From bcb0f7467874c97a63b78d279c2ddccf9a18824a Mon Sep 17 00:00:00 2001
From: joedolson <joedolson@git.wordpress.org>
Date: Wed, 10 Jan 2024 21:59:13 +0000
Subject: [PATCH] Media: Fix handling of multibyte exif description metadata.

The exif standards expect the UserComment field to be used as a substitute for ImageDescription if multibyte characters are needed. WordPress media only mapped the ImageDescription field and did not correctly handle descriptions with multibyte characters.

Fix metadata saving to better handle media with multibyte characters in metadata and update unit tests.

Props fotodrachen, antpb, joedolson, mikinc860, azaozz, nicolefurlan.
Fixes #58082.
Built from https://develop.svn.wordpress.org/trunk@57267


git-svn-id: http://core.svn.wordpress.org/trunk@56773 1a063a9b-81f0-0310-95a4-ce76da25c4cd
---
 wp-admin/includes/image.php | 43 +++++++++++++++++++++++++++++++------
 wp-includes/version.php     |  2 +-
 2 files changed, 37 insertions(+), 8 deletions(-)

diff --git a/wp-admin/includes/image.php b/wp-admin/includes/image.php
index 2bdcc505e4..d60ec8508b 100644
--- a/wp-admin/includes/image.php
+++ b/wp-admin/includes/image.php
@@ -863,22 +863,51 @@ function wp_read_image_metadata( $file ) {
 			$exif = array();
 		}
 
+		$exif_description = '';
+		$exif_usercomment = '';
 		if ( ! empty( $exif['ImageDescription'] ) ) {
-			mbstring_binary_safe_encoding();
-			$description_length = strlen( $exif['ImageDescription'] );
-			reset_mbstring_encoding();
+			$exif_description = trim( $exif['ImageDescription'] );
+		}
 
+		if ( ! empty( $exif['COMPUTED']['UserComment'] ) ) {
+			$exif_usercomment = trim( $exif['COMPUTED']['UserComment'] );
+		}
+
+		if ( $exif_description ) {
+			mbstring_binary_safe_encoding();
+			$description_length = strlen( $exif_description );
+			reset_mbstring_encoding();
 			if ( empty( $meta['title'] ) && $description_length < 80 ) {
 				// Assume the title is stored in ImageDescription.
-				$meta['title'] = trim( $exif['ImageDescription'] );
+				$meta['title'] = $exif_description;
 			}
 
-			if ( empty( $meta['caption'] ) && ! empty( $exif['COMPUTED']['UserComment'] ) ) {
-				$meta['caption'] = trim( $exif['COMPUTED']['UserComment'] );
+			// If both user comments and description are present.
+			if ( empty( $meta['caption'] ) && $exif_description && $exif_usercomment ) {
+				if ( ! empty( $meta['title'] ) && $exif_description === $meta['title'] ) {
+					$caption = $exif_usercomment;
+				} else {
+					if ( $exif_description === $exif_usercomment ) {
+						$caption = $exif_description;
+					} else {
+						$caption = trim( $exif_description . ' ' . $exif_usercomment );
+					}
+				}
+				$meta['caption'] = $caption;
+			}
+
+			if ( empty( $meta['caption'] ) && $exif_usercomment ) {
+				$meta['caption'] = $exif_usercomment;
 			}
 
 			if ( empty( $meta['caption'] ) ) {
-				$meta['caption'] = trim( $exif['ImageDescription'] );
+				$meta['caption'] = $exif_description;
+			}
+		} elseif ( empty( $meta['caption'] ) && $exif_usercomment ) {
+			$meta['caption']    = $exif_usercomment;
+			$description_length = strlen( $exif_usercomment );
+			if ( empty( $meta['title'] ) && $description_length < 80 ) {
+				$meta['title'] = trim( $exif_usercomment );
 			}
 		} elseif ( empty( $meta['caption'] ) && ! empty( $exif['Comments'] ) ) {
 			$meta['caption'] = trim( $exif['Comments'] );
diff --git a/wp-includes/version.php b/wp-includes/version.php
index 675e804d5c..2d4717c4ef 100644
--- a/wp-includes/version.php
+++ b/wp-includes/version.php
@@ -16,7 +16,7 @@
  *
  * @global string $wp_version
  */
-$wp_version = '6.5-alpha-57266';
+$wp_version = '6.5-alpha-57267';
 
 /**
  * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.