[PATCH 2/7] subtree: exclude commits predating add from recursive processing

From: Tom Clarkson via GitGitGadget <gitgitgadget@gmail.com>
Date: May 11, 2020, 05:49 UTC
Message-ID: <87af5a316a2ca75e28fda466a04c27bdb02b96b2.1589176201.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.493.git.1589176201.gitgitgadget@gmail.com>

From: Tom Clarkson <tom@tqclarkson.com>

Include recursion depth in debug logs so we can see when the recursion is getting out of hand.

Making the cache handle null mappings correctly and adding older commits to the cache allows the recursive algorithm to terminate at any point on mainline rather than needing to reach either the add point or the initial commit.

Signed-off-by: Tom Clarkson <tom@tqclarkson.com>
---
 contrib/subtree/git-subtree.sh | 37 +++++++++++++++++++++++++++++++---
 1 file changed, 34 insertions(+), 3 deletions(-)

diff --git a/contrib/subtree/git-subtree.sh b/contrib/subtree/git-subtree.sh
index 9867718503c..da0eede6979 100755
--- a/contrib/subtree/git-subtree.sh
+++ b/contrib/subtree/git-subtree.sh
@@ -244,7 +244,7 @@ check_parents () {
 	do
 		if ! test -r "$cachedir/notree/$miss"
 		then
-			debug "  incorrect order: $miss"
+			debug "  unprocessed parent commit: $miss ($indent)"
 			process_split_commit "$miss" "" "$indent"
 		fi
 	done
@@ -392,6 +392,26 @@ find_existing_splits () {
 	done
 }
 
+find_mainline_ref () {
+	debug "Looking for first split..."
+	dir="$1"
+	revs="$2"
+	main=
+	sub=
+	local grep_format="^git-subtree-dir: $dir/*\$"
+	git log --reverse --grep="$grep_format" \
+		--no-show-signature --pretty=format:'START %H%n%s%n%n%b%nEND%n' $revs |
+	while read a b junk
+	do
+		case "$a" in
+		git-subtree-mainline:)
+			echo "$b"
+			return
+			;;
+		esac
+	done
+}
+
 copy_commit () {
 	# We're going to set some environment vars here, so
 	# do it in a subshell to get rid of them safely later
@@ -646,9 +666,9 @@ process_split_commit () {
 
 	progress "$revcount/$revmax ($createcount) [$extracount]"
 
-	debug "Processing commit: $rev"
+	debug "Processing commit: $rev ($indent)"
 	exists=$(cache_get "$rev")
-	if test -n "$exists"
+	if test -z "$(cache_miss "$rev")"
 	then
 		debug "  prior: $exists"
 		return
@@ -773,6 +793,17 @@ cmd_split () {
 
 	unrevs="$(find_existing_splits "$dir" "$revs")"
 
+	mainline="$(find_mainline_ref "$dir" "$revs")"
+	if test -n "$mainline"
+	then
+		debug "Mainline $mainline predates subtree add"
+		git rev-list --topo-order --skip=1 $mainline |
+		while read rev
+		do
+			cache_set "$rev" ""
+		done || exit $?
+	fi
+
 	# We can't restrict rev-list to only $dir here, because some of our
 	# parents have the $dir contents the root, and those won't match.
 	# (and rev-list --follow doesn't seem to solve this)

-- 
gitgitgadget