[PATCH] Handle deltified object correctly in git-*-pull family.

When a remote repository is deltified, we need to get the
objects that a deltified object we want to obtain is based upon.
The initial parts of each retrieved SHA1 file is inflated and
inspected to see if it is deltified, and its base object is
asked from the remote side when it is.  Since this partial
inflation and inspection has a small performance hit, it can
optionally be skipped by giving -d flag to git-*-pull commands.
This flag should be used only when the remote repository is
known to have no deltified objects.

Rsync transport does not have this problem since it fetches
everything the remote side has.

Signed-off-by: Junio C Hamano <junkio@cox.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

10 files changed, 66 insertions, 6 deletions

diff --git a/Documentation/git-http-pull.txt b/Documentation/git-http-pull.txt
index 59cd090..8b54f09 100644
--- a/Documentation/git-http-pull.txt
+++ b/Documentation/git-http-pull.txt
@@ -9,7 +9,7 @@ git-http-pull - Downloads a remote GIT repository via HTTP
 
 SYNOPSIS
 --------
-'git-http-pull' [-c] [-t] [-a] [-v] commit-id url
+'git-http-pull' [-c] [-t] [-a] [-v] [-d] commit-id url
 
 DESCRIPTION
 -----------
@@ -21,6 +21,10 @@ Downloads a remote GIT repository via HTTP.
 	Get trees associated with the commit objects.
 -a::
 	Get all the objects.
+-d::
+	Do not check for delta base objects (use this option
+	only when you know the remote repository is not
+	deltified).
 -v::
 	Report what is downloaded.
 
diff --git a/Documentation/git-local-pull.txt b/Documentation/git-local-pull.txt
index 53f5d39..79d0f5c 100644
--- a/Documentation/git-local-pull.txt
+++ b/Documentation/git-local-pull.txt
@@ -9,7 +9,7 @@ git-local-pull - Duplicates another GIT repository on a local system
 
 SYNOPSIS
 --------
-'git-local-pull' [-c] [-t] [-a] [-l] [-s] [-n] [-v] commit-id path
+'git-local-pull' [-c] [-t] [-a] [-l] [-s] [-n] [-v] [-d] commit-id path
 
 DESCRIPTION
 -----------
@@ -23,6 +23,10 @@ OPTIONS
 	Get trees associated with the commit objects.
 -a::
 	Get all the objects.
+-d::
+	Do not check for delta base objects (use this option
+	only when you know the remote repository is not
+	deltified).
 -v::
 	Report what is downloaded.
 
diff --git a/Documentation/git-rpull.txt b/Documentation/git-rpull.txt
index 1807fc5..3a83866 100644
--- a/Documentation/git-rpull.txt
+++ b/Documentation/git-rpull.txt
@@ -10,7 +10,7 @@ git-rpull - Pulls from a remote repository over ssh connection
 
 SYNOPSIS
 --------
-'git-rpull' [-c] [-t] [-a] [-v] commit-id url
+'git-rpull' [-c] [-t] [-a] [-d] [-v] commit-id url
 
 DESCRIPTION
 -----------
@@ -25,6 +25,10 @@ OPTIONS
 	Get trees associated with the commit objects.
 -a::
 	Get all the objects.
+-d::
+	Do not check for delta base objects (use this option
+	only when you know the remote repository is not
+	deltified).
 -v::
 	Report what is downloaded.
 
diff --git a/cache.h b/cache.h
index aa74bcc..e54176b 100644
--- a/cache.h
+++ b/cache.h
@@ -153,6 +153,7 @@ extern char *sha1_file_name(const unsigned char *sha1);
 extern void * map_sha1_file(const unsigned char *sha1, unsigned long *size);
 extern int unpack_sha1_header(z_stream *stream, void *map, unsigned long mapsize, void *buffer, unsigned long size);
 extern int parse_sha1_header(char *hdr, char *type, unsigned long *sizep);
+extern int sha1_delta_base(const unsigned char *, unsigned char *);
 extern void * unpack_sha1_file(void *map, unsigned long mapsize, char *type, unsigned long *size);
 extern void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size);
 extern int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *return_sha1);
diff --git a/http-pull.c b/http-pull.c
index ba8585c..551663e 100644
--- a/http-pull.c
+++ b/http-pull.c
@@ -103,6 +103,8 @@ int main(int argc, char **argv)
 			get_tree = 1;
 		} else if (argv[arg][1] == 'c') {
 			get_history = 1;
+		} else if (argv[arg][1] == 'd') {
+			get_delta = 0;
 		} else if (argv[arg][1] == 'a') {
 			get_all = 1;
 			get_tree = 1;
@@ -113,7 +115,7 @@ int main(int argc, char **argv)
 		arg++;
 	}
 	if (argc < arg + 2) {
-		usage("git-http-pull [-c] [-t] [-a] [-v] commit-id url");
+		usage("git-http-pull [-c] [-t] [-a] [-d] [-v] commit-id url");
 		return 1;
 	}
 	commit_id = argv[arg];
diff --git a/local-pull.c b/local-pull.c
index 10d4ca8..e5d834f 100644
--- a/local-pull.c
+++ b/local-pull.c
@@ -74,7 +74,7 @@ int fetch(unsigned char *sha1)
 }
 
 static const char *local_pull_usage = 
-"git-local-pull [-c] [-t] [-a] [-l] [-s] [-n] [-v] commit-id path";
+"git-local-pull [-c] [-t] [-a] [-l] [-s] [-n] [-v] [-d] commit-id path";
 
 /* 
  * By default we only use file copy.
@@ -92,6 +92,8 @@ int main(int argc, char **argv)
 			get_tree = 1;
 		else if (argv[arg][1] == 'c')
 			get_history = 1;
+		else if (argv[arg][1] == 'd')
+			get_delta = 0;
 		else if (argv[arg][1] == 'a') {
 			get_all = 1;
 			get_tree = 1;
diff --git a/pull.c b/pull.c
index 0bed44f..cd77738 100644
--- a/pull.c
+++ b/pull.c
@@ -6,6 +6,7 @@
 
 int get_tree = 0;
 int get_history = 0;
+int get_delta = 1;
 int get_all = 0;
 int get_verbosely = 0;
 static unsigned char current_commit_sha1[20];
@@ -37,6 +38,12 @@ static int make_sure_we_have_it(const char *what, unsigned char *sha1)
 	status = fetch(sha1);
 	if (status && what)
 		report_missing(what, sha1);
+	if (get_delta) {
+		char delta_sha1[20];
+		status = sha1_delta_base(sha1, delta_sha1);
+		if (0 < status)
+			status = make_sure_we_have_it(what, delta_sha1);
+	}
 	return status;
 }
 
diff --git a/pull.h b/pull.h
index d2dca02..3cd14cf 100644
--- a/pull.h
+++ b/pull.h
@@ -13,6 +13,9 @@ extern int get_history;
 /** Set to fetch the trees in the commit history. **/
 extern int get_all;
 
+/* Set to zero to skip the check for delta object base. */
+extern int get_delta;
+
 /* Set to be verbose */
 extern int get_verbosely;
 
diff --git a/rpull.c b/rpull.c
index 36e49f7..8b3322f 100644
--- a/rpull.c
+++ b/rpull.c
@@ -27,6 +27,8 @@ int main(int argc, char **argv)
 			get_tree = 1;
 		} else if (argv[arg][1] == 'c') {
 			get_history = 1;
+		} else if (argv[arg][1] == 'd') {
+			get_delta = 0;
 		} else if (argv[arg][1] == 'a') {
 			get_all = 1;
 			get_tree = 1;
@@ -37,7 +39,7 @@ int main(int argc, char **argv)
 		arg++;
 	}
 	if (argc < arg + 2) {
-		usage("git-rpull [-c] [-t] [-a] [-v] commit-id url");
+		usage("git-rpull [-c] [-t] [-a] [-v] [-d] commit-id url");
 		return 1;
 	}
 	commit_id = argv[arg];
diff --git a/sha1_file.c b/sha1_file.c
index af39e88..ccfcca0 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -401,6 +401,37 @@ void * unpack_sha1_file(void *map, unsigned long mapsize, char *type, unsigned l
 	return unpack_sha1_rest(&stream, hdr, *size);
 }
 
+int sha1_delta_base(const unsigned char *sha1, unsigned char *base_sha1)
+{
+	int ret;
+	unsigned long mapsize, size;
+	void *map;
+	z_stream stream;
+	char hdr[64], type[20];
+	void *delta_data_head;
+
+	map = map_sha1_file(sha1, &mapsize);
+	if (!map)
+		return -1;
+	ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr));
+	if (ret < Z_OK || parse_sha1_header(hdr, type, &size) < 0) {
+		ret = -1;
+		goto out;
+	}
+	if (strcmp(type, "delta")) {
+		ret = 0;
+		goto out;
+	}
+
+	delta_data_head = hdr + strlen(hdr) + 1;
+	ret = 1;
+	memcpy(base_sha1, delta_data_head, 20);
+ out:
+	inflateEnd(&stream);
+	munmap(map, mapsize);
+	return ret;
+}
+
 void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size)
 {
 	unsigned long mapsize;