Address code review feedback

- Fixed wordnet.py to use the tokenize parameter as intended
- Fixed thai2fit and ltw2v to properly handle None corpus paths with clear error messages
- Fixed tokenization_small100.py type ignore comment formatting
- All mypy checks still passing (0 errors)

Co-authored-by: bact <128572+bact@users.noreply.github.com>

Author: Copilot

pythainlp/augment/word2vec/ltw2v.py

@@ -27,8 +27,12 @@ def tokenizer(self, text: str) -> list[str]:
 
     def load_w2v(self):  # insert substitute
         """Load LTW2V's word2vec model"""
-        ltw2v_wv = self.ltw2v_wv or ""
-        self.aug = Word2VecAug(ltw2v_wv, self.tokenizer, type="binary")
+        if self.ltw2v_wv is None:
+            raise ValueError(
+                "LTW2V word2vec model not found. "
+                "Please download it first using pythainlp.corpus.download('ltw2v_wv')"
+            )
+        self.aug = Word2VecAug(self.ltw2v_wv, self.tokenizer, type="binary")
 
     def augment(
         self, sentence: str, n_sent: int = 1, p: float = 0.7

pythainlp/augment/word2vec/thai2fit.py

@@ -28,8 +28,12 @@ def tokenizer(self, text: str) -> list[str]:
 
     def load_w2v(self):
         """Load Thai2Fit's word2vec model"""
-        thai2fit_wv = self.thai2fit_wv or ""
-        self.aug = Word2VecAug(thai2fit_wv, self.tokenizer, type="binary")
+        if self.thai2fit_wv is None:
+            raise ValueError(
+                "Thai2Fit word2vec model not found. "
+                "Please download it first using pythainlp.corpus.download('thai2fit_wv')"
+            )
+        self.aug = Word2VecAug(self.thai2fit_wv, self.tokenizer, type="binary")
 
     def augment(
         self, sentence: str, n_sent: int = 1, p: float = 0.7

pythainlp/augment/wordnet.py

@@ -188,7 +188,7 @@ def augment(
              ('เรา', 'ชอบ', 'ไปยัง', 'รร.')]
         """
         new_sentences = []
-        self.list_words = word_tokenize(sentence)
+        self.list_words = tokenize(sentence)
         self.list_synonym = []
         self.p_all = 1
         if postag:

pythainlp/translate/tokenization_small100.py

@@ -202,11 +202,8 @@ def __init__(
 
     @property
     def vocab_size(self) -> int:
-        return (
-            len(self.encoder)
-            + len(self.lang_token_to_id)
-            + self.num_madeup_words
-        )  # type: ignore[no-any-return]
+        # Type ignore for external library dict operations
+        return len(self.encoder) + len(self.lang_token_to_id) + self.num_madeup_words  # type: ignore[no-any-return]
 
     @property
     def tgt_lang(self) -> str: