def test_should_replace_affiliation_with_author_if_single_tokens(
self, test_helper: SingleFileAutoAnnotateEndToEndTestHelper):
author_text = 'Mary Maison 1, John Smith 1'
affiliation_text = '1 University of Science, Smithonia'
test_helper.tei_raw_file_path.write_bytes(
etree.tostring(
get_header_tei_node([
E.note(author_text),
E.lb(),
E.note(affiliation_text),
E.lb()
])))
test_helper.xml_file_path.write_bytes(
etree.tostring(
get_target_xml_node(author_nodes=[
E.contrib(
E.name(E.surname('Maison'), E('given-names', 'Mary'))),
E.contrib(
E.name(E.surname('Smith'), E('given-names', 'John'))),
E.aff(E.label('1'), E.institution('University of Science'),
E.country('Smithonia'))
])))
main(dict_to_args({
**test_helper.main_args_dict, 'fields':
','.join(['title', 'author', 'author_aff', 'abstract']),
'matcher':
'simple'
}),
save_main_session=False)
tei_auto_root = test_helper.get_tei_auto_root()
assert get_xpath_text(tei_auto_root,
'//byline/docAuthor') == author_text
assert get_xpath_text(tei_auto_root,
'//byline/affiliation') == affiliation_text
def test_should_auto_annotate_title(
self, test_helper: SingleFileAutoAnnotateEndToEndTestHelper):
test_helper.tei_raw_file_path.write_bytes(
etree.tostring(get_header_tei_node([E.note(TEXT_1)])))
test_helper.xml_file_path.write_bytes(
etree.tostring(get_target_xml_node(title=TEXT_1)))
main([*test_helper.main_args], save_main_session=False)
tei_auto_root = test_helper.get_tei_auto_root()
assert get_xpath_text(tei_auto_root, '//docTitle/titlePart') == TEXT_1
def test_should_auto_annotate_affiliation_preceding_number_using_simple_matcher(
self, test_helper: SingleFileAutoAnnotateEndToEndTestHelper):
author_text = 'Mary Maison 1, John Smith 1'
affiliation_text_1 = '1'
affiliation_text_2 = 'University of Science, Smithonia'
affiliation_text = ' '.join([affiliation_text_1, affiliation_text_2])
test_helper.tei_raw_file_path.write_bytes(
etree.tostring(
get_header_tei_node([
E.note(TITLE_1),
E.lb(),
E.note(author_text),
E.lb(),
E.note(affiliation_text_1),
E.lb(),
E.note(affiliation_text_2),
E.lb(),
E.note(ABSTRACT_PREFIX_1, E.lb(), ABSTRACT_1)
])))
test_helper.xml_file_path.write_bytes(
etree.tostring(
get_target_xml_node(
title=TITLE_1,
author_nodes=[
E.contrib(
E.name(E.surname('Maison'),
E('given-names', 'Mary'))),
E.contrib(
E.name(E.surname('Smith'),
E('given-names', 'John'))),
E.aff(E.institution('University of Science'),
E.country('Smithonia'))
],
abstract_node=E.abstract(E.p(ABSTRACT_1)))))
main(dict_to_args({
**test_helper.main_args_dict, 'fields':
','.join(['title', 'author', 'author_aff', 'abstract']),
'matcher':
'simple'
}),
save_main_session=False)
tei_auto_root = test_helper.get_tei_auto_root()
assert get_xpath_text(tei_auto_root, '//docTitle/titlePart') == TITLE_1
assert get_xpath_text(tei_auto_root,
'//byline/docAuthor') == author_text
assert get_xpath_text(tei_auto_root,
'//byline/affiliation') == affiliation_text
assert get_xpath_text(
tei_auto_root,
'//div[@type="abstract"]') == (ABSTRACT_PREFIX_1 + ABSTRACT_1)
def test_should_extend_title_annotation_to_whole_line(
self, test_helper: SingleFileAutoAnnotateEndToEndTestHelper):
title_text = 'Chocolate bars for mice'
test_helper.tei_raw_file_path.write_bytes(
etree.tostring(
get_header_tei_node([E.note('Title: ' + title_text)])))
test_helper.xml_file_path.write_bytes(
etree.tostring(get_target_xml_node(title=title_text)))
main([*test_helper.main_args, '--matcher=simple'],
save_main_session=False)
tei_auto_root = test_helper.get_tei_auto_root()
assert get_xpath_text(tei_auto_root,
'//docTitle/titlePart') == title_text
def test_should_skip_errors(
self, test_helper: SingleFileAutoAnnotateEndToEndTestHelper):
tei_raw_other_file_path = test_helper.tei_raw_path.joinpath(
'document0.header.tei.xml')
tei_raw_other_file_path.write_bytes(
etree.tostring(get_header_tei_node([E.note(TEXT_1)])))
xml_other_file_path = test_helper.xml_path.joinpath('document0.xml')
xml_other_file_path.write_bytes(
etree.tostring(get_target_xml_node(title=TEXT_1)) + b'error')
test_helper.tei_raw_file_path.write_bytes(
etree.tostring(get_header_tei_node([E.note(TEXT_1)])))
test_helper.xml_file_path.write_bytes(
etree.tostring(get_target_xml_node(title=TEXT_1)))
main([*test_helper.main_args, '--matcher=simple', '--skip-errors'],
save_main_session=False)
tei_auto_root = test_helper.get_tei_auto_root()
assert get_xpath_text(tei_auto_root, '//docTitle/titlePart') == TEXT_1
def test_should_filter_out_xml_if_selected_fields_are_not_matching(
self, test_helper: SingleFileAutoAnnotateEndToEndTestHelper,
actual_abstract: str, expected_abstract: str, expected_match: bool,
required_fields: str, relative_failed_output_path: str,
temp_dir: Path):
test_helper.tei_raw_file_path.write_bytes(
etree.tostring(
get_header_tei_node([
E.note(TITLE_1),
E.lb(),
E.note(ABSTRACT_PREFIX_1, E.lb(), actual_abstract)
])))
test_helper.xml_file_path.write_bytes(
etree.tostring(
get_target_xml_node(
title=TITLE_1,
abstract_node=(E.abstract(E.p(expected_abstract))
if expected_abstract else None))))
failed_output_path: str = (str(temp_dir / relative_failed_output_path)
if relative_failed_output_path else '')
main(dict_to_args({
**test_helper.main_args_dict, 'fields':
','.join(['title', 'author', 'author_aff', 'abstract']),
'require-matching-fields':
','.join(['abstract']),
'required-fields':
required_fields,
'failed-output-path':
failed_output_path,
'matcher':
'simple'
}),
save_main_session=False)
if not expected_match:
assert not test_helper.tei_auto_file_path.exists()
if failed_output_path:
assert (Path(failed_output_path) /
test_helper.tei_auto_file_path.name).exists()
else:
assert test_helper.tei_auto_file_path.exists()