wpseek.com
A WordPress-centric search engine for devs and theme authors

function wp_check_filetype_and_ext( $file, $filename, $mimes = null ) {
	$proper_filename = false;

	// Do basic extension validation and MIME mapping.
	$wp_filetype = wp_check_filetype( $filename, $mimes );
	$ext         = $wp_filetype['ext'];
	$type        = $wp_filetype['type'];

	// We can't do any further validation without a file to work with.
	if ( ! file_exists( $file ) ) {
		return compact( 'ext', 'type', 'proper_filename' );
	}

	$real_mime = false;

	// Validate image types.
	if ( $type && str_starts_with( $type, 'image/' ) ) {

		// Attempt to figure out what type of image it actually is.
		$real_mime = wp_get_image_mime( $file );

		$heic_images_extensions = array(
			'heif',
			'heics',
			'heifs',
		);

		if ( $real_mime && ( $real_mime !== $type || in_array( $ext, $heic_images_extensions, true ) ) ) {
			/**
			 * Filters the list mapping image mime types to their respective extensions.
			 *
			 * @since 3.0.0
			 *
			 * @param array $mime_to_ext Array of image mime types and their matching extensions.
			 */
			$mime_to_ext = apply_filters(
				'getimagesize_mimes_to_exts',
				array(
					'image/jpeg' => 'jpg',
					'image/png'  => 'png',
					'image/gif'  => 'gif',
					'image/bmp'  => 'bmp',
					'image/tiff' => 'tif',
					'image/webp' => 'webp',
					'image/avif' => 'avif',

					/*
					 * In theory there are/should be file extensions that correspond to the
					 * mime types: .heif, .heics and .heifs. However it seems that HEIC images
					 * with any of the mime types commonly have a .heic file extension.
					 * Seems keeping the status quo here is best for compatibility.
					 */
					'image/heic' => 'heic',
					'image/heif' => 'heic',
					'image/heic-sequence' => 'heic',
					'image/heif-sequence' => 'heic',
				)
			);

			// Replace whatever is after the last period in the filename with the correct extension.
			if ( ! empty( $mime_to_ext[ $real_mime ] ) ) {
				$filename_parts = explode( '.', $filename );

				array_pop( $filename_parts );
				$filename_parts[] = $mime_to_ext[ $real_mime ];
				$new_filename     = implode( '.', $filename_parts );

				if ( $new_filename !== $filename ) {
					$proper_filename = $new_filename; // Mark that it changed.
				}

				// Redefine the extension / MIME.
				$wp_filetype = wp_check_filetype( $new_filename, $mimes );
				$ext         = $wp_filetype['ext'];
				$type        = $wp_filetype['type'];
			} else {
				// Reset $real_mime and try validating again.
				$real_mime = false;
			}
		}
	}

	// Validate files that didn't get validated during previous checks.
	if ( $type && ! $real_mime && extension_loaded( 'fileinfo' ) ) {
		$finfo     = finfo_open( FILEINFO_MIME_TYPE );
		$real_mime = finfo_file( $finfo, $file );
		finfo_close( $finfo );

		$google_docs_types = array(
			'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
			'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
		);

		foreach ( $google_docs_types as $google_docs_type ) {
			/*
			 * finfo_file() can return duplicate mime type for Google docs,
			 * this conditional reduces it to a single instance.
			 *
			 * @see https://bugs.php.net/bug.php?id=77784
			 * @see https://core.trac.wordpress.org/ticket/57898
			 */
			if ( 2 === substr_count( $real_mime, $google_docs_type ) ) {
				$real_mime = $google_docs_type;
			}
		}

		// fileinfo often misidentifies obscure files as one of these types.
		$nonspecific_types = array(
			'application/octet-stream',
			'application/encrypted',
			'application/CDFV2-encrypted',
			'application/zip',
		);

		/*
		 * If $real_mime doesn't match the content type we're expecting from the file's extension,
		 * we need to do some additional vetting. Media types and those listed in $nonspecific_types are
		 * allowed some leeway, but anything else must exactly match the real content type.
		 */
		if ( in_array( $real_mime, $nonspecific_types, true ) ) {
			// File is a non-specific binary type. That's ok if it's a type that generally tends to be binary.
			if ( ! in_array( substr( $type, 0, strcspn( $type, '/' ) ), array( 'application', 'video', 'audio' ), true ) ) {
				$type = false;
				$ext  = false;
			}
		} elseif ( str_starts_with( $real_mime, 'video/' ) || str_starts_with( $real_mime, 'audio/' ) ) {
			/*
			 * For these types, only the major type must match the real value.
			 * This means that common mismatches are forgiven: application/vnd.apple.numbers is often misidentified as application/zip,
			 * and some media files are commonly named with the wrong extension (.mov instead of .mp4)
			 */
			if ( substr( $real_mime, 0, strcspn( $real_mime, '/' ) ) !== substr( $type, 0, strcspn( $type, '/' ) ) ) {
				$type = false;
				$ext  = false;
			}
		} elseif ( 'text/plain' === $real_mime ) {
			// A few common file types are occasionally detected as text/plain; allow those.
			if ( ! in_array(
				$type,
				array(
					'text/plain',
					'text/csv',
					'application/csv',
					'text/richtext',
					'text/tsv',
					'text/vtt',
				),
				true
			)
			) {
				$type = false;
				$ext  = false;
			}
		} elseif ( 'application/csv' === $real_mime ) {
			// Special casing for CSV files.
			if ( ! in_array(
				$type,
				array(
					'text/csv',
					'text/plain',
					'application/csv',
				),
				true
			)
			) {
				$type = false;
				$ext  = false;
			}
		} elseif ( 'text/rtf' === $real_mime ) {
			// Special casing for RTF files.
			if ( ! in_array(
				$type,
				array(
					'text/rtf',
					'text/plain',
					'application/rtf',
				),
				true
			)
			) {
				$type = false;
				$ext  = false;
			}
		} else {
			if ( $type !== $real_mime ) {
				/*
				 * Everything else including image/* and application/*:
				 * If the real content type doesn't match the file extension, assume it's dangerous.
				 */
				$type = false;
				$ext  = false;
			}
		}
	}

	// The mime type must be allowed.
	if ( $type ) {
		$allowed = get_allowed_mime_types();

		if ( ! in_array( $type, $allowed, true ) ) {
			$type = false;
			$ext  = false;
		}
	}

	/**
	 * Filters the "real" file type of the given file.
	 *
	 * @since 3.0.0
	 * @since 5.1.0 The $real_mime parameter was added.
	 *
	 * @param array         $wp_check_filetype_and_ext {
	 *     Values for the extension, mime type, and corrected filename.
	 *
	 *     @type string|false $ext             File extension, or false if the file doesn't match a mime type.
	 *     @type string|false $type            File mime type, or false if the file doesn't match a mime type.
	 *     @type string|false $proper_filename File name with its correct extension, or false if it cannot be determined.
	 * }
	 * @param string        $file                      Full path to the file.
	 * @param string        $filename                  The name of the file (may differ from $file due to
	 *                                                 $file being in a tmp directory).
	 * @param string[]|null $mimes                     Array of mime types keyed by their file extension regex, or null if
	 *                                                 none were provided.
	 * @param string|false  $real_mime                 The actual mime type or false if the type cannot be determined.
	 */
	return apply_filters( 'wp_check_filetype_and_ext', compact( 'ext', 'type', 'proper_filename' ), $file, $filename, $mimes, $real_mime );
}