Find file in git based on md5 checksum.

find-by-hash.sh

#!/bin/sh

usage() {
	echo "Usage: $0 [-m] [-s] hash file"
	echo "\t-m use md5 for hashing"
	echo "\t-s use sha1 for hashing (this is the default)"
	exit 1
}

HASHCMD="sha1sum"

while getopts ":m:s" opt; do
	case $opt in
		m)
			HASHCMD="md5sum"
			shift
			;;
		s)
			HASHCMD="sha1sum"
			shift
			;;
	esac
done

CHECKSUM=$1
FILE=$2

if [ -z "$CHECKSUM" -o -z "$FILE" ]; then
	usage
fi

# Check if valid git repo
ROOT=$(git rev-parse --show-toplevel)

if [ $? -ne 0 ]; then
	echo "Not a valid git repo."
	exit 1
fi

cd $ROOT

# git revision for file
REVS=$(git rev-list --all -- $FILE)

# temp file
file_to_check=$(mktemp)

# check each revision for checksum
FOUND=""
for rev in $REVS; do
	git show $rev:$FILE > $file_to_check 2>/dev/null
	if $HASHCMD $file_to_check | grep -q $CHECKSUM; then
		FOUND="$rev"
		# intentionally no break to see if we find an older revision
		# insert a break if you want the most recent commit instead of the oldest
	fi
done

# cleanup
rm $file_to_check

# output
if [ -n "$FOUND" ]; then
	echo "$FOUND"
	exit 0
else
	echo "Not found: $CHECKSUM $FILE"
	exit 1
fi