#!/bin/sh
# How much of the very original version from Linus survive?

_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"

initial=$(git rev-parse --verify e83c5163316f89bfbde7d9ab23ca2e25604af290) &&
this=$(git rev-parse --verify ${1-HEAD}^0) || exit

tmp="/var/tmp/Linus.$$"
trap 'rm -f "$tmp".*' 0

# We blame each file in the initial revision pretending as if it is a
# direct descendant of the given version, and also pretend that the
# latter is a root commit.  This way, lines in the initial revision
# that survived to the other version can be identified (they will be
# attributed to the other version).
graft="$tmp.graft" &&
{
	echo "$initial $this"
	echo "$this"
} >"$graft" || exit

opts='-C -C -C -w'

show () {
	s=$1 t=$2 n=$3
	p=$(($s * 100 / $t))
	c=$(($s * 10000 / $t - $p * 100))
	printf "%12d %12d %s (%d.%02d%%)\n" $s $t $n $p $c
}

git ls-tree -r "$initial" |
while read mode type sha1 name
do
	git blame $opts --porcelain -S "$graft" "$initial" -- "$name" |
	sed -ne "s/^\($_x40\) .*/\1/p" |
	sort |
	uniq -c | {
		# There are only two commits in the fake history, so
		# there will be at most two output from the above.
		read cnt1 commit1
		read cnt2 commit2
		if test -z "$commit2"
		then
			cnt2=0
		fi
		if test "$initial" != "$commit1"
		then
			cnt_surviving=$cnt1
		else
			cnt_surviving=$cnt2
		fi
		cnt_total=$(( $cnt1 + $cnt2 ))
		echo "$cnt_surviving $cnt_total	$name"
	}
done | {
	total=0
	surviving=0
	printf "%12s %12s %s (survival%%)\n" surviving original path
	while read s t n
	do
		total=$(( $total + $t )) surviving=$(( $surviving + $s ))
		# printf "%12d %12d %s\n" $s $t $n
		show $s $t $n
	done
	# printf "%12d %12d %s\n" $surviving $total Total
	show $surviving $total Total
}