From 246a70bdbfac3bd45ff71c7941deef1bb206b19a Mon Sep 17 00:00:00 2001
From: Jeremy Felt <jeremy.felt@gmail.com>
Date: Wed, 12 Dec 2018 23:01:47 +0000
Subject: [PATCH] Media: Improve verification of MIME file types.

Built from https://develop.svn.wordpress.org/branches/5.0@43988


git-svn-id: http://core.svn.wordpress.org/branches/5.0@43820 1a063a9b-81f0-0310-95a4-ce76da25c4cd
---
 wp-includes/functions.php | 51 +++++++++++++++++++++++++++++++++------
 wp-includes/version.php   |  2 +-
 2 files changed, 44 insertions(+), 9 deletions(-)

diff --git a/wp-includes/functions.php b/wp-includes/functions.php
index c44685e604..d4af13f2a8 100644
--- a/wp-includes/functions.php
+++ b/wp-includes/functions.php
@@ -2349,17 +2349,52 @@ function wp_check_filetype_and_ext( $file, $filename, $mimes = null ) {
 		$real_mime = finfo_file( $finfo, $file );
 		finfo_close( $finfo );
 
-		/*
-		 * If $real_mime doesn't match what we're expecting, we need to do some extra
-		 * vetting of application mime types to make sure this type of file is allowed.
-		 * Other mime types are assumed to be safe, but should be considered unverified.
-		 */
-		if ( $real_mime && ( $real_mime !== $type ) && ( 0 === strpos( $real_mime, 'application' ) ) ) {
-			$allowed = get_allowed_mime_types();
+		// fileinfo often misidentifies obscure files as one of these types
+		$nonspecific_types = array(
+			'application/octet-stream',
+			'application/encrypted',
+			'application/CDFV2-encrypted',
+			'application/zip',
+		);
 
-			if ( ! in_array( $real_mime, $allowed ) ) {
+		/*
+		 * 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' ) ) ) {
 				$type = $ext = false;
 			}
+		} elseif ( 0 === strpos( $real_mime, 'video/' ) || 0 === strpos( $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 = $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 = $ext = false;
+			}
+
+		}
+	}
+
+	// The mime type must be allowed 
+	if ( $type ) {
+		$allowed = get_allowed_mime_types();
+
+		if ( ! in_array( $type, $allowed ) ) {
+			$type = $ext = false;
 		}
 	}
 
diff --git a/wp-includes/version.php b/wp-includes/version.php
index d85ed13667..68c9277381 100644
--- a/wp-includes/version.php
+++ b/wp-includes/version.php
@@ -4,7 +4,7 @@
  *
  * @global string $wp_version
  */
-$wp_version = '5.0.1-alpha-43972';
+$wp_version = '5.0.1-alpha-43988';
 
 /**
  * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.