[thirdparty/git.git] / git-filter-branch.sh

#!/bin/sh
#
# Rewrite revision history
# Copyright (c) Petr Baudis, 2006
# Minimal changes to "port" it to core-git (c) Johannes Schindelin, 2007
#
# Lets you rewrite the revision history of the current branch, creating
# a new branch. You can specify a number of filters to modify the commits,
# files and trees.

# The following functions will also be available in the commit filter:

functions=$(cat << \EOF
warn () {
	echo "$*" >&2
}

map()
{
	# if it was not rewritten, take the original
	if test -r "$workdir/../map/$1"
	then
		cat "$workdir/../map/$1"
	else
		echo "$1"
	fi
}

# if you run 'skip_commit "$@"' in a commit filter, it will print
# the (mapped) parents, effectively skipping the commit.

skip_commit()
{
	shift;
	while [ -n "$1" ];
	do
		shift;
		map "$1";
		shift;
	done;
}

# if you run 'git_commit_non_empty_tree "$@"' in a commit filter,
# it will skip commits that leave the tree untouched, commit the other.
git_commit_non_empty_tree()
{
	if test $# = 3 && test "$1" = $(git rev-parse "$3^{tree}"); then
		map "$3"
	elif test $# = 1 && test "$1" = 4b825dc642cb6eb9a060e54bf8d69288fbee4904; then
		:
	else
		git commit-tree "$@"
	fi
}
# override die(): this version puts in an extra line break, so that
# the progress is still visible

die()
{
	echo >&2
	echo "$*" >&2
	exit 1
}
EOF
)

eval "$functions"

finish_ident() {
	# Ensure non-empty id name.
	echo "case \"\$GIT_$1_NAME\" in \"\") GIT_$1_NAME=\"\${GIT_$1_EMAIL%%@*}\" && export GIT_$1_NAME;; esac"
	# And make sure everything is exported.
	echo "export GIT_$1_NAME"
	echo "export GIT_$1_EMAIL"
	echo "export GIT_$1_DATE"
}

set_ident () {
	parse_ident_from_commit author AUTHOR committer COMMITTER
	finish_ident AUTHOR
	finish_ident COMMITTER
}

USAGE="[--setup <command>] [--subdirectory-filter <directory>] [--env-filter <command>]
	[--tree-filter <command>] [--index-filter <command>]
	[--parent-filter <command>] [--msg-filter <command>]
	[--commit-filter <command>] [--tag-name-filter <command>]
	[--original <namespace>]
	[-d <directory>] [-f | --force] [--state-branch <branch>]
	[--] [<rev-list options>...]"

OPTIONS_SPEC=
. git-sh-setup

if [ "$(is_bare_repository)" = false ]; then
	require_clean_work_tree 'rewrite branches'
fi

tempdir=.git-rewrite
filter_setup=
filter_env=
filter_tree=
filter_index=
filter_parent=
filter_msg=cat
filter_commit=
filter_tag_name=
filter_subdir=
state_branch=
orig_namespace=refs/original/
force=
prune_empty=
remap_to_ancestor=
while :
do
	case "$1" in
	--)
		shift
		break
		;;
	--force|-f)
		shift
		force=t
		continue
		;;
	--remap-to-ancestor)
		# deprecated ($remap_to_ancestor is set now automatically)
		shift
		remap_to_ancestor=t
		continue
		;;
	--prune-empty)
		shift
		prune_empty=t
		continue
		;;
	-*)
		;;
	*)
		break;
	esac

	# all switches take one argument
	ARG="$1"
	case "$#" in 1) usage ;; esac
	shift
	OPTARG="$1"
	shift

	case "$ARG" in
	-d)
		tempdir="$OPTARG"
		;;
	--setup)
		filter_setup="$OPTARG"
		;;
	--subdirectory-filter)
		filter_subdir="$OPTARG"
		remap_to_ancestor=t
		;;
	--env-filter)
		filter_env="$OPTARG"
		;;
	--tree-filter)
		filter_tree="$OPTARG"
		;;
	--index-filter)
		filter_index="$OPTARG"
		;;
	--parent-filter)
		filter_parent="$OPTARG"
		;;
	--msg-filter)
		filter_msg="$OPTARG"
		;;
	--commit-filter)
		filter_commit="$functions; $OPTARG"
		;;
	--tag-name-filter)
		filter_tag_name="$OPTARG"
		;;
	--original)
		orig_namespace=$(expr "$OPTARG/" : '\(.*[^/]\)/*$')/
		;;
	--state-branch)
		state_branch="$OPTARG"
		;;
	*)
		usage
		;;
	esac
done

case "$prune_empty,$filter_commit" in
,)
	filter_commit='git commit-tree "$@"';;
t,)
	filter_commit="$functions;"' git_commit_non_empty_tree "$@"';;
,*)
	;;
*)
	die "Cannot set --prune-empty and --commit-filter at the same time"
esac

case "$force" in
t)
	rm -rf "$tempdir"
;;
'')
	test -d "$tempdir" &&
		die "$tempdir already exists, please remove it"
esac
orig_dir=$(pwd)
mkdir -p "$tempdir/t" &&
tempdir="$(cd "$tempdir"; pwd)" &&
cd "$tempdir/t" &&
workdir="$(pwd)" ||
die ""

# Remove tempdir on exit
trap 'cd "$orig_dir"; rm -rf "$tempdir"' 0

ORIG_GIT_DIR="$GIT_DIR"
ORIG_GIT_WORK_TREE="$GIT_WORK_TREE"
ORIG_GIT_INDEX_FILE="$GIT_INDEX_FILE"
ORIG_GIT_AUTHOR_NAME="$GIT_AUTHOR_NAME"
ORIG_GIT_AUTHOR_EMAIL="$GIT_AUTHOR_EMAIL"
ORIG_GIT_AUTHOR_DATE="$GIT_AUTHOR_DATE"
ORIG_GIT_COMMITTER_NAME="$GIT_COMMITTER_NAME"
ORIG_GIT_COMMITTER_EMAIL="$GIT_COMMITTER_EMAIL"
ORIG_GIT_COMMITTER_DATE="$GIT_COMMITTER_DATE"

GIT_WORK_TREE=.
export GIT_DIR GIT_WORK_TREE

# Make sure refs/original is empty
git for-each-ref > "$tempdir"/backup-refs || exit
while read sha1 type name
do
	case "$force,$name" in
	,$orig_namespace*)
		die "Cannot create a new backup.
A previous backup already exists in $orig_namespace
Force overwriting the backup with -f"
	;;
	t,$orig_namespace*)
		git update-ref -d "$name" $sha1
	;;
	esac
done < "$tempdir"/backup-refs

# The refs should be updated if their heads were rewritten
git rev-parse --no-flags --revs-only --symbolic-full-name \
	--default HEAD "$@" > "$tempdir"/raw-heads || exit
sed -e '/^^/d' "$tempdir"/raw-heads >"$tempdir"/heads

test -s "$tempdir"/heads ||
	die "You must specify a ref to rewrite."

GIT_INDEX_FILE="$(pwd)/../index"
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"
then
	dashdash=--
else
	dashdash=
	remap_to_ancestor=t
fi

git rev-parse --revs-only "$@" >../parse

case "$filter_subdir" in
"")
	eval set -- "$(git rev-parse --sq --no-revs "$@")"
	;;
*)
	eval set -- "$(git rev-parse --sq --no-revs "$@" $dashdash \
		"$filter_subdir")"
	;;
esac

git rev-list --reverse --topo-order --default HEAD \
	--parents --simplify-merges --stdin "$@" <../parse >../revs ||
	die "Could not get the commits"
commits=$(wc -l <../revs | tr -d " ")

test $commits -eq 0 && die "Found nothing to rewrite"

# Rewrite the commits
report_progress ()
{
	if test -n "$progress" &&
		test $git_filter_branch__commit_count -gt $next_sample_at
	then
		count=$git_filter_branch__commit_count

		now=$(date +%s)
		elapsed=$(($now - $start_timestamp))
		remaining=$(( ($commits - $count) * $elapsed / $count ))
		if test $elapsed -gt 0
		then
			next_sample_at=$(( ($elapsed + 1) * $count / $elapsed ))
		else
			next_sample_at=$(($next_sample_at + 1))
		fi
		progress=" ($elapsed seconds passed, remaining $remaining predicted)"
	fi
	printf "\rRewrite $commit ($count/$commits)$progress    "
}

git_filter_branch__commit_count=0

progress= start_timestamp=
if date '+%s' 2>/dev/null | grep -q '^[0-9][0-9]*$'
then
	next_sample_at=0
	progress="dummy to ensure this is not empty"
	start_timestamp=$(date '+%s')
fi

if test -n "$filter_index" ||
   test -n "$filter_tree" ||
   test -n "$filter_subdir"
then
	need_index=t
else
	need_index=
fi

eval "$filter_setup" < /dev/null ||
	die "filter setup failed: $filter_setup"

while read commit parents; do
	git_filter_branch__commit_count=$(($git_filter_branch__commit_count+1))

	report_progress

	case "$filter_subdir" in
	"")
		if test -n "$need_index"
		then
			GIT_ALLOW_NULL_SHA1=1 git read-tree -i -m $commit
		fi
		;;
	*)
		# The commit may not have the subdirectory at all
		err=$(GIT_ALLOW_NULL_SHA1=1 \
		      git read-tree -i -m $commit:"$filter_subdir" 2>&1) || {
			if ! git rev-parse -q --verify $commit:"$filter_subdir"
			then
				rm -f "$GIT_INDEX_FILE"
			else
				echo >&2 "$err"
				false
			fi
		}
	esac || die "Could not initialize the index"

	GIT_COMMIT=$commit
	export GIT_COMMIT
	git cat-file commit "$commit" >../commit ||
		die "Cannot read commit $commit"

	eval "$(set_ident <../commit)" ||
		die "setting author/committer failed for commit $commit"
	eval "$filter_env" < /dev/null ||
		die "env filter failed: $filter_env"

	if [ "$filter_tree" ]; then
		git checkout-index -f -u -a ||
			die "Could not checkout the index"
		# files that $commit removed are now still in the working tree;
		# remove them, else they would be added again
		git clean -d -q -f -x
		eval "$filter_tree" < /dev/null ||
			die "tree filter failed: $filter_tree"

		(
			git diff-index -r --name-only --ignore-submodules $commit -- &&
			git ls-files --others
		) > "$tempdir"/tree-state || exit
		git update-index --add --replace --remove --stdin \
			< "$tempdir"/tree-state || exit
	fi

	eval "$filter_index" < /dev/null ||
		die "index filter failed: $filter_index"

	parentstr=
	for parent in $parents; do
		for reparent in $(map "$parent"); do
			case "$parentstr " in
			*" -p $reparent "*)
				;;
			*)
				parentstr="$parentstr -p $reparent"
				;;
			esac
		done
	done
	if [ "$filter_parent" ]; then
		parentstr="$(echo "$parentstr" | eval "$filter_parent")" ||
				die "parent filter failed: $filter_parent"
	fi

	{
		while IFS='' read -r header_line && test -n "$header_line"
		do
			# skip header lines...
			:;
		done
		# and output the actual commit message
		cat
	} <../commit |
		eval "$filter_msg" > ../message ||
			die "msg filter failed: $filter_msg"

	if test -n "$need_index"
	then
		tree=$(git write-tree)
	else
		tree=$(git rev-parse "$commit^{tree}")
	fi
	workdir=$workdir @SHELL_PATH@ -c "$filter_commit" "git commit-tree" \
		"$tree" $parentstr < ../message > ../map/$commit ||
			die "could not write rewritten commit"
done <../revs

# If we are filtering for paths, as in the case of a subdirectory
# filter, it is possible that a specified head is not in the set of
# rewritten commits, because it was pruned by the revision walker.
# Ancestor remapping fixes this by mapping these heads to the unique
# nearest ancestor that survived the pruning.

if test "$remap_to_ancestor" = t
then
	while read ref
	do
		sha1=$(git rev-parse "$ref"^0)
		test -f "$workdir"/../map/$sha1 && continue
		ancestor=$(git rev-list --simplify-merges -1 "$ref" "$@")
		test "$ancestor" && echo $(map $ancestor) >> "$workdir"/../map/$sha1
	done < "$tempdir"/heads
fi

# Finally update the refs

_x40='[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]'
_x40="$_x40$_x40$_x40$_x40$_x40$_x40$_x40$_x40"
echo
while read ref
do
	# avoid rewriting a ref twice
	test -f "$orig_namespace$ref" && continue

	sha1=$(git rev-parse "$ref"^0)
	rewritten=$(map $sha1)

	test $sha1 = "$rewritten" &&
		warn "WARNING: Ref '$ref' is unchanged" &&
		continue

	case "$rewritten" in
	'')
		echo "Ref '$ref' was deleted"
		git update-ref -m "filter-branch: delete" -d "$ref" $sha1 ||
			die "Could not delete $ref"
	;;
	$_x40)
		echo "Ref '$ref' was rewritten"
		if ! git update-ref -m "filter-branch: rewrite" \
					"$ref" $rewritten $sha1 2>/dev/null; then
			if test $(git cat-file -t "$ref") = tag; then
				if test -z "$filter_tag_name"; then
					warn "WARNING: You said to rewrite tagged commits, but not the corresponding tag."
					warn "WARNING: Perhaps use '--tag-name-filter cat' to rewrite the tag."
				fi
			else
				die "Could not rewrite $ref"
			fi
		fi
	;;
	*)
		# NEEDSWORK: possibly add -Werror, making this an error
		warn "WARNING: '$ref' was rewritten into multiple commits:"
		warn "$rewritten"
		warn "WARNING: Ref '$ref' points to the first one now."
		rewritten=$(echo "$rewritten" | head -n 1)
		git update-ref -m "filter-branch: rewrite to first" \
				"$ref" $rewritten $sha1 ||
			die "Could not rewrite $ref"
	;;
	esac
	git update-ref -m "filter-branch: backup" "$orig_namespace$ref" $sha1 ||
		 exit
done < "$tempdir"/heads

# TODO: This should possibly go, with the semantics that all positive given
#       refs are updated, and their original heads stored in refs/original/
# Filter tags

if [ "$filter_tag_name" ]; then
	git for-each-ref --format='%(objectname) %(objecttype) %(refname)' refs/tags |
	while read sha1 type ref; do
		ref="${ref#refs/tags/}"
		# XXX: Rewrite tagged trees as well?
		if [ "$type" != "commit" -a "$type" != "tag" ]; then
			continue;
		fi

		if [ "$type" = "tag" ]; then
			# Dereference to a commit
			sha1t="$sha1"
			sha1="$(git rev-parse -q "$sha1"^{commit})" || continue
		fi

		[ -f "../map/$sha1" ] || continue
		new_sha1="$(cat "../map/$sha1")"
		GIT_COMMIT="$sha1"
		export GIT_COMMIT
		new_ref="$(echo "$ref" | eval "$filter_tag_name")" ||
			die "tag name filter failed: $filter_tag_name"

		echo "$ref -> $new_ref ($sha1 -> $new_sha1)"

		if [ "$type" = "tag" ]; then
			new_sha1=$( ( printf 'object %s\ntype commit\ntag %s\n' \
						"$new_sha1" "$new_ref"
				git cat-file tag "$ref" |
				sed -n \
				    -e '1,/^$/{
					  /^object /d
					  /^type /d
					  /^tag /d
					}' \
				    -e '/^-----BEGIN PGP SIGNATURE-----/q' \
				    -e 'p' ) |
				git hash-object -t tag -w --stdin) ||
				die "Could not create new tag object for $ref"
			if git cat-file tag "$ref" | \
			   sane_grep '^-----BEGIN PGP SIGNATURE-----' >/dev/null 2>&1
			then
				warn "gpg signature stripped from tag object $sha1t"
			fi
		fi

		git update-ref "refs/tags/$new_ref" "$new_sha1" ||
			die "Could not write tag $new_ref"
	done
fi

unset GIT_DIR GIT_WORK_TREE GIT_INDEX_FILE
unset GIT_AUTHOR_NAME GIT_AUTHOR_EMAIL GIT_AUTHOR_DATE
unset GIT_COMMITTER_NAME GIT_COMMITTER_EMAIL GIT_COMMITTER_DATE
test -z "$ORIG_GIT_DIR" || {
	GIT_DIR="$ORIG_GIT_DIR" && export GIT_DIR
}
test -z "$ORIG_GIT_WORK_TREE" || {
	GIT_WORK_TREE="$ORIG_GIT_WORK_TREE" &&
	export GIT_WORK_TREE
}
test -z "$ORIG_GIT_INDEX_FILE" || {
	GIT_INDEX_FILE="$ORIG_GIT_INDEX_FILE" &&
	export GIT_INDEX_FILE
}
test -z "$ORIG_GIT_AUTHOR_NAME" || {
	GIT_AUTHOR_NAME="$ORIG_GIT_AUTHOR_NAME" &&
	export GIT_AUTHOR_NAME
}
test -z "$ORIG_GIT_AUTHOR_EMAIL" || {
	GIT_AUTHOR_EMAIL="$ORIG_GIT_AUTHOR_EMAIL" &&
	export GIT_AUTHOR_EMAIL
}
test -z "$ORIG_GIT_AUTHOR_DATE" || {
	GIT_AUTHOR_DATE="$ORIG_GIT_AUTHOR_DATE" &&
	export GIT_AUTHOR_DATE
}
test -z "$ORIG_GIT_COMMITTER_NAME" || {
	GIT_COMMITTER_NAME="$ORIG_GIT_COMMITTER_NAME" &&
	export GIT_COMMITTER_NAME
}
test -z "$ORIG_GIT_COMMITTER_EMAIL" || {
	GIT_COMMITTER_EMAIL="$ORIG_GIT_COMMITTER_EMAIL" &&
	export GIT_COMMITTER_EMAIL
}
test -z "$ORIG_GIT_COMMITTER_DATE" || {
	GIT_COMMITTER_DATE="$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($f = <F>);
				print H "$_:$f\n" or die;
			}
			close(H) or die;' || die "Unable to save state")
	state_tree=$(printf '100644 blob %s\tfilter.map\n' "$state_blob" | git mktree)
	if test -n "$state_commit"
	then
		state_commit=$(echo "Sync" | git commit-tree "$state_tree" -p "$state_commit")
	else
		state_commit=$(echo "Sync" | git commit-tree "$state_tree" )
	fi
	git update-ref "$state_branch" "$state_commit"
fi

cd "$orig_dir"
rm -rf "$tempdir"

trap - 0

if [ "$(is_bare_repository)" = false ]; then
	git read-tree -u -m HEAD || exit
fi

exit 0
Commit	Line	Data
6f6826c5 JS	1	#!/bin/sh
	2	#
	3	# Rewrite revision history
	4	# Copyright (c) Petr Baudis, 2006
	5	# Minimal changes to "port" it to core-git (c) Johannes Schindelin, 2007
	6	#
c401b33c JS	7	# Lets you rewrite the revision history of the current branch, creating
	8	# a new branch. You can specify a number of filters to modify the commits,
	9	# files and trees.
6f6826c5	10
16ed34ad JS	11	# The following functions will also be available in the commit filter:
	12
	13	functions=$(cat << \EOF
b5669a05	14	warn () {
285c6cbf	15	echo "$*" >&2
b5669a05 SP	16	}
b5669a05 SP	17
6f6826c5 JS	18	map()
6f6826c5 JS	19	{
3520e1e8	20	# if it was not rewritten, take the original
c57a3494 JS	21	if test -r "$workdir/../map/$1"
	22	then
	23	cat "$workdir/../map/$1"
	24	else
	25	echo "$1"
	26	fi
6f6826c5 JS	27	}
6f6826c5 JS	28
f95eef15 JS	29	# if you run 'skip_commit "$@"' in a commit filter, it will print
	30	# the (mapped) parents, effectively skipping the commit.
	31
	32	skip_commit()
	33	{
	34	shift;
	35	while [ -n "$1" ];
	36	do
	37	shift;
	38	map "$1";
	39	shift;
	40	done;
	41	}
	42
d3240d93 PH	43	# if you run 'git_commit_non_empty_tree "$@"' in a commit filter,
	44	# it will skip commits that leave the tree untouched, commit the other.
	45	git_commit_non_empty_tree()
	46	{
	47	if test $# = 3 && test "$1" = $(git rev-parse "$3^{tree}"); then
	48	map "$3"
a582a82d DP	49	elif test $# = 1 && test "$1" = 4b825dc642cb6eb9a060e54bf8d69288fbee4904; then
a582a82d DP	50	:
d3240d93 PH	51	else
	52	git commit-tree "$@"
	53	fi
	54	}
8c1ce0f4 JS	55	# override die(): this version puts in an extra line break, so that
	56	# the progress is still visible
	57
	58	die()
	59	{
	60	echo >&2
	61	echo "$*" >&2
	62	exit 1
	63	}
16ed34ad JS	64	EOF
	65	)
	66
	67	eval "$functions"
8c1ce0f4	68
3c730fab JK	69	finish_ident() {
	70	# Ensure non-empty id name.
	71	echo "case \"\$GIT_$1_NAME\" in \"\") GIT_$1_NAME=\"\${GIT_$1_EMAIL%%@*}\" && export GIT_$1_NAME;; esac"
	72	# And make sure everything is exported.
	73	echo "export GIT_$1_NAME"
	74	echo "export GIT_$1_EMAIL"
	75	echo "export GIT_$1_DATE"
	76	}
6f6826c5 JS	77
6f6826c5 JS	78	set_ident () {
3c730fab JK	79	parse_ident_from_commit author AUTHOR committer COMMITTER
	80	finish_ident AUTHOR
	81	finish_ident COMMITTER
6f6826c5 JS	82	}
6f6826c5 JS	83
e336afdf	84	USAGE="[--setup <command>] [--subdirectory-filter <directory>] [--env-filter <command>]
3b117f73 AH	85	[--tree-filter <command>] [--index-filter <command>]
	86	[--parent-filter <command>] [--msg-filter <command>]
	87	[--commit-filter <command>] [--tag-name-filter <command>]
e336afdf	88	[--original <namespace>]
bd2c79fb	89	[-d <directory>] [-f \| --force] [--state-branch <branch>]
d612975e	90	[--] [<rev-list options>...]"
7e0f1704	91
8f321a39	92	OPTIONS_SPEC=
7e0f1704 JS	93	. git-sh-setup
7e0f1704 JS	94
a4661b01	95	if [ "$(is_bare_repository)" = false ]; then
5347a50f	96	require_clean_work_tree 'rewrite branches'
a4661b01	97	fi
46eb449c	98
6f6826c5	99	tempdir=.git-rewrite
3b117f73	100	filter_setup=
6f6826c5 JS	101	filter_env=
	102	filter_tree=
	103	filter_index=
	104	filter_parent=
	105	filter_msg=cat
d3240d93	106	filter_commit=
6f6826c5	107	filter_tag_name=
685ef546	108	filter_subdir=
bd2c79fb	109	state_branch=
dfd05e38 JS	110	orig_namespace=refs/original/
dfd05e38 JS	111	force=
d3240d93	112	prune_empty=
f2f3a6b8	113	remap_to_ancestor=
822f7c73	114	while :
6f6826c5 JS	115	do
	116	case "$1" in
	117	--)
	118	shift
	119	break
	120	;;
dfd05e38 JS	121	--force\|-f)
	122	shift
	123	force=t
	124	continue
	125	;;
f2f3a6b8	126	--remap-to-ancestor)
7ec344d8	127	# deprecated ($remap_to_ancestor is set now automatically)
f2f3a6b8 TR	128	shift
	129	remap_to_ancestor=t
	130	continue
	131	;;
d3240d93 PH	132	--prune-empty)
	133	shift
	134	prune_empty=t
	135	continue
	136	;;
6f6826c5 JS	137	-*)
	138	;;
	139	*)
	140	break;
	141	esac
	142
	143	# all switches take one argument
	144	ARG="$1"
	145	case "$#" in 1) usage ;; esac
	146	shift
	147	OPTARG="$1"
	148	shift
	149
	150	case "$ARG" in
	151	-d)
	152	tempdir="$OPTARG"
	153	;;
3b117f73 AH	154	--setup)
	155	filter_setup="$OPTARG"
	156	;;
07c49845 DG	157	--subdirectory-filter)
	158	filter_subdir="$OPTARG"
	159	remap_to_ancestor=t
	160	;;
6f6826c5 JS	161	--env-filter)
	162	filter_env="$OPTARG"
	163	;;
	164	--tree-filter)
	165	filter_tree="$OPTARG"
	166	;;
	167	--index-filter)
	168	filter_index="$OPTARG"
	169	;;
	170	--parent-filter)
	171	filter_parent="$OPTARG"
	172	;;
	173	--msg-filter)
	174	filter_msg="$OPTARG"
	175	;;
	176	--commit-filter)
16ed34ad	177	filter_commit="$functions; $OPTARG"
6f6826c5 JS	178	;;
	179	--tag-name-filter)
	180	filter_tag_name="$OPTARG"
	181	;;
dfd05e38	182	--original)
55ced83d	183	orig_namespace=$(expr "$OPTARG/" : '\(.[^/]\)/$')/
dfd05e38	184	;;
bd2c79fb IC	185	--state-branch)
	186	state_branch="$OPTARG"
	187	;;
6f6826c5 JS	188	*)
	189	usage
	190	;;
	191	esac
	192	done
	193
d3240d93 PH	194	case "$prune_empty,$filter_commit" in
	195	,)
	196	filter_commit='git commit-tree "$@"';;
	197	t,)
	198	filter_commit="$functions;"' git_commit_non_empty_tree "$@"';;
	199	,*)
	200	;;
	201	*)
5da81713	202	die "Cannot set --prune-empty and --commit-filter at the same time"
d3240d93 PH	203	esac
d3240d93 PH	204
dfd05e38 JS	205	case "$force" in
	206	t)
	207	rm -rf "$tempdir"
	208	;;
	209	'')
	210	test -d "$tempdir" &&
	211	die "$tempdir already exists, please remove it"
	212	esac
97276019	213	orig_dir=$(pwd)
af580e9c	214	mkdir -p "$tempdir/t" &&
dfd05e38	215	tempdir="$(cd "$tempdir"; pwd)" &&
af580e9c JS	216	cd "$tempdir/t" &&
	217	workdir="$(pwd)" \|\|
	218	die ""
6f6826c5	219
def16e71	220	# Remove tempdir on exit
97276019	221	trap 'cd "$orig_dir"; rm -rf "$tempdir"' 0
def16e71	222
88e38808 LN	223	ORIG_GIT_DIR="$GIT_DIR"
	224	ORIG_GIT_WORK_TREE="$GIT_WORK_TREE"
	225	ORIG_GIT_INDEX_FILE="$GIT_INDEX_FILE"
7b1378bd IC	226	ORIG_GIT_AUTHOR_NAME="$GIT_AUTHOR_NAME"
	227	ORIG_GIT_AUTHOR_EMAIL="$GIT_AUTHOR_EMAIL"
	228	ORIG_GIT_AUTHOR_DATE="$GIT_AUTHOR_DATE"
	229	ORIG_GIT_COMMITTER_NAME="$GIT_COMMITTER_NAME"
	230	ORIG_GIT_COMMITTER_EMAIL="$GIT_COMMITTER_EMAIL"
	231	ORIG_GIT_COMMITTER_DATE="$GIT_COMMITTER_DATE"
	232
88e38808 LN	233	GIT_WORK_TREE=.
	234	export GIT_DIR GIT_WORK_TREE
	235
dfd05e38	236	# Make sure refs/original is empty
0ea29cce	237	git for-each-ref > "$tempdir"/backup-refs \|\| exit
dfd05e38 JS	238	while read sha1 type name
	239	do
	240	case "$force,$name" in
	241	,$orig_namespace*)
734cd572 JT	242	die "Cannot create a new backup.
	243	A previous backup already exists in $orig_namespace
	244	Force overwriting the backup with -f"
dfd05e38 JS	245	;;
	246	t,$orig_namespace*)
	247	git update-ref -d "$name" $sha1
	248	;;
	249	esac
	250	done < "$tempdir"/backup-refs
	251
418fa3a5	252	# The refs should be updated if their heads were rewritten
0ea29cce EK	253	git rev-parse --no-flags --revs-only --symbolic-full-name \
	254	--default HEAD "$@" > "$tempdir"/raw-heads \|\| exit
	255	sed -e '/^^/d' "$tempdir"/raw-heads >"$tempdir"/heads
dfd05e38 JS	256
dfd05e38 JS	257	test -s "$tempdir"/heads \|\|
69638939	258	die "You must specify a ref to rewrite."
dfd05e38	259
3addc94a JS	260	GIT_INDEX_FILE="$(pwd)/../index"
3addc94a JS	261	export GIT_INDEX_FILE
6f6826c5	262
af580e9c JS	263	# map old->new commit ids for rewriting parents
af580e9c JS	264	mkdir ../map \|\| die "Could not create map/ directory"
6f6826c5	265
bd2c79fb IC	266	if test -n "$state_branch"
	267	then
	268	state_commit=$(git rev-parse --no-flags --revs-only "$state_branch")
	269	if test -n "$state_commit"
	270	then
	271	echo "Populating map from $state_branch ($state_commit)" 1>&2
	272	perl -e'open(MAP, "-\|", "git show $ARGV[0]:filter.map") or die;
	273	while (<MAP>) {
	274	m/(.):(.)/ or die;
	275	open F, ">../map/$1" or die;
	276	print F "$2" or die;
	277	close(F) or die;
	278	}
	279	close(MAP) or die;' "$state_commit" \
	280	\|\| die "Unable to load state from $state_branch:filter.map"
	281	else
	282	echo "Branch $state_branch does not exist. Will create" 1>&2
	283	fi
	284	fi
	285
2c1d2d81 TR	286	# we need "--" only if there are no path arguments in $@
2c1d2d81 TR	287	nonrevs=$(git rev-parse --no-revs "$@") \|\| exit
7ec344d8 CH	288	if test -z "$nonrevs"
	289	then
	290	dashdash=--
	291	else
	292	dashdash=
	293	remap_to_ancestor=t
	294	fi
	295
3361a548	296	git rev-parse --revs-only "$@" >../parse
2c1d2d81	297
685ef546 JS	298	case "$filter_subdir" in
685ef546 JS	299	"")
2c1d2d81	300	eval set -- "$(git rev-parse --sq --no-revs "$@")"
685ef546 JS	301	;;
685ef546 JS	302	*)
2c1d2d81 TR	303	eval set -- "$(git rev-parse --sq --no-revs "$@" $dashdash \
	304	"$filter_subdir")"
	305	;;
	306	esac
	307
	308	git rev-list --reverse --topo-order --default HEAD \
3361a548	309	--parents --simplify-merges --stdin "$@" <../parse >../revs \|\|
2c1d2d81	310	die "Could not get the commits"
9d6f220c	311	commits=$(wc -l <../revs \| tr -d " ")
6f6826c5 JS	312
	313	test $commits -eq 0 && die "Found nothing to rewrite"
	314
dfd05e38	315	# Rewrite the commits
6a9d16a0 GB	316	report_progress ()
	317	{
	318	if test -n "$progress" &&
	319	test $git_filter_branch__commit_count -gt $next_sample_at
	320	then
71400d97 JH	321	count=$git_filter_branch__commit_count
	322
	323	now=$(date +%s)
	324	elapsed=$(($now - $start_timestamp))
	325	remaining=$(( ($commits - $count) * $elapsed / $count ))
	326	if test $elapsed -gt 0
6a9d16a0	327	then
71400d97	328	next_sample_at=$(( ($elapsed + 1) * $count / $elapsed ))
6a9d16a0 GB	329	else
	330	next_sample_at=$(($next_sample_at + 1))
	331	fi
71400d97	332	progress=" ($elapsed seconds passed, remaining $remaining predicted)"
6a9d16a0	333	fi
71400d97	334	printf "\rRewrite $commit ($count/$commits)$progress "
6a9d16a0	335	}
dfd05e38	336
d5b0c97d	337	git_filter_branch__commit_count=0
6a9d16a0 GB	338
	339	progress= start_timestamp=
	340	if date '+%s' 2>/dev/null \| grep -q '^[0-9][0-9]*$'
	341	then
	342	next_sample_at=0
	343	progress="dummy to ensure this is not empty"
	344	start_timestamp=$(date '+%s')
	345	fi
	346
348d4f2f JK	347	if test -n "$filter_index" \|\|
	348	test -n "$filter_tree" \|\|
	349	test -n "$filter_subdir"
	350	then
	351	need_index=t
	352	else
	353	need_index=
	354	fi
	355
3b117f73 AH	356	eval "$filter_setup" < /dev/null \|\|
	357	die "filter setup failed: $filter_setup"
	358
813b4734	359	while read commit parents; do
d5b0c97d	360	git_filter_branch__commit_count=$(($git_filter_branch__commit_count+1))
6a9d16a0 GB	361
6a9d16a0 GB	362	report_progress
6f6826c5	363
685ef546 JS	364	case "$filter_subdir" in
685ef546 JS	365	"")
348d4f2f JK	366	if test -n "$need_index"
	367	then
	368	GIT_ALLOW_NULL_SHA1=1 git read-tree -i -m $commit
	369	fi
685ef546 JS	370	;;
685ef546 JS	371	*)
5b044ac3	372	# The commit may not have the subdirectory at all
83bd7437 JK	373	err=$(GIT_ALLOW_NULL_SHA1=1 \
83bd7437 JK	374	git read-tree -i -m $commit:"$filter_subdir" 2>&1) \|\| {
d69da76d	375	if ! git rev-parse -q --verify $commit:"$filter_subdir"
5b044ac3 JH	376	then
	377	rm -f "$GIT_INDEX_FILE"
	378	else
	379	echo >&2 "$err"
	380	false
	381	fi
	382	}
af580e9c	383	esac \|\| die "Could not initialize the index"
6f6826c5	384
3addc94a JS	385	GIT_COMMIT=$commit
3addc94a JS	386	export GIT_COMMIT
af580e9c JS	387	git cat-file commit "$commit" >../commit \|\|
af580e9c JS	388	die "Cannot read commit $commit"
6f6826c5	389
3c730fab JK	390	eval "$(set_ident <../commit)" \|\|
3c730fab JK	391	die "setting author/committer failed for commit $commit"
8c1ce0f4 JS	392	eval "$filter_env" < /dev/null \|\|
8c1ce0f4 JS	393	die "env filter failed: $filter_env"
6f6826c5 JS	394
6f6826c5 JS	395	if [ "$filter_tree" ]; then
af580e9c JS	396	git checkout-index -f -u -a \|\|
af580e9c JS	397	die "Could not checkout the index"
6f6826c5 JS	398	# files that $commit removed are now still in the working tree;
6f6826c5 JS	399	# remove them, else they would be added again
6a589fda	400	git clean -d -q -f -x
8c1ce0f4 JS	401	eval "$filter_tree" < /dev/null \|\|
	402	die "tree filter failed: $filter_tree"
	403
1fe32cb9	404	(
4d2a3646	405	git diff-index -r --name-only --ignore-submodules $commit -- &&
1fe32cb9	406	git ls-files --others
0ea29cce EK	407	) > "$tempdir"/tree-state \|\| exit
	408	git update-index --add --replace --remove --stdin \
	409	< "$tempdir"/tree-state \|\| exit
6f6826c5 JS	410	fi
6f6826c5 JS	411
8c1ce0f4 JS	412	eval "$filter_index" < /dev/null \|\|
8c1ce0f4 JS	413	die "index filter failed: $filter_index"
6f6826c5 JS	414
6f6826c5 JS	415	parentstr=
813b4734	416	for parent in $parents; do
3520e1e8	417	for reparent in $(map "$parent"); do
79bc4ef3 CB	418	case "$parentstr " in
	419	" -p $reparent ")
	420	;;
	421	*)
	422	parentstr="$parentstr -p $reparent"
	423	;;
	424	esac
3520e1e8	425	done
6f6826c5 JS	426	done
6f6826c5 JS	427	if [ "$filter_parent" ]; then
8c1ce0f4 JS	428	parentstr="$(echo "$parentstr" \| eval "$filter_parent")" \|\|
8c1ce0f4 JS	429	die "parent filter failed: $filter_parent"
6f6826c5 JS	430	fi
6f6826c5 JS	431
df062010	432	{
a5a4b3ff	433	while IFS='' read -r header_line && test -n "$header_line"
df062010 JK	434	do
	435	# skip header lines...
	436	:;
	437	done
	438	# and output the actual commit message
	439	cat
	440	} <../commit \|
8c1ce0f4 JS	441	eval "$filter_msg" > ../message \|\|
8c1ce0f4 JS	442	die "msg filter failed: $filter_msg"
348d4f2f JK	443
	444	if test -n "$need_index"
	445	then
	446	tree=$(git write-tree)
	447	else
1dc413eb	448	tree=$(git rev-parse "$commit^{tree}")
348d4f2f	449	fi
0906f6e1	450	workdir=$workdir @SHELL_PATH@ -c "$filter_commit" "git commit-tree" \
348d4f2f	451	"$tree" $parentstr < ../message > ../map/$commit \|\|
0ea29cce	452	die "could not write rewritten commit"
6f6826c5 JS	453	done <../revs
6f6826c5 JS	454
f2f3a6b8 TR	455	# If we are filtering for paths, as in the case of a subdirectory
	456	# filter, it is possible that a specified head is not in the set of
	457	# rewritten commits, because it was pruned by the revision walker.
	458	# Ancestor remapping fixes this by mapping these heads to the unique
	459	# nearest ancestor that survived the pruning.
dfd05e38	460
f2f3a6b8	461	if test "$remap_to_ancestor" = t
a0e46390 TR	462	then
a0e46390 TR	463	while read ref
dfd05e38	464	do
a0e46390 TR	465	sha1=$(git rev-parse "$ref"^0)
a0e46390 TR	466	test -f "$workdir"/../map/$sha1 && continue
2c1d2d81	467	ancestor=$(git rev-list --simplify-merges -1 "$ref" "$@")
a0e46390 TR	468	test "$ancestor" && echo $(map $ancestor) >> "$workdir"/../map/$sha1
	469	done < "$tempdir"/heads
	470	fi
dfd05e38 JS	471
	472	# Finally update the refs
	473
	474	_x40='[0-9a-f][0-9a-f][0-9a-f][0-9a-f][0-9a-f]'
	475	_x40="$_x40$_x40$_x40$_x40$_x40$_x40$_x40$_x40"
dfd05e38 JS	476	echo
	477	while read ref
	478	do
	479	# avoid rewriting a ref twice
	480	test -f "$orig_namespace$ref" && continue
	481
	482	sha1=$(git rev-parse "$ref"^0)
	483	rewritten=$(map $sha1)
	484
	485	test $sha1 = "$rewritten" &&
	486	warn "WARNING: Ref '$ref' is unchanged" &&
	487	continue
	488
	489	case "$rewritten" in
	490	'')
	491	echo "Ref '$ref' was deleted"
	492	git update-ref -m "filter-branch: delete" -d "$ref" $sha1 \|\|
	493	die "Could not delete $ref"
98409060	494	;;
dfd05e38 JS	495	$_x40)
dfd05e38 JS	496	echo "Ref '$ref' was rewritten"
261044e8 TR	497	if ! git update-ref -m "filter-branch: rewrite" \
	498	"$ref" $rewritten $sha1 2>/dev/null; then
	499	if test $(git cat-file -t "$ref") = tag; then
	500	if test -z "$filter_tag_name"; then
	501	warn "WARNING: You said to rewrite tagged commits, but not the corresponding tag."
	502	warn "WARNING: Perhaps use '--tag-name-filter cat' to rewrite the tag."
	503	fi
	504	else
	505	die "Could not rewrite $ref"
	506	fi
	507	fi
98409060	508	;;
dfd05e38 JS	509	*)
	510	# NEEDSWORK: possibly add -Werror, making this an error
	511	warn "WARNING: '$ref' was rewritten into multiple commits:"
	512	warn "$rewritten"
	513	warn "WARNING: Ref '$ref' points to the first one now."
	514	rewritten=$(echo "$rewritten" \| head -n 1)
	515	git update-ref -m "filter-branch: rewrite to first" \
	516	"$ref" $rewritten $sha1 \|\|
	517	die "Could not rewrite $ref"
	518	;;
	519	esac
0ea29cce EK	520	git update-ref -m "filter-branch: backup" "$orig_namespace$ref" $sha1 \|\|
0ea29cce EK	521	exit
dfd05e38 JS	522	done < "$tempdir"/heads
	523
	524	# TODO: This should possibly go, with the semantics that all positive given
	525	# refs are updated, and their original heads stored in refs/original/
	526	# Filter tags
6f6826c5 JS	527
6f6826c5 JS	528	if [ "$filter_tag_name" ]; then
5be60078	529	git for-each-ref --format='%(objectname) %(objecttype) %(refname)' refs/tags \|
6f6826c5 JS	530	while read sha1 type ref; do
	531	ref="${ref#refs/tags/}"
	532	# XXX: Rewrite tagged trees as well?
	533	if [ "$type" != "commit" -a "$type" != "tag" ]; then
	534	continue;
	535	fi
	536
	537	if [ "$type" = "tag" ]; then
	538	# Dereference to a commit
	539	sha1t="$sha1"
7bd93c1c	540	sha1="$(git rev-parse -q "$sha1"^{commit})" \|\| continue
6f6826c5 JS	541	fi
	542
	543	[ -f "../map/$sha1" ] \|\| continue
	544	new_sha1="$(cat "../map/$sha1")"
3addc94a JS	545	GIT_COMMIT="$sha1"
3addc94a JS	546	export GIT_COMMIT
8c1ce0f4 JS	547	new_ref="$(echo "$ref" \| eval "$filter_tag_name")" \|\|
8c1ce0f4 JS	548	die "tag name filter failed: $filter_tag_name"
6f6826c5 JS	549
	550	echo "$ref -> $new_ref ($sha1 -> $new_sha1)"
	551
	552	if [ "$type" = "tag" ]; then
a9da1663 JS	553	new_sha1=$( ( printf 'object %s\ntype commit\ntag %s\n' \
	554	"$new_sha1" "$new_ref"
	555	git cat-file tag "$ref" \|
1bf6551e	556	sed -n \
9524cf29	557	-e '1,/^$/{
a9da1663 JS	558	/^object /d
	559	/^type /d
	560	/^tag /d
9524cf29	561	}' \
1bf6551e	562	-e '/^-----BEGIN PGP SIGNATURE-----/q' \
a9da1663	563	-e 'p' ) \|
b2c1ca6b	564	git hash-object -t tag -w --stdin) \|\|
1bf6551e BC	565	die "Could not create new tag object for $ref"
1bf6551e BC	566	if git cat-file tag "$ref" \| \
e1622bfc	567	sane_grep '^-----BEGIN PGP SIGNATURE-----' >/dev/null 2>&1
1bf6551e BC	568	then
	569	warn "gpg signature stripped from tag object $sha1t"
	570	fi
6f6826c5 JS	571	fi
6f6826c5 JS	572
af580e9c JS	573	git update-ref "refs/tags/$new_ref" "$new_sha1" \|\|
af580e9c JS	574	die "Could not write tag $new_ref"
6f6826c5 JS	575	done
	576	fi
	577
9273b562	578	unset GIT_DIR GIT_WORK_TREE GIT_INDEX_FILE
7b1378bd IC	579	unset GIT_AUTHOR_NAME GIT_AUTHOR_EMAIL GIT_AUTHOR_DATE
7b1378bd IC	580	unset GIT_COMMITTER_NAME GIT_COMMITTER_EMAIL GIT_COMMITTER_DATE
9273b562 EK	581	test -z "$ORIG_GIT_DIR" \|\| {
	582	GIT_DIR="$ORIG_GIT_DIR" && export GIT_DIR
	583	}
	584	test -z "$ORIG_GIT_WORK_TREE" \|\| {
	585	GIT_WORK_TREE="$ORIG_GIT_WORK_TREE" &&
	586	export GIT_WORK_TREE
	587	}
	588	test -z "$ORIG_GIT_INDEX_FILE" \|\| {
	589	GIT_INDEX_FILE="$ORIG_GIT_INDEX_FILE" &&
	590	export GIT_INDEX_FILE
	591	}
7b1378bd IC	592	test -z "$ORIG_GIT_AUTHOR_NAME" \|\| {
	593	GIT_AUTHOR_NAME="$ORIG_GIT_AUTHOR_NAME" &&
	594	export GIT_AUTHOR_NAME
	595	}
	596	test -z "$ORIG_GIT_AUTHOR_EMAIL" \|\| {
	597	GIT_AUTHOR_EMAIL="$ORIG_GIT_AUTHOR_EMAIL" &&
	598	export GIT_AUTHOR_EMAIL
	599	}
	600	test -z "$ORIG_GIT_AUTHOR_DATE" \|\| {
	601	GIT_AUTHOR_DATE="$ORIG_GIT_AUTHOR_DATE" &&
	602	export GIT_AUTHOR_DATE
	603	}
	604	test -z "$ORIG_GIT_COMMITTER_NAME" \|\| {
	605	GIT_COMMITTER_NAME="$ORIG_GIT_COMMITTER_NAME" &&
	606	export GIT_COMMITTER_NAME
	607	}
	608	test -z "$ORIG_GIT_COMMITTER_EMAIL" \|\| {
	609	GIT_COMMITTER_EMAIL="$ORIG_GIT_COMMITTER_EMAIL" &&
	610	export GIT_COMMITTER_EMAIL
	611	}
	612	test -z "$ORIG_GIT_COMMITTER_DATE" \|\| {
	613	GIT_COMMITTER_DATE="$ORIG_GIT_COMMITTER_DATE" &&
	614	export GIT_COMMITTER_DATE
	615	}
9273b562	616
bd2c79fb IC	617	if test -n "$state_branch"
	618	then
	619	echo "Saving rewrite state to $state_branch" 1>&2
	620	state_blob=$(
	621	perl -e'opendir D, "../map" or die;
	622	open H, "\|-", "git hash-object -w --stdin" or die;
	623	foreach (sort readdir(D)) {
	624	next if m/^\.\.?$/;
	625	open F, "<../map/$_" or die;
	626	chomp($f = <F>);
	627	print H "$_:$f\n" or die;
	628	}
	629	close(H) or die;' \|\| die "Unable to save state")
206a6ae0	630	state_tree=$(printf '100644 blob %s\tfilter.map\n' "$state_blob" \| git mktree)
bd2c79fb IC	631	if test -n "$state_commit"
bd2c79fb IC	632	then
206a6ae0	633	state_commit=$(echo "Sync" \| git commit-tree "$state_tree" -p "$state_commit")
bd2c79fb	634	else
206a6ae0	635	state_commit=$(echo "Sync" \| git commit-tree "$state_tree" )
bd2c79fb IC	636	fi
	637	git update-ref "$state_branch" "$state_commit"
	638	fi
	639
d24813c4 IC	640	cd "$orig_dir"
	641	rm -rf "$tempdir"
	642
	643	trap - 0
	644
a4661b01	645	if [ "$(is_bare_repository)" = false ]; then
0ea29cce	646	git read-tree -u -m HEAD \|\| exit
a4661b01	647	fi
46eb449c	648
0ea29cce	649	exit 0