[Zope-Checkins] CVS: Zope/lib/python/TAL - HTMLParser.py:1.21.30.1

[Fred L. Drake, Jr.]

Update of /cvs-repository/Zope/lib/python/TAL
In directory cvs.zope.org:/tmp/cvs-serv5632

Modified Files:
      Tag: Zope-2_5-branch
	HTMLParser.py 
Log Message:
"Fix" false bug:  When something that looks like an end tag occurs in CDATA
content, but does not match the expected end tag, treat it as character data.
This is mostly useful when script includes string literal that include end 
tags.


=== Zope/lib/python/TAL/HTMLParser.py 1.21 => 1.21.30.1 ===
         return self.__starttag_text
 
-    def set_cdata_mode(self):
+    cdata_endtag = None
+
+    def set_cdata_mode(self, endtag=None):
+        self.cdata_endtag = endtag
         self.interesting = interesting_cdata
 
     def clear_cdata_mode(self):
+        self.cdata_endtag = None
         self.interesting = interesting_normal
 
     # Internal -- handle data as far as reasonable.  May leave state
@@ -291,7 +295,7 @@
         else:
             self.handle_starttag(tag, attrs)
             if tag in self.CDATA_CONTENT_ELEMENTS:
-                self.set_cdata_mode()
+                self.set_cdata_mode(tag)
         return endpos
 
     # Internal -- check to see if we have a complete starttag; return end
@@ -337,8 +341,15 @@
         match = endtagfind.match(rawdata, i) # </ + tag + >
         if not match:
             self.error("bad end tag: %s" % `rawdata[i:j]`)
-        tag = match.group(1)
-        self.handle_endtag(string.lower(tag))
+        tag = string.lower(match.group(1))
+        if (  self.cdata_endtag is not None
+              and tag != self.cdata_endtag):
+            # Should be a mismatched end tag, but we'll treat it
+            # as text anyway, since most HTML authors aren't
+            # interested in the finer points of syntax.
+            self.handle_data(match.group(0))
+        else:
+            self.handle_endtag(tag)
         return j
 
     # Overridable -- finish processing of start+end tag: <tag.../>