From f73d4893b5a2a7149b6c72b4756d161851bb1ac1 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Tue, 3 Feb 2026 10:34:10 +0000 Subject: [PATCH 1/3] Initial plan From 988c81835f6bb829c882c6b04b45b4e524f912af Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Tue, 3 Feb 2026 10:43:09 +0000 Subject: [PATCH 2/3] Add type hints with no-any-return annotations for external library wrappers Fixed type hints for modules used in extra test suite: - pythainlp.corpus.wordnet: All functions now have proper type ignore annotations - pythainlp.spell.tltk and phunspell: Added type ignore for external library returns - pythainlp.transliterate.tltk and ipa: Fixed transliteration functions - pythainlp.tag.tltk: Fixed pos_tag function - pythainlp.word_vector.core: Fixed all no-any-return errors Analyzed NLTK wordnet source to verify return types are correct. Co-authored-by: bact <128572+bact@users.noreply.github.com> --- pythainlp/corpus/wordnet.py | 20 ++++++++++---------- pythainlp/spell/phunspell.py | 2 +- pythainlp/spell/tltk.py | 2 +- pythainlp/tag/tltk.py | 2 +- pythainlp/transliterate/ipa.py | 6 +++--- pythainlp/transliterate/tltk.py | 6 +++--- pythainlp/word_vector/core.py | 10 +++++----- 7 files changed, 24 insertions(+), 24 deletions(-) diff --git a/pythainlp/corpus/wordnet.py b/pythainlp/corpus/wordnet.py index a61e940fb..a52828d3b 100644 --- a/pythainlp/corpus/wordnet.py +++ b/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] diff --git a/pythainlp/spell/phunspell.py b/pythainlp/spell/phunspell.py index c42fd54e3..a63287071 100644 --- a/pythainlp/spell/phunspell.py +++ b/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] diff --git a/pythainlp/spell/tltk.py b/pythainlp/spell/tltk.py index 225a20c02..29a17bfef 100644 --- a/pythainlp/spell/tltk.py +++ b/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] diff --git a/pythainlp/tag/tltk.py b/pythainlp/tag/tltk.py index 92d3fb45b..6a83bd1f0 100644 --- a/pythainlp/tag/tltk.py +++ b/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: diff --git a/pythainlp/transliterate/ipa.py b/pythainlp/transliterate/ipa.py index 7432347f2..a18c5014e 100644 --- a/pythainlp/transliterate/ipa.py +++ b/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] diff --git a/pythainlp/transliterate/tltk.py b/pythainlp/transliterate/tltk.py index 9148fb6b7..a1b79172f 100644 --- a/pythainlp/transliterate/tltk.py +++ b/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(" ")].replace("", "") + return _temp[: _temp.rfind(" ")].replace("", "") # 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("")[1].replace("|", "").replace("|", " ") - return _temp.replace("", "") + return _temp.replace("", "") # 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(" ")].replace("", "") + return _temp[: _temp.rfind(" ")].replace("", "") # type: ignore[no-any-return] diff --git a/pythainlp/word_vector/core.py b/pythainlp/word_vector/core.py index 9abdd5189..33e81c77e 100644 --- a/pythainlp/word_vector/core.py +++ b/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] From c2edfb384ab2c15b249745668216ad776700d550 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Tue, 3 Feb 2026 10:46:40 +0000 Subject: [PATCH 3/3] Add proper numpy type annotations and fix benchmarks module - Added explicit np.intp type annotations for numpy sum operations - Fixed _binary_representation to properly annotate bin_rept as np.ndarray - Added type ignore for bpemb and wangchanberta external library returns - All tests in benchmarks and augment modules pass Co-authored-by: bact <128572+bact@users.noreply.github.com> --- pythainlp/augment/lm/wangchanberta.py | 2 +- pythainlp/augment/word2vec/bpemb_wv.py | 2 +- pythainlp/benchmarks/word_tokenization.py | 14 +++++++------- 3 files changed, 9 insertions(+), 9 deletions(-) diff --git a/pythainlp/augment/lm/wangchanberta.py b/pythainlp/augment/lm/wangchanberta.py index bb4d611a7..aef83400a 100644 --- a/pythainlp/augment/lm/wangchanberta.py +++ b/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] diff --git a/pythainlp/augment/word2vec/bpemb_wv.py b/pythainlp/augment/word2vec/bpemb_wv.py index b5605fa67..8a9433f96 100644 --- a/pythainlp/augment/word2vec/bpemb_wv.py +++ b/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 diff --git a/pythainlp/benchmarks/word_tokenization.py b/pythainlp/benchmarks/word_tokenization.py index 36cd0a08c..601f07090 100644 --- a/pythainlp/benchmarks/word_tokenization.py +++ b/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, ""))