Add git-archive

git-archive is a command to make TAR and ZIP archives of a git tree.
It helps prevent a proliferation of git-{format}-tree commands.

Instead of directly calling git-{tar,zip}-tree command, it defines
a very simple API, that archiver should implement and register in
"git-archive.c". This API is made up by 2 functions whose prototype
is defined in "archive.h" file.

 - The first one is used to parse 'extra' parameters which have
   signification only for the specific archiver. That would allow
   different archive backends to have different kind of options.

 - The second one is used to ask to an archive backend to build
   the archive given some already resolved parameters.

The main reason for making this API is to avoid using
git-{tar,zip}-tree commands, hence making them useless. Maybe it's
time for them to die ?

It also implements remote operations by defining a very simple
protocol: it first sends the name of the specific uploader followed
the repository name (git-upload-tar git://example.org/repo.git).
Then it sends options. It's done by sending a sequence of one
argument per packet, with prefix "argument ", followed by a flush.

The remote protocol is implemented in "git-archive.c" for client
side and is triggered by "--remote=<repo>" option. For example,
to fetch a TAR archive in a remote repo, you can issue:

$ git archive --format=tar --remote=git://xxx/yyy/zzz.git HEAD

We choose to not make a new command "git-fetch-archive" for example,
avoind one more GIT command which should be nice for users (less
commands to remember, keeps existing --remote option).

Signed-off-by: Franck Bui-Huu <vagabon.xyz@gmail.com>
Acked-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Junio C Hamano <junkio@cox.net>

8 files changed, 375 insertions, 1 deletions

diff --git a/.gitignore b/.gitignore
index 0d608fe12..a3f33d420 100644
--- a/.gitignore
+++ b/.gitignore
@@ -8,6 +8,7 @@ git-apply
 git-applymbox
 git-applypatch
 git-archimport
+git-archive
 git-bisect
 git-branch
 git-cat-file
diff --git a/Documentation/git-archive.txt b/Documentation/git-archive.txt
new file mode 100644
index 000000000..913528d37
--- /dev/null
+++ b/Documentation/git-archive.txt
@@ -0,0 +1,100 @@
+git-archive(1)
+==============
+
+NAME
+----
+git-archive - Creates a archive of the files in the named tree
+
+
+SYNOPSIS
+--------
+'git-archive' --format=<fmt> [--list] [--prefix=<prefix>/] [<extra>]
+	      [--remote=<repo>] <tree-ish> [path...]
+
+DESCRIPTION
+-----------
+Creates an archive of the specified format containing the tree
+structure for the named tree.  If <prefix> is specified it is
+prepended to the filenames in the archive.
+
+'git-archive' behaves differently when given a tree ID versus when
+given a commit ID or tag ID.  In the first case the current time is
+used as modification time of each file in the archive.  In the latter
+case the commit time as recorded in the referenced commit object is
+used instead.  Additionally the commit ID is stored in a global
+extended pax header if the tar format is used; it can be extracted
+using 'git-get-tar-commit-id'. In ZIP files it is stored as a file
+comment.
+
+OPTIONS
+-------
+
+--format=<fmt>::
+	Format of the resulting archive: 'tar', 'zip'...
+
+--list::
+	Show all available formats.
+
+--prefix=<prefix>/::
+	Prepend <prefix>/ to each filename in the archive.
+
+<extra>::
+	This can be any options that the archiver backend understand.
+
+--remote=<repo>::
+	Instead of making a tar archive from local repository,
+	retrieve a tar archive from a remote repository.
+
+<tree-ish>::
+	The tree or commit to produce an archive for.
+
+path::
+	If one or more paths are specified, include only these in the
+	archive, otherwise include all files and subdirectories.
+
+CONFIGURATION
+-------------
+By default, file and directories modes are set to 0666 or 0777 in tar
+archives.  It is possible to change this by setting the "umask" variable
+in the repository configuration as follows :
+
+[tar]
+        umask = 002	;# group friendly
+
+The special umask value "user" indicates that the user's current umask
+will be used instead. The default value remains 0, which means world
+readable/writable files and directories.
+
+EXAMPLES
+--------
+git archive --format=tar --prefix=junk/ HEAD | (cd /var/tmp/ && tar xf -)::
+
+	Create a tar archive that contains the contents of the
+	latest commit on the current branch, and extracts it in
+	`/var/tmp/junk` directory.
+
+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 --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
+	global extended pax header.
+
+git archive --format=zip --prefix=git-docs/ HEAD:Documentation/ > git-1.4.0-docs.zip::
+
+	Put everything in the current head's Documentation/ directory
+	into 'git-1.4.0-docs.zip', with the prefix 'git-docs/'.
+
+Author
+------
+Written by Franck Bui-Huu and Rene Scharfe.
+
+Documentation
+--------------
+Documentation by David Greaves, Junio C Hamano and the git-list <git@vger.kernel.org>.
+
+GIT
+---
+Part of the gitlink:git[7] suite
diff --git a/Makefile b/Makefile
index 7b3114f3a..8f62ceffa 100644
--- a/Makefile
+++ b/Makefile
@@ -232,7 +232,7 @@ LIB_FILE=libgit.a
 XDIFF_LIB=xdiff/lib.a
 
 LIB_H = \
-	blob.h cache.h commit.h csum-file.h delta.h \
+	archive.h blob.h cache.h commit.h csum-file.h delta.h \
 	diff.h object.h pack.h pkt-line.h quote.h refs.h \
 	run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \
 	tree-walk.h log-tree.h dir.h path-list.h unpack-trees.h builtin.h
@@ -256,6 +256,7 @@ LIB_OBJS = \
 BUILTIN_OBJS = \
 	builtin-add.o \
 	builtin-apply.o \
+	builtin-archive.o \
 	builtin-cat-file.o \
 	builtin-checkout-index.o \
 	builtin-check-ref-format.o \
diff --git a/archive.h b/archive.h
new file mode 100644
index 000000000..24b016f00
--- /dev/null
+++ b/archive.h
@@ -0,0 +1,41 @@
+#ifndef ARCHIVE_H
+#define ARCHIVE_H
+
+#define MAX_EXTRA_ARGS	32
+#define MAX_ARGS	(MAX_EXTRA_ARGS + 32)
+
+struct archiver_args {
+	const char *base;
+	struct tree *tree;
+	const unsigned char *commit_sha1;
+	time_t time;
+	const char **pathspec;
+	void *extra;
+};
+
+typedef int (*write_archive_fn_t)(struct archiver_args *);
+
+typedef void *(*parse_extra_args_fn_t)(int argc, const char **argv);
+
+struct archiver {
+	const char *name;
+	const char *remote;
+	struct archiver_args args;
+	write_archive_fn_t write_archive;
+	parse_extra_args_fn_t parse_extra;
+};
+
+extern struct archiver archivers[];
+
+extern int parse_archive_args(int argc,
+			      const char **argv,
+			      struct archiver *ar);
+
+extern void parse_treeish_arg(const char **treeish,
+			      struct archiver_args *ar_args,
+			      const char *prefix);
+
+extern void parse_pathspec_arg(const char **pathspec,
+			       struct archiver_args *args);
+
+#endif	/* ARCHIVE_H */
diff --git a/builtin-archive.c b/builtin-archive.c
new file mode 100644
index 000000000..f6bc269fd
--- /dev/null
+++ b/builtin-archive.c
@@ -0,0 +1,228 @@
+/*
+ * Copyright (c) 2006 Franck Bui-Huu
+ * Copyright (c) 2006 Rene Scharfe
+ */
+#include <time.h>
+#include "cache.h"
+#include "builtin.h"
+#include "archive.h"
+#include "commit.h"
+#include "tree-walk.h"
+#include "exec_cmd.h"
+#include "pkt-line.h"
+
+static const char archive_usage[] = \
+"git-archive --format=<fmt> [--prefix=<prefix>/] [<extra>] <tree-ish> [path...]";
+
+struct archiver archivers[] = {
+	{ "" /* dummy */ },
+};
+
+static int run_remote_archiver(struct archiver *ar, int argc,
+			       const char **argv)
+{
+	char *url, buf[1024];
+	int fd[2], i, len, rv;
+	pid_t pid;
+
+	sprintf(buf, "git-upload-archive");
+
+	url = xstrdup(ar->remote);
+	pid = git_connect(fd, url, buf);
+	if (pid < 0)
+		return pid;
+
+	for (i = 1; i < argc; i++) {
+		if (!strncmp(argv[i], "--remote=", 9))
+			continue;
+		packet_write(fd[1], "argument %s\n", argv[i]);
+	}
+	packet_flush(fd[1]);
+
+	len = packet_read_line(fd[0], buf, sizeof(buf));
+	if (!len)
+		die("git-archive: expected ACK/NAK, got EOF");
+	if (buf[len-1] == '\n')
+		buf[--len] = 0;
+	if (strcmp(buf, "ACK")) {
+		if (len > 5 && !strncmp(buf, "NACK ", 5))
+			die("git-archive: NACK %s", buf + 5);
+		die("git-archive: protocol error");
+	}
+
+	len = packet_read_line(fd[0], buf, sizeof(buf));
+	if (len)
+		die("git-archive: expected a flush");
+
+	/* Now, start reading from fd[0] and spit it out to stdout */
+	rv = copy_fd(fd[0], 1);
+
+	close(fd[0]);
+	rv |= finish_connect(pid);
+
+	return !!rv;
+}
+
+static int init_archiver(const char *name, struct archiver *ar)
+{
+	int rv = -1, i;
+
+	for (i = 0; i < ARRAY_SIZE(archivers); i++) {
+		if (!strcmp(name, archivers[i].name)) {
+			memcpy(ar, &archivers[i], sizeof(struct archiver));
+			rv = 0;
+			break;
+		}
+	}
+	return rv;
+}
+
+void parse_pathspec_arg(const char **pathspec, struct archiver_args *ar_args)
+{
+	ar_args->pathspec = get_pathspec(ar_args->base, pathspec);
+}
+
+void parse_treeish_arg(const char **argv, struct archiver_args *ar_args,
+		       const char *prefix)
+{
+	const char *name = argv[0];
+	const unsigned char *commit_sha1;
+	time_t archive_time;
+	struct tree *tree;
+	struct commit *commit;
+	unsigned char sha1[20];
+
+	if (get_sha1(name, sha1))
+		die("Not a valid object name");
+
+	commit = lookup_commit_reference_gently(sha1, 1);
+	if (commit) {
+		commit_sha1 = commit->object.sha1;
+		archive_time = commit->date;
+	} else {
+		commit_sha1 = NULL;
+		archive_time = time(NULL);
+	}
+
+	tree = parse_tree_indirect(sha1);
+	if (tree == NULL)
+		die("not a tree object");
+
+	if (prefix) {
+		unsigned char tree_sha1[20];
+		unsigned int mode;
+		int err;
+
+		err = get_tree_entry(tree->object.sha1, prefix,
+				     tree_sha1, &mode);
+		if (err || !S_ISDIR(mode))
+			die("current working directory is untracked");
+
+		free(tree);
+		tree = parse_tree_indirect(tree_sha1);
+	}
+	ar_args->tree = tree;
+	ar_args->commit_sha1 = commit_sha1;
+	ar_args->time = archive_time;
+}
+
+static const char *default_parse_extra(struct archiver *ar,
+				       const char **argv)
+{
+	static char msg[64];
+
+	snprintf(msg, sizeof(msg) - 4, "'%s' format does not handle %s",
+		 ar->name, *argv);
+
+	return strcat(msg, "...");
+}
+
+int parse_archive_args(int argc, const char **argv, struct archiver *ar)
+{
+	const char *extra_argv[MAX_EXTRA_ARGS];
+	int extra_argc = 0;
+	const char *format = NULL; /* might want to default to "tar" */
+	const char *remote = NULL;
+	const char *base = "";
+	int list = 0;
+	int i;
+
+	for (i = 1; i < argc; i++) {
+		const char *arg = argv[i];
+
+		if (!strcmp(arg, "--list") || !strcmp(arg, "-l")) {
+			list = 1;
+			continue;
+		}
+		if (!strncmp(arg, "--format=", 9)) {
+			format = arg + 9;
+			continue;
+		}
+		if (!strncmp(arg, "--prefix=", 9)) {
+			base = arg + 9;
+			continue;
+		}
+		if (!strncmp(arg, "--remote=", 9)) {
+			remote = arg + 9;
+			continue;
+		}
+		if (!strcmp(arg, "--")) {
+			i++;
+			break;
+		}
+		if (arg[0] == '-') {
+			if (extra_argc > MAX_EXTRA_ARGS - 1)
+				die("Too many extra options");
+			extra_argv[extra_argc++] = arg;
+			continue;
+		}
+		break;
+	}
+
+	if (list) {
+		if (!remote) {
+			for (i = 0; i < ARRAY_SIZE(archivers); i++)
+				printf("%s\n", archivers[i].name);
+			exit(0);
+		}
+		die("--list and --remote are mutually exclusive");
+	}
+
+	if (argc - i < 1)
+		usage(archive_usage);
+	if (!format)
+		die("You must specify an archive format");
+	if (init_archiver(format, ar) < 0)
+		die("Unknown archive format '%s'", format);
+
+	if (extra_argc && !remote) {
+		if (!ar->parse_extra) {
+			die("%s", default_parse_extra(ar, extra_argv));
+		}
+		ar->args.extra = ar->parse_extra(extra_argc, extra_argv);
+	}
+	ar->remote = remote;
+	ar->args.base = base;
+
+	return i;
+}
+
+int cmd_archive(int argc, const char **argv, const char *prefix)
+{
+	struct archiver ar;
+	int tree_idx;
+
+	tree_idx = parse_archive_args(argc, argv, &ar);
+
+	if (ar.remote)
+		return run_remote_archiver(&ar, argc, argv);
+
+	if (prefix == NULL)
+		prefix = setup_git_directory();
+
+	argv += tree_idx;
+	parse_treeish_arg(argv, &ar.args, prefix);
+	parse_pathspec_arg(argv + 1, &ar.args);
+
+	return ar.write_archive(&ar.args);
+}
diff --git a/builtin.h b/builtin.h
index 25431d708..50852cd6a 100644
--- a/builtin.h
+++ b/builtin.h
@@ -15,6 +15,7 @@ extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix);
 
 extern int cmd_add(int argc, const char **argv, const char *prefix);
 extern int cmd_apply(int argc, const char **argv, const char *prefix);
+extern int cmd_archive(int argc, const char **argv, const char *prefix);
 extern int cmd_cat_file(int argc, const char **argv, const char *prefix);
 extern int cmd_checkout_index(int argc, const char **argv, const char *prefix);
 extern int cmd_check_ref_format(int argc, const char **argv, const char *prefix);
diff --git a/generate-cmdlist.sh b/generate-cmdlist.sh
index ec1eda20d..5450918be 100755
--- a/generate-cmdlist.sh
+++ b/generate-cmdlist.sh
@@ -12,6 +12,7 @@ struct cmdname_help common_cmds[] = {"
 sort <<\EOF |
 add
 apply
+archive
 bisect
 branch
 checkout
diff --git a/git.c b/git.c
index 335f405c2..8c64b2753 100644
--- a/git.c
+++ b/git.c
@@ -220,6 +220,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 	} commands[] = {
 		{ "add", cmd_add, RUN_SETUP },
 		{ "apply", cmd_apply },
+		{ "archive", cmd_archive },
 		{ "cat-file", cmd_cat_file, RUN_SETUP },
 		{ "checkout-index", cmd_checkout_index, RUN_SETUP },
 		{ "check-ref-format", cmd_check_ref_format },