git-similarity

#! /bin/sh
#
# git-similarity: script to compute similarity of two files

. git-sh-setup # for die() etc

TAB=$'\t'

# should probably use OPTIONS_SPEC, but not yet
usage()
{
	echo "usage: git similarity file1 file2"
}

case $# in
2) ;;
*) usage 1>&2; exit 1;;
esac

test -f "$1" || die "cannot find file $1, or not a regular file"
test -f "$2" || die "cannot find file $2, or not a regular file"
test "x$1" != "x$2" || die "file names $1 and $2 are identical"

TF=$(mktemp) || exit 1

trap "rm -f $TF" 0 1 2 3 15
export GIT_INDEX_FILE=$TF

# Create a tree holding (just) the argument file.
# TODO: handle files outside the repository entirely, by
# using git hash-object and git mktree directly.  (This
# will also remove the need for the temporary-file index.)
maketree() {
	rm -f $TF
	git add "$1" || exit 1
	git write-tree || exit 1
}

# Use git diff-tree here for repeatibility.  We expect output of
# the form Rnnn$TAB$file1$TAB$file2, but if we get two lines,
# with D and A, we'll just print 000 here.
print_similarity() {
	set $(git diff-tree -r --name-status --find-renames=01 $1 $2)
	case "$1" in
	R*) echo "${1#R}";;
	*) echo "000";;
	esac
}

h1=$(maketree "$1")
h2=$(maketree "$2")
print_similarity $h1 $h2