Efficiently detect content-duplicate files between two directories (app/ and vendor/) regardless of path. This script computes SHA256 hashes and file sizes to identify files in app/ that are binary-equivalent to any file in vendor/. It avoids expensive cmp comparisons by leveraging sorted hash lists and join. Ideal for large codebases with poten…

find-file-equivalents.sh

#!/bin/bash

# Step 1: Hash all files in app/ and vendor/ using sha256 and file size
find app -type f -exec stat --format="%s %n" {} + | while read -r size file; do
  hash=$(sha256sum "$file" | cut -d' ' -f1)
  echo "$size $hash $file"
done | sort > /tmp/app_files.txt

find vendor -type f -exec stat --format="%s %n" {} + | while read -r size file; do
  hash=$(sha256sum "$file" | cut -d' ' -f1)
  echo "$size $hash $file"
done | sort > /tmp/vendor_files.txt

# Step 2: Match based on size + hash
join -j 1 -o 1.1 1.2 1.3 2.3 -t' ' /tmp/app_files.txt /tmp/vendor_files.txt | awk '
  {
    printf "MATCH:\n  app:    %s\n  vendor: %s\n\n", $3, $4
  }
'