These are various scripts written by Nicole to assist the help desk in doing public records requests.

• email.php
  This script parses all the .eml files in a directory tree and attempts to scan them for a given list of words. It requires the MimeMailParser class.

  <?php
   
  // Import our mail parser
  require_once('MimeMailParser.class.php');
   
  // The list of words we want to keep
  $words = array(
  	'bail',
  	'pretrial release',
  	'pretrial justice',
  	'bond',
  	'bondsman',
  	'custody release',
  	'house arrest with electronic monitoring',
  	'written promise',
  	'surety',
  	'jail',
  	'jailer',
  	'juvenile detention center',	
  );
   
  // Get all of the files
  $files = getDirContents( getcwd() . '/emails' );
   
  for( $i = 0; $i < count( $files ); $i++ ) {
  	$move = false;
   
  	$filename = $files[ $i ];
   
  	echo 'Working on: ' . $filename . '<br>';
   
  	$parser = new MimeMailParser();
   
  	$parser->setPath( $filename );
   
  	$subject = $parser->getHeader( 'subject' );
   
  	$text = $parser->getMessageBody( 'text' );
   
  	if( contains( $subject, $words ) || contains( $text, $words ) ) {
  		unset( $parser );
   
  		// Get our destination directory
  		$newname = str_replace( 'C:\wamp64\www\email\emails', 'C:\wamp64\www\email\SAVED-EMAILS', $filename );
   
  		// Try to copy the file	
  		if( !copy( $filename, $newname ) ) {
   
  			// copy returned false, which means we hit an error!
  			echo 'Error on copy: ' . $filename . ' to ' . $newname . '<br>';	
   
  		// Copy was fine
  		} else {
   
  			// Delete the source file
  			unlink( $filename );
  		}
   
  	} else {
  		unset( $parser );
   
  		// Delete the source file
  		unlink( $filename );
  	}
  }
   
   
  /*
  $path = 'test.eml'; 
  $parser = new MimeMailParser(); 
  $parser->setPath( $path );
   
  $subject = $parser->getHeader( 'subject' );
   
  $text = $parser->getMessageBody( 'text' );
   
  echo $subject;
   
  echo '<br>';
   
  echo $text;
  */
   
   
  /*
   *  https://stackoverflow.com/questions/24783862/list-all-the-files-and-folders-in-a-directory-with-php-recursive-function
   */
  function getDirContents($dir, &$results = array()){
      $files = scandir($dir);
   
      foreach($files as $key => $value){
          $path = realpath($dir.DIRECTORY_SEPARATOR.$value);
   
          if(!is_dir($path)) {
              $results[] = $path;
          } else if($value != "." && $value != "..") {
              getDirContents($path, $results);
              $results[] = $path;
          }
      }
   
      return $results;
  }
   
   
  /*
   * https://stackoverflow.com/questions/13795789/check-if-string-contains-word-in-array
   */
  function contains($str, array $arr)
  {
      foreach($arr as $a) {
          if (stripos($str,$a) !== false) return true;
      }
      return false;
  }

• files.php
  This is a script that reads all the files in a directory tree and attempts to determine whether or not they contain any of the words in a list.

  <?php
   
  /*
   * This file is best run from the command line
   *  in the root directory of the files that need
   *  to be scanned.
   */
   
  /*
      composer.json contents:
   
      {
          "require": {
              "smalot/pdfparser": "*"
          }
      }
   
  */
   
  // Set the memory limit to something stupidly high so we can load large files
  ini_set('memory_limit','128G');
   
  // Include the composer autoloader.
  include 'vendor/autoload.php';
   
  // The list of words we want to keep
  $words = array(
  	'judicial standards commission',
  	'hunt gwynn',
  	'gwynn',
  );
   
  // The fallback word which will be used to "force" a document to be saved when
  //  it cannot be read. This fixes problems with "secure" PDFs.
  $catchWord = 'gwynn';
   
  // Only keep files on or after this date
  $start = '2018-06-01';
   
  // Get all of the files
  $files = getDirContents( getcwd() . '/files' );
   
  // Keep running while we have stuff to do
  while( count( $files ) > 0 ) {
   
      // Remove the first filename on the array
      $filename = array_shift( $files );
   
      // Windows loves to make stuff read only, fix that
      chmod( $filename, 0777 );
   
      // Output what file we're working on
  	echo "Working on: " . $filename . "\n";
   
      // Get some information about the file
      $pathInfo = pathinfo( $filename );
      $fileType = filetype( $filename );
   
      // Is this a directory?
      if( $fileType === 'dir' ) {
   
          // Output that it is
          echo "Investigating directory: " . $filename . "\n";
   
          // Is this directory empty?
          if( dir_is_empty( $filename ) ) {
   
              // Open the directory in PHP
              $handle = opendir( $filename );
   
              // Indicate this directory needs to go
              echo "     Removing directory: " . $filename . "\n";    
   
              // Close the directory in PHP - this allows it to be removed
              closedir( $handle );
   
              // Remove the directory
              rmdir( $filename );
   
              // Go to the next loop iteration
              continue;
   
          // Not empty, do nothing
          } else {
   
              // Put the filename back on the array at the end
              $files[] = $filename;
              continue;
          }
      }
   
      // Convert the lower bound time to a unix time
      $startTime = strtotime( $start );
   
      // Is the file older than the start time?
      if( filemtime( $filename ) < $startTime ) {
   
          // Indicate we're deleting it for being old
          echo '     Deleted due to age (' . date ( "F d Y H:i:s.", filemtime( $filename ) ) . ')\n';
   
          // Delete the file
          unlink( $filename );
   
          // Go to the next iteration of the loop
          continue;
      }
   
      // Set up a variable to hold the text of the document
      $text = '';
   
      // Do different things based on the file extension
      switch( $pathInfo[ 'extension' ] ) {
   
          // Is this a pdf?
          case 'pdf':
   
              // Attempt to parse the file using PdfParser
              try {
                  $parser = new \Smalot\PdfParser\Parser();
                  $pdf = $parser->parseFile( $filename );
                  $text = $pdf->getText();
   
              // This is a catch to ensure any secure pdfs (which can't be scanned)
              // are just assumed to be relevant
              } catch( Exception $e ) {
                  $text = $catchWord;
              }
   
              break;
   
          // Is it an office document?
          case 'docx':
          case 'xlsx':
          case 'pptx':
          case 'doc':
          	$docObj = new DocxConversion( $filename );
          	$text = $docObj->convertToText();
              break;
   
          // Everything else just dump the raw file into our text variable
          default:
              $text = file_get_contents( $filename );
              break;
   
      }
   
      // Check if the filename or file contents contain any of our words
  	if( contains( $filename, $words ) || contains( $text, $words ) ) {
   
  		// Get our destination directory
          $newdir = str_replace( '\files\\', '\saved\\', $pathInfo[ 'dirname'] );
   
          // Create our new filename using the new path
          $newname = $newdir . $pathInfo[ 'basename' ];
   
          // Check if the destination directory exists
          if (!file_exists( $newdir ) ) {
   
              // Create it
              mkdir( $newdir, 0777, true);
          }
   
  		// Try to copy the file	
  		if( !copy( $filename, $newname ) ) {
   
  			// copy returned false, which means we hit an error!
  			echo "     Error on copy: " . $filename . " to " . $newname . "\n";	
   
  		// Copy was fine
  		} else {
   
              // Indicate we're keeping the file
              echo "     KEEP: " . $filename . "\n";
   
  			// Delete the source file
  			unlink( $filename );
  		}
   
      // Words not found
  	} else {
   
          // Indicate we're deleting it
          echo "     DELETE: " . $filename . "\n";
   
  		// Delete the source file
  		unlink( $filename );
  	}
  }
   
   
  /*
   *  https://stackoverflow.com/questions/24783862/list-all-the-files-and-folders-in-a-directory-with-php-recursive-function
   */
  function getDirContents($dir, &$results = array()){
      $files = scandir($dir);
   
      foreach($files as $key => $value){
          $path = realpath($dir.DIRECTORY_SEPARATOR.$value);
   
          if(!is_dir($path)) {
              $results[] = $path;
          } else if($value != "." && $value != "..") {
              getDirContents($path, $results);
              $results[] = $path;
          }
      }
   
      return $results;
  }
   
   
  /*
   * https://stackoverflow.com/questions/7497733/how-can-i-use-php-to-check-if-a-directory-is-empty
   */
  function dir_is_empty($dir) {
    $handle = opendir($dir);
    while (false !== ($entry = readdir($handle))) {
      if ($entry != "." && $entry != "..") {
        closedir($handle);
        return FALSE;
      }
    }
    closedir($handle);
    return TRUE;
  }
   
   
  /*
   * https://stackoverflow.com/questions/13795789/check-if-string-contains-word-in-array
   */
  function contains($str, array $arr)
  {
      foreach($arr as $a) {
          if (stripos($str,$a) !== false) return true;
      }
      return false;
  }
   
   
      class DocxConversion{
      private $filename;
   
      public function __construct($filePath) {
          $this->filename = $filePath;
      }
   
      private function read_doc() {
          $fileHandle = fopen($this->filename, "r");
          $line = @fread($fileHandle, filesize($this->filename));   
          $lines = explode(chr(0x0D),$line);
          $outtext = "";
          foreach($lines as $thisline)
            {
              $pos = strpos($thisline, chr(0x00));
              if (($pos !== FALSE)||(strlen($thisline)==0))
                {
                } else {
                  $outtext .= $thisline." ";
                }
            }
           $outtext = preg_replace("/[^a-zA-Z0-9\s\,\.\-\n\r     @\/\_\(\)]/","",$outtext);
          return $outtext;
      }
   
      private function read_docx(){
   
          $striped_content = '';
          $content = '';
   
          $zip = zip_open($this->filename);
   
          if (!$zip || is_numeric($zip)) return false;
   
          while ($zip_entry = zip_read($zip)) {
   
              if (zip_entry_open($zip, $zip_entry) == FALSE) continue;
   
              if (zip_entry_name($zip_entry) != "word/document.xml") continue;
   
              $content .= zip_entry_read($zip_entry, zip_entry_filesize($zip_entry));
   
              zip_entry_close($zip_entry);
          }// end while
   
          zip_close($zip);
   
          $content = str_replace('</w:r></w:p></w:tc><w:tc>', " ", $content);
          $content = str_replace('</w:r></w:p>', "\r\n", $content);
          $striped_content = strip_tags($content);
   
          return $striped_content;
      }
   
   
  /*
   * Functions from stackoverflow to change office stuff into text files
   */
  function xlsx_to_text($input_file){
      $xml_filename = "xl/sharedStrings.xml"; //content file name
      $zip_handle = new ZipArchive;
      $output_text = "";
      if(true === $zip_handle->open($input_file)){
          if(($xml_index = $zip_handle->locateName($xml_filename)) !== false){
              $xml_datas = $zip_handle->getFromIndex($xml_index);
              $xml_handle = DOMDocument::loadXML($xml_datas, LIBXML_NOENT | LIBXML_XINCLUDE | LIBXML_NOERROR | LIBXML_NOWARNING);
              $output_text = strip_tags($xml_handle->saveXML());
          }else{
              $output_text .="";
          }
          $zip_handle->close();
      }else{
      $output_text .="";
      }
      return $output_text;
  }
   
  function pptx_to_text($input_file){
      $zip_handle = new ZipArchive;
      $output_text = "";
      if(true === $zip_handle->open($input_file)){
          $slide_number = 1; //loop through slide files
          while(($xml_index = $zip_handle->locateName("ppt/slides/slide".$slide_number.".xml")) !== false){
              $xml_datas = $zip_handle->getFromIndex($xml_index);
              $xml_handle = DOMDocument::loadXML($xml_datas, LIBXML_NOENT | LIBXML_XINCLUDE | LIBXML_NOERROR | LIBXML_NOWARNING);
              $output_text .= strip_tags($xml_handle->saveXML());
              $slide_number++;
          }
          if($slide_number == 1){
              $output_text .="";
          }
          $zip_handle->close();
      }else{
      $output_text .="";
      }
      return $output_text;
  }
   
   
  public function convertToText() {
      if(isset($this->filename) && !file_exists($this->filename)) {
          return "File Not exists";
      }
   
      $fileArray = pathinfo($this->filename);
   
      $file_ext  = $fileArray['extension'];
   
      if($file_ext == "doc" || $file_ext == "docx" || $file_ext == "xlsx" || $file_ext == "pptx")
          {
              if($file_ext == "doc") {
                  return $this->read_doc();
              } elseif($file_ext == "docx") {
                  return $this->read_docx();
              } elseif($file_ext == "xlsx") {
                  return $this->xlsx_to_text($this->filename);
              }elseif($file_ext == "pptx") {
                  return $this->pptx_to_text($this->filename);
              }
          } else {
              return "Invalid File Type";
          }
      }
  }