Add one-pass check for unconnected molecules

selfies/utils/encoding_utils.py

@@ -47,21 +47,18 @@ def selfies_to_encoding(
  selfies += "[nop]" * (pad_to_len - len_selfies(selfies))
 
  # integer encode
- char_list = split_selfies(selfies)
-
- try:
- integer_encoded = [vocab_stoi[char] for char in char_list]
- except KeyError as e:
- if e.args[0] == ".":
+ integer_encoded = []
+ for char in split_selfies(selfies):
+ if (char == ".") and ("." not in vocab_stoi):
  raise KeyError(
  "The SELFIES string contains two unconnected molecules "
  "(given by the '.' character), but vocab_stoi does not "
  "contain the '.' key. Please add it to the vocabulary "
  "or separate the molecules."
  )
- raise KeyError(e.args[0])
-
 
+ integer_encoded.append(vocab_stoi[char])
+
  if enc_type == "label":
  return integer_encoded