#364: WHED appendix title handline rewritten to complement #359

interpparser/gpo_cfr.py

@@ -11,7 +11,7 @@
 from regparser.tree.depth import markers as mtypes
 from regparser.tree.depth import heuristics, rules
 from regparser.tree.depth.derive import derive_depths
-from regparser.tree.gpo_cfr.appendices import appendix_headers
+from regparser.tree.gpo_cfr import appendices
 from regparser.tree.struct import Node, treeify
 from regparser.tree.xml_parser import matchers, tree_utils
 
@@ -292,26 +292,14 @@ def per_node(node):
 
 def build_supplement_tree(reg_part, node):
     """ Build the tree for the supplement section. """
-    title = tree_utils.get_node_text(appendix_headers(node)[0])
     root = Node(
         node_type=Node.INTERP,
         label=[reg_part, Node.INTERP_MARK],
-        title=title)
+        title=appendices.get_appendix_title(node))
 
     return parse_from_xml(root, node.getchildren())
 
 
 @matchers.match_tag('INTERP')
 def parse_interp(parent, xml_node):
     parent.children.append(build_supplement_tree(parent.cfr_part, xml_node))
-
-
-def get_app_title(node):
-    """ Appendix/Supplement sections have the title in an HD tag, or
-    if they are reserved, in a <RESERVED> tag. Extract the title. """
-
-    titles = node.xpath("./HD[@SOURCE='HED']")
-    if titles:
-        return titles[0].text
-    else:
-        return node.xpath("./RESERVED")[0]

interpparser/preprocessors.py

@@ -1,4 +1,4 @@
-from interpparser.gpo_cfr import get_app_title
+from regparser.tree.gpo_cfr import appendices
 
 _CONTAINS_SUPPLEMENT = "contains(., 'Supplement I')"
 _SUPPLEMENT_HD = "//REGTEXT//HD[@SOURCE='HD1' and {0}]".format(
@@ -28,6 +28,6 @@ def supplement_amdpar(xml):
 def appendix_to_interp(xml):
     """Convert Supplement I APPENDIX tags to INTERP"""
     for appendix in xml.xpath('.//APPENDIX'):
-        section_title = get_app_title(appendix)
+        section_title = appendices.get_appendix_title(appendix)
         if 'Supplement' in section_title and 'Part' in section_title:
             appendix.tag = 'INTERP'

regparser/tree/gpo_cfr/appendices.py

@@ -46,8 +46,13 @@ def remove_toc(appendix, letter):
 
 
 def appendix_headers(node):
+    """ Retrieve Appendix/Supplement section HD, WHED, and RESERVED tags. """
     return node.xpath('./RESERVED|./HD[@SOURCE="HED"]|./WHED')
 
+def get_appendix_title(node):
+    """ Retrieve the first Appendix/Supplement title from its headers. """
+    return tree_utils.get_node_text(appendix_headers(node)[0])
+
 
 _first_markers = [re.compile(r'[\)\.|,|;|-|—]\s*\(' + lvl[0] + r'\)')
                   for lvl in p_levels]