import traceback
from collections import namedtuple, defaultdict
from itertools import count as it_count
from log.Logger import Logger
from request_type.Parser import StopWords, Parser
from strategy.phrase_finder import PhraseFinder
logger = Logger()
phrase_finder = PhraseFinder()
class JSONExportParser(Parser):
def parse(self):
try:
response = dict()
self.faq_payload = self.read_file('json')
self.print_verbose('pre processing input data ...')
stop_tokens = self.get_stopwords_for_json()
questions_map, ques_to_altq_map = self.create_question_maps()
response['question_map'] = questions_map
response['altq_map'] = ques_to_altq_map
response['stop_words'] = stop_tokens
response['graph_synonyms'] = self.update_generated_synonyms(
self.args['syn_file_path'], self.get_graph_level_synonyms())
return response
except Exception:
error_msg = traceback.format_exc()
logger.error(error_msg)
self.print_verbose(error_msg)
from collections import defaultdict
from tqdm import tqdm
from common import nlp, BOT_NAME
from strategy.phrase_finder import PhraseFinder
from log.Logger import Logger
import copy
import traceback
import re
from analyzer.kg_export.language.Lemmatize import Lemmatizer
logger = Logger()
phrase_finder_obj = PhraseFinder()
lemma = Lemmatizer()
class GramBasedGenerator(object):
def __init__(self):
pass
@staticmethod
def _filter_substrings(node_names):
new_node_names = copy.deepcopy(node_names)
for node_1 in node_names:
node_1_stripped = node_1.strip()
for node_2 in node_names:
node_2_stripped = node_2.strip()
try:
if node_1_stripped != node_2_stripped:
if node_2_stripped in node_1_stripped:
new_node_names.remove(node_2)
except Exception: