Verify and fix type hints, annotations, and docstrings

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

pythainlp/augment/word2vec/ltw2v.py

@@ -26,13 +26,17 @@ def tokenizer(self, text: str) -> list[str]:
         return word_tokenize(text, engine="newmm")
 
     def load_w2v(self):  # insert substitute
-        """Load LTW2V's word2vec model
-        """
+        """Load LTW2V's word2vec model"""
+        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
-    ) -> list[tuple[str]]:
+    ) -> list[tuple[str, ...]]:
         """Text Augment using word2vec from Thai2Fit
 
         :param str sentence: Thai sentence

pythainlp/augment/word2vec/thai2fit.py

@@ -24,16 +24,20 @@ def tokenizer(self, text: str) -> list[str]:
         :rtype: List[str]
         """
         tok = thai2fit_tokenizer()
-        return tok.word_tokenize(text)
+        return tok.word_tokenize(text)  # type: ignore[no-any-return]
 
     def load_w2v(self):
-        """Load Thai2Fit's word2vec model
-        """
+        """Load Thai2Fit's word2vec model"""
+        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
-    ) -> list[tuple[str]]:
+    ) -> list[tuple[str, ...]]:
         """Text Augment using word2vec from Thai2Fit
 
         :param str sentence: Thai sentence

pythainlp/augment/wordnet.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""Thank https://dev.to/ton_ami/text-data-augmentation-synonym-replacement-4h8l
-"""
+"""Thank https://dev.to/ton_ami/text-data-augmentation-synonym-replacement-4h8l"""
 
 from __future__ import annotations
 
@@ -13,7 +12,7 @@
 
 import itertools
 from collections import OrderedDict
-from typing import Optional
+from typing import Callable, Optional
 
 from nltk.corpus import wordnet as wn
 
@@ -117,14 +116,16 @@ def postype2wordnet(pos: str, corpus: str):
 
 
 class WordNetAug:
-    """Text Augment using wordnet
-    """
+    """Text Augment using wordnet"""
 
     def __init__(self):
         pass
 
     def find_synonyms(
-        self, word: str, pos: Optional[str] = None, postag_corpus: str = "orchid"
+        self,
+        word: str,
+        pos: Optional[str] = None,
+        postag_corpus: str = "orchid",
     ) -> list[str]:
         """Find synonyms using wordnet
 
@@ -156,7 +157,7 @@ def find_synonyms(
     def augment(
         self,
         sentence: str,
-        tokenize: object = word_tokenize,
+        tokenize: Callable[[str], list[str]] = word_tokenize,
         max_syn_sent: int = 6,
         postag: bool = True,
         postag_corpus: str = "orchid",
@@ -210,5 +211,5 @@ def augment(
         if max_syn_sent > self.p_all:
             max_syn_sent = self.p_all
         for x in list(itertools.product(*self.list_synonym))[0:max_syn_sent]:
-            new_sentences.append(x)
+            new_sentences.append(list(x))
         return new_sentences

pythainlp/benchmarks/__init__.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""Performance benchmarking.
-"""
+"""Performance benchmarking."""
 
 __all__ = ["benchmark"]
 

pythainlp/benchmarks/word_tokenization.py

@@ -152,7 +152,10 @@ def compute_stats(ref_sample: str, raw_sample: str) -> dict:
     sample_arr = _binary_representation(raw_sample)
 
     # Compute character-level statistics
-    c_pos_pred, c_neg_pred = np.argwhere(sample_arr == 1), np.argwhere(sample_arr == 0)
+    c_pos_pred, c_neg_pred = (
+        np.argwhere(sample_arr == 1),
+        np.argwhere(sample_arr == 0),
+    )
 
     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]]

pythainlp/chat/__init__.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""pythainlp.chat
-"""
+"""pythainlp.chat"""
 
 __all__ = ["ChatBotModel"]
 

pythainlp/chat/core.py

@@ -8,13 +8,11 @@
 
 class ChatBotModel:
     def __init__(self):
-        """Chat using AI generation
-        """
+        """Chat using AI generation"""
         self.history = []
 
     def reset_chat(self):
-        """Reset chat by cleaning history
-        """
+        """Reset chat by cleaning history"""
         self.history = []
 
     def load_model(
@@ -88,4 +86,4 @@ def chat(self, text: str) -> str:
         )
         _bot = self.model.gen_instruct(_temp)
         self.history.append((text, _bot))
-        return _bot
+        return _bot  # type: ignore[no-any-return]

pythainlp/classify/__init__.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""pythainlp.classify
-"""
+"""pythainlp.classify"""
 
 __all__ = ["GzipModel"]
 

pythainlp/cli/data.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""Command line for PyThaiNLP's dataset/corpus management.
-"""
+"""Command line for PyThaiNLP's dataset/corpus management."""
 
 from __future__ import annotations
 

pythainlp/cli/tag.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""Command line for PyThaiNLP's taggers.
-"""
+"""Command line for PyThaiNLP's taggers."""
 
 from __future__ import annotations
 

pythainlp/cli/tokenize.py

@@ -6,7 +6,7 @@
 from __future__ import annotations
 
 import argparse
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Any
 
 from pythainlp import cli
 from pythainlp.tokenize import (
@@ -31,7 +31,7 @@
 class SubAppBase:
     separator: str
     algorithm: str
-    run: Callable[..., list[str]]
+    run: Callable[..., Any]
 
     def __init__(self, name: str, argv: Sequence[str]) -> None:
         parser = argparse.ArgumentParser(**cli.make_usage("tokenize " + name))  # type: ignore[arg-type]

pythainlp/coref/__init__.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""PyThaiNLP Coreference Resolution
-"""
+"""PyThaiNLP Coreference Resolution"""
 
 __all__ = ["coreference_resolution"]
 

pythainlp/coref/core.py

@@ -3,11 +3,15 @@
 # SPDX-License-Identifier: Apache-2.0
 from __future__ import annotations
 
+from typing import Union
+
 _MODEL = None
 
 
 def coreference_resolution(
-    texts: list[str], model_name: str = "han-coref-v1.0", device: str = "cpu"
+    texts: Union[str, list[str]],
+    model_name: str = "han-coref-v1.0",
+    device: str = "cpu",
 ) -> list[dict]:
     """Coreference Resolution