def __iter__(self):
for filename in self.file_list[0:1]:
sent_file = os.path.join(self.annotation_dir, filename)
with open(sent_file) as file:
lc = LoopTimer(update_after=100)
lastid = None
for line in file:
if self.print_status:
lc.update("Word Sent Stream")
data = json.loads(line)
xml = data['annotation']
id = data['id']
if lastid != id:
para_num = 0
else:
para_num += 1
lastid = id
token_list = mf.xml2words(xml)
pos_list = mf.xml2pos(xml)
for i in range(0, len(token_list)):
token_cleaned, pos_cleaned = utils.posFilterString(token_list[i], pos_list[i])
if len(token_cleaned) > 0:
yield id, para_num, token_cleaned
def __iter__(self):
for filename in self.file_list[0:1]:
sent_file = os.path.join(self.annotation_dir, filename)
with open(sent_file) as file:
lc = LoopTimer(update_after=100)
abs_list = []
lastid = None
for line in file:
if self.print_status:
lc.update("Pos Doc Stream")
data = json.loads(line)
doc_id = data['id']
xml = data['annotation']
if lastid != doc_id and len(abs_list) > 0:
# Yield Stuff
yield lastid, abs_list
abs_list = []
lastid = doc_id
token_list = mf.xml2words(xml)
pos_list = mf.xml2pos(xml)
for i in range(0, len(token_list)):
token_cleaned, pos_cleaned = utils.posFilterString(token_list[i], pos_list[i])
if len(pos_cleaned) > 0:
for j in range(0, len(pos_cleaned)):
abs_list.append(pos_cleaned[j])
if len(abs_list) > 0:
# Yield Stuff
yield doc_id, abs_list