def check_next_few(self,
pq_obj: PyQuery) -> Tuple[Optional[Date], re.Match]:
date = None
cursor = pq_obj.next()
for i in range(self.check_next):
m = is_date(cursor.text())
if m:
logger.info("Date found",
extra={
"pdf_page": self.current_page + 1,
"pdf_name": self.filename
})
date = Date.from_re_match(m)
break
cursor = cursor.next()
return date, m
def extract_topic(self, pq_obj: PyQuery):
cursor = pq_obj.next()
# skip till date occurs
date_found = False
for i in range(self.check_next):
if is_date(cursor.text()):
date_found = True
date_text = cursor.text()
cursor = pq_obj.next() # reset
break
cursor = cursor.next()
if not date_found:
logger.error(
"Date not found. Extract should not have been called.",
extra={
"pdf_page": self.current_page + 1,
"pdf_name": self.filename
})
# cursor is after date
topic = []
topic_ended = False
for i in range(self.max_topic_range):
if (cursor.text()) == date_text:
cursor = cursor.next()
continue
t = cursor.text()
if self.end_of_topic(t):
topic_ended = True
break
topic.append(t)
cursor = cursor.next()
if not topic_ended:
# breakpoint()
err = "Topic did not end in {} lines".format(self.current_page)
logger.error(err,
extra={
"pdf_page": self.current_page + 1,
"pdf_name": self.filename
})
logger.debug("Last line read for topic was : {}".format(t),
extra={
"pdf_page": self.current_page + 1,
"pdf_name": self.filename
})
# raise PDFQueryException(err)
topic_str = ' '.join(topic)
if not topic_str.strip():
logger.error("Registerd empty topic",
extra={
"pdf_page": self.current_page + 1,
"pdf_name": self.filename
})
return ""
else:
return topic_str
