File: shame512.sh
   1 #!/bin/sh
   2 
   3 # The MIT License (MIT)
   4 #
   5 # Copyright © 2025 pacman64
   6 #
   7 # Permission is hereby granted, free of charge, to any person obtaining a copy
   8 # of this software and associated documentation files (the “Software”), to deal
   9 # in the Software without restriction, including without limitation the rights
  10 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  11 # copies of the Software, and to permit persons to whom the Software is
  12 # furnished to do so, subject to the following conditions:
  13 #
  14 # The above copyright notice and this permission notice shall be included in
  15 # all copies or substantial portions of the Software.
  16 #
  17 # THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  18 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  19 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  20 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  21 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  22 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  23 # SOFTWARE.
  24 
  25 
  26 # shame512 [options...] [files/folders...]
  27 #
  28 # Group files by common/same SHA-512 hashes: having the same hash means a high
  29 # chance of having the same contents, even though that's not a guarantee.
  30 #
  31 # Files and folder names can be given together for convenience: folder names
  32 # are searched recursively to find all files, including in any subfolders.
  33 #
  34 # The only option available is to show this help message, using any of
  35 # `-h`, `--h`, `-help`, or `--help`, without the quotes.
  36 
  37 
  38 case "$1" in
  39     -h|--h|-help|--help)
  40         awk '/^# +shame512 /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  41         exit 0
  42     ;;
  43 esac
  44 
  45 [ "$1" = "--" ] && shift
  46 
  47 if [ $# -eq 0 ]; then
  48     awk '/^# +shame512 /, /^$/ { gsub(/^# ?/, ""); print }' "$0" >&2
  49     exit 1
  50 fi
  51 
  52 for arg in "${@:-.}"; do
  53     if [ -f "${arg}" ]; then
  54         printf "%s\n" "${arg}"
  55         continue
  56     fi
  57 
  58     if [ -d "${arg}" ]; then
  59         if echo "${arg}" | grep -q '/$'; then
  60             stdbuf -oL find "${arg}" -type f
  61         else
  62             stdbuf -oL find "${arg}/" -type f
  63         fi
  64     fi
  65 done | awk -v ORS='\000' '!names[$0]++' | xargs -0 sha512sum | awk '
  66     {
  67         hash = $1
  68         name = substr($0, length($1) + 1)
  69         gsub(/^ *| *\r?$/, "", name)
  70 
  71         if (!(hash in names)) hashes[++num_hashes] = hash
  72         names[hash][length(names[hash]) + 1] = name
  73     }
  74 
  75     END {
  76         for (i = 1; i <= num_hashes; i++) {
  77             if (i > 1) print ""
  78             k = hashes[i]
  79             n = length(names[k])
  80             print k
  81             for (j = 1; j <= n; j++) print names[k][j]
  82         }
  83     }
  84 '