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 <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

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
 --------

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]);
+	}
 }

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