Bash script to find duplicated images with different file names

dupes.sh

#!/opt/homebrew/bin/bash

image_dir="$1"
delete_mode=false

# Check if directory is provided
if [[ -z "$image_dir" ]]; then
    echo "Usage: $0 <image_directory> [--delete]"
    echo "If duplicates found, run with --delete to remove them."
    exit 1
fi

# Check if --delete parameter is provided
if [[ "$2" == "--delete" ]]; then
    delete_mode=true
fi

# Check if directory exists
if [[ ! -d "$image_dir" ]]; then
    echo "Error: Directory '$image_dir' does not exist."
    exit 1
fi

temp_file=$(mktemp) || exit 1

# Convert relative paths to absolute paths
image_dir=$(cd "$image_dir" && pwd)

# Find all image files, compute their hashes, and store in a temp file
find "$image_dir" -type f \( -name "*.jpg" -o -name "*.jpeg" -o -name "*.png" -o -name "*.gif" \) -print0 | while IFS= read -r -d $'\0' image_file; do
  image_hash=$(shasum -a 256 "$image_file" | awk '{print $1}')
  date_added=$(mdls -raw -n kMDItemDateAdded "$image_file")
  echo "$image_hash;$image_file;$date_added" >> "$temp_file"
done

# Read the temp file, sort by hash and date, and process duplicates
declare -A groups
while IFS=';' read -r hash file date; do
    if [[ -z "${groups[$hash]}" ]]; then
        groups["$hash"]="$file;$date" # First file in group (to keep)
    else
        groups["$hash"]+=$'\n'"$file;$date" # Additional files in group (to delete)
    fi
done < <(sort -t';' -k1,1 -k3 "$temp_file")

# Process each group of duplicates
for hash in "${!groups[@]}"; do
    IFS=$'\n' read -r -d '' -a files <<< "${groups[$hash]}"
    if [[ ${#files[@]} -gt 1 ]]; then # Only process groups with duplicates
        echo "Duplicate group (hash: $hash):"
        echo "  [KEEP] file://${files[0]%;*} (added: ${files[0]#*;})" # First file in group
        for ((i=1; i<${#files[@]}; i++)); do
            echo "  [DELETE] file://${files[$i]%;*} (added: ${files[$i]#*;})" # Additional files
        done

        if [[ "$delete_mode" == true ]]; then
            echo
            echo "The following files will be deleted:"
            for ((i=1; i<${#files[@]}; i++)); do
                echo "  file://${files[$i]%;*}"
            done
            read -p "Confirm delete? (y/n): " confirm
            if [[ "$confirm" == "y" || "$confirm" == "Y" ]]; then
                for ((i=1; i<${#files[@]}; i++)); do
                    rm "${files[$i]%;*}"
                    echo "Deleted: ${files[$i]%;*}"
                done
            else
                echo "Skipping deletion for this group."
            fi
        fi
    fi
done

rm "$temp_file"