def test_should_create_separate_author_node(self):
xml_root = extracted_items_to_xml([
ExtractedItem(Tags.AUTHOR, TEXT_1),
ExtractedItem(Tags.AUTHOR, TEXT_2)
])
assert xml_root is not None
assert get_text_content_list(xml_root.findall(
XmlPaths.AUTHOR)) == [TEXT_1, TEXT_2]
def test_should_append_to_abstract(self):
xml_root = extracted_items_to_xml([
ExtractedItem(Tags.ABSTRACT, TEXT_1),
ExtractedItem(Tags.ABSTRACT, TEXT_2)
])
assert xml_root is not None
assert get_text_content(xml_root.find(XmlPaths.ABSTRACT)) == '\n'.join(
[TEXT_1, TEXT_2])
def test_should_not_append_to_abstract_after_another_tag_occured(self):
xml_root = extracted_items_to_xml([
ExtractedItem(Tags.ABSTRACT, TEXT_1),
ExtractedItem(Tags.AUTHOR, TEXT_2),
ExtractedItem(Tags.ABSTRACT, TEXT_3)
])
assert xml_root is not None
assert get_text_content(xml_root.find(XmlPaths.ABSTRACT)) == '\n'.join(
[TEXT_1])
def _create_author_extracted_items(given_names, surname):
return [
ExtractedItem(Tags.AUTHOR,
' '.join([given_names, surname]),
sub_items=[
ExtractedItem(SubTags.AUTHOR_GIVEN_NAMES,
given_names),
ExtractedItem(SubTags.AUTHOR_SURNAME, surname)
])
]
def test_should_extract_author_surname_and_given_names_from_single_author(
self):
xml_root = extracted_items_to_xml([
ExtractedItem(Tags.AUTHOR,
' '.join([TEXT_1, TEXT_2]),
sub_items=[
ExtractedItem(SubTags.AUTHOR_GIVEN_NAMES,
TEXT_1),
ExtractedItem(SubTags.AUTHOR_SURNAME, TEXT_2)
])
])
assert xml_root is not None
author = xml_root.find(XmlPaths.AUTHOR)
assert author is not None
assert get_text_content(author.find(
SubXmlPaths.AUTHOR_GIVEN_NAMES)) == TEXT_1
assert get_text_content(author.find(
SubXmlPaths.AUTHOR_SURNAME)) == TEXT_2
def test_should_populate_title(self):
xml_root = extracted_items_to_xml([ExtractedItem(Tags.TITLE, TEXT_1)])
assert xml_root is not None
assert get_text_content(xml_root.find(XmlPaths.TITLE)) == TEXT_1