def test_table_data_store():
# Testing with 'include_node_content' set to True. Should result in 3 columns
pipeline = Pipeline(
Document.from_kdxa(
os.path.join(get_test_directory(), 'tongue_twister.kdxa')))
pipeline.add_step(
NodeTagger(selector='//*[contentRegex(".*flue.*")]',
tag_to_apply='has_flue',
node_only=True,
node_tag_uuid='test'))
pipeline.add_step(
TagsToKeyValuePairExtractor(store_name='tagged_data',
include_node_content=True))
context = pipeline.run()
compare_store(context, 'tagged_data', 'basic_store_tagged_data1.json')
# Testing with 'include_node_content' set to False. Should result in 2 columns
pipeline2 = Pipeline(
Document.from_kdxa(
os.path.join(get_test_directory(), 'tongue_twister.kdxa')))
pipeline2.add_step(
NodeTagger(selector='//*[contentRegex(".*flue.*")]',
tag_to_apply='has_flue',
node_only=True))
pipeline2.add_step(
TagsToKeyValuePairExtractor(store_name='tagged_data_2',
include_node_content=False))
context2 = pipeline2.run()
compare_store(context2, 'tagged_data_2', 'basic_store_tagged_data2.json')
def get_test_document():
document = Document(DocumentMetadata())
node = document.create_node(node_type='foo')
node.content = "cheese"
document.content_node = node
document.content_node.add_child(
document.create_node(node_type='bar', content='fishstick'))
return document
def test_tagged_content():
document = Document.from_msgpack(open(os.path.join(get_test_directory(), 'news-tagged.kdxa'), 'rb').read())
all_nodes = document.content_node.select('//*[hasTag($entityName)]', {"entityName": "ORG"})
assert len(all_nodes) == 9
all_nodes = document.content_node.select('//p stream *[hasTag("ORG")] stream *[hasTag("ORG")]')
assert len(all_nodes) == 7
all_nodes = document.content_node.select('//p intersect //*[hasTag("ORG")]')
assert len(all_nodes) == 7
# Has any tag to start
tagged_nodes = document.content_node.select('//*[hasTag()]')
assert len(tagged_nodes) == 22
feature_nodes = document.content_node.select('//*[hasFeature()]')
assert len(feature_nodes) == 32
all_nodes = document.content_node.select('//*[hasTag("ORG")]')
assert len(all_nodes) == 9
union_nodes = document.content_node.select('//*[hasTag("ORG")] | //*[hasTag("ORG")]')
assert len(union_nodes) == 18
node_match = all_nodes[0].select('*[tagRegex("O.*")]')
assert len(node_match) == 1
node_match2 = all_nodes[0].select('*[tagRegex("CHE.*")]')
assert len(node_match2) == 0
def test_uuid_select():
document = Document.from_msgpack(open(os.path.join(get_test_directory(), 'news-tagged.kdxa'), 'rb').read())
node_uuid = document.select_first('//p').uuid
print(document.select_first('//p').uuid)
print(document.select_first('//p').content)
assert document.select_first(f'//p[uuid({node_uuid})]').content == document.select_first('//p').content
def test_tag_regex():
document = Document.from_text("Hello World")
results = document.content_node.select('*[typeRegex("te.*")]')
assert len(results) == 1
assert results[0].content == "Hello World"
results2 = document.content_node.select('*[typeRegex("chee.*")]')
assert len(results2) == 0
def test_selector_regex():
document = Document.from_text("Hello World")
results = document.select('hasTag() = false()')
assert len(results) == 1
results = document.select('hasTag()')
assert len(results) == 0
results = document.content_node.select('.')
assert len(results) == 1
assert results[0].content == "Hello World"
results = document.content_node.select('*[contentRegex("Hello.*")]')
assert len(results) == 1
assert results[0].content == "Hello World"
results2 = document.content_node.select('*[contentRegex("Cheese.*")]')
assert len(results2) == 0
results = document.content_node.select('*[content()="Hello World"]')
assert len(results) == 1
assert results[0].content == "Hello World"
results2 = document.content_node.select('*[contentRegex("Cheese.*",true)]')
assert len(results2) == 0
def test_html_rollup():
document = Document.from_msgpack(
open(os.path.join(get_test_directory(), 'news.kdxa'), 'rb').read())
# before rollup
assert document.select('//a')[0].content == 'HSBC'
assert document.select('//a')[1].content == 'Hang Seng Index'
assert len(
document.select('//*[contentRegex(".*Hang Seng Index.*")]')
[0].get_content_parts()) == 1
# Collapse out all the <a> tags
step = RollupTransformer(collapse_type_res=["a"])
step.process(document)
# after rollup
assert len(document.select('//a')) == 0
# see where the href rolled up
assert document.select(
'//*[contentRegex(".*Hang Seng Index.*")]'
)[0].get_all_content(
) == 'The London-headquartered bank is a heavyweight component of the Hang Seng Index . HSBC shares in Hong Kong closed 2.78% lower.'
assert len(
document.select('//*[contentRegex(".*Hang Seng Index.*")]')
[0].get_content_parts()) == 3
def test_node_only_tagging():
doc = Document.from_text("Hello World")
doc.content_node.tag(node_only=True, content_re="Hello World", tag_to_apply="test")
assert len(doc.content_node.get_tag_values("test")) == 1
doc.content_node.tag(node_only=True, content_re="Hello Cheese", tag_to_apply="test2")
assert len(doc.content_node.get_tag_values("test2")) == 0
def test_basic_local_document_store():
lds = LocalDocumentStore(store_path='/tmp/s1', force_initialize=True)
lds.put('my-doc', Document.from_text('hello!'))
assert len(lds.list_objects()) == 1
lds2 = LocalDocumentStore(store_path='/tmp/s1')
assert len(lds2.list_objects()) == 1
def test_html_rollup():
document = Document.from_msgpack(
open(os.path.join(get_test_directory(), 'news.mdoc'), 'rb').read())
# Collapse out all the <a> tags
step = Rollup(collapse_type_res=["a"])
result = step.process(document)
print(DocumentRender(result).to_text())
def test_tag_key_value_include_exclude():
# Testing include parameter
include_tags = ['DATE', 'LOC']
document = Document.from_msgpack(
open(os.path.join(get_test_directory(), 'news-tagged.kdxa'),
'rb').read())
step = TagsToKeyValuePairExtractor(store_name='test_store',
include=include_tags)
context = PipelineContext()
step.process(document, context)
assert context.get_store('test_store').count() == 11
# Testing exclude parameter
exclude_tags = ['DATE', 'LOC']
document = Document.from_msgpack(
open(os.path.join(get_test_directory(), 'news-tagged.kdxa'),
'rb').read())
step = TagsToKeyValuePairExtractor(store_name='test_store',
exclude=exclude_tags)
context = PipelineContext()
step.process(document, context)
assert context.get_store('test_store').count() == 34
# Testing both include and exclude parameters
include_tags = ['LOC']
exclude_tags = ['DATE']
document = Document.from_msgpack(
open(os.path.join(get_test_directory(), 'news-tagged.kdxa'),
'rb').read())
step = TagsToKeyValuePairExtractor(store_name='test_store',
include=include_tags,
exclude=exclude_tags)
context = PipelineContext()
step.process(document, context)
assert context.get_store('test_store').count() == 5
# Testing both include - this should be the same as before as 'exclude' shouldn't have really done anything
include_tags = ['LOC']
document = Document.from_msgpack(
open(os.path.join(get_test_directory(), 'news-tagged.kdxa'),
'rb').read())
step = TagsToKeyValuePairExtractor(store_name='test_store',
include=include_tags)
context = PipelineContext()
step.process(document, context)
assert context.get_store('test_store').count() == 5
def test_tag_multiple_regex_matches():
doc_string = "Mary had a little lamb, little lamb, little lamb. Mary had a little lamb whose fleece was white as snow."
document = Document.from_text(doc_string)
pipeline = Pipeline(document)
pipeline.add_step(NodeTagger(selector='//*', tag_to_apply='SIZE', content_re=r'(little)', node_only=False))
context = pipeline.run()
tags = context.output_document.get_root().get_all_tags()
assert len(tags) == 1
# we expect 4 tags to be applied, one for each instance of the word 'little'
feature_values = context.output_document.get_root().get_feature_values('tag', 'SIZE')
assert type(feature_values) == list and len(feature_values) == 4
assert feature_values[2]['start'] == 37
assert feature_values[2]['end'] == 43
# Because we didn't pass in a tag_uuid to the NodeTagger, each of the feature values should have a different UUID
features_uuids = list(set(dic['uuid'] for dic in feature_values))
assert len(features_uuids) == 4
# Run the multiple tag test again, but this time pass in a tag_uuid
document = Document.from_text(doc_string)
pipeline = Pipeline(document)
pipeline.add_step(NodeTagger(selector='//*', tag_to_apply='SIZE', content_re=r'(little)', node_only=False,
node_tag_uuid=str(uuid.uuid4())))
context = pipeline.run()
# Now each of the feature values should have the same UUID
feature_values = context.output_document.get_root().get_feature_values('tag', 'SIZE')
features_uuids = list(set(dic['uuid'] for dic in feature_values))
assert len(features_uuids) == 1
# Now test that tagging the entire node, rather than references within the node, only produce 1 feature
document = Document.from_text(doc_string)
pipeline = Pipeline(document)
pipeline.add_step(NodeTagger(selector='//*', tag_to_apply='SIZE_2', content_re=r'.*(little).*', node_only=True))
context = pipeline.run()
tags = context.output_document.get_root().get_all_tags()
assert len(tags) == 1
# we expect one tag to be applied and there to be no start or end value
feature_values = context.output_document.get_root().get_feature_value('tag', 'SIZE_2')
assert feature_values['start'] is None and feature_values['end'] is None
def test_parent_axis():
document = Document.from_msgpack(open(os.path.join(get_test_directory(), 'news-tagged.kdxa'), 'rb').read())
first_paragraph = document.select('(//p)[0]')
assert len(first_paragraph) == 1
assert len(first_paragraph[0].select('parent::div')) == 1
assert first_paragraph[0].select('parent::div')[0].node_type == 'div'
link = document.select('//a')[0]
assert link.select('parent::div')[0].node_type == 'div'
def test_instance_indexes():
document = Document.from_msgpack(open(os.path.join(get_test_directory(), 'news-tagged.kdxa'), 'rb').read())
first_paragraph = document.select('(//p)[0]')
assert len(first_paragraph) == 1
# Note this is important - the index here is not the position in the results
# but the index of the node itself
first_paragraph = document.select('//p[0]')
assert len(first_paragraph) == 18
def test_fixed_tagging_remove():
doc = Document.from_text("Hello Philip")
doc.content_node.tag('name', fixed_position=[6, 12])
assert doc.content_node.get_tag_values('name')[0] == 'Philip'
doc.content_node.remove_tag('name')
assert len(doc.content_node.get_tag_values('name')) == 0
def test_tag_key_value():
document = Document.from_msgpack(
open(os.path.join(get_test_directory(), 'news-tagged.mdoc'),
'rb').read())
# Collapse out all the <a> tags
step = ExtractTagsToKeyValuePair(store_name='test_store')
context = PipelineContext()
result = step.process(document, context)
print(context.get_store('test_store').rows)
def simplify_document(document: Document) -> dict:
"""
Args:
document: Document:
Returns:
"""
return {"content_node": simplify_node(document.get_root())}
def test_tag_key_value():
document = Document.from_msgpack(
open(os.path.join(get_test_directory(), 'news-tagged.kdxa'),
'rb').read())
step = TagsToKeyValuePairExtractor(store_name='test_store')
context = PipelineContext()
step.process(document, context)
assert context.get_store('test_store').count() == 45
assert context.get_store('test_store').rows[14][0] == 'LOC'
assert context.get_store('test_store').rows[14][1] == 'Europe'
def test_selector_complex_doc_1():
document = Document.from_msgpack(open(os.path.join(get_test_directory(), 'news.kdxa'), 'rb').read())
all_nodes = document.content_node.select('//*')
assert len(all_nodes) == 39
all_ps = document.content_node.select('//p')
assert len(all_ps) == 18
for pos in range(18):
selected_p = document.content_node.select(f'(//p)[{pos}]')
assert len(selected_p) == 1
assert selected_p[0].uuid == all_ps[pos].uuid
def get_output_document(self, execution):
final_reference = None
for document_reference in execution.documentReferences:
if document_reference.referenceType == 'OUTPUT':
final_reference = document_reference
if final_reference:
doc = requests.get(
f"{self.cloud_url}/api/sessions/{self.cloud_session.id}/executions/{execution.id}/documents/{final_reference.cloudDocument.id}",
headers={"x-access-token": self.access_token})
return Document.from_msgpack(doc.content)
else:
return None
def test_tagging_issue_with_html():
kdxa_doc = Document.from_kdxa(get_test_directory() + 'tagging_issue.kdxa')
all_content = kdxa_doc.content_node.get_all_content(strip=False)
assert "IIJ" == all_content[707:710]
# Now we tag the same location and try and get the content from the tag
kdxa_doc.content_node.tag("test_tag", use_all_content=True, node_only=False, fixed_position=(707, 710))
node = kdxa_doc.select('//*[hasTag("test_tag")]')[0]
feature = node.get_feature_value("tag", "test_tag")
assert feature['value'] == 'IIJ'
assert "IIJ" == kdxa_doc.select("//*[hasTag('test_tag')]")[0].get_all_content(strip=False)[
feature['start']:feature['end']]
def test_spatial_doc_sample_two():
# This test document and this portion of code is a snippet
# from a test in the spatial actions tests. Adding this saved doc
# and this section to ensure NodeTagger is tested.
page_footer_re = r'Page \d+ of \d+$'
document = Document.from_kdxa(get_test_directory() + 'before_fail.kdxa')
pipeline = Pipeline(document)
pipeline.add_step(
NodeTagger(selector='//*[typeRegex("line.*")]', content_re=page_footer_re, tag_to_apply='page_footer'))
pipeline.run()
doc = pipeline.context.output_document
assert doc.get_root() is not None
def test_fixed_tagging_with_child():
doc = Document.from_text("Hello")
doc.content_node.add_child_content("text", "Philip")
doc.content_node.add_child_content("text", "Dodds")
# Hello Philip Dodds
# 012345678901234567
assert doc.content_node.get_all_content(strip=False)[6:12] == 'Philip'
assert doc.content_node.get_all_content(strip=False)[13:18] == 'Dodds'
doc.content_node.tag('name', fixed_position=[6, 12], separator=" ")
assert doc.content_node.get_tag_values('name', include_children=True)[0] == 'Philip'
doc.content_node.tag('lastName', fixed_position=[13, 18], separator=" ")
assert doc.content_node.get_tag_values('lastName', include_children=True)[0] == 'Dodds'
def test_selector_operators():
document = Document.from_text("Hello World")
# combining multiple functions
# Feeling crazy?
assert len(document.content_node.select('//*[typeRegex("te.*") and contentRegex("H.*D")]')) == 0
# no dice - handle your capitalization correctly! :-)
assert len(document.content_node.select('//*[typeRegex("te.*") or contentRegex("H.*D")]')) == 1
# This should obviously return zero nodes, as 'Howdy' isn't in the document
assert len(document.content_node.select('//*[typeRegex("te.*") and contentRegex("Howdy")]')) == 0
# What about this? There's an H and a W...
assert len(document.content_node.select('//*[typeRegex("te.*") and contentRegex("H*W")]')) == 0
# Try that again, but modify the contentRegex
assert len(document.content_node.select('//*[typeRegex("te.*") and contentRegex("H.*W")]')) == 1
# yea!
# Another variation - we expect success
assert len(document.content_node.select('//*[typeRegex("te.*") and contentRegex("H.*d")]')) == 1
def test_fax2tagging():
kdxa_doc = Document.from_kdxa(get_test_directory() + 'fax2.kdxa')
kdxa_doc.content_node.tag("phone", use_all_content=True, fixed_position=[146, 158])
assert kdxa_doc.select("//*[hasTag('phone')]")[0].content == '785-368-1772'
assert kdxa_doc.select("//*[hasTag('phone')]")[0].get_feature_value("tag", "phone")['value'] == '785-368-1772'
def test_tag_copy():
doc_string = "Mary had a little lamb, little lamb, little lamb. Mary had a little lamb whose fleece was white as snow."
# data setup - creating a single tag with multiple matches...and then copying it
document = Document.from_text(doc_string)
pipeline = Pipeline(document)
pipeline.add_step(NodeTagger(selector='//*', tag_to_apply='SIZE', content_re=r'(little)', node_only=False))
context = pipeline.run()
# both existing and new tag names must be provided, and they must be different, test for that first.
for n in document.select('//*[hasTag("SIZE")]'):
n.copy_tag(existing_tag_name=None, new_tag_name='NewTagNone')
for n in document.select('//*[hasTag("SIZE")]'):
n.copy_tag(existing_tag_name='SIZE', new_tag_name=None)
for n in document.select('//*[hasTag("SIZE")]'):
n.copy_tag(existing_tag_name='SIZE', new_tag_name='SIZE')
# verify that the only tag that exists is tag 'SIZE' and that there are only 4 feature values for it
assert len(document.get_root().get_all_tags()) == 1
assert 'SIZE' in document.get_root().get_all_tags()
# now, let's copy the SIZE tags and create new ones called LAMB_INFO
# reusing the previously tagged document and testing out NodeTagCopy action
pipeline = Pipeline(document)
pipeline.add_step(NodeTagCopy(selector='//*[hasTag("SIZE")]', existing_tag_name='SIZE', new_tag_name='LAMB_INFO'))
context = pipeline.run()
# we should now have 4 feature values for 'LAMB_INFO' and 4 feature values for 'SIZE' - all with different UUIDs
size_feature_values = context.output_document.get_root().get_feature_values('tag', 'SIZE')
assert type(size_feature_values) == list and len(size_feature_values) == 4
lamb_info_feature_values = context.output_document.get_root().get_feature_values('tag', 'LAMB_INFO')
assert type(lamb_info_feature_values) == list and len(lamb_info_feature_values) == 4
lamb_info_features_uuids = set(dic['uuid'] for dic in lamb_info_feature_values)
assert len(list(lamb_info_features_uuids)) == 4
# Now test that tagging the entire node, rather than references within the node, only produce 1 feature
document = Document.from_text(doc_string) # starting with a clean document
pipeline = Pipeline(document)
pipeline.add_step(NodeTagger(selector='//*', tag_to_apply='SIZE_2', content_re=r'.*(little).*', node_only=True))
context = pipeline.run()
# now, let's copy the SIZE_2 tags and create new ones called LAMB_INFO (using node's tag_copy)
for n in document.select('//*[hasTag("SIZE_2")]'):
n.copy_tag(existing_tag_name='SIZE_2', new_tag_name='LAMB_INFO_2')
# we should now have 1 feature values for 'LAMB_INFO_2' and 1 feature values for 'SIZE_2'
size_2_feature_values = context.output_document.get_root().get_feature_value('tag', 'SIZE_2')
assert type(size_2_feature_values) != list
lamb_info_2_feature_values = context.output_document.get_root().get_feature_value('tag', 'LAMB_INFO_2')
assert type(lamb_info_2_feature_values) != list
# now we need to test that when features are related (indicated by the same tag_uuid), they remain related when copying
document = Document.from_text(doc_string) # starting with a clean document
pipeline = Pipeline(document)
pipeline.add_step(
NodeTagger(selector='//*', tag_to_apply='FLEECE_INFO', content_re=r'((white|snow))', node_only=False,
node_tag_uuid=str(uuid.uuid4())))
context = pipeline.run()
# now, let's copy the SIZE tags and create new ones called LAMB_INFO
pipeline = Pipeline(document) # reusing the previously tagged document & testing out the NodeTagCopy action
pipeline.add_step(
NodeTagCopy(selector='//*[hasTag("FLEECE_INFO")]', existing_tag_name='FLEECE_INFO', new_tag_name='WOOL_INFO'))
context = pipeline.run()
# The feature values should have the same UUID - for both WOOL_INFO and FLEECE_INFO
wool_values = context.output_document.get_root().get_feature_values('tag', 'WOOL_INFO')
assert type(wool_values) == list and len(wool_values) == 2
wool_uuids = set(dic['uuid'] for dic in wool_values)
assert len(list(wool_uuids)) == 1
fleece_info_values = context.output_document.get_root().get_feature_values('tag', 'FLEECE_INFO')
assert type(fleece_info_values) == list and len(fleece_info_values) == 2
def test_rollup_of_pdf():
# first test - collapsing words and lines up to their common parent
test_doc = Document.from_kdxa(get_test_directory() + '20200709.kdxa')
# how many pre-rollup lines?
assert len(test_doc.select('//line')) == 3824
# how many pre-rollup words?
assert len(test_doc.select('//word')) == 52903
# how many pre-rollup content-areas?
assert len(test_doc.select('//content-area')) == 817
# what is the pre-rollup length of ALL the content in the document?
assert len(test_doc.get_root().get_all_content()) == 329792
rollup_pipeline = Pipeline(test_doc)
rollup_pipeline.add_step(
RollupTransformer(collapse_type_res=["word", "line"],
separator_character=' '))
rollup_pipeline.run()
collapsed_doc = rollup_pipeline.context.output_document
# how many post-rollup lines?
assert len(test_doc.select('//line')) == 0
# how many post-rollup words?
assert len(test_doc.select('//word')) == 0
# how many post-rollup content-areas?
assert len(test_doc.select('//content-area')) == 817
# what is the post-rollup length of ALL the content in the document?
assert len(test_doc.get_root().get_all_content()) == 329792
assert len(
collapsed_doc.select("//content-area")[12].get_all_content()) == 235
# second test - just collapse the line up to its parent (content-area) - roll up the line's children
test_doc = Document.from_kdxa(get_test_directory() + '20200709.kdxa')
rollup_pipeline = Pipeline(test_doc)
rollup_pipeline.add_step(
RollupTransformer(collapse_type_res=["line"],
separator_character=' ',
get_all_content=True))
rollup_pipeline.run()
collapsed_doc = rollup_pipeline.context.output_document
# how many post-rollup lines?
assert len(test_doc.select('//line')) == 0
# how many post-rollup words?
assert len(test_doc.select('//word')) == 0
# how many post-rollup content-areas?
assert len(test_doc.select('//content-area')) == 817
# what is the post-rollup length of ALL the content in the document?
assert len(test_doc.get_root().get_all_content()) == 329792
# verify that we can collapse line nodes AND include their children
assert len(
collapsed_doc.select("//content-area")[12].get_all_content()) == 235
# third test - select specific nodes in which we'll do the roll ups
test_doc = Document.from_kdxa(get_test_directory() + '20200709.kdxa')
node_selector = "//content-area[contentRegex('.*LOAN AGREEMENT.*', true)]"
# verify we have 3 nodes match this selector
node_matches = test_doc.select(node_selector)
assert len(node_matches) == 3
# before we rollup, let's make sure the matching nodes conform to known expectations
assert len(node_matches[0].select('//word')) == 2
assert len(node_matches[0].select('//line')) == 1
assert len(node_matches[0].select('//content-area')) == 1
assert len(node_matches[0].get_all_content()) == 14
assert len(node_matches[1].select('//word')) == 2
assert len(node_matches[1].select('//line')) == 1
assert len(node_matches[1].select('//content-area')) == 1
assert len(node_matches[1].get_all_content()) == 14
assert len(node_matches[2].select('//word')) == 71
assert len(node_matches[2].select('//line')) == 6
assert len(node_matches[2].select('//content-area')) == 1
assert len(node_matches[2].get_all_content()) == 500
rollup_pipeline = Pipeline(test_doc)
rollup_pipeline.add_step(
RollupTransformer(
selector="//content-area[contentRegex('.*LOAN AGREEMENT.*', true)]",
collapse_type_res=["line"],
separator_character=' ',
get_all_content=True))
rollup_pipeline.run()
collapsed_doc = rollup_pipeline.context.output_document
# check those matching nodes - we shouldn't have any words or lines, but
# all other node_types should exist and the content should stay the same.
assert len(node_matches[0].select('//word')) == 0
assert len(node_matches[0].select('//line')) == 0
assert len(node_matches[0].select('//content-area')) == 1
assert len(node_matches[0].get_all_content()) == 14
assert len(node_matches[1].select('//word')) == 0
assert len(node_matches[1].select('//line')) == 0
assert len(node_matches[1].select('//content-area')) == 1
assert len(node_matches[1].get_all_content()) == 14
assert len(node_matches[2].select('//word')) == 0
assert len(node_matches[2].select('//line')) == 0
assert len(node_matches[2].select('//content-area')) == 1
assert len(node_matches[2].get_all_content()) == 500
# how many post-rollup lines? (still have some lines, but fewer than we started with)
assert len(test_doc.select('//line')) == 3816
# how many post-rollup words? (still have some words, but fewer than we started with)
assert len(test_doc.select('//word')) == 52828
# how many post-rollup content-areas? (same number of content-areas)
assert len(test_doc.select('//content-area')) == 817
# what is the post-rollup length of ALL the content in the document?
assert len(test_doc.get_root().get_all_content()) == 329792
# verify that we can collapse line nodes AND include their children
assert len(
collapsed_doc.select("//content-area")[12].get_all_content()) == 235
def test_parent_child():
document = Document.from_kdxa(get_test_directory() + 'before_fail.kdxa')
page = document.select('//page')[0]
assert page.select('//line')[0].select_first('parent::page').uuid == page.uuid
def test_selector_deep():
document = Document.from_kdxa(get_test_directory() + 'before_fail.kdxa')
assert len(document.select('//page')[0].select('//line')) == 63
assert len(document.select('//line')) == 3143
def test_selector_2():
document = Document.from_text("Hello World")
results = document.content_node.select('*')
assert len(results) == 1
assert results[0].content == "Hello World"