Tag 4.0.6. Built from https://develop.svn.wordpress.org/@33403

git-svn-id: http://core.svn.wordpress.org/tags/4.0.6@33371 1a063a9b-81f0-0310-95a4-ce76da25c4cd
Bump 4.0 branch to version 4.0.6.
2015-07-23 12:13:47 +00:00 · 2015-07-23 11:07:33 +00:00 · 2015-07-23 04:50:37 +00:00 · 2015-07-23 04:01:36 +00:00 · 2015-05-06 23:28:36 +00:00 · 2015-05-06 23:13:58 +00:00
17 changed files with 965 additions and 117 deletions
--- a/readme.html
+++ b/readme.html
@@ -9,7 +9,7 @@
 <body>
 <h1 id="logo">
 	<a href="https://wordpress.org/"><img alt="WordPress" src="wp-admin/images/wordpress-logo.png" /></a>
-	<br /> Version 4.0.3
+	<br /> Version 4.0.6
 </h1>
 <p style="text-align: center">Semantic Personal Publishing Platform</p>

--- a/wp-admin/about.php
+++ b/wp-admin/about.php
@@ -42,18 +42,30 @@ include( ABSPATH . 'wp-admin/admin-header.php' );
 </h2>

 <div class="changelog point-releases">
-	<h3><?php echo _n( 'Maintenance and Security Release', 'Maintenance and Security Releases', 3 ); ?></h3>
+	<h3><?php echo _n( 'Maintenance and Security Release', 'Maintenance and Security Releases', 6 ); ?></h3>
+	<p><?php printf( _n( '<strong>Version %1$s</strong> addressed a security issue.',
+         '<strong>Version %1$s</strong> addressed some security issues.', 2 ), '4.0.6' ); ?>
+		<?php printf( __( 'For more information, see <a href="%s">the release notes</a>.' ), 'https://codex.wordpress.org/Version_4.0.6' ); ?>
+ 	</p>
+	<p><?php printf( _n( '<strong>Version %1$s</strong> addressed some security issues and fixed %2$s bug.',
+         '<strong>Version %1$s</strong> addressed some security issues and fixed %2$s bugs.', 3 ), '4.0.5', number_format_i18n( 3 ) ); ?>
+		<?php printf( __( 'For more information, see <a href="%s">the release notes</a>.' ), 'https://codex.wordpress.org/Version_4.0.5' ); ?>
+	</p>
+	<p><?php printf( _n( '<strong>Version %1$s</strong> addressed a security issue.',
+         '<strong>Version %1$s</strong> addressed some security issues.', 1 ), '4.0.4' ); ?>
+		<?php printf( __( 'For more information, see <a href="%s">the release notes</a>.' ), 'https://codex.wordpress.org/Version_4.0.4' ); ?>
+ 	</p>
 	<p><?php printf( _n( '<strong>Version %1$s</strong> addressed %2$s bug.',
         '<strong>Version %1$s</strong> addressed %2$s bugs.', 1 ), '4.0.3', number_format_i18n( 1 ) ); ?>
 		<?php printf( __( 'For more information, see <a href="%s">the release notes</a>.' ), 'https://codex.wordpress.org/Version_4.0.3' ); ?>
 	</p>
 	<p><?php printf( _n( '<strong>Version %1$s</strong> addressed a security issue.',
         '<strong>Version %1$s</strong> addressed some security issues.', 8 ), '4.0.2' ); ?>
-		<?php printf( __( 'For more information, see <a href="%s">the release notes</a>.' ), 'http://codex.wordpress.org/Version_4.0.2' ); ?>
+		<?php printf( __( 'For more information, see <a href="%s">the release notes</a>.' ), 'https://codex.wordpress.org/Version_4.0.2' ); ?>
 	</p>
 	<p><?php printf( _n( '<strong>Version %1$s</strong> addressed some security issues and fixed %2$s bug.',
         '<strong>Version %1$s</strong> addressed some security issues and fixed %2$s bugs.', 23 ), '4.0.1', number_format_i18n( 23 ) ); ?>
-		<?php printf( __( 'For more information, see <a href="%s">the release notes</a>.' ), 'http://codex.wordpress.org/Version_4.0.1' ); ?>
+		<?php printf( __( 'For more information, see <a href="%s">the release notes</a>.' ), 'https://codex.wordpress.org/Version_4.0.1' ); ?>
 	</p>
 </div>

--- a/wp-admin/includes/dashboard.php
+++ b/wp-admin/includes/dashboard.php
@@ -416,6 +416,10 @@ function wp_network_dashboard_right_now() {
 function wp_dashboard_quick_press( $error_msg = false ) {
 	global $post_ID;

+	if ( ! current_user_can( 'edit_posts' ) ) {
+		return;
+	}
+
 	/* Check if a new auto-draft (= no new post_ID) is needed or if the old can be used */
 	$last_post_id = (int) get_user_option( 'dashboard_quick_press_last_post_id' ); // Get the last post_ID
 	if ( $last_post_id ) {
--- a/wp-admin/includes/update-core.php
+++ b/wp-admin/includes/update-core.php
@@ -1011,6 +1011,9 @@ function update_core($from, $to) {
 		$wp_filesystem->delete($old_file, true);
 	}

+	// Remove any Genericons example.html's from the filesystem
+	_upgrade_422_remove_genericons();
+
 	// Upgrade DB with separate request
 	/** This filter is documented in wp-admin/includes/update-core.php */
 	apply_filters( 'update_feedback', __( 'Upgrading database&#8230;' ) );
@@ -1149,3 +1152,67 @@ window.location = 'about.php?updated';
 	exit();
 }
 add_action( '_core_updated_successfully', '_redirect_to_about_wordpress' );
+
+/**
+ * Cleans up Genericons example files.
+ *
+ * @since 4.2.2
+ */
+function _upgrade_422_remove_genericons() {
+	global $wp_theme_directories, $wp_filesystem;
+
+	// A list of the affected files using the filesystem absolute paths.
+	$affected_files = array();
+
+	// Themes
+	foreach ( $wp_theme_directories as $directory ) {
+		$affected_theme_files = _upgrade_422_find_genericons_files_in_folder( $directory );
+		$affected_files       = array_merge( $affected_files, $affected_theme_files );
+	}
+
+	// Plugins
+	$affected_plugin_files = _upgrade_422_find_genericons_files_in_folder( WP_PLUGIN_DIR );
+	$affected_files        = array_merge( $affected_files, $affected_plugin_files );
+
+	foreach ( $affected_files as $file ) {
+		$gen_dir = $wp_filesystem->find_folder( trailingslashit( dirname( $file ) ) );
+		if ( empty( $gen_dir ) ) {
+			continue;
+		}
+
+		// The path when the file is accessed via WP_Filesystem may differ in the case of FTP
+		$remote_file = $gen_dir . basename( $file );
+
+		if ( ! $wp_filesystem->exists( $remote_file ) ) {
+			continue;
+		}
+
+		if ( ! $wp_filesystem->delete( $remote_file, false, 'f' ) ) {
+			$wp_filesystem->put_contents( $remote_file, '' );
+		}
+	}
+}
+
+/**
+ * Recursively find Genericons example files in a given folder.
+ *
+ * @ignore
+ * @since 4.2.2
+ *
+ * @param string $directory Directory path. Expects trailingslashed.
+ * @return array
+ */
+function _upgrade_422_find_genericons_files_in_folder( $directory ) {
+	$directory = trailingslashit( $directory );
+	$files     = array();
+
+	if ( file_exists( "{$directory}example.html" ) && false !== strpos( file_get_contents( "{$directory}example.html" ), '<title>Genericons</title>' ) ) {
+		$files[] = "{$directory}example.html";
+	}
+
+	foreach ( glob( $directory . '*', GLOB_ONLYDIR ) as $dir ) {
+		$files = array_merge( $files, _upgrade_422_find_genericons_files_in_folder( $dir ) );
+	}
+
+	return $files;
+}
--- a/wp-admin/includes/upgrade.php
+++ b/wp-admin/includes/upgrade.php
@@ -440,6 +440,9 @@ function upgrade_all() {
 	if ( $wp_current_db_version < 29630 )
 		upgrade_400();

+	if ( $wp_current_db_version < 29632 )
+		upgrade_405();
+
 	maybe_disable_link_manager();

 	maybe_disable_automattic_widgets();
@@ -1326,6 +1329,62 @@ function upgrade_400() {
 	}
 }

+/**
+ * Execute changes made in WordPress 4.0.4.
+ *
+ * @since 4.0.4
+ */
+function upgrade_404() {
+}
+
+/**
+ * Execute changes made in WordPress 4.0.5.
+ *
+ * @since 4.0.5
+ */
+function upgrade_405() {
+	global $wp_current_db_version, $wpdb;
+
+	if ( $wp_current_db_version < 29632 ) {
+		$content_length = $wpdb->get_col_length( $wpdb->comments, 'comment_content' );
+
+		if ( is_wp_error( $content_length ) ) {
+			return;
+		}
+
+		if ( false === $content_length ) {
+			$content_length = array(
+				'type'   => 'byte',
+				'length' => 65535,
+			);
+		} elseif ( ! is_array( $content_length ) ) {
+			$length = (int) $content_length > 0 ? (int) $content_length : 65535;
+			$content_length = array(
+				'type'	 => 'byte',
+				'length' => $length
+			);
+		}
+
+		if ( 'byte' !== $content_length['type'] || 0 === $content_length['length'] ) {
+			// Sites with malformed DB schemas are on their own.
+			return;
+		}
+
+		$allowed_length = intval( $content_length['length'] ) - 10;
+
+		$comments = $wpdb->get_results(
+			"SELECT `comment_ID` FROM `{$wpdb->comments}`
+				WHERE `comment_date_gmt` > '2015-04-26'
+				AND LENGTH( `comment_content` ) >= {$allowed_length}
+				AND ( `comment_content` LIKE '%<%' OR `comment_content` LIKE '%>%' )"
+		);
+
+		foreach ( $comments as $comment ) {
+			wp_delete_comment( $comment->comment_ID, true );
+		}
+	}
+}
+
 /**
 * Execute network level changes
 *
--- a/wp-admin/post.php
+++ b/wp-admin/post.php
@@ -113,8 +113,9 @@ case 'post-quickdraft-save':
 	if ( ! wp_verify_nonce( $nonce, 'add-post' ) )
 		$error_msg = __( 'Unable to submit this form, please refresh and try again.' );

-	if ( ! current_user_can( 'edit_posts' ) )
-		$error_msg = __( 'Oops, you don&#8217;t have access to add new drafts.' );
+	if ( ! current_user_can( 'edit_posts' ) ) {
+		exit;
+	}

 	if ( $error_msg )
 		return wp_dashboard_quick_press( $error_msg );
--- a/wp-includes/capabilities.php
+++ b/wp-includes/capabilities.php
@@ -1114,8 +1114,10 @@ function map_meta_cap( $cap, $user_id ) {
 	case 'edit_post':
 	case 'edit_page':
 		$post = get_post( $args[0] );
-		if ( empty( $post ) )
+		if ( empty( $post ) ) {
+			$caps[] = 'do_not_allow';
 			break;
+		}

 		if ( 'revision' == $post->post_type ) {
 			$post = get_post( $post->post_parent );
--- a/wp-includes/class-wp-embed.php
+++ b/wp-includes/class-wp-embed.php
@@ -60,7 +60,7 @@ class WP_Embed {
 		add_shortcode( 'embed', array( $this, 'shortcode' ) );

 		// Do the shortcode (only the [embed] one is registered)
-		$content = do_shortcode( $content );
+		$content = do_shortcode( $content, true );

 		// Put the original shortcodes back
 		$shortcode_tags = $orig_shortcode_tags;
@@ -326,6 +326,10 @@ class WP_Embed {
 	 * @return string Potentially modified $content.
 	 */
 	public function autoembed( $content ) {
+		// Strip newlines from all elements.
+		$content = wp_replace_in_html_tags( $content, array( "\n" => " " ) );
+
+		// Find URLs that are on their own line.
 		return preg_replace_callback( '|^\s*(https?://[^\s"]+)\s*$|im', array( $this, 'autoembed_callback' ), $content );
 	}

--- a/wp-includes/compat.php
+++ b/wp-includes/compat.php
@@ -13,23 +13,141 @@ if ( !function_exists('_') ) {
 	}
 }

-if ( !function_exists('mb_substr') ):
-	function mb_substr( $str, $start, $length=null, $encoding=null ) {
-		return _mb_substr($str, $start, $length, $encoding);
+/**
+ * Returns whether PCRE/u (PCRE_UTF8 modifier) is available for use.
+ *
+ * @ignore
+ * @since 4.2.2
+ * @access private
+ *
+ * @param bool $set - Used for testing only
+ *             null   : default - get PCRE/u capability
+ *             false  : Used for testing - return false for future calls to this function
+ *             'reset': Used for testing - restore default behavior of this function
+ */
+function _wp_can_use_pcre_u( $set = null ) {
+	static $utf8_pcre = 'reset';
+
+	if ( null !== $set ) {
+		$utf8_pcre = $set;
+	}
+
+	if ( 'reset' === $utf8_pcre ) {
+		$utf8_pcre = @preg_match( '/^./u', 'a' );
+	}
+
+	return $utf8_pcre;
+}
+
+if ( ! function_exists( 'mb_substr' ) ) :
+	function mb_substr( $str, $start, $length = null, $encoding = null ) {
+		return _mb_substr( $str, $start, $length, $encoding );
 	}
 endif;

-function _mb_substr( $str, $start, $length=null, $encoding=null ) {
-	// the solution below, works only for utf-8, so in case of a different
-	// charset, just use built-in substr
-	$charset = get_option( 'blog_charset' );
-	if ( !in_array( $charset, array('utf8', 'utf-8', 'UTF8', 'UTF-8') ) ) {
-		return is_null( $length )? substr( $str, $start ) : substr( $str, $start, $length);
+/*
+ * Only understands UTF-8 and 8bit.  All other character sets will be treated as 8bit.
+ * For $encoding === UTF-8, the $str input is expected to be a valid UTF-8 byte sequence.
+ * The behavior of this function for invalid inputs is undefined.
+ */
+function _mb_substr( $str, $start, $length = null, $encoding = null ) {
+	if ( null === $encoding ) {
+		$encoding = get_option( 'blog_charset' );
 	}
-	// use the regex unicode support to separate the UTF-8 characters into an array
-	preg_match_all( '/./us', $str, $match );
-	$chars = is_null( $length )? array_slice( $match[0], $start ) : array_slice( $match[0], $start, $length );
-	return implode( '', $chars );
+
+	// The solution below works only for UTF-8,
+	// so in case of a different charset just use built-in substr()
+	if ( ! in_array( $encoding, array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) ) ) {
+		return is_null( $length ) ? substr( $str, $start ) : substr( $str, $start, $length );
+	}
+
+	if ( _wp_can_use_pcre_u() ) {
+		// Use the regex unicode support to separate the UTF-8 characters into an array
+		preg_match_all( '/./us', $str, $match );
+		$chars = is_null( $length ) ? array_slice( $match[0], $start ) : array_slice( $match[0], $start, $length );
+		return implode( '', $chars );
+	}
+
+	$regex = '/(
+		  [\x00-\x7F]                  # single-byte sequences   0xxxxxxx
+		| [\xC2-\xDF][\x80-\xBF]       # double-byte sequences   110xxxxx 10xxxxxx
+		| \xE0[\xA0-\xBF][\x80-\xBF]   # triple-byte sequences   1110xxxx 10xxxxxx * 2
+		| [\xE1-\xEC][\x80-\xBF]{2}
+		| \xED[\x80-\x9F][\x80-\xBF]
+		| [\xEE-\xEF][\x80-\xBF]{2}
+		| \xF0[\x90-\xBF][\x80-\xBF]{2} # four-byte sequences   11110xxx 10xxxxxx * 3
+		| [\xF1-\xF3][\x80-\xBF]{3}
+		| \xF4[\x80-\x8F][\x80-\xBF]{2}
+	)/x';
+
+	$chars = array( '' ); // Start with 1 element instead of 0 since the first thing we do is pop
+	do {
+		// We had some string left over from the last round, but we counted it in that last round.
+		array_pop( $chars );
+
+		// Split by UTF-8 character, limit to 1000 characters (last array element will contain the rest of the string)
+		$pieces = preg_split( $regex, $str, 1000, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
+
+		$chars = array_merge( $chars, $pieces );
+	} while ( count( $pieces ) > 1 && $str = array_pop( $pieces ) ); // If there's anything left over, repeat the loop.
+
+	return join( '', array_slice( $chars, $start, $length ) );
+}
+
+if ( ! function_exists( 'mb_strlen' ) ) :
+	function mb_strlen( $str, $encoding = null ) {
+		return _mb_strlen( $str, $encoding );
+	}
+endif;
+
+/*
+ * Only understands UTF-8 and 8bit.  All other character sets will be treated as 8bit.
+ * For $encoding === UTF-8, the $str input is expected to be a valid UTF-8 byte sequence.
+ * The behavior of this function for invalid inputs is undefined.
+ */
+function _mb_strlen( $str, $encoding = null ) {
+	if ( null === $encoding ) {
+		$encoding = get_option( 'blog_charset' );
+	}
+
+	// The solution below works only for UTF-8,
+	// so in case of a different charset just use built-in strlen()
+	if ( ! in_array( $encoding, array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) ) ) {
+		return strlen( $str );
+	}
+
+	if ( _wp_can_use_pcre_u() ) {
+		// Use the regex unicode support to separate the UTF-8 characters into an array
+		preg_match_all( '/./us', $str, $match );
+		return count( $match[0] );
+	}
+
+	$regex = '/(?:
+		  [\x00-\x7F]                  # single-byte sequences   0xxxxxxx
+		| [\xC2-\xDF][\x80-\xBF]       # double-byte sequences   110xxxxx 10xxxxxx
+		| \xE0[\xA0-\xBF][\x80-\xBF]   # triple-byte sequences   1110xxxx 10xxxxxx * 2
+		| [\xE1-\xEC][\x80-\xBF]{2}
+		| \xED[\x80-\x9F][\x80-\xBF]
+		| [\xEE-\xEF][\x80-\xBF]{2}
+		| \xF0[\x90-\xBF][\x80-\xBF]{2} # four-byte sequences   11110xxx 10xxxxxx * 3
+		| [\xF1-\xF3][\x80-\xBF]{3}
+		| \xF4[\x80-\x8F][\x80-\xBF]{2}
+	)/x';
+
+	$count = 1; // Start at 1 instead of 0 since the first thing we do is decrement
+	do {
+		// We had some string left over from the last round, but we counted it in that last round.
+		$count--;
+
+		// Split by UTF-8 character, limit to 1000 characters (last array element will contain the rest of the string)
+		$pieces = preg_split( $regex, $str, 1000 );
+
+		// Increment
+		$count += count( $pieces );
+	} while ( $str = array_pop( $pieces ) ); // If there's anything left over, repeat the loop.
+
+	// Fencepost: preg_split() always returns one extra item in the array
+	return --$count;
 }

 if ( !function_exists('hash_hmac') ):
--- a/wp-includes/formatting.php
+++ b/wp-includes/formatting.php
@@ -405,6 +405,9 @@ function wpautop($pee, $br = true) {
 	$pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
 	$pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines

+	// Strip newlines from all elements.
+	$pee = wp_replace_in_html_tags( $pee, array( "\n" => " " ) );
+
 	if ( strpos( $pee, '<option' ) !== false ) {
 		// no P/BR around option
 		$pee = preg_replace( '|\s*<option|', '<option', $pee );
@@ -459,6 +462,74 @@ function wpautop($pee, $br = true) {
 	return $pee;
 }

+/**
+ * Replace characters or phrases within HTML elements only.
+ *
+ * @since 4.2.3
+ *
+ * @param string $haystack The text which has to be formatted.
+ * @param array $replace_pairs In the form array('from' => 'to', ...).
+ * @return string The formatted text.
+ */
+function wp_replace_in_html_tags( $haystack, $replace_pairs ) {
+	// Find all elements.
+	$comments =
+		  '!'           // Start of comment, after the <.
+		. '(?:'         // Unroll the loop: Consume everything until --> is found.
+		.     '-(?!->)' // Dash not followed by end of comment.
+		.     '[^\-]*+' // Consume non-dashes.
+		. ')*+'         // Loop possessively.
+		. '(?:-->)?';   // End of comment. If not found, match all input.
+
+	$regex =
+		  '/('              // Capture the entire match.
+		.     '<'           // Find start of element.
+		.     '(?(?=!--)'   // Is this a comment?
+		.         $comments // Find end of comment.
+		.     '|'
+		.         '[^>]*>?' // Find end of element. If not found, match all input.
+		.     ')'
+		. ')/s';
+
+	$textarr = preg_split( $regex, $haystack, -1, PREG_SPLIT_DELIM_CAPTURE );
+	$changed = false;
+
+	// Optimize when searching for one item.
+	if ( 1 === count( $replace_pairs ) ) {
+		// Extract $needle and $replace.
+		foreach ( $replace_pairs as $needle => $replace );
+
+		// Loop through delimeters (elements) only.
+		for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) { 
+			if ( false !== strpos( $textarr[$i], $needle ) ) {
+				$textarr[$i] = str_replace( $needle, $replace, $textarr[$i] );
+				$changed = true;
+			}
+		}
+	} else {
+		// Extract all $needles.
+		$needles = array_keys( $replace_pairs );
+
+		// Loop through delimeters (elements) only.
+		for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) { 
+			foreach ( $needles as $needle ) {
+				if ( false !== strpos( $textarr[$i], $needle ) ) {
+					$textarr[$i] = strtr( $textarr[$i], $replace_pairs );
+					$changed = true;
+					// After one strtr() break out of the foreach loop and look at next element.
+					break;
+				}
+			}
+		}
+	}
+
+	if ( $changed ) {
+		$haystack = implode( $textarr );
+	}
+
+	return $haystack;
+}
+
 /**
 * Newline preservation help function for wpautop
 *
--- a/wp-includes/js/tinymce/plugins/wordpress/plugin.js
+++ b/wp-includes/js/tinymce/plugins/wordpress/plugin.js
@@ -102,6 +102,10 @@ tinymce.PluginManager.add( 'wordpress', function( editor ) {
 					'<img src="' + tinymce.Env.transparentSrc + '" data-wp-more="nextpage" class="wp-more-tag mce-wp-nextpage" ' +
 						'title="' + title + '" data-mce-resize="false" data-mce-placeholder="1" />' );
 			}
+
+			if ( e.content.indexOf( '<?"' ) !== -1 ) {
+				e.content = e.content.replace( /<\?"/g, '' );
+			}
 		}
 	});

--- a/wp-includes/js/tinymce/plugins/wordpress/plugin.min.js
+++ b/wp-includes/js/tinymce/plugins/wordpress/plugin.min.js
--- a/wp-includes/js/tinymce/wp-tinymce.js.gz
+++ b/wp-includes/js/tinymce/wp-tinymce.js.gz
--- a/wp-includes/kses.php
+++ b/wp-includes/kses.php
@@ -493,6 +493,82 @@ function wp_kses( $string, $allowed_html, $allowed_protocols = array() ) {
 	return wp_kses_split($string, $allowed_html, $allowed_protocols);
 }

+/**
+ * Filters one attribute only and ensures its value is allowed.
+ *
+ * This function has the advantage of being more secure than esc_attr() and can
+ * escape data in some situations where wp_kses() must strip the whole attribute.
+ *
+ * @since 4.2.3
+ *
+ * @param string $string The 'whole' attribute, including name and value.
+ * @param string $element The element name to which the attribute belongs.
+ * @return string Filtered attribute.
+ */
+function wp_kses_one_attr( $string, $element ) {
+	$uris = array('xmlns', 'profile', 'href', 'src', 'cite', 'classid', 'codebase', 'data', 'usemap', 'longdesc', 'action');
+	$allowed_html = wp_kses_allowed_html( 'post' );
+	$allowed_protocols = wp_allowed_protocols();
+	$string = wp_kses_no_null( $string, array( 'slash_zero' => 'keep' ) );
+	$string = wp_kses_js_entities( $string );
+	$string = wp_kses_normalize_entities( $string );
+
+	// Preserve leading and trailing whitespace.
+	$matches = array();
+	preg_match('/^\s*/', $string, $matches);
+	$lead = $matches[0];
+	preg_match('/\s*$/', $string, $matches);
+	$trail = $matches[0];
+	if ( empty( $trail ) ) {
+		$string = substr( $string, strlen( $lead ) );
+	} else {
+		$string = substr( $string, strlen( $lead ), -strlen( $trail ) );
+	}
+	
+	// Parse attribute name and value from input.
+	$split = preg_split( '/\s*=\s*/', $string, 2 );
+	$name = $split[0];
+	if ( count( $split ) == 2 ) {
+		$value = $split[1];
+
+		// Remove quotes surrounding $value.
+		// Also guarantee correct quoting in $string for this one attribute.
+		if ( '' == $value ) {
+			$quote = '';
+		} else {
+			$quote = $value[0];
+		}
+		if ( '"' == $quote || "'" == $quote ) {
+			if ( substr( $value, -1 ) != $quote ) {
+				return '';
+			}
+			$value = substr( $value, 1, -1 );
+		} else {
+			$quote = '"';
+		}
+
+		// Sanitize quotes and angle braces.
+		$value = htmlspecialchars( $value, ENT_QUOTES, null, false );
+
+		// Sanitize URI values.
+		if ( in_array( strtolower( $name ), $uris ) ) {
+			$value = wp_kses_bad_protocol( $value, $allowed_protocols );
+		}
+
+		$string = "$name=$quote$value$quote";
+		$vless = 'n';
+	} else {
+		$value = '';
+		$vless = 'y';
+	}
+	
+	// Sanitize attribute by name.
+	wp_kses_attr_check( $name, $value, $string, $vless, $element, $allowed_html );
+
+	// Restore whitespace.
+	return $lead . $string . $trail;
+}
+
 /**
 * Return a list of allowed tags and attributes for a given context.
 *
@@ -714,45 +790,11 @@ function wp_kses_attr($element, $attr, $allowed_html, $allowed_protocols) {
 	# Go through $attrarr, and save the allowed attributes for this element
 	# in $attr2
 	$attr2 = '';
-
-	$allowed_attr = $allowed_html[strtolower($element)];
-	foreach ($attrarr as $arreach) {
-		if ( ! isset( $allowed_attr[strtolower($arreach['name'])] ) )
-			continue; # the attribute is not allowed
-
-		$current = $allowed_attr[strtolower($arreach['name'])];
-		if ( $current == '' )
-			continue; # the attribute is not allowed
-
-		if ( strtolower( $arreach['name'] ) == 'style' ) {
-			$orig_value = $arreach['value'];
-			$value = safecss_filter_attr( $orig_value );
-
-			if ( empty( $value ) )
-				continue;
-
-			$arreach['value'] = $value;
-			$arreach['whole'] = str_replace( $orig_value, $value, $arreach['whole'] );
-		}
-
-		if ( ! is_array($current) ) {
+	foreach ( $attrarr as $arreach ) {
+		if ( wp_kses_attr_check( $arreach['name'], $arreach['value'], $arreach['whole'], $arreach['vless'], $element, $allowed_html ) ) {
 			$attr2 .= ' '.$arreach['whole'];
-		# there are no checks
-
-		} else {
-			# there are some checks
-			$ok = true;
-			foreach ($current as $currkey => $currval) {
-				if ( ! wp_kses_check_attr_val($arreach['value'], $arreach['vless'], $currkey, $currval) ) {
-					$ok = false;
-					break;
-				}
-			}
-
-			if ( $ok )
-				$attr2 .= ' '.$arreach['whole']; # it passed them
-		} # if !is_array($current)
-	} # foreach
+		}
+	}

 	# Remove any "<" or ">" characters
 	$attr2 = preg_replace('/[<>]/', '', $attr2);
@@ -760,6 +802,53 @@ function wp_kses_attr($element, $attr, $allowed_html, $allowed_protocols) {
 	return "<$element$attr2$xhtml_slash>";
 }

+/**
+ * Determine whether an attribute is allowed.
+ *
+ * @since 4.2.3
+ *
+ * @param string $name The attribute name. Returns empty string when not allowed.
+ * @param string $value The attribute value. Returns a filtered value.
+ * @param string $whole The name=value input. Returns filtered input.
+ * @param string $vless 'y' when attribute like "enabled", otherwise 'n'.
+ * @param string $element The name of the element to which this attribute belongs.
+ * @param array $allowed_html The full list of allowed elements and attributes.
+ * @return bool Is the attribute allowed?
+ */
+function wp_kses_attr_check( &$name, &$value, &$whole, $vless, $element, $allowed_html ) {
+	$allowed_attr = $allowed_html[strtolower( $element )];
+
+	$name_low = strtolower( $name );
+	if ( ! isset( $allowed_attr[$name_low] ) || '' == $allowed_attr[$name_low] ) {
+		$name = $value = $whole = '';
+		return false;
+	}
+
+	if ( 'style' == $name_low ) {
+		$new_value = safecss_filter_attr( $value );
+
+		if ( empty( $new_value ) ) {
+			$name = $value = $whole = '';
+			return false;
+		}
+
+		$whole = str_replace( $value, $new_value, $whole );
+		$value = $new_value;
+	}
+
+	if ( is_array( $allowed_attr[$name_low] ) ) {
+		// there are some checks
+		foreach ( $allowed_attr[$name_low] as $currkey => $currval ) {
+			if ( ! wp_kses_check_attr_val( $value, $vless, $currkey, $currval ) ) {
+				$name = $value = $whole = '';
+				return false;
+			}
+		}
+	}
+
+	return true;
+}
+
 /**
 * Builds an attribute list from string containing attributes.
 *
@@ -889,6 +978,109 @@ function wp_kses_hair($attr, $allowed_protocols) {
 	return $attrarr;
 }

+/**
+ * Finds all attributes of an HTML element.
+ *
+ * Does not modify input.  May return "evil" output.
+ *
+ * Based on wp_kses_split2() and wp_kses_attr()
+ *
+ * @since 4.2.3
+ *
+ * @param string $element HTML element/tag
+ * @return array|bool List of attributes found in $element. Returns false on failure.
+ */
+function wp_kses_attr_parse( $element ) {
+	$valid = preg_match('%^(<\s*)(/\s*)?([a-zA-Z0-9]+\s*)([^>]*)(>?)$%', $element, $matches);
+	if ( 1 !== $valid ) {
+		return false;
+	}
+
+	$begin =  $matches[1];
+	$slash =  $matches[2];
+	$elname = $matches[3];
+	$attr =   $matches[4];
+	$end =    $matches[5];
+
+	if ( '' !== $slash ) {
+		// Closing elements do not get parsed.
+		return false;
+	}
+
+	// Is there a closing XHTML slash at the end of the attributes?
+	if ( 1 === preg_match( '%\s*/\s*$%', $attr, $matches ) ) {
+		$xhtml_slash = $matches[0];
+		$attr = substr( $attr, 0, -strlen( $xhtml_slash ) );
+	} else {
+		$xhtml_slash = '';
+	}
+	
+	// Split it
+	$attrarr = wp_kses_hair_parse( $attr );
+	if ( false === $attrarr ) {
+		return false;
+	}
+
+	// Make sure all input is returned by adding front and back matter.
+	array_unshift( $attrarr, $begin . $slash . $elname );
+	array_push( $attrarr, $xhtml_slash . $end );
+	
+	return $attrarr;
+}
+
+/**
+ * Builds an attribute list from string containing attributes.
+ *
+ * Does not modify input.  May return "evil" output.
+ * In case of unexpected input, returns false instead of stripping things.
+ *
+ * Based on wp_kses_hair() but does not return a multi-dimensional array.
+ *
+ * @since 4.2.3
+ *
+ * @param string $attr Attribute list from HTML element to closing HTML element tag
+ * @return array|bool List of attributes found in $attr. Returns false on failure.
+ */
+function wp_kses_hair_parse( $attr ) {
+	if ( '' === $attr ) {
+		return array();
+	}
+
+	$regex =
+	  '(?:'
+	.     '[-a-zA-Z:]+'   // Attribute name.
+	. '|'
+	.     '\[\[?[^\[\]]+\]\]?' // Shortcode in the name position implies unfiltered_html.
+	. ')'
+	. '(?:'               // Attribute value.
+	.     '\s*=\s*'       // All values begin with '='
+	.     '(?:'
+	.         '"[^"]*"'   // Double-quoted
+	.     '|'
+	.         "'[^']*'"   // Single-quoted
+	.     '|'
+	.         '[^\s"\']+' // Non-quoted
+	.         '(?:\s|$)'  // Must have a space
+	.     ')'
+	. '|'
+	.     '(?:\s|$)'      // If attribute has no value, space is required.
+	. ')'
+	. '\s*';              // Trailing space is optional except as mentioned above.
+
+	// Although it is possible to reduce this procedure to a single regexp,
+	// we must run that regexp twice to get exactly the expected result.
+
+	$validation = "%^($regex)+$%";
+	$extraction = "%$regex%";
+
+	if ( 1 === preg_match( $validation, $attr ) ) {
+		preg_match_all( $extraction, $attr, $attrarr );
+		return $attrarr[0];
+	} else {
+		return false;
+	}
+}
+
 /**
 * Performs different checks for attribute values.
 *
--- a/wp-includes/shortcodes.php
+++ b/wp-includes/shortcodes.php
@@ -188,9 +188,10 @@ function has_shortcode( $content, $tag ) {
 * @uses get_shortcode_regex() Gets the search pattern for searching shortcodes.
 *
 * @param string $content Content to search for shortcodes
+ * @param bool $ignore_html When true, shortcodes inside HTML elements will be skipped.
 * @return string Content with shortcodes filtered out.
 */
-function do_shortcode($content) {
+function do_shortcode( $content, $ignore_html = false ) {
 	global $shortcode_tags;

 	if ( false === strpos( $content, '[' ) ) {
@@ -200,8 +201,24 @@ function do_shortcode($content) {
 	if (empty($shortcode_tags) || !is_array($shortcode_tags))
 		return $content;

+	$tagnames = array_keys($shortcode_tags);
+	$tagregexp = join( '|', array_map('preg_quote', $tagnames) );
+	$pattern = "/\\[($tagregexp)/s";
+
+	if ( 1 !== preg_match( $pattern, $content ) ) {
+		// Avoids parsing HTML when there are no shortcodes or embeds anyway.
+		return $content;
+	}
+
+	$content = do_shortcodes_in_html_tags( $content, $ignore_html );
+
 	$pattern = get_shortcode_regex();
-	return preg_replace_callback( "/$pattern/s", 'do_shortcode_tag', $content );
+	$content = preg_replace_callback( "/$pattern/s", 'do_shortcode_tag', $content );
+	
+	// Always restore square braces so we don't break things like <!--[if IE ]>
+	$content = unescape_invalid_shortcodes( $content );
+	
+	return $content;
 }

 /**
@@ -294,6 +311,141 @@ function do_shortcode_tag( $m ) {
 	}
 }

+/**
+ * Search only inside HTML elements for shortcodes and process them.
+ *
+ * Any [ or ] characters remaining inside elements will be HTML encoded
+ * to prevent interference with shortcodes that are outside the elements.
+ * Assumes $content processed by KSES already.  Users with unfiltered_html
+ * capability may get unexpected output if angle braces are nested in tags.
+ *
+ * @since 4.2.3
+ *
+ * @param string $content Content to search for shortcodes
+ * @param bool $ignore_html When true, all square braces inside elements will be encoded.
+ * @return string Content with shortcodes filtered out.
+ */
+function do_shortcodes_in_html_tags( $content, $ignore_html ) {
+	// Normalize entities in unfiltered HTML before adding placeholders.
+	$trans = array( '&#91;' => '&#091;', '&#93;' => '&#093;' );
+	$content = strtr( $content, $trans );
+	$trans = array( '[' => '&#91;', ']' => '&#93;' );
+	
+	$pattern = get_shortcode_regex();
+
+	$comment_regex =
+		  '!'           // Start of comment, after the <.
+		. '(?:'         // Unroll the loop: Consume everything until --> is found.
+		.     '-(?!->)' // Dash not followed by end of comment.
+		.     '[^\-]*+' // Consume non-dashes.
+		. ')*+'         // Loop possessively.
+		. '(?:-->)?';   // End of comment. If not found, match all input.
+
+	$regex =
+		  '/('                   // Capture the entire match.
+		.     '<'                // Find start of element.
+		.     '(?(?=!--)'        // Is this a comment?
+		.         $comment_regex // Find end of comment.
+		.     '|'
+		.         '[^>]*>?'      // Find end of element. If not found, match all input.
+		.     ')'
+		. ')/s';
+
+	$textarr = preg_split( $regex, $content, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
+
+	foreach ( $textarr as &$element ) {
+		if ( '<' !== $element[0] ) {
+			continue;
+		}
+
+		$noopen = false === strpos( $element, '[' );
+		$noclose = false === strpos( $element, ']' );
+		if ( $noopen || $noclose ) {
+			// This element does not contain shortcodes.
+			if ( $noopen xor $noclose ) {
+				// Need to encode stray [ or ] chars.
+				$element = strtr( $element, $trans );
+			}
+			continue;
+		}
+
+		if ( $ignore_html || '<!--' === substr( $element, 0, 4 ) ) {
+			// Encode all [ and ] chars.
+			$element = strtr( $element, $trans );
+			continue;
+		}
+
+		$attributes = wp_kses_attr_parse( $element );
+		if ( false === $attributes ) {
+			// Looks like we found some crazy unfiltered HTML.  Skipping it for sanity.
+			$element = strtr( $element, $trans );
+			continue;
+		}
+		
+		// Get element name
+		$front = array_shift( $attributes );
+		$back = array_pop( $attributes );
+		$matches = array();
+		preg_match('%[a-zA-Z0-9]+%', $front, $matches);
+		$elname = $matches[0];
+		
+		// Look for shortcodes in each attribute separately.
+		foreach ( $attributes as &$attr ) {
+			$open = strpos( $attr, '[' );
+			$close = strpos( $attr, ']' );
+			if ( false === $open || false === $close ) {
+				continue; // Go to next attribute.  Square braces will be escaped at end of loop.
+			}
+			$double = strpos( $attr, '"' );
+			$single = strpos( $attr, "'" );
+			if ( ( false === $single || $open < $single ) && ( false === $double || $open < $double ) ) {
+				// $attr like '[shortcode]' or 'name = [shortcode]' implies unfiltered_html.
+				// In this specific situation we assume KSES did not run because the input
+				// was written by an administrator, so we should avoid changing the output
+				// and we do not need to run KSES here.
+				$attr = preg_replace_callback( "/$pattern/s", 'do_shortcode_tag', $attr );
+			} else {
+				// $attr like 'name = "[shortcode]"' or "name = '[shortcode]'"
+				// We do not know if $content was unfiltered. Assume KSES ran before shortcodes.
+				$count = 0;
+				$new_attr = preg_replace_callback( "/$pattern/s", 'do_shortcode_tag', $attr, -1, $count );
+				if ( $count > 0 ) {
+					// Sanitize the shortcode output using KSES.
+					$new_attr = wp_kses_one_attr( $new_attr, $elname );
+					if ( '' !== $new_attr ) {
+						// The shortcode is safe to use now.
+						$attr = $new_attr;
+					}
+				}
+			}
+		}
+		$element = $front . implode( '', $attributes ) . $back;
+		
+		// Now encode any remaining [ or ] chars.
+		$element = strtr( $element, $trans );
+	}
+	
+	$content = implode( '', $textarr );
+	
+	return $content;
+}
+
+/**
+ * Remove placeholders added by do_shortcodes_in_html_tags().
+ *
+ * @since 4.2.3
+ *
+ * @param string $content Content to search for placeholders.
+ * @return string Content with placeholders removed.
+ */
+function unescape_invalid_shortcodes( $content ) {
+        // Clean up entire string, avoids re-parsing HTML.
+        $trans = array( '&#91;' => '[', '&#93;' => ']' );
+        $content = strtr( $content, $trans );
+        
+        return $content;
+}
+
 /**
 * Retrieve all attributes from the shortcodes tag.
 *
@@ -393,9 +545,15 @@ function strip_shortcodes( $content ) {
 	if (empty($shortcode_tags) || !is_array($shortcode_tags))
 		return $content;

-	$pattern = get_shortcode_regex();
+	$content = do_shortcodes_in_html_tags( $content, true );

-	return preg_replace_callback( "/$pattern/s", 'strip_shortcode_tag', $content );
+	$pattern = get_shortcode_regex();
+	$content = preg_replace_callback( "/$pattern/s", 'strip_shortcode_tag', $content );
+
+	// Always restore square braces so we don't break things like <!--[if IE ]>
+	$content = unescape_invalid_shortcodes( $content );
+	
+	return $content;
 }

 function strip_shortcode_tag( $m ) {
--- a/wp-includes/version.php
+++ b/wp-includes/version.php
@@ -4,21 +4,21 @@
 *
 * @global string $wp_version
 */
-$wp_version = '4.0.3';
+$wp_version = '4.0.6';

 /**
 * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.
 *
 * @global int $wp_db_version
 */
-$wp_db_version = 29630;
+$wp_db_version = 29632;

 /**
 * Holds the TinyMCE version
 *
 * @global string $tinymce_version
 */
-$tinymce_version = '4104-20140822';
+$tinymce_version = '4104-20150505';

 /**
 * Holds the required PHP version
--- a/wp-includes/wp-db.php
+++ b/wp-includes/wp-db.php
@@ -1787,6 +1787,8 @@ class wpdb {
 	 * @return int|false The number of rows affected, or false on error.
 	 */
 	function _insert_replace_helper( $table, $data, $format = null, $type = 'INSERT' ) {
+		$this->insert_id = 0;
+
 		if ( ! in_array( strtoupper( $type ), array( 'REPLACE', 'INSERT' ) ) ) {
 			return false;
 		}
@@ -1807,7 +1809,6 @@ class wpdb {

 		$sql = "$type INTO `$table` ($fields) VALUES ($formats)";

-		$this->insert_id = 0;
 		$this->check_current_query = false;
 		return $this->query( $this->prepare( $sql, $values ) );
 	}
@@ -1928,11 +1929,20 @@ class wpdb {
 	 */
 	protected function process_fields( $table, $data, $format ) {
 		$data = $this->process_field_formats( $data, $format );
+		if ( false === $data ) {
+			return false;
+		}
+
 		$data = $this->process_field_charsets( $data, $table );
 		if ( false === $data ) {
 			return false;
 		}

+		$data = $this->process_field_lengths( $data, $table );
+		if ( false === $data ) {
+			return false;
+		}
+
 		$converted_data = $this->strip_invalid_text( $data );

 		if ( $data !== $converted_data ) {
@@ -1994,17 +2004,41 @@ class wpdb {
 				// We can skip this field if we know it isn't a string.
 				// This checks %d/%f versus ! %s because it's sprintf() could take more.
 				$value['charset'] = false;
-			} elseif ( $this->check_ascii( $value['value'] ) ) {
-				// If it's ASCII, then we don't need the charset. We can skip this field.
-				$value['charset'] = false;
 			} else {
 				$value['charset'] = $this->get_col_charset( $table, $field );
 				if ( is_wp_error( $value['charset'] ) ) {
 					return false;
 				}
+			}

-				// This isn't ASCII. Don't have strip_invalid_text() re-check.
-				$value['ascii'] = false;
+			$data[ $field ] = $value;
+		}
+
+		return $data;
+	}
+
+	/**
+	 * For string fields, record the maximum string length that field can safely save.
+	 *
+	 * @since 4.2.1
+	 * @access protected
+	 *
+	 * @param array  $data  As it comes from the wpdb::process_field_charsets() method.
+	 * @param string $table Table name.
+	 * @return array|False The same array as $data with additional 'length' keys, or false if
+	 *                     any of the values were too long for their corresponding field.
+	 */
+	protected function process_field_lengths( $data, $table ) {
+		foreach ( $data as $field => $value ) {
+			if ( '%d' === $value['format'] || '%f' === $value['format'] ) {
+				// We can skip this field if we know it isn't a string.
+				// This checks %d/%f versus ! %s because it's sprintf() could take more.
+				$value['length'] = false;
+			} else {
+				$value['length'] = $this->get_col_length( $table, $field );
+				if ( is_wp_error( $value['length'] ) ) {
+					return false;
+				}
 			}

 			$data[ $field ] = $value;
@@ -2211,7 +2245,10 @@ class wpdb {
 		}

 		$charsets = $columns = array();
-		$results = $this->get_results( "SHOW FULL COLUMNS FROM `$table`" );
+
+		$table_parts = explode( '.', $table );
+		$table = '`' . implode( '`.`', $table_parts ) . '`';
+		$results = $this->get_results( "SHOW FULL COLUMNS FROM $table" );
 		if ( ! $results ) {
 			return new WP_Error( 'wpdb_get_table_charset_failure' );
 		}
@@ -2334,6 +2371,99 @@ class wpdb {
 		return $charset;
 	}

+	/**
+	 * Retrieve the maximum string length allowed in a given column.
+	 * The length may either be specified as a byte length or a character length.
+	 *
+	 * @since 4.2.1
+	 * @access public
+	 *
+	 * @param string $table  Table name.
+	 * @param string $column Column name.
+	 * @return mixed array( 'length' => (int), 'type' => 'byte' | 'char' )
+	 *               false if the column has no length (for example, numeric column)
+	 *               WP_Error object if there was an error.
+	 */
+	public function get_col_length( $table, $column ) {
+		$tablekey = strtolower( $table );
+		$columnkey = strtolower( $column );
+
+		// Skip this entirely if this isn't a MySQL database.
+		if ( false === $this->is_mysql ) {
+			return false;
+		}
+
+		if ( empty( $this->col_meta[ $tablekey ] ) ) {
+			// This primes column information for us.
+			$table_charset = $this->get_table_charset( $table );
+			if ( is_wp_error( $table_charset ) ) {
+				return $table_charset;
+			}
+		}
+
+		if ( empty( $this->col_meta[ $tablekey ][ $columnkey ] ) ) {
+			return false;
+		}
+
+		$typeinfo = explode( '(', $this->col_meta[ $tablekey ][ $columnkey ]->Type );
+
+		$type = strtolower( $typeinfo[0] );
+		if ( ! empty( $typeinfo[1] ) ) {
+			$length = trim( $typeinfo[1], ')' );
+		} else {
+			$length = false;
+		}
+
+		switch( $type ) {
+			case 'char':
+			case 'varchar':
+				return array(
+					'type'   => 'char',
+					'length' => (int) $length,
+				);
+				break;
+			case 'binary':
+			case 'varbinary':
+				return array(
+					'type'   => 'byte',
+					'length' => (int) $length,
+				);
+				break;
+			case 'tinyblob':
+			case 'tinytext':
+				return array(
+					'type'   => 'byte',
+					'length' => 255,        // 2^8 - 1
+				);
+				break;
+			case 'blob':
+			case 'text':
+				return array(
+					'type'   => 'byte',
+					'length' => 65535,      // 2^16 - 1
+				);
+				break;
+			case 'mediumblob':
+			case 'mediumtext':
+				return array(
+					'type'   => 'byte',
+					'length' => 16777215,   // 2^24 - 1
+				);
+				break;
+			case 'longblob':
+			case 'longtext':
+				return array(
+					'type'   => 'byte',
+					'length' => 4294967295, // 2^32 - 1
+				);
+				break;
+			default:
+				return false;
+		}
+
+		return false;
+	}
+
 	/**
 	 * Check if a string is ASCII.
 	 *
@@ -2374,7 +2504,7 @@ class wpdb {

 		// We don't need to check the collation for queries that don't read data.
 		$query = ltrim( $query, "\r\n\t (" );
-		if ( preg_match( '/^(?:SHOW|DESCRIBE|DESC|EXPLAIN)\s/i', $query ) ) {
+		if ( preg_match( '/^(?:SHOW|DESCRIBE|DESC|EXPLAIN|CREATE)\s/i', $query ) ) {
 			return true;
 		}

@@ -2432,50 +2562,55 @@ class wpdb {
 	 */
 		// If any of the columns don't have one of these collations, it needs more sanity checking.
 	protected function strip_invalid_text( $data ) {
-		// Some multibyte character sets that we can check in PHP.
-		$mb_charsets = array(
-			'ascii'   => 'ASCII',
-			'big5'    => 'BIG-5',
-			'eucjpms' => 'eucJP-win',
-			'gb2312'  => 'EUC-CN',
-			'ujis'    => 'EUC-JP',
-			'utf32'   => 'UTF-32',
-		);
-
-		$supported_charsets = array();
-		if ( function_exists( 'mb_list_encodings' ) ) {
-			$supported_charsets = mb_list_encodings();
-		}
-
 		$db_check_string = false;

 		foreach ( $data as &$value ) {
 			$charset = $value['charset'];

-			// Column isn't a string, or is latin1, which will will happily store anything.
-			if ( false === $charset || 'latin1' === $charset ) {
+			if ( is_array( $value['length'] ) ) {
+				$length = $value['length']['length'];
+			} else {
+				$length = false;
+			}
+
+			// There's no charset to work with.
+			if ( false === $charset ) {
 				continue;
 			}

+			// Column isn't a string.
 			if ( ! is_string( $value['value'] ) ) {
 				continue;
 			}

-			// ASCII is always OK.
-			if ( ! isset( $value['ascii'] ) && $this->check_ascii( $value['value'] ) ) {
-				continue;
+			$truncate_by_byte_length = 'byte' === $value['length']['type'];
+
+			$needs_validation = true;
+			if (
+				// latin1 can store any byte sequence
+				'latin1' === $charset
+			||
+				// ASCII is always OK.
+				( ! isset( $value['ascii'] ) && $this->check_ascii( $value['value'] ) )
+			) {
+				$truncate_by_byte_length = true;
+				$needs_validation = false;
 			}

-			// Convert the text locally.
-			if ( $supported_charsets ) {
-				if ( isset( $mb_charsets[ $charset ] ) && in_array( $mb_charsets[ $charset ], $supported_charsets ) ) {
-					$value['value'] = mb_convert_encoding( $value['value'], $mb_charsets[ $charset ], $mb_charsets[ $charset ] );
+			if ( $truncate_by_byte_length ) {
+				mbstring_binary_safe_encoding();
+				if ( false !== $length && strlen( $value['value'] ) > $length ) {
+					$value['value'] = substr( $value['value'], 0, $length );
+				}
+				reset_mbstring_encoding();
+
+				if ( ! $needs_validation ) {
 					continue;
 				}
 			}

 			// utf8 can be handled by regex, which is a bunch faster than a DB lookup.
-			if ( 'utf8' === $charset || 'utf8mb3' === $charset || 'utf8mb4' === $charset ) {
+			if ( ( 'utf8' === $charset || 'utf8mb3' === $charset || 'utf8mb4' === $charset ) && function_exists( 'mb_strlen' ) ) {
 				$regex = '/
 					(
 						(?: [\x00-\x7F]                  # single-byte sequences   0xxxxxxx
@@ -2485,7 +2620,7 @@ class wpdb {
 						|   \xED[\x80-\x9F][\x80-\xBF]
 						|   [\xEE-\xEF][\x80-\xBF]{2}';

-				if ( 'utf8mb4' === $charset) {
+				if ( 'utf8mb4' === $charset ) {
 					$regex .= '
 						|    \xF0[\x90-\xBF][\x80-\xBF]{2} # four-byte sequences   11110xxx 10xxxxxx * 3
 						|    [\xF1-\xF3][\x80-\xBF]{3}
@@ -2493,11 +2628,16 @@ class wpdb {
 					';
 				}

-				$regex .= '){1,50}                          # ...one or more times
+				$regex .= '){1,40}                          # ...one or more times
 					)
 					| .                                  # anything else
 					/x';
 				$value['value'] = preg_replace( $regex, '$1', $value['value'] );
+
+
+				if ( false !== $length && mb_strlen( $value['value'], 'UTF-8' ) > $length ) {
+					$value['value'] = mb_substr( $value['value'], 0, $length, 'UTF-8' );
+				}
 				continue;
 			}

@@ -2514,8 +2654,14 @@ class wpdb {
 						$queries[ $value['charset'] ] = array();
 					}

-					// Split the CONVERT() calls by charset, so we can make sure the connection is right
-					$queries[ $value['charset'] ][ $col ] = $this->prepare( "CONVERT( %s USING {$value['charset']} )", $value['value'] );
+					// We're going to need to truncate by characters or bytes, depending on the length value we have.
+					if ( 'byte' === $value['length']['type'] ) {
+						// Split the CONVERT() calls by charset, so we can make sure the connection is right
+						$queries[ $value['charset'] ][ $col ] = $this->prepare( "CONVERT( LEFT( CONVERT( %s USING binary ), %d ) USING {$value['charset']} )", $value['value'], $value['length']['length'] );
+					} else {
+						$queries[ $value['charset'] ][ $col ] = $this->prepare( "LEFT( CONVERT( %s USING {$value['charset']} ), %d )", $value['value'], $value['length']['length'] );
+					}
+
 					unset( $data[ $col ]['db'] );
 				}
 			}
@@ -2534,16 +2680,19 @@ class wpdb {

 				$this->check_current_query = false;

-				$row = $this->get_row( "SELECT " . implode( ', ', $query ), ARRAY_N );
+				$sql = array();
+				foreach ( $query as $column => $column_query ) {
+					$sql[] = $column_query . " AS x_$column";
+				}
+
+				$row = $this->get_row( "SELECT " . implode( ', ', $sql ), ARRAY_A );
 				if ( ! $row ) {
 					$this->set_charset( $this->dbh, $connection_charset );
 					return new WP_Error( 'wpdb_strip_invalid_text_failure' );
 				}

-				$cols = array_keys( $query );
-				$col_count = count( $cols );
-				for ( $ii = 0; $ii < $col_count; $ii++ ) {
-					$data[ $cols[ $ii ] ]['value'] = $row[ $ii ];
+				foreach ( array_keys( $query ) as $column ) {
+					$data[ $column ]['value'] = $row["x_$column"];
 				}
 			}

@@ -2566,6 +2715,12 @@ class wpdb {
 	 * @return string|WP_Error The converted query, or a {@see WP_Error} object if the conversion fails.
 	 */
 	protected function strip_invalid_text_from_query( $query ) {
+		// We don't need to check the collation for queries that don't read data.
+		$trimmed_query = ltrim( $query, "\r\n\t (" );
+		if ( preg_match( '/^(?:SHOW|DESCRIBE|DESC|EXPLAIN|CREATE)\s/i', $trimmed_query ) ) {
+			return $query;
+		}
+
 		$table = $this->get_table_from_query( $query );
 		if ( $table ) {
 			$charset = $this->get_table_charset( $table );
@@ -2585,6 +2740,7 @@ class wpdb {
 			'value'   => $query,
 			'charset' => $charset,
 			'ascii'   => false,
+			'length'  => false,
 		);

 		$data = $this->strip_invalid_text( array( $data ) );
@@ -2607,7 +2763,7 @@ class wpdb {
 	 * @return string|WP_Error The converted string, or a `WP_Error` object if the conversion fails.
 	 */
 	public function strip_invalid_text_for_column( $table, $column, $value ) {
-		if ( ! is_string( $value ) || $this->check_ascii( $value ) ) {
+		if ( ! is_string( $value ) ) {
 			return $value;
 		}

@@ -2624,7 +2780,7 @@ class wpdb {
 			$column => array(
 				'value'   => $value,
 				'charset' => $charset,
-				'ascii'   => false,
+				'length'  => $this->get_col_length( $table, $column ),
 			)
 		);

@@ -2665,16 +2821,16 @@ class wpdb {
 				. '|REPLACE(?:\s+LOW_PRIORITY|\s+DELAYED)?(?:\s+INTO)?'
 				. '|UPDATE(?:\s+LOW_PRIORITY)?(?:\s+IGNORE)?'
 				. '|DELETE(?:\s+LOW_PRIORITY|\s+QUICK|\s+IGNORE)*(?:\s+FROM)?'
-				. ')\s+`?([\w-]+)`?/is', $query, $maybe ) ) {
-			return $maybe[1];
+				. ')\s+((?:[0-9a-zA-Z$_.`]|[\xC2-\xDF][\x80-\xBF])+)/is', $query, $maybe ) ) {
+			return str_replace( '`', '', $maybe[1] );
 		}

 		// SHOW TABLE STATUS and SHOW TABLES
 		if ( preg_match( '/^\s*(?:'
 				. 'SHOW\s+TABLE\s+STATUS.+(?:LIKE\s+|WHERE\s+Name\s*=\s*)'
 				. '|SHOW\s+(?:FULL\s+)?TABLES.+(?:LIKE\s+|WHERE\s+Name\s*=\s*)'
-				. ')\W([\w-]+)\W/is', $query, $maybe ) ) {
-			return $maybe[1];
+				. ')\W((?:[0-9a-zA-Z$_.`]|[\xC2-\xDF][\x80-\xBF])+)\W/is', $query, $maybe ) ) {
+			return str_replace( '`', '', $maybe[1] );
 		}

 		// Big pattern for the rest of the table-related queries.
@@ -2692,8 +2848,8 @@ class wpdb {
 				. '|LOAD\s+DATA.*INFILE.*INTO\s+TABLE'
 				. '|(?:GRANT|REVOKE).*ON\s+TABLE'
 				. '|SHOW\s+(?:.*FROM|.*TABLE)'
-				. ')\s+\(*\s*`?([\w-]+)`?\s*\)*/is', $query, $maybe ) ) {
-			return $maybe[1];
+				. ')\s+\(*\s*((?:[0-9a-zA-Z$_.`]|[\xC2-\xDF][\x80-\xBF])+)\s*\)*/is', $query, $maybe ) ) {
+			return str_replace( '`', '', $maybe[1] );
 		}

 		return false;
Author	SHA1	Message	Date
Dion Hulse	150dd442d2	Tag 4.0.6. Built from https://develop.svn.wordpress.org/@33403 git-svn-id: http://core.svn.wordpress.org/tags/4.0.6@33371 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-07-23 12:13:47 +00:00
Gary Pendergast	b3356b6f77	Bump 4.0 branch to version 4.0.6. Built from https://develop.svn.wordpress.org/branches/4.0@33397 git-svn-id: http://core.svn.wordpress.org/branches/4.0@33365 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-07-23 11:07:33 +00:00
Gary Pendergast	60eb789f93	Shortcodes: Improve the reliablity of shortcodes inside HTML tags. Merge of [33359] to the 4.0 branch. Props miqrogroove. See #15694. Built from https://develop.svn.wordpress.org/branches/4.0@33381 git-svn-id: http://core.svn.wordpress.org/branches/4.0@33352 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-07-23 04:50:37 +00:00
Gary Pendergast	5d196f2b09	Capabilities: When creating an auto-draft, ensure that the current user still has permission to do so. Merge of [33357] to the 4.0 branch. Built from https://develop.svn.wordpress.org/branches/4.0@33376 git-svn-id: http://core.svn.wordpress.org/branches/4.0@33347 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-07-23 04:01:36 +00:00
Dominik Schilling	9e426bbb49	4.0.5 version bumps. Built from https://develop.svn.wordpress.org/branches/4.0@32436 git-svn-id: http://core.svn.wordpress.org/branches/4.0@32406 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-05-06 23:28:36 +00:00
Michael Adams	cfd130d33a	Upgrade: `$wpdb->get_col_length()` sanity check: bail on unexpected return value. Merges [32429] for the 4.0 branch. See #32165. Built from https://develop.svn.wordpress.org/branches/4.0@32432 git-svn-id: http://core.svn.wordpress.org/branches/4.0@32402 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-05-06 23:13:58 +00:00
Michael Adams	551057bb68	Upgrade: Ensure unintelligible DB schemas don't result in content loss. Merge of [32417] to the 4.0 branch. See #32165. Props ocean90. Built from https://develop.svn.wordpress.org/branches/4.0@32420 git-svn-id: http://core.svn.wordpress.org/branches/4.0@32390 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-05-06 21:52:03 +00:00
John Blackbourn	6dbcbfae60	WPDB: Allow queries to reference tables in the dbname.tablename format, and allow table names to contain any valid character, rather than just ASCII. Merge of [32368] to the 4.0 branch. Props pento, willstedt for the initial patch. See #32090. Built from https://develop.svn.wordpress.org/branches/4.0@32413 git-svn-id: http://core.svn.wordpress.org/branches/4.0@32383 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-05-06 21:04:34 +00:00
Aaron Jorbin	a820c920f9	When upgrading WordPress remove genericons example.html files [32385] for 4.0 branch Props @dd32, @boonebgorges, @johnjamesjacoby, @drewapicture, @jorbin Built from https://develop.svn.wordpress.org/branches/4.0@32404 git-svn-id: http://core.svn.wordpress.org/branches/4.0@32374 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-05-06 20:05:33 +00:00
Dominik Schilling	c9168e3a54	WPDB: When sanity checking query character sets, there's no need to check queries that don't return user data. Merges [32374] to the 4.0 branch. props pento. see #32104. Built from https://develop.svn.wordpress.org/branches/4.0@32403 git-svn-id: http://core.svn.wordpress.org/branches/4.0@32373 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-05-06 20:04:38 +00:00
Helen Hou-Sandí	69de48fd72	The UTF-8 regex can occasionally fail on very low memory machines. Reduce the amount of memory it uses. Merges [32375] to the 4.0 branch. props pento. See #32204. Built from https://develop.svn.wordpress.org/branches/4.0@32397 git-svn-id: http://core.svn.wordpress.org/branches/4.0@32367 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-05-06 19:43:37 +00:00
Michael Adams	7e35f92679	WPDB: When checking that a string can be sent to MySQL, we shouldn't use `mb_convert_encoding()`, as it behaves differently to MySQL's character encoding conversion. Merge of [32364] to the 4.0 branch. Props mdawaffe, pento, nbachiyski, jorbin, johnjamesjacoby, jeremyfelt. See #32165. Built from https://develop.svn.wordpress.org/branches/4.0@32388 git-svn-id: http://core.svn.wordpress.org/branches/4.0@32358 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-05-06 19:09:39 +00:00
Andrew Ozz	d6df175451	TinyMCE: work-around a bug in the tags matching regex. For 4.0. Built from https://develop.svn.wordpress.org/branches/4.0@32372 git-svn-id: http://core.svn.wordpress.org/branches/4.0@32342 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-05-06 05:34:38 +00:00
Gary Pendergast	4fe0310d7a	4.0: - WPDB: Sanity check that any strings being stored in the DB are not too long to store correctly. - When upgrading, remove any suspicious comments. Built from https://develop.svn.wordpress.org/branches/4.0@32313 git-svn-id: http://core.svn.wordpress.org/branches/4.0@32284 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-04-27 17:17:37 +00:00
Gary Pendergast	4b6fa85282	4.0 branch is now 4.0.4. Built from https://develop.svn.wordpress.org/branches/4.0@32302 git-svn-id: http://core.svn.wordpress.org/branches/4.0@32273 1a063a9b-81f0-0310-95a4-ce76da25c4cd	2015-04-27 14:11:37 +00:00