preprocessors.py

+class AtfI50032(PreProcessorBase):
+    """478.103 contains a chunk of text which is meant to appear in a poster
+    and be easily copy-paste-able. Unfortunately, the XML post 2003 isn't
+    structured to contain all of the appropriate elements within the EXTRACT
+    associated with the poster. This PreProcessor moves these additional
+    elements back into the appropriate EXTRACT."""
+    MARKER = ("//SECTNO[contains(., '478.103')]/.."     # In 478.103
+              # Look for a P with the appropriate key words
+              "/P[contains(., 'ATF I 5300.2') and contains(., 'shall state')]")
+
+    def transform(self, xml):
+        for p in xml.xpath(self.MARKER):
+            next_el = p.getnext()
+            to_move = []
+            while next_el is not None and next_el.tag != 'EXTRACT':
+                to_move.append(next_el)
+                next_el = next_el.getnext()
+            if next_el is not None:
+                extract = next_el
+                # reversed as we're inserting into the beginning
+                for xml_el in reversed(to_move):
+                    extract.insert(0, xml_el)
+
+