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_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_process_appendix_fp_dash():
with XMLBuilder("APPENDIX") as ctx:
ctx.EAR("Pt. 1111, App. A")
ctx.HD("Appendix A to Part 1111-Awesome", SOURCE="HED")
ctx.FP("FP-DASH filled out with dashes", SOURCE="FP-DASH")
appendix = appendices.process_appendix(ctx.xml, 1111)
assert len(appendix.children) == 1
fp_dash = appendix.children[0]
assert fp_dash.text.strip() == 'FP-DASH filled out with dashes_____'
def test_process_notes():
with XMLBuilder('APPENDIX') as ctx:
ctx.HD("Appendix A to Part 1111-Awesome", SOURCE='HED')
with ctx.NOTE():
ctx.P("Par")
ctx.E("Emem")
ctx.P("Parparpar")
appendix = appendices.process_appendix(ctx.xml, 1111)
assert appendix.label == ['1111', 'A']
assert len(appendix.children) == 1
note = appendix.children[0]
assert note.text == '```note\nPar\nEmem\nParparpar\n```'
def test_process_code():
with XMLBuilder('APPENDIX') as ctx:
ctx.HD("Appendix A to Part 1111-Awesome", SOURCE='HED')
with ctx.CODE(LANGUAGE='scala'):
ctx.P("// Non-tail-recursive list reverse")
ctx.FP("def rev[A](lst: List[A]):List[A] =", SOUURCE='FP-2')
ctx.FP("lst match {", SOURCE='FP-2')
ctx.FP(" case Nil => Nil", SOURCE='FP-2')
ctx.FP(" case head :: tail =>", SOURCE='FP-2')
ctx.FP(" rev(tail) ++ List(head)", SOURCE='FP-2')
ctx.FP("}", SOURCE='FP-2')
appendix = appendices.process_appendix(ctx.xml, 1111)
assert appendix.label == ['1111', 'A']
assert len(appendix.children) == 1
code = appendix.children[0]
text = "\n".join(p.text.strip() for p in ctx.xml.xpath("//P | //FP"))
assert code.text == "```scala\n" + text + "\n```"
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 == []
def test_process_appendix_header_depth():
with XMLBuilder('APPENDIX') as ctx:
ctx.EAR("Pt. 1111, App. A")
ctx.HD("Appendix A to Part 1111-Awesome", SOURCE='HED')
ctx.P("1. Some content")
ctx.HD("An Interruption", SOURCE='HD3')
ctx.P("Moo")
ctx.P("2. More content")
appendix = appendices.process_appendix(ctx.xml, 1111)
appendix = NodeAccessor(appendix)
assert appendix.label == ['1111', 'A']
assert appendix.child_labels == ['1', '2']
assert appendix['1'].child_labels == ['h1']
assert appendix['1'].text == '1. Some content'
assert appendix['2'].children == []
assert appendix['2'].text == '2. More content'
def test_process_spaces():
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>1. For<PRTPAGE P="650" />example</P>')
with ctx.P("2. And "):
ctx.E("et seq.", T="03")
with ctx.P("3. And"):
ctx.E("et seq.", T="03")
ctx.child_from_string('<P>More<PRTPAGE P="651" />content</P>')
with ctx.P("And"):
ctx.E("et seq.", T="03")
appendix = appendices.process_appendix(ctx.xml, 1111)
appendix = NodeAccessor(appendix)
assert appendix.child_labels == ['1', '2', '3', 'p1', 'p2']
for child in appendix.children:
assert child.children == []
assert appendix['1'].text == '1. For example'
assert appendix['2'].text == '2. And et seq.'
assert appendix['3'].text == '3. And et seq.'
assert appendix['p1'].text == 'More content'
assert appendix['p2'].text == 'And et seq.'
def parse_appendix(xml, cfr_part, letter):
"""Attempt to parse an appendix. Used when the entire appendix has been
replaced/added or when we can use the section headers to determine our
place. If the format isn't what we expect, display a warning."""
xml = deepcopy(xml)
hds = xml.xpath('//HD[contains(., "Appendix {0} to Part {1}")]'.format(
letter, cfr_part))
if len(hds) == 0:
logger.warning("Could not find Appendix %s to part %s",
letter, cfr_part)
elif len(hds) > 1:
logger.warning("Too many headers for %s to part %s",
letter, cfr_part)
else:
hd = hds[0]
hd.set('SOURCE', 'HED')
extract = hd.getnext()
if extract is not None and extract.tag == 'EXTRACT':
extract.insert(0, hd)
for trailing in dropwhile(lambda n: n.tag != 'AMDPAR',
extract.getchildren()):
extract.remove(trailing)
return process_appendix(extract, cfr_part)
logger.warning("Bad format for whole appendix")
def test_process_appendix():
"""Integration test for appendices"""
with XMLBuilder("APPENDIX") as ctx:
ctx.EAR("Pt. 1111, App. A")
ctx.HD("Appendix A to Part 1111-Awesome", SOURCE="HED")
ctx.P("Intro text")
ctx.HD("Header 1", SOURCE="HD1")
ctx.P("Content H1-1")
ctx.P("Content H1-2")
ctx.HD("Subheader", SOURCE="HD2")
ctx.P("Subheader content")
with ctx.HD("Header ", SOURCE="HD1"):
ctx.E("2", T="03")
ctx.P("www.example.com")
with ctx.P("Final "):
ctx.E("Content", T="03")
with ctx.GPH():
ctx.PRTPAGE(P="650")
ctx.GID("MYGID")
with ctx.GPOTABLE(CDEF="s50,15,15", COLS="3", OPTS="L2"):
with ctx.BOXHD():
with ctx.CHED("For some reason", H="1"):
ctx.LI("lis")
ctx.CHED("column two", H="2")
ctx.CHED("a third column", H="2")
with ctx.ROW():
ctx.ENT("0", I="01")
ctx.ENT()
ctx.ENT("Content3")
with ctx.ROW():
ctx.ENT("Cell 1")
ctx.ENT("Cell 2")
ctx.ENT("Cell 3")
ctx.FP("A-3 Some header here", SOURCE="FR-1")
ctx.P("Content A-3")
ctx.P("A-4 Another header")
ctx.P("Content A-4")
appendix = appendices.process_appendix(ctx.xml, 1111)
appendix = NodeAccessor(appendix)
assert appendix.child_labels == ['p1', 'h1', 'h3', '3', '4']
assert appendix['p1'].children == []
assert appendix['p1'].text == "Intro text"
assert appendix['h1'].child_labels == ['p2', 'p3', 'h2']
assert appendix['h1'].title == 'Header 1'
assert appendix['h1']['p2'].children == []
assert appendix['h1']['p2'].text == 'Content H1-1'
assert appendix['h1']['p3'].children == []
assert appendix['h1']['p3'].text == 'Content H1-2'
assert appendix['h1']['h2'].child_labels == ['p4']
assert appendix['h1']['h2'].title == 'Subheader'
assert appendix['h1']['h2']['p4'].text == 'Subheader content'
assert appendix['h3'].child_labels == ['p5', 'p6', 'p7', 'p8']
assert appendix['h3'].title == 'Header 2'
assert appendix['h3']['p5'].text == 'www.example.com'
assert appendix['h3']['p6'].text == 'Final Content'
assert appendix['h3']['p7'].text == ''
table_lines = appendix['h3']['p8'].text.split('\n')
assert table_lines[0] == '|For some reason lis|column two|a third column|'
assert table_lines[1] == '|---|---|---|'
assert table_lines[2] == '|0||Content3|'
assert table_lines[3] == '|Cell 1|Cell 2|Cell 3|'
assert appendix['3'].title == 'A-3 Some header here'
assert appendix['4'].title == 'A-4 Another header'
