Fix sentence IDs in turns

combo/data/tokenizers/lambo_tokenizer.py

@@ -71,9 +71,9 @@ class LamboTokenizer(Tokenizer):
 
         if split_level.upper() == "TURN":
             for turn in document.turns:
+                _reset_idx()
                 sentence_tokens = []
                 for sentence in turn.sentences:
-                    _reset_idx()
                     for token in sentence.tokens:
                         sentence_tokens.extend(_sentence_tokens(token, split_multiwords))
                 tokens.append(sentence_tokens)
@@ -96,8 +96,8 @@ class LamboTokenizer(Tokenizer):
                     tokens.append(sentence_tokens)
         else:
             for turn in document.turns:
-                for sentence in turn.sentences:
                 _reset_idx()
+                for sentence in turn.sentences:
                     for token in sentence.tokens:
                         tokens.extend(_sentence_tokens(token, split_multiwords))
             tokens = [tokens]

pyproject.toml

@@ -3,7 +3,7 @@ requires = ["setuptools"]
 
 [project]
 name = "combo"
-version = "3.2.1"
+version = "3.2.2"
 authors = [
     {name = "Maja Jablonska", email = "maja.jablonska@ipipan.waw.pl"}
 ]