Use a subclass of buildindex.Node to clean up the HTML and get the

ordering fixed up (this makes sure that "xml.dom" comes before
"xml.dom.minidom" in the Module Index, which was not true before because
some HTML cruft crept into the data structures).

diff --git a/Doc/tools/mkmodindex b/Doc/tools/mkmodindex
index 257e30aa01858de67a82c33385e329e274748410..3bc4b956ea20c721a8c1e050aa1e579e11db9461 100755 (executable)
--- a/Doc/tools/mkmodindex
+++ b/Doc/tools/mkmodindex
@@ -48,6 +48,23 @@ class IndexOptions(support.Options):
         print __doc__ % {"program": program}
 
 
+class Node(buildindex.Node):
+    annotation = ""
+
+    def __init__(self, link, str, seqno):
+        parts = str.split(None, 1)
+        if parts[0].endswith("</tt>"):
+            self.modname = parts[0][:-5]
+        else:
+            self.modname = parts[0]
+        if len(parts) == 2:
+            self.annotation = parts[1]
+        buildindex.Node.__init__(self, link, self.modname, seqno)
+
+    def __str__(self):
+        return '<tt class="module">%s</tt> %s' \
+               % (self.modname, self.annotation)
+
 _rx = re.compile(
     "<dt><a href='(module-.*\.html)#l2h-\d+'><tt class='module'>"
     "([a-zA-Z_][a-zA-Z0-9_.]*</tt>(\s*<em>"
@@ -83,10 +100,7 @@ def main():
                 basename, modname = m.group(1, 2)
                 has_plat_flag = has_plat_flag or m.group(3)
                 linkfile = os.path.join(dirname, basename)
-                nodes.append(buildindex.Node(
-                    '<a href="%s">' % linkfile,
-                    "<tt class=module>%s</tt>" % modname,
-                    seqno))
+                nodes.append(Node('<a href="%s">' % linkfile, modname, seqno))
                 seqno = seqno + 1
         ifp.close()
     #