Ticket #5678: 5678.r6631.diff

wp-includes/formatting.php

@@ -1257 +1257 @@
         return $matches[0];
 }
 
+/**
+ * strip_html_newlines() - Strip unnecessary newlines from HTML code
+ *
+ * This function removes any unnecessary newlines in HTML
+ * code. Useful for cleaning up RSS feeds before import.
+ *
+ * @since 2.5
+ *
+ * @param string $text The HTML code to strip newlines from
+ * @return string $text with newlines stripped
+ */
+function strip_html_newlines($text) {
+        $textarr = preg_split("/(<[^>]+>)/Us", $text, -1, PREG_SPLIT_DELIM_CAPTURE);
+        $stop = count($textarr); $skip = false; $output = ''; // loop stuff
+        for ($ci = 0; $ci < $stop; $ci++) {
+                $curl = $textarr[$ci];
+                if (! $skip && isset($curl{0}) && '<' != $curl{0}) { // If it's not a tag
+                        $curl = preg_replace('/[\n\r]+/', ' ', $curl);
+                } elseif (strpos($curl, '<code') !== false || strpos($curl, '<pre') !== false || strpos($curl, '<kbd') !== false || strpos($curl, '<style') !== false || strpos($curl, '<script') !== false) {
+                        $next = false;
+                } else {
+                        $next = true;
+                }
+                $output .= $curl;
+        }
+        return $output;
+}
+
 ?>

wp-admin/import/rss.php

@@ -90 +90 @@
                         $post_content = preg_replace('|<(/?[A-Z]+)|e', "'<' . strtolower('$1')", $post_content);
                         $post_content = str_replace('<br>', '<br />', $post_content);
                         $post_content = str_replace('<hr>', '<hr />', $post_content);
+                        $post_content = strip_html_newlines($post_content);
 
                         $post_author = 1;
                         $post_status = 'publish';