def assert_func(rfile, headers):
log.info('Text extraction results are ready...')
rs: RequestStatus = RequestStatus.from_json(rfile)
assert rs.status == 'DONE'
assert os.path.basename(fn) == rs.original_file_name
assert rs.converted_cleaned_pdf
assert rs.tables_extracted is False
assert rs.plain_text_extracted
assert rs.text_structure_extracted
assert rs.additional_info == 'hello world'
text = client.get_plain_text(rs.request_id)
for i in range(1, 22):
assert f'This is page {i}' in text
with client.get_pdf_as_local_file(rs.request_id) as tfn:
with pikepdf.open(tfn) as pdf:
assert len(pdf.pages) == 22
text_struct: PlainTextStructure = client.get_extracted_text_structure_as_msgpack(
rs.request_id)
assert text_struct.language == 'en'
assert len(text_struct.pages) == 22
assert len(text_struct.paragraphs) == 1
assert len(text_struct.sentences) > 2
log.info('Text extraction results look good. All assertions passed.')
def assert_func(rfile, headers):
log.info('Text extraction results are ready...')
rs: RequestStatus = RequestStatus.from_json(rfile)
assert rs.status == 'DONE'
assert os.path.basename(fn) == rs.original_file_name
assert rs.pdf_pages_ocred
assert rs.searchable_pdf_created
log.info('Text extraction results look good. All assertions passed.')
def assert_func(rfile, headers):
log.info('Text extraction results are ready...')
rs: RequestStatus = RequestStatus.from_json(rfile)
assert rs.status == 'DONE'
assert os.path.basename(fn) == rs.original_file_name
assert rs.converted_cleaned_pdf is False
assert rs.searchable_pdf_created
assert not rs.tables_extracted
assert rs.plain_text_extracted
assert rs.text_structure_extracted
log.info('Text extraction results look good. All assertions passed.')
def assert_func(rfile, headers):
log.info('Text extraction results are ready...')
rs: RequestStatus = RequestStatus.from_json(rfile)
assert rs.status == 'DONE'
assert os.path.basename(fn) == rs.original_file_name
assert rs.converted_cleaned_pdf is False
assert rs.searchable_pdf_created
assert rs.tables_extracted
assert rs.plain_text_extracted
assert rs.text_structure_extracted
table_list_json: TableList = client.get_extracted_tables_as_msgpack(
rs.request_id)
assert len(table_list_json.tables) == 6
log.info('Text extraction results look good. All assertions passed.')
def assert_func(rfile, headers):
log.info('Text extraction results are ready...')
rs: RequestStatus = RequestStatus.from_json(rfile)
assert rs.status == 'DONE'
assert os.path.basename(fn) == rs.original_file_name
assert rs.converted_cleaned_pdf
assert rs.plain_text_extracted
assert rs.text_structure_extracted
assert rs.additional_info == 'hello world'
text = client.get_plain_text(rs.request_id)
text_struct: PlainTextStructure = client.get_extracted_text_structure_as_msgpack(
rs.request_id)
assert len(text_struct.pages) == 4
assert 'REPRODUCTION, AND DISTRIBUTION' in text # page 1
assert 'subsequently incorporated' in text # page 2
assert 'conditions stated in this License. ' in text # page 3
assert 'See the License for the specific language governing' in text # page 4
log.info('Text extraction results look good. All assertions passed.')
def assert_func(rfile, headers):
log.info('Text extraction results are ready...')
rs: RequestStatus = RequestStatus.from_json(rfile)
assert rs.status == 'DONE'
assert os.path.basename(fn) == rs.original_file_name
assert rs.converted_cleaned_pdf is False
assert rs.tables_extracted is False
assert rs.plain_text_extracted
assert rs.text_structure_extracted
text = client.get_plain_text(rs.request_id)
with client.get_pdf_as_local_file(rs.request_id) as tfn:
with pikepdf.open(tfn) as pdf:
assert len(pdf.pages) == 1
text_struct: PlainTextStructure = client.get_extracted_text_structure_as_msgpack(
rs.request_id)
assert text_struct.language in ('en', 'ru')
if text_struct.language == 'en':
assert 'This is top secret' in text
assert 'Top.' in text
assert 'являлся Тор.' not in text
elif text_struct.language == 'ru':
assert 'This is top secret' not in text
assert 'Top.' not in text
assert 'являлся Тор.' in text
assert len(text_struct.pages) == 1
assert len(text_struct.paragraphs) == 1
for i in text_struct.paragraphs:
assert i.language == text_struct.language
assert len(text_struct.sentences) == 3
for i in text_struct.sentences:
assert i.language == text_struct.language
log.info('Text extraction results look good. All assertions passed.')
def assert_func(rfile, headers):
log.info('Text extraction results are ready...')
rs: RequestStatus = RequestStatus.from_json(rfile)
assert rs.status == 'FAILURE'
log.info('Text extraction results look good. All assertions passed.')
def get_data_extraction_task_status(self, request_id: str) -> RequestStatus:
url = f'{self.base_url}/api/v1/data_extraction_tasks/{request_id}/status.json'
resp = requests.get(url)
self.raise_for_status(resp)
return RequestStatus.from_json(resp.content)