Force to read text file with utf-8

Author: whwang299

.gitignore

@@ -1,4 +1,6 @@
-/sqlova/**/*.pyc
-/wikisql/**/*.pyc
+sqlova/**/*.pyc
+wikisql/**/*.pyc
+sqlnet/__pycache__
+bert/__pycache__
 .idea
 *.swp

bert/tokenization.py

@@ -70,7 +70,7 @@ def load_vocab(vocab_file):
  """Loads a vocabulary file into a dictionary."""
  vocab = collections.OrderedDict()
  index = 0
- with open(vocab_file, "r") as reader:
+ with open(vocab_file, "r", encoding="utf-8") as reader:
  while True:
  token = convert_to_unicode(reader.readline())
  if not token: