Display transliterated files and folders to non-accented ASCII characters script - rename feature tested successfully with a filesystem of over 65,000 files - USE AT OWN RISK!

transliterate_files.php

#!/usr/bin/php
<?php
// show and optionally rename files and dirs to transliterated unaccented ascii from current working folder
// 2019-12-24 Vijay Mahrra [email protected]
// code is public domain

define('DEBUG', true); // use pre-generated file list
define('VERBOSE', true);
define('RENAME', false); // allow renaming
define('RENAME_FILES', false);
define('RENAME_DIRS', false);
define('PRESERVE_TIME', true); // preserve earliest file time from m/c/atime

function output($message, $str = '', $date_format = 'Y-m-d h:i:s') {
    if (is_array($message)) {
      $message = print_r($message,1);
    }
    if (is_array($str)) {
      $str = print_r($str,1);
    }
    fwrite(STDOUT, sprintf("\n%s\t%s", date($date_format), $message));
    if (!empty($str)) {
      fwrite(STDOUT, "\n\t" . $str);
    }
    flush();
}

// get minimum, earliest time of a file path
function filetime_min($path) {
  if (!file_exists($path)) {
    return false;
  }
  $atime = fileatime($path);
  $mtime = filemtime($path);
  $ctime = filectime($path);
  return min($atime, $mtime, $ctime);
}

$include_paths = ['/data/','/media/', '/Users/', '/home/']; // ONLY process paths containing these strings
$ignore_paths = ['.debris', '/backup/']; // IGNORE paths containing these strings

if (DEBUG) {
  output("Include Path: ", $include_paths);
  output("Ignore Path: ", $ignore_paths);
}

//$tmpfile = 'files.txt'; // find . -type f > files.txt
if (!empty($tmpfile) && !file_exists($tmpfile)) {
  output("File to process does not exist: $tmpfile");
  goto end;
}

// generate a tmp file to be deleted after script ends
$i = 0;
if (empty($tmpfile)) {
    $delete_file = true;
    // get a temporary filename to process all files in subfolders
    $tmpfile = realpath(tempnam(sys_get_temp_dir(), 'php_transliterate_'));
    if (DEBUG)
      output("Created tmpfile: $tmpfile");
    $cmd = 'find ' . getcwd()  . ' -type f > ' . realpath($tmpfile);
    if (DEBUG)
      output("Generating files list: $cmd");
    system($cmd);
    if (0 == filesize($tmpfile)) {
      if (DEBUG) {
        output("Could not generate tmp file: $tmpfile\n");
        goto end;
      }
    }
}

// dirs and files to be renamed
$rename_dirs = [];
$rename_files = [];

$h = fopen($tmpfile, 'r'); // process line by line to avoid memory issues
while (($path = fgets($h)) !== false) {
    $i++;

    // check if the path should be ignored or not
    $path = trim($path);
    $path_ok = false;
    foreach ($include_paths as $str) {
        if (!empty($str) && strstr($path, $str) !== false) {
            $path_ok = true;
            break;
        }
    }
    foreach ($ignore_paths as $str) {
        if (!empty($str) && strstr($path, $str) !== false) {
            $path_ok = false;
            break;
        }
    }
    if (!$path_ok) {
      if (VERBOSE) {
        output("Skipping:", $path);
      }
      continue;
    }

    // get the current dir and filename
    if (DEBUG) {
      if (VERBOSE) {
        output("Checking:", $path);
      }
    }
    $filename = basename($path);
    $dir = substr($path, 0, strlen($path) - strlen($filename) - 1);

    // check the dir has characters that can be transliterated, if so, add to list
    $newdir =  iconv('UTF-8', 'ASCII//TRANSLIT//IGNORE', $dir);
    if (!empty($newdir) && $newdir !== $dir && !array_key_exists($newdir, $rename_dirs)) {
        if (VERBOSE)
        output("Will transliterate directory: $dir");
        $rename_dirs[iconv('ASCII//TRANSLIT//IGNORE', 'UTF-8', $newdir)] = $dir;
    }

    // if the filename can be transliterated, add to list
    $newfilename = iconv('UTF-8', 'ASCII//TRANSLIT//IGNORE', $filename);
    if (!empty($newfilename) && $newfilename !== $filename) {
      if (VERBOSE)
      output("Will transliterate file: $filename");
      $rename_files[$path] = $dir . '/' . iconv('ASCII//TRANSLIT//IGNORE', 'UTF-8', $newfilename);
    }
}
fclose($h);

// list files normalized
echo "\n";
foreach ($rename_files as $path => $newpath) {
    printf("\n%s\n%s\t\n%s\t\n", $path, basename($path), basename($newpath));
    if (RENAME && RENAME_FILES) { //  && file_exists($path) && is_file($path)
      $ts = filetime_min($path);
      if (!rename($path, $newpath)) {
          if (VERBOSE)
            output("Could not rename file!\n\t$path\n\t$newpath");
      } else if (file_exists($newpath) && PRESERVE_TIME) {
        touch($newpath, $ts, $ts);
      }
    }
}

echo "\n";
$renames = [];
foreach ($rename_dirs as $dest => $src) {
    $src_parts = (preg_split('/\//', $src));
    $dest_parts = (preg_split('/\//', $dest));
    foreach ($src_parts as $i => $part) {
      if ($src_parts[$i] !== $dest_parts[$i]) {
        $a = '/' . join('/', array_slice($src_parts,1,$i));
        $b = '/' . join('/', array_slice($dest_parts,1,$i));
        $src_parts[$i] = $dest_parts[$i];
        $renames[$a] = $b;
      }
    }
}
foreach ($renames as $path => $newpath) {
    printf("\n%s\t\n%s\t\n", $path, $newpath);
    if (RENAME && RENAME_DIRS && file_exists($path) && is_dir($path)) {
      $ts = filetime_min($path);
      if (!rename($path, $newpath)) {
          if (VERBOSE)
            output("Could not rename file!\n\t$path\n\t$newpath");
      } else if (file_exists($newpath) && PRESERVE_TIME) {
        touch($newpath, $ts, $ts);
      }
    }
}

// if tmp file was created
if (!empty($delete_file)) {
    if (DEBUG)
      output("Deleting tmp file: " . $tmpfile);
    unlink($tmpfile);
}

end:
output("Processed files: " . (int) $i);

if (!empty($rename_files)) {
  output("Transliterated files: " . count($rename_files));
}
if (!empty($rename_dirs)) {
  output("Transliterated dirs: " . count($rename_dirs));
}

echo "\n";