Used to cleanup duplicate files. (by filename local to the folder)

dedup.php

#!/usr/bin/php
<?php

/**
 * 1. Find all files that have the common symbols for copied files " (1)."
 * 2. Sort list by the largest file size
 * 3. Delete all other matches (and original filename without the number indication)
 * 4. Rename the largest to match the original name
 *
 * This program uses a TXT to read in the index of files.
 * Run the following to dump the file list.
 *
 *   find "$PWD" -type f > index.txt
 *
 * Glob was not used since the normal find command can speed through it and allow for testing.
 *
 */

echo "Finding Files" . PHP_EOL;

$all = file('index.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);

// Detect Duplicate Files from the Index
$dups = array_filter($all, function ($fname) {
	return preg_match("/ \(\d+\)\./m", $fname);
});

$pairs = [];

// Loop through the files and pair them up by the "root" or "main" part of the filename
foreach($dups as $fname) {
	// Remove the duplicate number indication using regex.
	$pk = preg_replace("/ \(\d+\)\./m", ".", $fname);
	$pkFn = basename($pk);
	
	if(!isset($pairs[ $pkFn ])) {
		$pairs[ $pkFn ] = array();
		
		// Check if a file exists without the duplicate number indication
		if (file_exists($pk)) {
			$pairs[ $pkFn ][] = $pk;
		}
	}
	
	$pairs[ $pkFn ][] = $fname;
}

// Order Each of the Pairs by Size (Largest First)
foreach($pairs as $key => $set) {
	usort($pairs[$key], function ($a, $b){
		// Check filesize
		return filesize($b) - filesize($a);
	});
}

// Loop through each pair and rename the first entry [0] (largest) and delete the others
foreach($pairs as $bestName => $set) {
	if(count($set) === 1) {
		echo "Skip" . PHP_EOL;
		continue;
	}
	
	$newFileOldName = $set[0];
	foreach($set as $index => $fname) {
		// Skip the first entry.
		if ($index === 0) continue;
		echo "Remove " . $fname . PHP_EOL;
		unlink($fname);
	}
	
	// Rename the new file to be the correct file
	$newFileNewName = str_replace(basename($newFileOldName), $bestName, $newFileOldName);
	
	if ($newFileNewName !== $newFileOldName) {
		echo "Rename " . $newFileOldName . " -> " . $newFileNewName . PHP_EOL;
	}
	
	rename($newFileOldName, $newFileNewName);

	echo PHP_EOL;
	echo PHP_EOL;
}


echo "Done" . PHP_EOL;

?>