Find paths with some file hash in HWP

same-hash.sh

#!/bin/bash

IGNORE_HASHES=f6b0091b7e45d7d7a322157a88549b28

# Unzip all files
for user_dir in *; do
    if [ -d "$user_dir" ]; then
        # enter dir
        cd "$user_dir"
        # Extract
        for file in *; do
            if [ "${file: -4}" == ".zip" ]; then
                unzip -o "$file" > /dev/null
            elif [ "${file: -4}" == ".rar" ]; then
                unrar -o+ e "$file" > /dev/null
            elif [ "${file: -7}" == ".tar.gz" ]; then
                tar xf "$file" --overwrite > /dev/null
            elif [ "${file: -3}" == ".7z" ]; then
                7z -y e "$file" > /dev/null
            else
                echo "Unknown file type on $file"
            fi || exit 1
        done
        # exit dir
        cd ..
    fi
done

# Remove all garbage files
find . -iname \*.dpl -exec rm '{}' \;
find . -iname \*.dat -exec rm '{}' \;
find . -type d -name __MACOSX -exec rm -r '{}' \;

# Prehash all files for performance reasons
find . -type f -exec md5sum '{}' \; | rg -v $(echo $IGNORE_HASHES) > all_hashes.md5

# Hash all files and print checksums that occur more then once
cat all_hashes.md5 \
    | awk '{ print $1 }' \
    | sort \
    | uniq -c \
    | sort -n \
    | rg -v '^ *1 ' \
    | awk '{ print $2 }' > dub_hashes.txt

for sum in `cat dub_hashes.txt`; do
    echo ====================
    cat all_hashes.md5 \
        | rg "$sum" \
        | awk 'BEGIN{FS="  "} { print $2 }'
done