Compare all filenames inside a folder for similarity.

similar-filenames.sh

#!/bin/bash

# Exit on errors, use last pipe error code, do not overwrite files, ensure
# variables exist
set -o errexit -o pipefail -o noclobber -o nounset

# allow matching of files by glob directly without find
shopt -s globstar nullglob

# Set color codes for use with echo
LIGHT_BLUE='\e[94m'
LIGHT_GREEN='\e[92m'
LIGHT_RED='\e[91m'
LIGHT_YELLOW='\e[93m'
NC='\e[0m'

if ! hash fstrcmp 2>/dev/null; then
	echo -e "${LIGHT_BLUE}fstrcmp${LIGHT_YELLOW} is not available.${NC}"

	if ! hash lsb_release 2>/dev/null; then
		echo -e "${LIGHT_RED}Could not determine OS distribution!${NC}"
		echo -e "${LIGHT_BLUE}lsb_release${NC} is not available."
		exit 1
	fi

	if [[ ("$(lsb_release -is)" == "Debian") || (\
	"$(lsb_release -is)" == "Ubuntu") ]]; then
		sudo apt-get install -y fstrcmp
	else
		echo -e "${LIGHT_RED}Could not install ${LIGHT_BLUE}fstrcmp${LIGHT_RED}" \
			" automatically!${NC}"
		echo -e "Please install it manually."
		exit 1
	fi
fi

DISTANCE_MINIMUM=0.9
INPUT_PATH=""
IS_PROGRESS_SHOWN=false

function usage() {
	echo -e "usage: ${0##*/} ${LIGHT_YELLOW}<options>${NC}"
	echo -e ""
	echo -e "${LIGHT_YELLOW}options${NC}"
	echo -e "    -d, --distance            The minimum distance for comparison."
	echo -e "    -i, --input-path *        The files' source path."
	echo -e "    -h, --help                Display this help."
	echo -e "    -p, --progress            Display progress."
	echo -e ""
	echo -e "*=required"
	exit 1
}

FILES=()

function scan() {
	INPUT_PATH="$1"

	echo -e "Scanning directory..."

	while read -r -d $'\0' name
	do
		fileName="$(basename "$name")"
		FILES+=("$fileName")
	done < <(find "$INPUT_PATH" -type f -print0)
}

function compare() {
	DISTANCE_MINIMUM="$1"
	IS_PROGRESS_SHOWN="$2"

    comparison_count=$((((${#FILES[@]})*(${#FILES[@]}-1))/2))
    comparison_index=0

	echo -e "Comparing with minimum distance $DISTANCE_MINIMUM (${#FILES[@]} files, $comparison_count comparisons)..."

	for i in $(eval echo "{0..$((${#FILES[@]}-1))}")
    do
        if [ "$i" = $((${#FILES[@]}-1)) ]; then
            break
        fi

        for j in $(eval echo "{$(("$i"+1))..$((${#FILES[@]}-1))}")
        do
            distance=$(fstrcmp "${FILES[$i]}" "${FILES[$j]}")

            if [ "$IS_PROGRESS_SHOWN" = "true" ]; then
                comparison_index=$(("$comparison_index"+1))
                echo -ne "$((100*"$comparison_index"/"$comparison_count"))% ($comparison_index/$comparison_count)\r"
            fi

            if (( $(echo "$distance > $DISTANCE_MINIMUM" | bc -l) )); then
                echo -e "\n${FILES[$i]}\n${FILES[$j]}\n$distance"
            fi
        done
    done
}

# Check if getopt is available
# shellcheck disable=SC2251
! getopt --test >/dev/null
if [[ ${PIPESTATUS[0]} -ne 4 ]]; then
	echo -e "${LIGHT_RED}Cannot parse parameters!${NC}"
	exit 1
fi

# Parse command line parameters
OPTIONS=d:hi:p
LONGOPTS=distance:,help,input-path:,progress

# shellcheck disable=SC2251
! PARSED=$(getopt --options=$OPTIONS --longoptions=$LONGOPTS \
	--name "$0" -- "$@")
if [[ ${PIPESTATUS[0]} -ne 0 ]]; then
	exit 2
fi

eval set -- "$PARSED"

while true; do
	case "$1" in
	-d | --distance)
		DISTANCE_MINIMUM="$2"
        shift 2
		;;
	-h | --help)
		echo -e "Find similar filenames."
		echo -e ""
		usage
		;;
	-i | --input-path)
		INPUT_PATH="$2"
		shift 2
		;;
	-p | --progress)
		IS_PROGRESS_SHOWN=true
		shift 1
		;;
	--)
		shift
		break
		;;
	*)
		echo -e "${LIGHT_RED}Programming error!${NC}"
		exit 2
		;;
	esac
done

if [ -z "$INPUT_PATH" ]; then
	echo -e "${LIGHT_RED}Input path not provided!${NC}"
	usage
	exit 1
fi

if [ ! -d "$INPUT_PATH" ]; then
	echo -e "${LIGHT_RED}Input path is not a directory!${NC}"
	exit 1
fi

scan "$INPUT_PATH"
compare "$DISTANCE_MINIMUM" "$IS_PROGRESS_SHOWN"

echo -e "\n${LIGHT_GREEN}Done${NC}"