def test_process_markerless_collapsed(self):
"""Should be able to find collapsed markers in a markerless
paragraph"""
with XMLBuilder("ROOT") as ctx:
ctx.P("Intro text")
ctx.child_from_string(
'<P><E T="03">Some term.</E> (a) First definition</P>')
ctx.P("(b) Second definition")
root = Node(label=['111', '22'])
root = reg_text.RegtextParagraphProcessor().process(ctx.xml, root)
root = NodeAccessor(root)
self.assertEqual(['111', '22'], root.label)
self.assertEqual(2, len(root.child_labels))
self.assertTrue(all(c.is_markerless for c in root.children))
keyterm_label = root.child_labels[1]
self.assertTrue(len(keyterm_label) > 5)
self.assertEqual(['a', 'b'], root[keyterm_label].child_labels)
def test_process_nested_uscode(self):
with XMLBuilder("ROOT") as ctx:
ctx.P("Some intro")
with ctx.EXTRACT():
ctx.HD("The U.S. Code!")
with ctx.USCODE():
ctx.P("(x)(1) Some content")
ctx.P("(A) Sub-sub-paragraph")
ctx.P("(i)(I) Even more nested")
root = reg_text.RegtextParagraphProcessor().process(ctx.xml, Node())
root = NodeAccessor(root)
self.assertEqual(root['p1'].text, "Some intro")
self.assertEqual(root['p2']['p1'].title, 'The U.S. Code!')
code = root['p2']['p2']
self.assertEqual(code.source_xml.tag, 'USCODE')
self.assertEqual(code['x'].text, '(x)')
self.assertEqual(code['x']['1'].text, '(1) Some content')
self.assertEqual(code['x']['1']['A'].text, '(A) Sub-sub-paragraph')
self.assertEqual(code['x']['1']['A']['i'].text, '(i)')
self.assertEqual(code['x']['1']['A']['i']['I'].text,
'(I) Even more nested')