X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/7f1521bf193b382565eb753043c161f4cb3fcda7..dc1231b7312fbdca99e9e887cc2bb35a28f85cdc:/wp-includes/shortcodes.php?ds=sidebyside

diff --git a/wp-includes/shortcodes.php b/wp-includes/shortcodes.php
index e3c267a4..86976a21 100644
--- a/wp-includes/shortcodes.php
+++ b/wp-includes/shortcodes.php
@@ -81,16 +81,14 @@ $shortcode_tags = array();
  *
  * @since 2.5.0
  *
- * @uses $shortcode_tags
+ * @global array $shortcode_tags
  *
- * @param string $tag Shortcode tag to be searched in post content.
+ * @param string   $tag  Shortcode tag to be searched in post content.
  * @param callable $func Hook to run when shortcode is found.
  */
 function add_shortcode($tag, $func) {
 	global $shortcode_tags;
-
-	if ( is_callable($func) )
-		$shortcode_tags[$tag] = $func;
+	$shortcode_tags[ $tag ] = $func;
 }
 
 /**
@@ -98,7 +96,7 @@ function add_shortcode($tag, $func) {
  *
  * @since 2.5.0
  *
- * @uses $shortcode_tags
+ * @global array $shortcode_tags
  *
  * @param string $tag Shortcode tag to remove hook for.
  */
@@ -117,7 +115,7 @@ function remove_shortcode($tag) {
  *
  * @since 2.5.0
  *
- * @uses $shortcode_tags
+ * @global array $shortcode_tags
  */
 function remove_all_shortcodes() {
 	global $shortcode_tags;
@@ -184,9 +182,10 @@ function has_shortcode( $content, $tag ) {
  * @global array $shortcode_tags List of shortcode tags and their callback hooks.
  *
  * @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( $content, '[' ) ) {
@@ -196,8 +195,24 @@ function do_shortcode($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;
 }
 
 /**
@@ -217,7 +232,7 @@ function do_shortcode($content) {
  *
  * @since 2.5.0
  *
- * @uses $shortcode_tags
+ * @global array $shortcode_tags
  *
  * @return string The shortcode search regular expression
  */
@@ -265,10 +280,11 @@ function get_shortcode_regex() {
  *
  * @since 2.5.0
  * @access private
- * @uses $shortcode_tags
+ *
+ * @global array $shortcode_tags
  *
  * @param array $m Regular expression match array
- * @return mixed False on failure.
+ * @return string|false False on failure.
  */
 function do_shortcode_tag( $m ) {
 	global $shortcode_tags;
@@ -281,6 +297,12 @@ function do_shortcode_tag( $m ) {
 	$tag = $m[2];
 	$attr = shortcode_parse_atts( $m[3] );
 
+	if ( ! is_callable( $shortcode_tags[ $tag ] ) ) {
+		$message = sprintf( __( 'Attempting to parse a shortcode without a valid callback: %s' ), $tag );
+		_doing_it_wrong( __FUNCTION__, $message, '4.3.0' );
+		return $m[0];
+	}
+
 	if ( isset( $m[5] ) ) {
 		// enclosing tag - extra parameter
 		return $m[1] . call_user_func( $shortcode_tags[$tag], $attr, $m[5], $tag ) . $m[6];
@@ -290,6 +312,127 @@ 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();
+	$textarr = wp_html_split( $content );
+
+	foreach ( $textarr as &$element ) {
+		if ( '' == $element || '<' !== $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 ) || '<![CDATA[' === substr( $element, 0, 9 ) ) {
+			// Encode all [ and ] chars.
+			$element = strtr( $element, $trans );
+			continue;
+		}
+
+		$attributes = wp_kses_attr_parse( $element );
+		if ( false === $attributes ) {
+			// Some plugins are doing things like [name] <[email]>.
+			if ( 1 === preg_match( '%^<\s*\[\[?[^\[\]]+\]%', $element ) ) {
+				$element = preg_replace_callback( "/$pattern/s", 'do_shortcode_tag', $element );
+			}
+
+			// 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 ( '' !== trim( $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.
  *
@@ -304,7 +447,7 @@ function do_shortcode_tag( $m ) {
  */
 function shortcode_parse_atts($text) {
 	$atts = array();
-	$pattern = '/(\w+)\s*=\s*"([^"]*)"(?:\s|$)|(\w+)\s*=\s*\'([^\']*)\'(?:\s|$)|(\w+)\s*=\s*([^\s\'"]+)(?:\s|$)|"([^"]*)"(?:\s|$)|(\S+)(?:\s|$)/';
+	$pattern = '/([\w-]+)\s*=\s*"([^"]*)"(?:\s|$)|([\w-]+)\s*=\s*\'([^\']*)\'(?:\s|$)|([\w-]+)\s*=\s*([^\s\'"]+)(?:\s|$)|"([^"]*)"(?:\s|$)|(\S+)(?:\s|$)/';
 	$text = preg_replace("/[\x{00a0}\x{200b}]+/u", " ", $text);
 	if ( preg_match_all($pattern, $text, $match, PREG_SET_ORDER) ) {
 		foreach ($match as $m) {
@@ -319,6 +462,15 @@ function shortcode_parse_atts($text) {
 			elseif (isset($m[8]))
 				$atts[] = stripcslashes($m[8]);
 		}
+
+		// Reject any unclosed HTML elements
+		foreach( $atts as &$value ) {
+			if ( false !== strpos( $value, '<' ) ) {
+				if ( 1 !== preg_match( '/^[^<]*+(?:<[^>]*+>[^<]*+)*+$/', $value ) ) {
+					$value = '';
+				}
+			}
+		}
 	} else {
 		$atts = ltrim($text);
 	}
@@ -337,8 +489,8 @@ function shortcode_parse_atts($text) {
  *
  * @since 2.5.0
  *
- * @param array $pairs Entire list of supported attributes and their defaults.
- * @param array $atts User defined attributes in shortcode tag.
+ * @param array  $pairs     Entire list of supported attributes and their defaults.
+ * @param array  $atts      User defined attributes in shortcode tag.
  * @param string $shortcode Optional. The name of the shortcode, provided for context to enable filtering
  * @return array Combined and filtered attribute list.
  */
@@ -359,9 +511,9 @@ function shortcode_atts( $pairs, $atts, $shortcode = '' ) {
 	 *
 	 * @since 3.6.0
 	 *
-	 * @param array $out The output array of shortcode attributes.
+	 * @param array $out   The output array of shortcode attributes.
 	 * @param array $pairs The supported attributes and their defaults.
-	 * @param array $atts The user defined shortcode attributes.
+	 * @param array $atts  The user defined shortcode attributes.
 	 */
 	if ( $shortcode )
 		$out = apply_filters( "shortcode_atts_{$shortcode}", $out, $pairs, $atts );
@@ -374,7 +526,7 @@ function shortcode_atts( $pairs, $atts, $shortcode = '' ) {
  *
  * @since 2.5.0
  *
- * @uses $shortcode_tags
+ * @global array $shortcode_tags
  *
  * @param string $content Content to remove shortcode tags.
  * @return string Content without shortcode tags.
@@ -389,11 +541,22 @@ function strip_shortcodes( $content ) {
 	if (empty($shortcode_tags) || !is_array($shortcode_tags))
 		return $content;
 
+	$content = do_shortcodes_in_html_tags( $content, true );
+
 	$pattern = get_shortcode_regex();
+	$content = preg_replace_callback( "/$pattern/s", 'strip_shortcode_tag', $content );
 
-	return 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;
 }
 
+/**
+ *
+ * @param array $m
+ * @return string|false
+ */
 function strip_shortcode_tag( $m ) {
 	// allow [[foo]] syntax for escaping a tag
 	if ( $m[1] == '[' && $m[6] == ']' ) {