def try_parse_document(self,
ptrs: ParsingTaskParams) -> DocumentParsingResults:
"""
:return: (text, 'msword', None)
"""
try:
log_func = lambda s: ptrs.logger.info(s) if ptrs.logger else None
xtractor = XmlWordxExtractor(log_func=log_func)
if not xtractor.can_process_file(ptrs.original_file_name):
return DocumentParsingResults()
if ptrs.logger:
ptrs.logger.info('Trying MS Word extract for file: ' +
ptrs.original_file_name)
return DocumentParsingResults(
MarkedUpText(xtractor.parse_file(ptrs.file_path)), 'msword',
None, xtractor.tables)
except Exception as ex:
if ptrs.logger:
ptrs.logger.info(
'Caught exception while trying to parse file '
f'with MS Word parser: {ptrs.original_file_name}'
f'\n{format_exc()}')
if ptrs.propagate_exceptions:
raise ex
return DocumentParsingResults()
def test_tables_plain(self):
file_path = self.get_file_path('tables_only.docx')
xtractor = XmlWordxExtractor()
self.assertTrue(xtractor.can_process_file(file_path))
text = xtractor.parse_file(file_path)
self.assertGreater(len(text), 100)
regexp = re.compile(r'Row 1, column 1\s+Row 1, column 2\s+Row 1, column 3')
self.assertTrue(regexp.search(text))
self.assertTrue('r1c1: Contrary to popular belief' in text)
regexp = re.compile(r'\s+r2c3: The first line of Lorem Ipsum')
self.assertTrue(regexp.search(text))
