, 0);
 }
diff --git a/builtin/upload-archive.c b/builtin/upload-archive.c
index e6bb97d..2d0b383 100644
--- a/builtin/upload-archive.c
+++ b/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, NULL);
+	return write_archive(sent_argc, sent_argv, prefix, 0, NULL, 1);
 }
 
 __attribute__((format (printf, 1, 2)))
diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh
index 070250e..9e3ba98 100755
--- a/t/t5000-tar-tree.sh
+++ b/t/t5000-tar-tree.sh
@@ -256,7 +256,8 @@ test_expect_success 'git-archive --prefix=olde-' '
 
 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.command "tr ab ba" &&
+	git config tar.bar.remote true
 '
 
 test_expect_success 'archive --list mentions user filter' '
@@ -265,9 +266,9 @@ test_expect_success 'archive --list mentions user filter' '
 	grep "^bar\$" output
 '
 
-test_expect_success 'archive --list shows remote user filters' '
+test_expect_success 'archive --list shows only enabled remote filters' '
 	git archive --list --remote=. >output &&
-	grep "^tar\.foo\$" output &&
+	! grep "^tar\.foo\$" output &&
 	grep "^bar\$" output
 '
 
@@ -297,6 +298,13 @@ test_expect_success 'extension matching requires dot' '
 	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
@@ -333,4 +341,15 @@ test_expect_success GZIP,GUNZIP 'extract tgz file' '
 	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
-- 
cgit v0.10.2-6-g49f6