def test_process_inner_child(self):
xml = """
<ROOT>
<HD>Title</HD>
<P>1. 111. i. iii</P>
<STARS />
<P>A. AAA</P>
<P><E T="03">1.</E> eee</P>
</ROOT>"""
node = etree.fromstring(xml).xpath('//HD')[0]
stack = tree_utils.NodeStack()
interpretations.process_inner_children(stack, node)
while stack.size() > 1:
stack.unwind()
n1 = stack.m_stack[0][0][1]
self.assertEqual(['1'], n1.label)
self.assertEqual(1, len(n1.children))
n1i = n1.children[0]
self.assertEqual(['1', 'i'], n1i.label)
self.assertEqual(n1i.text.strip(), 'i. iii')
self.assertEqual(1, len(n1i.children))
n1iA = n1i.children[0]
self.assertEqual(['1', 'i', 'A'], n1iA.label)
self.assertEqual(1, len(n1iA.children))
n1iA1 = n1iA.children[0]
self.assertEqual(['1', 'i', 'A', '1'], n1iA1.label)
self.assertEqual(0, len(n1iA1.children))
def test_process_inner_child_has_citation(self):
xml = """
<ROOT>
<HD>Title</HD>
<P>1. Something something see comment 22(a)-2.i. please</P>
</ROOT>"""
node = etree.fromstring(xml).xpath('//HD')[0]
stack = tree_utils.NodeStack()
interpretations.process_inner_children(stack, node)
while stack.size() > 1:
stack.unwind()
tree = stack.m_stack[0][0][1]
self.assertEqual(0, len(tree.children))
def test_process_inner_child_incorrect_xml(self):
xml = """
<ROOT>
<HD>Title</HD>
<P><E T="03">1.</E> 111</P>
<P>i. iii</P>
<P><E T="03">2.</E> 222 Incorrect Content</P>
</ROOT>"""
node = etree.fromstring(xml).xpath('//HD')[0]
stack = tree_utils.NodeStack()
interpretations.process_inner_children(stack, node)
while stack.size() > 1:
stack.unwind()
self.assertEqual(2, len(stack.m_stack[0]))
def test_process_inner_child_no_marker(self):
xml = """
<ROOT>
<HD>Title</HD>
<P>1. 111</P>
<P>i. iii</P>
<P>Howdy Howdy</P>
</ROOT>"""
node = etree.fromstring(xml).xpath('//HD')[0]
stack = tree_utils.NodeStack()
interpretations.process_inner_children(stack, node)
while stack.size() > 1:
stack.unwind()
i1 = stack.m_stack[0][0][1]
self.assertEqual(1, len(i1.children))
i1i = i1.children[0]
self.assertEqual(0, len(i1i.children))
self.assertEqual(i1i.text.strip(), "i. iii\n\nHowdy Howdy")
def test_process_inner_child_collapsed_i(self):
xml = """
<ROOT>
<HD>Title</HD>
<P>1. <E T="03">Keyterm text</E> i. Content content</P>
<P>ii. Other stuff</P>
</ROOT>"""
node = etree.fromstring(xml).xpath('//HD')[0]
stack = tree_utils.NodeStack()
interpretations.process_inner_children(stack, node)
while stack.size() > 1:
stack.unwind()
tree = stack.m_stack[0][0][1]
self.assertEqual(['1'], tree.label)
self.assertEqual(2, len(tree.children))
self.assertEqual(['1', 'i'], tree.children[0].label)
self.assertEqual(0, len(tree.children[0].children))
self.assertEqual(['1', 'ii'], tree.children[1].label)
self.assertEqual(0, len(tree.children[1].children))
def test_process_inner_child_space(self):
xml = """
<ROOT>
<HD>Title</HD>
<P>1. 111</P>
<P>i. See country A. Not that country</P>
</ROOT>"""
node = etree.fromstring(xml).xpath('//HD')[0]
stack = tree_utils.NodeStack()
interpretations.process_inner_children(stack, node)
while stack.size() > 1:
stack.unwind()
n1 = stack.m_stack[0][0][1]
self.assertEqual(['1'], n1.label)
self.assertEqual(1, len(n1.children))
n1i = n1.children[0]
self.assertEqual(['1', 'i'], n1i.label)
self.assertEqual(0, len(n1i.children))
def test_process_inner_child_stars_and_inline(self):
xml = """
<ROOT>
<HD>Title</HD>
<STARS />
<P>2. Content. * * *</P>
<STARS />
<P>xi. Content</P>
<STARS />
</ROOT>"""
node = etree.fromstring(xml).xpath('//HD')[0]
stack = tree_utils.NodeStack()
interpretations.process_inner_children(stack, node)
while stack.size() > 1:
stack.unwind()
tree = stack.m_stack[0][0][1]
self.assertEqual(['2'], tree.label)
self.assertEqual(1, len(tree.children))
self.assertEqual(['2', 'xi'], tree.children[0].label)
self.assertEqual(0, len(tree.children[0].children))
def process_without_headers(cfr_part, parent_xml, amended_labels):
"""Sometimes, we only get a list of paragraphs that have changes, but no
header indicating with which sections they are associated. Accommodate
by trying to match up amended_labels with paragraphs"""
parent_xml = standardize_xml(parent_xml)
relevant_labels = [al.label for al in
filter(_is_interp_amend, amended_labels)]
label_indices = []
for idx, child in enumerate(parent_xml):
text = tree_utils.get_node_text(child)
if len(relevant_labels) > len(label_indices):
marker = relevant_labels[len(label_indices)][-1] + '.'
if text.startswith(marker):
label_indices.append(idx)
labelXindex = zip(relevant_labels, label_indices)
nodes = []
# Reverse it so we can delete from the bottom
for label, idx in reversed(labelXindex):
stack = tree_utils.NodeStack()
prefix = label[:label.index(Node.INTERP_MARK) + 1]
section = Node(node_type=Node.INTERP, label=prefix)
stack.add(2, section)
interpretations.process_inner_children(stack, parent_xml[idx - 1])
while stack.size() > 1:
stack.unwind()
nodes.append(stack.m_stack[0][0][1])
# delete the tail
while len(parent_xml.getchildren()) > idx:
parent_xml.remove(parent_xml[idx])
if nodes:
nodes.append(Node(node_type=Node.INTERP,
label=[cfr_part, Node.INTERP_MARK]))
# Reverse it again into normal flow
return treeify(list(reversed(nodes)))[0]
else:
return None
