Merge branch 'rs/subtree-fixes'

Various subtree fixes.

* rs/subtree-fixes:
  subtree: performance improvement for finding unexpected parent commits
  subtree: improve decision on merges kept in split
  subtree: use commits before rejoins for splits
  subtree: make --ignore-joins pay attention to adds
  subtree: refactor split of a commit into standalone method

1 files changed, 83 insertions, 46 deletions

diff --git a/contrib/subtree/git-subtree.sh b/contrib/subtree/git-subtree.sh
index d3f39a862a..147201dc6c 100755
--- a/contrib/subtree/git-subtree.sh
+++ b/contrib/subtree/git-subtree.sh
@@ -231,12 +231,14 @@ cache_miss () {
 }
 
 check_parents () {
-	missed=$(cache_miss "$@")
+	missed=$(cache_miss "$1")
+	local indent=$(($2 + 1))
 	for miss in $missed
 	do
 		if ! test -r "$cachedir/notree/$miss"
 		then
 			debug "  incorrect order: $miss"
+			process_split_commit "$miss" "" "$indent"
 		fi
 	done
 }
@@ -340,7 +342,12 @@ find_existing_splits () {
 	revs="$2"
 	main=
 	sub=
-	git log --grep="^git-subtree-dir: $dir/*\$" \
+	local grep_format="^git-subtree-dir: $dir/*\$"
+	if test -n "$ignore_joins"
+	then
+		grep_format="^Add '$dir/' from commit '"
+	fi
+	git log --grep="$grep_format" \
 		--no-show-signature --pretty=format:'START %H%n%s%n%n%b%nEND%n' $revs |
 	while read a b junk
 	do
@@ -534,6 +541,7 @@ copy_or_skip () {
 	nonidentical=
 	p=
 	gotparents=
+	copycommit=
 	for parent in $newparents
 	do
 		ptree=$(toptree_for_commit $parent) || exit $?
@@ -541,7 +549,24 @@ copy_or_skip () {
 		if test "$ptree" = "$tree"
 		then
 			# an identical parent could be used in place of this rev.
-			identical="$parent"
+			if test -n "$identical"
+			then
+				# if a previous identical parent was found, check whether
+				# one is already an ancestor of the other
+				mergebase=$(git merge-base $identical $parent)
+				if test "$identical" = "$mergebase"
+				then
+					# current identical commit is an ancestor of parent
+					identical="$parent"
+				elif test "$parent" != "$mergebase"
+				then
+					# no common history; commit must be copied
+					copycommit=1
+				fi
+			else
+				# first identical parent detected
+				identical="$parent"
+			fi
 		else
 			nonidentical="$parent"
 		fi
@@ -564,7 +589,6 @@ copy_or_skip () {
 		fi
 	done
 
-	copycommit=
 	if test -n "$identical" && test -n "$nonidentical"
 	then
 		extras=$(git rev-list --count $identical..$nonidentical)
@@ -598,6 +622,58 @@ ensure_valid_ref_format () {
 		die "'$1' does not look like a ref"
 }
 
+process_split_commit () {
+	local rev="$1"
+	local parents="$2"
+	local indent=$3
+
+	if test $indent -eq 0
+	then
+		revcount=$(($revcount + 1))
+	else
+		# processing commit without normal parent information;
+		# fetch from repo
+		parents=$(git rev-parse "$rev^@")
+		extracount=$(($extracount + 1))
+	fi
+
+	progress "$revcount/$revmax ($createcount) [$extracount]"
+
+	debug "Processing commit: $rev"
+	exists=$(cache_get "$rev")
+	if test -n "$exists"
+	then
+		debug "  prior: $exists"
+		return
+	fi
+	createcount=$(($createcount + 1))
+	debug "  parents: $parents"
+	check_parents "$parents" "$indent"
+	newparents=$(cache_get $parents)
+	debug "  newparents: $newparents"
+
+	tree=$(subtree_for_commit "$rev" "$dir")
+	debug "  tree is: $tree"
+
+	# ugly.  is there no better way to tell if this is a subtree
+	# vs. a mainline commit?  Does it matter?
+	if test -z "$tree"
+	then
+		set_notree "$rev"
+		if test -n "$newparents"
+		then
+			cache_set "$rev" "$rev"
+		fi
+		return
+	fi
+
+	newrev=$(copy_or_skip "$rev" "$tree" "$newparents") || exit $?
+	debug "  newrev is: $newrev"
+	cache_set "$rev" "$newrev"
+	cache_set latest_new "$newrev"
+	cache_set latest_old "$rev"
+}
+
 cmd_add () {
 	if test -e "$dir"
 	then
@@ -689,12 +765,7 @@ cmd_split () {
 		done
 	fi
 
-	if test -n "$ignore_joins"
-	then
-		unrevs=
-	else
-		unrevs="$(find_existing_splits "$dir" "$revs")"
-	fi
+	unrevs="$(find_existing_splits "$dir" "$revs")"
 
 	# We can't restrict rev-list to only $dir here, because some of our
 	# parents have the $dir contents the root, and those won't match.
@@ -703,45 +774,11 @@ cmd_split () {
 	revmax=$(eval "$grl" | wc -l)
 	revcount=0
 	createcount=0
+	extracount=0
 	eval "$grl" |
 	while read rev parents
 	do
-		revcount=$(($revcount + 1))
-		progress "$revcount/$revmax ($createcount)"
-		debug "Processing commit: $rev"
-		exists=$(cache_get "$rev")
-		if test -n "$exists"
-		then
-			debug "  prior: $exists"
-			continue
-		fi
-		createcount=$(($createcount + 1))
-		debug "  parents: $parents"
-		newparents=$(cache_get $parents)
-		debug "  newparents: $newparents"
-
-		tree=$(subtree_for_commit "$rev" "$dir")
-		debug "  tree is: $tree"
-
-		check_parents $parents
-
-		# ugly.  is there no better way to tell if this is a subtree
-		# vs. a mainline commit?  Does it matter?
-		if test -z "$tree"
-		then
-			set_notree "$rev"
-			if test -n "$newparents"
-			then
-				cache_set "$rev" "$rev"
-			fi
-			continue
-		fi
-
-		newrev=$(copy_or_skip "$rev" "$tree" "$newparents") || exit $?
-		debug "  newrev is: $newrev"
-		cache_set "$rev" "$newrev"
-		cache_set latest_new "$newrev"
-		cache_set latest_old "$rev"
+		process_split_commit "$rev" "$parents" 0
 	done || exit $?
 
 	latest_new=$(cache_get latest_new)