filter-branch: stash away ref map in a branch

With "--state-branch=<branchname>" option, the mapping from old object names
and filtered ones in ./map/ directory is stashed away in the object database,
and the one from the previous run is read to populate the ./map/ directory,
allowing for incremental updates of large trees.

Signed-off-by: Ian Campbell <ijc@hellion.org.uk>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/git-filter-branch.txt

@@ -14,7 +14,7 @@ SYNOPSIS
 	[--commit-filter <command>] [--tag-name-filter <command>]
 	[--subdirectory-filter <directory>] [--prune-empty]
 	[--original <namespace>] [-d <directory>] [-f | --force]
-	[--] [<rev-list options>...]
+	[--state-branch <branch>] [--] [<rev-list options>...]
 
 DESCRIPTION
 -----------
@@ -198,6 +198,12 @@ to other tags will be rewritten to point to the underlying commit.
 	directory or when there are already refs starting with
 	'refs/original/', unless forced.
 
+--state-branch <branch>::
+	This option will cause the mapping from old to new objects to
+	be loaded from named branch upon startup and saved as a new
+	commit to that branch upon exit, enabling incremental of large
+	trees. If '<branch>' does not exist it will be created.
+
 <rev-list options>...::
 	Arguments for 'git rev-list'.  All positive refs included by
 	these options are rewritten.  You may also specify options

git-filter-branch.sh

@@ -86,7 +86,7 @@ USAGE="[--setup <command>] [--env-filter <command>]
 	[--parent-filter <command>] [--msg-filter <command>]
 	[--commit-filter <command>] [--tag-name-filter <command>]
 	[--subdirectory-filter <directory>] [--original <namespace>]
-	[-d <directory>] [-f | --force]
+	[-d <directory>] [-f | --force] [--state-branch <branch>]
 	[--] [<rev-list options>...]"
 
 OPTIONS_SPEC=
@@ -106,6 +106,7 @@ filter_msg=cat
 filter_commit=
 filter_tag_name=
 filter_subdir=
+state_branch=
 orig_namespace=refs/original/
 force=
 prune_empty=
@@ -181,6 +182,9 @@ do
 	--original)
 		orig_namespace=$(expr "$OPTARG/" : '\(.*[^/]\)/*$')/
 		;;
+	--state-branch)
+		state_branch="$OPTARG"
+		;;
 	*)
 		usage
 		;;
@@ -259,6 +263,26 @@ export GIT_INDEX_FILE
 # map old->new commit ids for rewriting parents
 mkdir ../map || die "Could not create map/ directory"
 
+if test -n "$state_branch"
+then
+	state_commit=$(git rev-parse --no-flags --revs-only "$state_branch")
+	if test -n "$state_commit"
+	then
+		echo "Populating map from $state_branch ($state_commit)" 1>&2
+		perl -e'open(MAP, "-|", "git show $ARGV[0]:filter.map") or die;
+			while (<MAP>) {
+				m/(.*):(.*)/ or die;
+				open F, ">../map/$1" or die;
+				print F "$2" or die;
+				close(F) or die;
+			}
+			close(MAP) or die;' "$state_commit" \
+				|| die "Unable to load state from $state_branch:filter.map"
+	else
+		echo "Branch $state_branch does not exist. Will create" 1>&2
+	fi
+fi
+
 # we need "--" only if there are no path arguments in $@
 nonrevs=$(git rev-parse --no-revs "$@") || exit
 if test -z "$nonrevs"
@@ -590,6 +614,29 @@ test -z "$ORIG_GIT_COMMITTER_DATE" || {
 	export GIT_COMMITTER_DATE
 }
 
+if test -n "$state_branch"
+then
+	echo "Saving rewrite state to $state_branch" 1>&2
+	state_blob=$(
+		perl -e'opendir D, "../map" or die;
+			open H, "|-", "git hash-object -w --stdin" or die;
+			foreach (sort readdir(D)) {
+				next if m/^\.\.?$/;
+				open F, "<../map/$_" or die;
+				chomp($f = <F>);
+				print H "$_:$f\n" or die;
+			}
+			close(H) or die;' || die "Unable to save state")
+	state_tree=$(/bin/echo -e "100644 blob $state_blob\tfilter.map" | git mktree)
+	if test -n "$state_commit"
+	then
+		state_commit=$(/bin/echo "Sync" | git commit-tree "$state_tree" -p "$state_commit")
+	else
+		state_commit=$(/bin/echo "Sync" | git commit-tree "$state_tree" )
+	fi
+	git update-ref "$state_branch" "$state_commit"
+fi
+
 cd "$orig_dir"
 rm -rf "$tempdir"