in deploy_code/multipagepdfa2i_humancomplete/clean_data.py [0:0]
def get_word_and_line(data):
dict_word = {}
dict_line = {}
for block in data["blocks"]:
if block["blockType"] == "WORD":
dict_word[block["id"]] = block["text"]
if block["blockType"] == "LINE":
dict_line[block["id"]] = block["text"]
return dict_word, dict_line