Merge pull request #1267 from PyThaiNLP/copilot/add-type-hints-to-submodules-one-more-time

Add type hints to modules in extra test suite

Author: bact

pythainlp/augment/lm/wangchanberta.py

@@ -74,4 +74,4 @@ def augment(self, sentence: str, num_replace_tokens: int = 3) -> list[str]:
              'ช้างมีทั้งหมด 50 ตัว บนหัว']
         """
         sent2 = self.generate(sentence, num_replace_tokens)
-        return sent2
+        return sent2  # type: ignore[no-any-return]

pythainlp/augment/word2vec/bpemb_wv.py

@@ -24,7 +24,7 @@ def tokenizer(self, text: str) -> list[str]:
         """:param str text: Thai text
         :rtype: List[str]
         """
-        return self.bpemb_temp.encode(text)
+        return self.bpemb_temp.encode(text)  # type: ignore[no-any-return]
 
     def load_w2v(self):
         """Load BPEmb model

pythainlp/benchmarks/word_tokenization.py

@@ -157,11 +157,11 @@ def compute_stats(ref_sample: str, raw_sample: str) -> dict:
     c_pos_pred = c_pos_pred[c_pos_pred < ref_sample_arr.shape[0]]
     c_neg_pred = c_neg_pred[c_neg_pred < ref_sample_arr.shape[0]]
 
-    c_tp = np.sum(ref_sample_arr[c_pos_pred] == 1)
-    c_fp = np.sum(ref_sample_arr[c_pos_pred] == 0)
+    c_tp: np.intp = np.sum(ref_sample_arr[c_pos_pred] == 1)
+    c_fp: np.intp = np.sum(ref_sample_arr[c_pos_pred] == 0)
 
-    c_tn = np.sum(ref_sample_arr[c_neg_pred] == 0)
-    c_fn = np.sum(ref_sample_arr[c_neg_pred] == 1)
+    c_tn: np.intp = np.sum(ref_sample_arr[c_neg_pred] == 0)
+    c_fn: np.intp = np.sum(ref_sample_arr[c_neg_pred] == 1)
 
     # Compute word-level statistics
 
@@ -174,7 +174,7 @@ def compute_stats(ref_sample: str, raw_sample: str) -> dict:
         word_boundaries, ss_boundaries
     )
 
-    correctly_tokenised_words = np.sum(tokenization_indicators)
+    correctly_tokenised_words: np.intp = np.sum(tokenization_indicators)
 
     tokenization_indicators_str = list(map(str, tokenization_indicators))
 
@@ -206,14 +206,14 @@ def _binary_representation(txt: str, verbose: bool = False) -> np.ndarray:
     :param bool verbose: for debugging purposes
 
     :return: {0, 1} sequence
-    :rtype: str
+    :rtype: np.ndarray
     """
     chars = np.array(list(txt))
 
     boundary = np.argwhere(chars == SEPARATOR).reshape(-1)
     boundary = boundary - np.array(range(boundary.shape[0]))
 
-    bin_rept = np.zeros(len(txt) - boundary.shape[0])
+    bin_rept: np.ndarray = np.zeros(len(txt) - boundary.shape[0])
     bin_rept[list(boundary) + [0]] = 1
 
     sample_wo_seps = list(txt.replace(SEPARATOR, ""))

pythainlp/corpus/wordnet.py

@@ -74,7 +74,7 @@ def synsets(word: str, pos: Optional[str] = None, lang: str = "tha") -> list[wor
         >>> synsets("แรง", pos="a", lang="tha")
         [Synset('hard.s.10'), Synset('strong.s.02')]
     """
-    return wordnet.synsets(lemma=word, pos=pos, lang=lang)
+    return wordnet.synsets(lemma=word, pos=pos, lang=lang)  # type: ignore[no-any-return]
 
 
 def synset(name_synsets: str) -> wordnet.Synset:
@@ -140,7 +140,7 @@ def all_lemma_names(pos: Optional[str] = None, lang: str = "tha") -> list[str]:
         >>> len(all_lemma_names(pos="a"))
         5277
     """
-    return wordnet.all_lemma_names(pos=pos, lang=lang)
+    return wordnet.all_lemma_names(pos=pos, lang=lang)  # type: ignore[no-any-return]
 
 
 def all_synsets(pos: Optional[str] = None) -> Iterable[wordnet.Synset]:
@@ -170,7 +170,7 @@ def all_synsets(pos: Optional[str] = None) -> Iterable[wordnet.Synset]:
         >>> next(generator)
         Synset('unable.a.01')
     """
-    return wordnet.all_synsets(pos=pos)
+    return wordnet.all_synsets(pos=pos)  # type: ignore[no-any-return]
 
 
 def langs() -> list[str]:
@@ -188,7 +188,7 @@ def langs() -> list[str]:
          'pol', 'por', 'qcn', 'slv', 'spa', 'swe', 'tha',
          'zsm']
     """
-    return wordnet.langs()
+    return wordnet.langs()  # type: ignore[no-any-return]
 
 
 def lemmas(word: str, pos: Optional[str] = None, lang: str = "tha") -> list[wordnet.Lemma]:
@@ -231,7 +231,7 @@ def lemmas(word: str, pos: Optional[str] = None, lang: str = "tha") -> list[word
         >>> lemmas("ม้วน", pos="n")
         [Lemma('roll.n.11.ม้วน')]
     """
-    return wordnet.lemmas(word, pos=pos, lang=lang)
+    return wordnet.lemmas(word, pos=pos, lang=lang)  # type: ignore[no-any-return]
 
 
 def lemma(name_synsets: str) -> wordnet.Lemma:
@@ -323,7 +323,7 @@ def path_similarity(synsets1: wordnet.Synset, synsets2: wordnet.Synset) -> float
         >>> path_similarity(obj, cat)
         0.08333333333333333
     """
-    return wordnet.path_similarity(synsets1, synsets2)
+    return wordnet.path_similarity(synsets1, synsets2)  # type: ignore[no-any-return]
 
 
 def lch_similarity(synsets1: wordnet.Synset, synsets2: wordnet.Synset) -> float:
@@ -360,7 +360,7 @@ def lch_similarity(synsets1: wordnet.Synset, synsets2: wordnet.Synset) -> float:
         >>> lch_similarity(obj, cat)
         1.1526795099383855
     """
-    return wordnet.lch_similarity(synsets1, synsets2)
+    return wordnet.lch_similarity(synsets1, synsets2)  # type: ignore[no-any-return]
 
 
 def wup_similarity(synsets1: wordnet.Synset, synsets2: wordnet.Synset) -> float:
@@ -391,7 +391,7 @@ def wup_similarity(synsets1: wordnet.Synset, synsets2: wordnet.Synset) -> float:
         >>> wup_similarity(obj, cat)
         0.35294117647058826
     """
-    return wordnet.wup_similarity(synsets1, synsets2)
+    return wordnet.wup_similarity(synsets1, synsets2)  # type: ignore[no-any-return]
 
 
 def morphy(form: str, pos: Optional[str] = None) -> str:
@@ -421,7 +421,7 @@ def morphy(form: str, pos: Optional[str] = None) -> str:
         >>> morphy("calculated")
         'calculate'
     """
-    return wordnet.morphy(form, pos=None)
+    return wordnet.morphy(form, pos=None)  # type: ignore[no-any-return]
 
 
 def custom_lemmas(tab_file, lang: str) -> None:
@@ -432,4 +432,4 @@ def custom_lemmas(tab_file, lang: str) -> None:
     :param tab_file: Tab file as a file or file-like object
     :param str lang: abbreviation of language (i.e. *eng*, *tha*).
     """
-    return wordnet.custom_lemmas(tab_file, lang)
+    return wordnet.custom_lemmas(tab_file, lang)  # type: ignore[no-any-return]

pythainlp/spell/phunspell.py

@@ -27,4 +27,4 @@ def spell(text: str) -> list[str]:
 
 
 def correct(text: str) -> str:
-    return list(pspell.suggest(text))[0]
+    return list(pspell.suggest(text))[0]  # type: ignore[no-any-return]

pythainlp/spell/tltk.py

@@ -21,4 +21,4 @@
 
 
 def spell(text: str) -> list[str]:
-    return spell_candidates(text)
+    return spell_candidates(text)  # type: ignore[no-any-return]

pythainlp/tag/tltk.py

@@ -20,7 +20,7 @@
 def pos_tag(words: list[str], corpus: str = "tnc") -> list[tuple[str, str]]:
     if corpus != "tnc":
         raise ValueError(f"tltk not support {0} corpus.")
-    return nlp.pos_tag_wordlist(words)
+    return nlp.pos_tag_wordlist(words)  # type: ignore[no-any-return]
 
 
 def _post_process(text: str) -> str:

pythainlp/transliterate/ipa.py

@@ -17,12 +17,12 @@
 
 
 def transliterate(text: str) -> str:
-    return _EPI_THA.transliterate(text)
+    return _EPI_THA.transliterate(text)  # type: ignore[no-any-return]
 
 
 def trans_list(text: str) -> list[str]:
-    return _EPI_THA.trans_list(text)
+    return _EPI_THA.trans_list(text)  # type: ignore[no-any-return]
 
 
 def xsampa_list(text: str) -> list[str]:
-    return _EPI_THA.xsampa_list(text)
+    return _EPI_THA.xsampa_list(text)  # type: ignore[no-any-return]

pythainlp/transliterate/tltk.py

@@ -21,18 +21,18 @@ def romanize(text: str) -> str:
     # Replace ฅ with ค to avoid KeyError in tltk (out-of-vocabulary issue)
     text = text.replace("ฅ", "ค")
     _temp = th2roman(text)
-    return _temp[: _temp.rfind(" <s/>")].replace("<s/>", "")
+    return _temp[: _temp.rfind(" <s/>")].replace("<s/>", "")  # type: ignore[no-any-return]
 
 
 def tltk_g2p(text: str) -> str:
     # Replace ฅ with ค to avoid KeyError in tltk (out-of-vocabulary issue)
     text = text.replace("ฅ", "ค")
     _temp = g2p(text).split("<tr/>")[1].replace("|<s/>", "").replace("|", " ")
-    return _temp.replace("<s/>", "")
+    return _temp.replace("<s/>", "")  # type: ignore[no-any-return]
 
 
 def tltk_ipa(text: str) -> str:
     # Replace ฅ with ค to avoid KeyError in tltk (out-of-vocabulary issue)
     text = text.replace("ฅ", "ค")
     _temp = th2ipa(text)
-    return _temp[: _temp.rfind(" <s/>")].replace("<s/>", "")
+    return _temp[: _temp.rfind(" <s/>")].replace("<s/>", "")  # type: ignore[no-any-return]

pythainlp/word_vector/core.py

@@ -108,7 +108,7 @@ def doesnt_match(self, words: list[str]) -> str:
         >>> wv.doesnt_match(words)
         'เรือ'
         """
-        return self.model.doesnt_match(words)
+        return self.model.doesnt_match(words)  # type: ignore[no-any-return]
 
     def most_similar_cosmul(
         self, positive: list[str], negative: list[str]
@@ -209,7 +209,7 @@ def most_similar_cosmul(
         >>> wv.most_similar_cosmul(list_positive, list_negative)
         KeyError: "word 'เมนูอาหารไทย' not in vocabulary"
         """
-        return self.model.most_similar_cosmul(
+        return self.model.most_similar_cosmul(  # type: ignore[no-any-return]
             positive=positive, negative=negative
         )
 
@@ -249,7 +249,7 @@ def similarity(self, word1: str, word2: str) -> float:
         0.04300258
 
         """
-        return self.model.similarity(word1, word2)
+        return self.model.similarity(word1, word2)  # type: ignore[no-any-return]
 
     def sentence_vectorizer(self, text: str, use_mean: bool = True) -> ndarray:
         """Converts a Thai sentence into a vector.
@@ -302,7 +302,7 @@ def sentence_vectorizer(self, text: str, use_mean: bool = True) -> ndarray:
         len_words = len(words)
 
         if not len_words:
-            return vec
+            return vec  # type: ignore[no-any-return]
 
         for word in words:
             if word == " " and self.model_name == "thai2fit_wv":
@@ -316,4 +316,4 @@ def sentence_vectorizer(self, text: str, use_mean: bool = True) -> ndarray:
         if use_mean:
             vec /= len_words
 
-        return vec
+        return vec  # type: ignore[no-any-return]