Ticket #2272: 2272_2.patch

_whatsnew.html

@@ -67 +67 @@
                 <li>[<a target="_blank" href="http://dev.fckeditor.net/ticket/2322">#2322</a>] Fixed the issue
                         where the fit window command loses the current selection and scroll position in the
                         editing area.</li>
+                <li>[<a target="_blank" href="http://dev.fckeditor.net/ticket/2272">#2272</a>] Improved the
+                        garbage filter in Paste from Word dialog.</li>
         </ul>
         <p>
                 <a href="_whatsnew_history.html">See previous versions history</a></p>

editor/dialog/fck_paste.html

@@ -187 +187 @@
         var html = oNode.innerHTML ;
 
         html = html.replace(/<o:p>\s*<\/o:p>/g, '') ;
-        html = html.replace(/<o:p>.*?<\/o:p>/g, '&nbsp;') ;
+        html = html.replace(/<o:p>[\s\S]*?<\/o:p>/g, '&nbsp;') ;
 
         // Remove mso-xxx styles.
         html = html.replace( /\s*mso-[^:]+:[^;"]+;?/gi, '' ) ;
@@ -224 +224 @@
         if ( bRemoveStyles )
                 html = html.replace( /<(\w[^>]*) style="([^\"]*)"([^>]*)/gi, "<$1$3" ) ;
 
+        // Remove style, meta and link tags
+        html = html.replace( /<STYLE[^>]*>[\s\S]*?<\/STYLE[^>]*>/gi, '' ) ;
+        html = html.replace( /<(?:META|LINK)[^>]*>\s*/gi, '' ) ;
+
         // Remove empty styles.
         html =  html.replace( /\s*style="\s*"/gi, '' ) ;
 
@@ -234 +238 @@
         // Remove Lang attributes
         html = html.replace(/<(\w[^>]*) lang=([^ |>]*)([^>]*)/gi, "<$1$3") ;
 
-        html = html.replace( /<SPAN\s*>(.*?)<\/SPAN>/gi, '$1' ) ;
+        html = html.replace( /<SPAN\s*>([\s\S]*?)<\/SPAN>/gi, '$1' ) ;
 
-        html = html.replace( /<FONT\s*>(.*?)<\/FONT>/gi, '$1' ) ;
+        html = html.replace( /<FONT\s*>([\s\S]*?)<\/FONT>/gi, '$1' ) ;
 
         // Remove XML elements and declarations
         html = html.replace(/<\\?\?xml[^>]*>/gi, '' ) ;
 
+        // Remove w: tags with contents.
+        html = html.replace( /<w:[^>]*>[\s\S]*?<\/w:[^>]*>/gi, '' ) ;
+
         // Remove Tags with XML namespace declarations: <o:p><\/o:p>
         html = html.replace(/<\/?\w+:[^>]*>/gi, '' ) ;
 
         // Remove comments [SF BUG-1481861].
-        html = html.replace(/<\!--.*?-->/g, '' ) ;
+        html = html.replace(/<\!--[\s\S]*?-->/g, '' ) ;
 
         html = html.replace( /<(U|I|STRIKE)>&nbsp;<\/\1>/g, '&nbsp;' ) ;
 
         html = html.replace( /<H\d>\s*<\/H\d>/gi, '' ) ;
 
         // Remove "display:none" tags.
-        html = html.replace( /<(\w+)[^>]*\sstyle="[^"]*DISPLAY\s?:\s?none(.*?)<\/\1>/ig, '' ) ;
+        html = html.replace( /<(\w+)[^>]*\sstyle="[^"]*DISPLAY\s?:\s?none[\s\S]*?<\/\1>/ig, '' ) ;
 
         // Remove language tags
         html = html.replace( /<(\w[^>]*) language=([^ |>]*)([^>]*)/gi, "<$1$3") ;
@@ -267 +274 @@
                 html = html.replace( /<H(\d)([^>]*)>/gi, '<h$1>' ) ;
 
                 // Word likes to insert extra <font> tags, when using MSIE. (Wierd).
-                html = html.replace( /<(H\d)><FONT[^>]*>(.*?)<\/FONT><\/\1>/gi, '<$1>$2<\/$1>' );
-                html = html.replace( /<(H\d)><EM>(.*?)<\/EM><\/\1>/gi, '<$1>$2<\/$1>' );
+                html = html.replace( /<(H\d)><FONT[^>]*>([\s\S]*?)<\/FONT><\/\1>/gi, '<$1>$2<\/$1>' );
+                html = html.replace( /<(H\d)><EM>([\s\S]*?)<\/EM><\/\1>/gi, '<$1>$2<\/$1>' );
         }
         else
         {
@@ -282 +289 @@
                 html = html.replace( /<\/H\d>/gi, '<\/font><\/b><\/div>' ) ;
 
                 // Transform <P> to <DIV>
-                var re = new RegExp( '(<P)([^>]*>.*?)(<\/P>)', 'gi' ) ; // Different because of a IE 5.0 error
+                var re = new RegExp( '(<P)([^>]*>[\\s\\S]*?)(<\/P>)', 'gi' ) ;  // Different because of a IE 5.0 error
                 html = html.replace( re, '<div$2<\/div>' ) ;
 
                 // Remove empty tags (three times, just to be sure).