def test_process_appendix_header_is_paragraph():
with XMLBuilder('APPENDIX') as ctx:
ctx.EAR("Pt. 1111, App. A")
ctx.HD("Appendix A to Part 1111-Awesome", SOURCE='HED')
ctx.HD("A-1 - First kind of awesome", SOURCE='HD2')
ctx.HD("(A) First Subkind", SOURCE='HD3')
ctx.P("1. Content")
ctx.HD("(B) Next Subkind", SOURCE='HD3')
ctx.P("1. Moar Contents")
ctx.HD("I. Remains Header", SOURCE='HD3')
ctx.P("1. Content tent")
appendix = appendices.process_appendix(ctx.xml, 1111)
appendix = NodeAccessor(appendix)
assert appendix.label == ['1111', 'A']
assert appendix.child_labels == ['1']
assert appendix['1'].child_labels == ['A', 'B']
assert appendix['1'].title == 'A-1 - First kind of awesome'
assert appendix['1']['A'].child_labels == ['1']
assert appendix['1']['A'].text == '(A) First Subkind'
assert appendix['1']['A']['1'].text == '1. Content'
assert appendix['1']['B'].child_labels == ['1']
assert appendix['1']['B'].text == '(B) Next Subkind'
assert appendix['1']['B']['1'].text == '1. Moar Contents'
assert appendix['1']['B']['1'].child_labels == ['h1']
assert appendix['1']['B']['1']['h1'].title == 'I. Remains Header'
assert appendix['1']['B']['1']['h1'].child_labels == ['1']
assert appendix['1']['B']['1']['h1']['1'].text == '1. Content tent'
def test_build_from_section_example():
"""Account for paragraphs within an EXAMPLE tag"""
with section_ctx() as ctx:
ctx.P("(a) aaaa")
with ctx.EXAMPLE():
ctx.P("You need a form if:")
ctx.P("1. Some content")
ctx.P("2. Other content")
with ctx.EXAMPLE():
ctx.P("You do not need a form if:")
ctx.P("1. Some content")
ctx.P("2. Other content")
node = section.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
assert node.child_labels == ['a']
assert node['a'].text == '(a) aaaa'
assert node['a'].child_labels == ['p1', 'p2']
assert node['a']['p1'].text == ''
assert node['a']['p1'].child_labels == ['p1', 'p2', 'p3']
assert node['a']['p1']['p1'].text == 'You need a form if:'
assert node['a']['p1']['p2'].text == '1. Some content'
assert node['a']['p1']['p3'].text == '2. Other content'
assert node['a']['p2'].text == ''
assert node['a']['p2'].child_labels == ['p1', 'p2', 'p3']
assert node['a']['p2']['p1'].text == 'You do not need a form if:'
assert node['a']['p2']['p2'].text == '1. Some content'
assert node['a']['p2']['p3'].text == '2. Other content'
def test_process_same_sub_level():
with XMLBuilder('APPENDIX') as ctx:
ctx.HD("Appendix A to Part 1111-Awesome", SOURCE='HED')
ctx.P("1. 1 1 1")
ctx.P("a. 1a 1a 1a")
ctx.P("b. 1b 1b 1b")
ctx.P("c. 1c 1c 1c")
ctx.P("d. 1d 1d 1d")
ctx.P("e. 1e 1e 1e")
ctx.P("f. 1f 1f 1f")
ctx.P("2. 2 2 2")
ctx.P("a. 2a 2a 2a")
ctx.P("i. 2ai 2ai 2ai")
ctx.P("ii. 2aii 2aii 2aii")
ctx.P("a. 2aiia 2aiia 2aiia")
ctx.P("b. 2aiib 2aiib 2aiib")
ctx.P("c. 2aiic 2aiic 2aiic")
ctx.P("d. 2aiid 2aiid 2aiid")
ctx.P("b. 2b 2b 2b")
appendix = appendices.process_appendix(ctx.xml, 1111)
appendix = NodeAccessor(appendix)
assert appendix.child_labels == ['1', '2']
assert appendix['1'].child_labels == ['a', 'b', 'c', 'd', 'e', 'f']
assert appendix['2'].child_labels == ['a', 'b']
assert appendix['2']['a'].child_labels == ['i', 'ii']
assert appendix['2']['a']['i'].children == []
assert appendix['2']['a']['ii'].child_labels == ['a', 'b', 'c', 'd']
assert appendix['2']['b'].children == []
def test_build_from_section_extract():
"""Account for paragraphs within an EXTRACT tag"""
with section_ctx() as ctx:
ctx.P("(a) aaaa")
with ctx.EXTRACT():
ctx.P("1. Some content")
ctx.P("2. Other content")
ctx.P("(3) This paragraph has parens for some reason")
node = section.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
assert node.label == ['8675', '309']
assert node.child_labels == ['a']
assert node.text == ''
assert node.node_type == 'regtext'
assert node['a'].text == '(a) aaaa'
assert node['a'].node_type == 'regtext'
assert node['a'].child_labels == ['p1']
assert node['a']['p1'].text == ''
assert node['a']['p1'].node_type == 'extract'
assert node['a']['p1'].child_labels == ['p1', 'p2', 'p3']
for child in node['a']['p1'].children:
assert child.node_type == 'regtext'
assert node['a']['p1']['p1'].text == "1. Some content"
assert node['a']['p1']['p2'].text == "2. Other content"
assert node['a']['p1']['p3'].text == (
"(3) This paragraph has parens for some reason")
def test_build_from_section_double_collapsed():
with section_ctx() as ctx:
ctx.child_from_string(
'<P>(a) <E T="03">Keyterm</E>—(1)(i) Content</P>')
ctx.P("(ii) Content2")
node = section.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
assert node.child_labels == ['a']
assert node['a'].child_labels == ['1']
assert node['a']['1'].child_labels == ['i', 'ii']
def test_build_from_section_double_collapsed(self):
with self.section() as ctx:
ctx.child_from_string(
u'<P>(a) <E T="03">Keyterm</E>—(1)(i) Content</P>')
ctx.P("(ii) Content2")
node = reg_text.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
self.assertEqual(['a'], node.child_labels)
self.assertEqual(['1'], node['a'].child_labels)
self.assertEqual(['i', 'ii'], node['a']['1'].child_labels)
def test_process_collapsed_keyterm():
with XMLBuilder('APPENDIX') as ctx:
ctx.EAR("Pt. 1111, App. A")
ctx.HD("Appendix A to Part 1111-Awesome", SOURCE="HED")
ctx.child_from_string('<P>(a) <E T="03">Keyterm</E> (1) Content</P>')
appendix = appendices.AppendixProcessor(1111).process(ctx.xml)
appendix = NodeAccessor(appendix)
assert appendix.child_labels == ['a']
assert appendix['a'].child_labels == ['1']
assert appendix['a']['1'].children == []
def _setup_for_ambiguous(self, final_par):
with self.section() as ctx:
ctx.P("(g) Some Content")
ctx.P("(h) H Starts")
ctx.P("(1) H-1")
ctx.P("(2) H-2")
ctx.P("(i) Is this 8675-309-h-2-i or 8675-309-i")
ctx.P(final_par)
node = reg_text.build_from_section('8675', ctx.xml)[0]
return NodeAccessor(node)
def test_build_from_section_bad_spaces():
with section_ctx(section=16) as ctx:
ctx.STARS()
ctx.child_from_string(
'<P>(b)<E T="03">General.</E>Content Content.</P>')
node = section.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
assert node.label == ['8675', '16']
assert node.child_labels == ['b']
assert node['b'].text == "(b) General. Content Content."
def test_build_from_section_intro_text(self):
with self.section() as ctx:
ctx.P("Some content about this section.")
ctx.P("(a) something something")
node = reg_text.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
self.assertEqual('Some content about this section.', node.text.strip())
self.assertEqual(['a'], node.child_labels)
self.assertEqual('(a) something something', node['a'].text.strip())
self.assertEqual([], node['a'].children)
def test_build_from_section_intro_text():
with section_ctx() as ctx:
ctx.P("Some content about this section.")
ctx.P("(a) something something")
node = section.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
assert node.text == 'Some content about this section.'
assert node.child_labels == ['a']
assert node['a'].text == '(a) something something'
assert node['a'].children == []
def test_build_from_section_bad_spaces(self):
with self.section(section=16) as ctx:
ctx.STARS()
ctx.child_from_string(
'<P>(b)<E T="03">General.</E>Content Content.</P>')
node = reg_text.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
self.assertEqual(['8675', '16'], node.label)
self.assertEqual(['b'], node.child_labels)
self.assertEqual(node['b'].text.strip(),
"(b) General. Content Content.")
def test_build_from_section_collapsed(self):
with self.section() as ctx:
ctx.P("(a) aaa")
ctx.P("(1) 111")
ctx.child_from_string(u'<P>(2) 222—(i) iii. (A) AAA</P>')
ctx.P("(B) BBB")
n309 = reg_text.build_from_section('8675', ctx.xml)[0]
n309 = NodeAccessor(n309)
self.assertEqual(['a'], n309.child_labels)
self.assertEqual(['1', '2'], n309['a'].child_labels)
self.assertEqual(['i'], n309['a']['2'].child_labels)
self.assertEqual(['A', 'B'], n309['a']['2']['i'].child_labels)
def test_build_from_section_collapsed():
with section_ctx() as ctx:
ctx.P("(a) aaa")
ctx.P("(1) 111")
ctx.child_from_string('<P>(2) 222—(i) iii. (A) AAA</P>')
ctx.P("(B) BBB")
n309 = section.build_from_section('8675', ctx.xml)[0]
n309 = NodeAccessor(n309)
assert n309.child_labels == ['a']
assert n309['a'].child_labels == ['1', '2']
assert n309['a']['2'].child_labels == ['i']
assert n309['a']['2']['i'].child_labels == ['A', 'B']
def test_build_from_section_collapsed_level():
with section_ctx() as ctx:
ctx.child_from_string(
'<P>(a) <E T="03">Transfers </E>—(1) <E T="03">Notice.</E> '
'follow</P>')
ctx.P("(2) More text")
ctx.child_from_string('<P>(b) <E T="03">Contents</E> (1) Here</P>')
ctx.P("(2) More text")
node = section.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
assert node.child_labels == ['a', 'b']
assert node['a'].child_labels == ['1', '2']
assert node['b'].child_labels == ['1', '2']
def test_build_from_section_collapsed_level(self):
with self.section() as ctx:
ctx.child_from_string(
u'<P>(a) <E T="03">Transfers </E>—(1) <E T="03">Notice.</E> '
u'follow</P>')
ctx.P("(2) More text")
ctx.child_from_string('<P>(b) <E T="03">Contents</E> (1) Here</P>')
ctx.P("(2) More text")
node = reg_text.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
self.assertEqual(['a', 'b'], node.child_labels)
self.assertEqual(['1', '2'], node['a'].child_labels)
self.assertEqual(['1', '2'], node['b'].child_labels)
def test_build_from_section_collapsed_level_emph():
with section_ctx() as ctx:
ctx.P("(a) aaaa")
ctx.P("(1) 1111")
ctx.P("(i) iiii")
ctx.child_from_string('<P>(A) AAA—(<E T="03">1</E>) eeee</P>')
ctx.STARS()
node = section.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
a1ia = node['a']['1']['i']['A']
assert a1ia.text == "(A) AAA—"
assert a1ia.child_labels == ['1']
assert a1ia['1'].text == "(1) eeee"
def test_build_from_section_fp():
with section_ctx() as ctx:
ctx.P("(a) aaa")
ctx.P("(b) bbb")
ctx.FP("fpfpfp")
ctx.P("(c) ccc")
node = section.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
assert node.child_labels == ['a', 'b', 'c']
assert node['a'].child_labels == []
assert node['b'].child_labels == ['p1']
assert node['b']['p1'].child_labels == []
assert node['c'].child_labels == []
def test_build_from_section_collapsed_level_emph(self):
with self.section() as ctx:
ctx.P("(a) aaaa")
ctx.P("(1) 1111")
ctx.P("(i) iiii")
ctx.child_from_string(u'<P>(A) AAA—(<E T="03">1</E>) eeee</P>')
ctx.STARS()
node = reg_text.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
a1iA = node['a']['1']['i']['A']
self.assertEqual(u"(A) AAA—", a1iA.text)
self.assertEqual(['1'], a1iA.child_labels)
self.assertEqual("(1) eeee", a1iA['1'].text.strip())
def test_build_from_section_fp(self):
with self.section() as ctx:
ctx.P("(a) aaa")
ctx.P("(b) bbb")
ctx.FP("fpfpfp")
ctx.P("(c) ccc")
node = reg_text.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
self.assertEqual(['a', 'b', 'c'], node.child_labels)
self.assertEqual([], node['a'].child_labels)
self.assertEqual(['p1'], node['b'].child_labels)
self.assertEqual([], node['b']['p1'].child_labels)
self.assertEqual([], node['c'].child_labels)
def test_build_from_section_notes():
"""Account for paragraphs within a NOTES tag"""
with section_ctx() as ctx:
ctx.P("(a) aaaa")
with ctx.NOTES():
ctx.PRTPAGE(P="8")
ctx.P("1. Some content")
ctx.P("2. Other content")
node = NodeAccessor(section.build_from_section('8675', ctx.xml)[0])
assert node.child_labels == ['a']
assert node['a'].child_labels == ['p1']
assert node['a']['p1'].node_type == Node.NOTE
assert node['a']['p1'].child_labels == ['1', '2']
def test_process_collapsed():
with XMLBuilder('APPENDIX') as ctx:
ctx.EAR("Pt. 1111, App. A")
ctx.HD("Appendix A to Part 1111-Awesome", SOURCE="HED")
ctx.HD("Part I - Something", SOURCE="HD1")
ctx.P(u"(a) Something referencing § 999.2(a)(1). (1) Content")
ctx.P("(2) Something else")
appendix = appendices.AppendixProcessor(1111).process(ctx.xml)
appendix = NodeAccessor(appendix)
assert appendix.child_labels == ['I']
assert appendix['I'].child_labels == ['a']
assert appendix['I']['a'].child_labels == ['1', '2']
assert appendix['I']['a']['1'].text == '(1) Content'
assert appendix['I']['a']['2'].text == '(2) Something else'
def test_process_header_depth():
with XMLBuilder('APPENDIX') as ctx:
ctx.EAR("Pt. 1111, App. A")
ctx.HD("Appendix A to Part 1111-Awesome", SOURCE="HED")
ctx.HD("Title 1", SOURCE="HD1")
ctx.P("(1) Content 1")
ctx.P("(2) Content 2")
ctx.HD("Title 2", SOURCE="HD1")
ctx.P("A. Content")
appendix = appendices.AppendixProcessor(1111).process(ctx.xml)
appendix = NodeAccessor(appendix)
assert appendix.child_labels == ['h1', 'h2']
assert appendix['h1'].child_labels == ['1', '2']
assert appendix['h2'].child_labels == ['A']
def test_build_from_section_image(self):
"""We should process images (GPH/GID)"""
with XMLBuilder("SECTION", "\n\n") as ctx:
ctx.SECTNO(u"§ 8675.309")
ctx.SUBJECT("subsubsub")
ctx.P("(a) aaa")
with ctx.GPH():
ctx.GID("a-gid")
ctx.P("(b) bbb")
node = NodeAccessor(reg_text.build_from_section('8675', ctx.xml)[0])
self.assertEqual(['a', 'b'], node.child_labels)
self.assertEqual(['p1'], node['a'].child_labels)
self.assertEqual('', node['a']['p1'].text)
def test_build_from_section_notes(self):
"""Account for paragraphs within a NOTES tag"""
with self.section() as ctx:
ctx.P("(a) aaaa")
with ctx.NOTES():
ctx.PRTPAGE(P="8")
ctx.P("1. Some content")
ctx.P("2. Other content")
node = NodeAccessor(reg_text.build_from_section('8675', ctx.xml)[0])
self.assertEqual(['a'], node.child_labels)
self.assertEqual(['p1'], node['a'].child_labels)
self.assertEqual(Node.NOTE, node['a']['p1'].node_type)
self.assertEqual(['1', '2'], node['a']['p1'].child_labels)
def test_build_from_section_italic_levels():
with section_ctx() as ctx:
ctx.P("(a) aaa")
ctx.P("(1) 111")
ctx.P("(i) iii")
ctx.P("(A) AAA")
ctx.child_from_string('<P>(<E T="03">1</E>) i1i1i1</P>')
ctx.child_from_string('<P>\n(<E T="03">2</E>) i2i2i2</P>')
node = section.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
assert node.child_labels == ['a']
assert node['a'].child_labels == ['1']
assert node['a']['1'].child_labels == ['i']
assert node['a']['1']['i'].child_labels == ['A']
assert node['a']['1']['i']['A'].child_labels == ['1', '2']
def test_build_from_section_italic_levels(self):
with self.section() as ctx:
ctx.P("(a) aaa")
ctx.P("(1) 111")
ctx.P("(i) iii")
ctx.P("(A) AAA")
ctx.child_from_string('<P>(<E T="03">1</E>) i1i1i1</P>')
ctx.child_from_string('<P>\n(<E T="03">2</E>) i2i2i2</P>')
node = reg_text.build_from_section('8675', ctx.xml)[0]
node = NodeAccessor(node)
self.assertEqual(['a'], node.child_labels)
self.assertEqual(['1'], node['a'].child_labels)
self.assertEqual(['i'], node['a']['1'].child_labels)
self.assertEqual(['A'], node['a']['1']['i'].child_labels)
self.assertEqual(['1', '2'], node['a']['1']['i']['A'].child_labels)
def test_process_separated_by_header():
with XMLBuilder('APPENDIX') as ctx:
ctx.EAR('Pt. 1111, App. A')
ctx.HD('Appendix A to Part 1111-Awesome', SOURCE='HED')
ctx.P('(a) aaaaaa')
ctx.P('(1) 111111')
ctx.HD('Random Header', SOURCE='HD1')
ctx.P('(2) 222222')
ctx.P('Markerless')
appendix = appendices.AppendixProcessor(1111).process(ctx.xml)
appendix = NodeAccessor(appendix)
assert appendix.child_labels == ['a']
assert appendix['a'].child_labels == ['1', '2', 'p1']
assert appendix['a']['1'].child_labels == ['h1']
assert appendix['a']['2'].children == []
assert appendix['a']['p1'].children == []
def test_process_markerless_collapsed():
"""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 = section.RegtextParagraphProcessor().process(ctx.xml, root)
root = NodeAccessor(root)
assert root.label == ['111', '22']
assert len(root.children) == 2
assert all(c.is_markerless for c in root.children)
keyterm_label = root.child_labels[1]
assert len(keyterm_label) > 5
assert root[keyterm_label].child_labels == ['a', 'b']
def test_header_ordering():
with XMLBuilder('APPENDIX') as ctx:
ctx.EAR("Pt. 1111, App. A")
ctx.HD("Appendix A to Part 1111-Awesome", SOURCE='HED')
ctx.HD("A-1 Content", SOURCE='HD1')
ctx.HD("Level 1", SOURCE='HD3')
ctx.HD("Level 2", SOURCE='HD2') # Note HD3 then HD2
ctx.P("Paragraph")
ctx.HD("A-1(A) More Content", SOURCE='HD1')
ctx.P("A1A Paragraph")
appendix = appendices.process_appendix(ctx.xml, 1111)
appendix = NodeAccessor(appendix)
assert appendix.child_labels == ['1', '1(A)']
assert appendix['1'].child_labels == ['h1']
assert appendix['1']['h1'].child_labels == ['h2']
assert appendix['1']['h1']['h2'].child_labels == ['p1']
assert appendix['1']['h1']['h2']['p1'].children == []
