Merge pull request #1268 from PyThaiNLP/copilot/verify-type-hints-and-docs

Verify and fix type hints, annotations, and docstrings

Author: bact

pyproject.toml

@@ -433,6 +433,7 @@ module = [
     "torch.*",
     "tqdm.*",
     "transformers.*",
+    "ufal.*",
     "ufal.chu_liu_edmonds.*",
     "word2word.*",
     "wtpsplit.*",

pythainlp/__init__.py

@@ -14,14 +14,14 @@
 thai_above_vowels = "\u0e31\u0e34\u0e35\u0e36\u0e37\u0e4d\u0e47"  # 7
 thai_below_vowels = "\u0e38\u0e39"  # 2
 
-thai_tonemarks = "\u0e48\u0e49\u0e4a\u0e4b"  # 4
+thai_tonemarks: str = "\u0e48\u0e49\u0e4a\u0e4b"  # 4
 
 # Paiyannoi, Maiyamok, Phinthu, Thanthakhat, Nikhahit, Yamakkan:
 # These signs can be part of a word
 thai_signs = "\u0e2f\u0e3a\u0e46\u0e4c\u0e4d\u0e4e"  # 6 chars
 
 # Any Thai character that can be part of a word
-thai_letters = "".join(
+thai_letters: str = "".join(
     [thai_consonants, thai_vowels, thai_tonemarks, thai_signs]
 )  # 74
 

pythainlp/ancient/__init__.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""Ancient versions of the Thai language
-"""
+"""Ancient versions of the Thai language"""
 
 __all__ = ["aksonhan_to_current", "convert_currency"]
 

pythainlp/augment/__init__.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""Thai text augment
-"""
+"""Thai text augment"""
 
 __all__ = ["WordNetAug"]
 

pythainlp/augment/lm/__init__.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""Language Models
-"""
+"""Language Models"""
 
 __all__ = [
     "FastTextAug",

pythainlp/augment/lm/fasttext.py

@@ -15,8 +15,7 @@ class FastTextAug:
     """
 
     def __init__(self, model_path: str):
-        """:param str model_path: path of model file
-        """
+        """:param str model_path: path of model file"""
         from gensim.models.fasttext import FastText as FastText_gensim
         from gensim.models.keyedvectors import KeyedVectors
 
@@ -38,8 +37,8 @@ def tokenize(self, text: str) -> list[str]:
         """
         return word_tokenize(text, engine="icu")
 
-    def modify_sent(self, sent: str, p: float = 0.7) -> list[list[str]]:
-        """:param str sent: text of sentence
+    def modify_sent(self, sent: list[str], p: float = 0.7) -> list[list[str]]:
+        """:param list[str] sent: text of sentence
         :param float p: probability
         :rtype: List[List[str]]
         """
@@ -57,7 +56,7 @@ def modify_sent(self, sent: str, p: float = 0.7) -> list[list[str]]:
 
     def augment(
         self, sentence: str, n_sent: int = 1, p: float = 0.7
-    ) -> list[tuple[str]]:
+    ) -> list[tuple[str, ...]]:
         """Text Augment from fastText
 
         You may want to download the Thai model

pythainlp/augment/lm/phayathaibert.py

@@ -20,7 +20,9 @@ def __init__(self) -> None:
         )
 
         self.tokenizer = AutoTokenizer.from_pretrained(_MODEL_NAME)
-        self.model_for_masked_lm = AutoModelForMaskedLM.from_pretrained(_MODEL_NAME)
+        self.model_for_masked_lm = AutoModelForMaskedLM.from_pretrained(
+            _MODEL_NAME
+        )
         self.model = pipeline(
             "fill-mask",
             tokenizer=self.tokenizer,
@@ -53,7 +55,9 @@ def generate(
 
         return gen_txt
 
-    def augment(self, text: str, num_augs: int = 3, sample: bool = False) -> list[str]:
+    def augment(
+        self, text: str, num_augs: int = 3, sample: bool = False
+    ) -> list[str]:
         """Text augmentation from PhayaThaiBERT
 
         :param str text: Thai text
@@ -87,7 +91,9 @@ def augment(self, text: str, num_augs: int = 3, sample: bool = False) -> list[st
         if num_augs <= MAX_NUM_AUGS:
             for rank in range(num_augs):
                 gen_text = self.generate(text, rank, sample=sample)
-                processed_text = re.sub("<_>", " ", self.processor.preprocess(gen_text))
+                processed_text = re.sub(
+                    "<_>", " ", self.processor.preprocess(gen_text)
+                )
                 augment_list.append(processed_text)
         else:
             raise ValueError(

pythainlp/augment/word2vec/__init__.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""Word2Vec
-"""
+"""Word2Vec"""
 
 __all__ = ["Word2VecAug", "Thai2fitAug", "LTW2VAug"]
 

pythainlp/augment/word2vec/bpemb_wv.py

@@ -27,8 +27,7 @@ def tokenizer(self, text: str) -> list[str]:
         return self.bpemb_temp.encode(text)  # type: ignore[no-any-return]
 
     def load_w2v(self):
-        """Load BPEmb model
-        """
+        """Load BPEmb model"""
         self.aug = Word2VecAug(
             self.model, tokenize=self.tokenizer, type="model"
         )

pythainlp/augment/word2vec/core.py

@@ -9,7 +9,10 @@
 
 class Word2VecAug:
     def __init__(
-        self, model: str, tokenize: Callable[[str], list[str]], type: str = "file"
+        self,
+        model: str,
+        tokenize: Callable[[str], list[str]],
+        type: str = "file",
     ) -> None:
         """:param str model: path of model
         :param Callable[[str], list[str]] tokenize: tokenize function