[PATCH] pull: gracefully recover from delta retrieval failure.

This addresses a concern raised by Jason McMullan in the mailing
list discussion.  After retrieving and storing a potentially
deltified object, pull logic tries to check and fulfil its delta
dependency.  When the pull procedure is killed at this point,
however, there was no easy way to recover by re-running pull,
since next run would have found that we already have that
deltified object and happily reported success, without really
checking its delta dependency is satisfied.

This patch introduces --recover option to git-*-pull family
which causes them to re-validate dependency of deltified objects
we are fetching.  A new test t5100-delta-pull.sh covers such a
failure mode.
Signed-off-by: NJunio C Hamano <junkio@cox.net>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

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] [-d] commit-id url
+'git-http-pull' [-c] [-t] [-a] [-v] [-d] [--recover] commit-id url
 
 DESCRIPTION
 -----------
@@ -25,6 +25,9 @@ Downloads a remote GIT repository via HTTP.
 	Do not check for delta base objects (use this option
 	only when you know the remote repository is not
 	deltified).
+--recover::
+	Check dependency of deltified object more carefully than
+	usual, to recover after earlier pull that was interrupted.
 -v::
 	Report what is downloaded.
 

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] [-d] commit-id path
+'git-local-pull' [-c] [-t] [-a] [-l] [-s] [-n] [-v] [-d] [--recover] commit-id path
 
 DESCRIPTION
 -----------
@@ -27,6 +27,9 @@ OPTIONS
 	Do not check for delta base objects (use this option
 	only when you know the remote repository is not
 	deltified).
+--recover::
+	Check dependency of deltified object more carefully than
+	usual, to recover after earlier pull that was interrupted.
 -v::
 	Report what is downloaded.
 

Documentation/git-rpull.txt

@@ -10,7 +10,7 @@ git-rpull - Pulls from a remote repository over ssh connection
 
 SYNOPSIS
 --------
-'git-rpull' [-c] [-t] [-a] [-d] [-v] commit-id url
+'git-rpull' [-c] [-t] [-a] [-d] [-v] [--recover] commit-id url
 
 DESCRIPTION
 -----------
@@ -29,6 +29,9 @@ OPTIONS
 	Do not check for delta base objects (use this option
 	only when you know the remote repository is not
 	deltified).
+--recover::
+	Check dependency of deltified object more carefully than
+	usual, to recover after earlier pull that was interrupted.
 -v::
 	Report what is downloaded.
 

http-pull.c

@@ -105,6 +105,8 @@ int main(int argc, char **argv)
 			get_history = 1;
 		} else if (argv[arg][1] == 'd') {
 			get_delta = 0;
+		} else if (!strcmp(argv[arg], "--recover")) {
+			get_delta = 2;
 		} else if (argv[arg][1] == 'a') {
 			get_all = 1;
 			get_tree = 1;
@@ -115,7 +117,7 @@ int main(int argc, char **argv)
 		arg++;
 	}
 	if (argc < arg + 2) {
-		usage("git-http-pull [-c] [-t] [-a] [-d] [-v] commit-id url");
+		usage("git-http-pull [-c] [-t] [-a] [-d] [-v] [--recover] commit-id url");
 		return 1;
 	}
 	commit_id = argv[arg];

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] [-d] commit-id path";
+"git-local-pull [-c] [-t] [-a] [-l] [-s] [-n] [-v] [-d] [--recover] commit-id path";
 
 /* 
  * By default we only use file copy.
@@ -94,6 +94,8 @@ int main(int argc, char **argv)
 			get_history = 1;
 		else if (argv[arg][1] == 'd')
 			get_delta = 0;
+		else if (!strcmp(argv[arg], "--recover"))
+			get_delta = 2;
 		else if (argv[arg][1] == 'a') {
 			get_all = 1;
 			get_tree = 1;

pull.c

@@ -6,6 +6,7 @@
 
 int get_tree = 0;
 int get_history = 0;
+/* 1 means "get delta", 2 means "really check delta harder */
 int get_delta = 1;
 int get_all = 0;
 int get_verbosely = 0;
@@ -32,12 +33,16 @@ static void report_missing(const char *what, const unsigned char *missing)
 
 static int make_sure_we_have_it(const char *what, unsigned char *sha1)
 {
-	int status;
-	if (has_sha1_file(sha1))
+	int status = 0;
+
+	if (!has_sha1_file(sha1)) {
+		status = fetch(sha1);
+		if (status && what)
+			report_missing(what, sha1);
+	}
+	else if (get_delta < 2)
 		return 0;
-	status = fetch(sha1);
-	if (status && what)
-		report_missing(what, sha1);
+
 	if (get_delta) {
 		char delta_sha1[20];
 		status = sha1_delta_base(sha1, delta_sha1);

pull.h

@@ -13,7 +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. */
+/* Set to zero to skip the check for delta object base;
+ * set to two to check delta dependency even for objects we already have.
+ */
 extern int get_delta;
 
 /* Set to be verbose */

rpull.c

@@ -52,6 +52,8 @@ int main(int argc, char **argv)
 			get_history = 1;
 		} else if (argv[arg][1] == 'd') {
 			get_delta = 0;
+		} else if (!strcmp(argv[arg], "--recover")) {
+			get_delta = 2;
 		} else if (argv[arg][1] == 'a') {
 			get_all = 1;
 			get_tree = 1;
@@ -62,7 +64,7 @@ int main(int argc, char **argv)
 		arg++;
 	}
 	if (argc < arg + 2) {
-		usage("git-rpull [-c] [-t] [-a] [-v] [-d] commit-id url");
+		usage("git-rpull [-c] [-t] [-a] [-v] [-d] [--recover] commit-id url");
 		return 1;
 	}
 	commit_id = argv[arg];

t/t5100-delta-pull.sh

+#!/bin/sh
+#
+# Copyright (c) 2005 Junio C Hamano
+#
+
+test_description='Test pulling deltified objects
+
+'
+. ./test-lib.sh
+
+locate_obj='s|\(..\)|.git/objects/\1/|'
+
+test_expect_success \
+    setup \
+    'cat ../README >a &&
+    git-update-cache --add a &&
+    a0=`git-ls-files --stage |
+        sed -e '\''s/^[0-7]* \([0-9a-f]*\) .*/\1/'\''` &&
+
+    sed -e 's/test/TEST/g' ../README >a &&
+    git-update-cache a &&
+    a1=`git-ls-files --stage |
+        sed -e '\''s/^[0-7]* \([0-9a-f]*\) .*/\1/'\''` &&
+    tree=`git-write-tree` &&
+    commit=`git-commit-tree $tree </dev/null` &&
+    a0f=`echo "$a0" | sed -e "$locate_obj"` &&
+    a1f=`echo "$a1" | sed -e "$locate_obj"` &&
+    echo commit $commit &&
+    echo a0 $a0 &&
+    echo a1 $a1 &&
+    ls -l $a0f $a1f &&
+    echo $commit >.git/HEAD &&
+    git-mkdelta -v $a0 $a1 &&
+    ls -l $a0f $a1f'
+
+# Now commit has a tree that records delitified "a" whose SHA1 is a1.
+# Create a new repo and pull this commit into it.
+
+test_expect_success \
+    'setup and cd into new repo' \
+    'mkdir dest && cd dest && rm -fr .git && git-init-db'
+     
+test_expect_success \
+    'pull from deltified repo into a new repo without -d' \
+    'rm -fr .git a && git-init-db &&
+     git-local-pull -v -a $commit ../.git/ &&
+     git-cat-file blob $a1 >a &&
+     diff -u a ../a'
+
+test_expect_failure \
+    'pull from deltified repo into a new repo with -d' \
+    'rm -fr .git a && git-init-db &&
+     git-local-pull -v -a -d $commit ../.git/ &&
+     git-cat-file blob $a1 >a &&
+     diff -u a ../a'
+
+test_expect_failure \
+    'pull from deltified repo after delta failure without --recover' \
+    'rm -f a &&
+     git-local-pull -v -a $commit ../.git/ &&
+     git-cat-file blob $a1 >a &&
+     diff -u a ../a'
+
+test_expect_success \
+    'pull from deltified repo after delta failure with --recover' \
+    'rm -f a &&
+     git-local-pull -v -a --recover $commit ../.git/ &&
+     git-cat-file blob $a1 >a &&
+     diff -u a ../a'
+
+test_expect_success \
+    'missing-tree or missing-blob should be re-fetched without --recover' \
+    'rm -f a $a0f $a1f &&
+     git-local-pull -v -a $commit ../.git/ &&
+     git-cat-file blob $a1 >a &&
+     diff -u a ../a'
+
+test_done
+