Symfony 1 validator for Microsoft Office 2007 docs

sfValidatorOffice2007File.class.php

<?php

/**
 * Adds MIME-type guessers for Office 2007 documents
 *
 * @author John Kary <johnkary@ku.edu>
 */
class sfValidatorOffice2007File extends sfValidatorFile
{
    /**
     * Office 2007 MIME-types by file extension
     *
     * @var array
     */
    protected $office2007MimeTypes = array(
        'docm' => 'application/vnd.ms-word.document.macroEnabled.12',
        'docx' => 'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
        'dotx' => 'application/vnd.openxmlformats-officedocument.wordprocessingml.template',
        'potm' => 'application/vnd.ms-powerpoint.template.macroEnabled.12',
        'potx' => 'application/vnd.openxmlformats-officedocument.presentationml.template',
        'ppam' => 'application/vnd.ms-powerpoint.addin.macroEnabled.12',
        'ppsm' => 'application/vnd.ms-powerpoint.slideshow.macroEnabled.12',
        'ppsx' => 'application/vnd.openxmlformats-officedocument.presentationml.slideshow',
        'pptm' => 'application/vnd.ms-powerpoint.presentation.macroEnabled.12',
        'pptx' => 'application/vnd.openxmlformats-officedocument.presentationml.presentation',
        'xlam' => 'application/vnd.ms-excel.addin.macroEnabled.12',
        'xlsb' => 'application/vnd.ms-excel.sheet.binary.macroEnabled.12',
        'xlsm' => 'application/vnd.ms-excel.sheet.macroEnabled.12',
        'xlsx' => 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
        'xltm' => 'application/vnd.ms-excel.template.macroEnabled.12',
        'xltx' => 'application/vnd.openxmlformats-officedocument.spreadsheetml.template',
    );

    protected function configure($options = array(), $messages = array())
    {
        parent::configure($options, $messages);

        $this->setOption('mime_type_guessers', array(array($this, 'guessOffice2007WordDoc')) + $this->getOption('mime_type_guessers'));
    }

    /**
     * Guesses Office 2007 MIME-type of file, if applicable
     *
     * @param string $file  Absolute path to the file
     * @return string       The mime type of the file (null if not guessable)
     */
    protected function guessOffice2007WordDoc($file)
    {
        if (!$this->isZipMimeType($file)) {
            return null;
        }

        if (!class_exists('ZipArchive')) {
            //PHP not compiled with zip extension
            return null;
        }

        $zip = new \ZipArchive();
        if (!$zip->open($file)) {
            //Unable to open zip file
            return null;
        }

        if (!$zip->getFromName('[Content_Types].xml')) {
            //Not a valid Office 2007+ document
            return null;
        }

        //@todo - More stringent validation of files in archive
        // - Unzip contents to dir
        // - Get list of all files in zip archive dir
        //   - Invalid if directory levels greater than 10
        // - Validate all MIME-types of files against whitelist
        //   - Must be: XML or image files validated by getimagesize($file)

        //Assuming it's a DOCX for now
        return $this->office2007MimeTypes['docx'];
    }

    /**
     * Checks if a file is a valid ZIP file based on returned MIME-type
     *
     * @param string $file Absolute path to file
     * @return boolean
     */
    protected function isZipMimeType($file)
    {
        return ('application/zip' == $this->guessFromFileinfo($file));
    }
}