Patch #912410: Replace HTML entity references for attribute values

loewis · loewis · commit ab8a6bba250b · 2007-03-06T14:43:00.000Z
in HTMLParser.
diff --git a/Doc/lib/libhtmlparser.tex b/Doc/lib/libhtmlparser.tex
@@ -75,14 +75,18 @@ \section{\module{HTMLParser} ---
 be overridden by a derived class; the base class implementation does
 nothing.  
 
-The \var{tag} argument is the name of the tag converted to
-lower case.  The \var{attrs} argument is a list of \code{(\var{name},
-\var{value})} pairs containing the attributes found inside the tag's
-\code{<>} brackets.  The \var{name} will be translated to lower case
-and double quotes and backslashes in the \var{value} have been
-interpreted.  For instance, for the tag \code{<A
-HREF="http://www.cwi.nl/">}, this method would be called as
+The \var{tag} argument is the name of the tag converted to lower case.
+The \var{attrs} argument is a list of \code{(\var{name}, \var{value})}
+pairs containing the attributes found inside the tag's \code{<>}
+brackets.  The \var{name} will be translated to lower case, and quotes
+in the \var{value} have been removed, and character and entity
+references have been replaced.  For instance, for the tag \code{<A
+  HREF="http://www.cwi.nl/">}, this method would be called as
 \samp{handle_starttag('a', [('href', 'http://www.cwi.nl/')])}.
+
+\versionchanged[All entity references from htmlentitydefs are now
+replaced in the attribute values]{2.6}
+
 \end{methoddesc}
 
 \begin{methoddesc}{handle_startendtag}{tag, attrs}
diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py
@@ -358,12 +358,30 @@ def unknown_decl(self, data):
         self.error("unknown declaration: %r" % (data,))
 
     # Internal -- helper to remove special character quoting
+    entitydefs = None
     def unescape(self, s):
         if '&' not in s:
             return s
-        s = s.replace("&lt;", "<")
-        s = s.replace("&gt;", ">")
-        s = s.replace("&apos;", "'")
-        s = s.replace("&quot;", '"')
-        s = s.replace("&amp;", "&") # Must be last
-        return s
+        def replaceEntities(s):
+            s = s.groups()[0]
+            if s[0] == "#":
+                s = s[1:]
+                if s[0] in ['x','X']:
+                    c = int(s[1:], 16)
+                else:
+                    c = int(s)
+                return unichr(c)
+            else:
+                # Cannot use name2codepoint directly, because HTMLParser supports apos,
+                # which is not part of HTML 4
+                import htmlentitydefs
+                if HTMLParser.entitydefs is None:
+                    entitydefs = HTMLParser.entitydefs = {'apos':u"'"}
+                    for k, v in htmlentitydefs.name2codepoint.iteritems():
+                        entitydefs[k] = unichr(v)
+                try:
+                    return self.entitydefs[s]
+                except KeyError:
+                    return '&'+s+';'
+
+        return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", replaceEntities, s)
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
@@ -309,6 +309,11 @@ def test_cdata_content(self):
             ("endtag", "script"),
             ])
 
+    def test_entityrefs_in_attributes(self):
+        self._run_check("<html foo='&euro;&amp;&#97;&#x61;&unsupported;'>", [
+                ("starttag", "html", [("foo", u"\u20AC&aa&unsupported;")])
+                ])
+
 
 def test_main():
     test_support.run_unittest(HTMLParserTestCase)
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -141,6 +141,9 @@ Core and builtins
 Library
 -------
 
+- Patch #912410: Replace HTML entity references for attribute values 
+  in HTMLParser.
+
 - Patch #1663234: you can now run doctest on test files and modules
   using "python -m doctest [-v] filename ...".
 
