Fix errors reported by ruff

pythainlp/augment/lm/phayathaibert.py

@@ -5,7 +5,7 @@
 
 import random
 import re
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
     from transformers import AutoModelForMaskedLM, AutoTokenizer, Pipeline

pythainlp/augment/lm/wangchanberta.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
     from transformers import CamembertTokenizer, Pipeline

pythainlp/augment/word2vec/bpemb_wv.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING
 
 from pythainlp.augment.word2vec.core import Word2VecAug
 

pythainlp/augment/word2vec/core.py

@@ -4,7 +4,7 @@
 from __future__ import annotations
 
 import itertools
-from typing import TYPE_CHECKING, Any, Callable
+from typing import TYPE_CHECKING, Callable
 
 if TYPE_CHECKING:
     from gensim.models.keyedvectors import KeyedVectors

pythainlp/corpus/core.py

@@ -11,7 +11,7 @@
 import sys
 import tarfile
 import zipfile
-from http.client import HTTPResponse
+from http.client import HTTPMessage, HTTPResponse
 from importlib.resources import files
 from typing import TYPE_CHECKING
 
@@ -34,7 +34,7 @@ class _ResponseWrapper:
     """Wrapper to provide requests.Response-like interface for urllib response."""
 
     status_code: int
-    headers: "http.client.HTTPMessage"
+    headers: HTTPMessage
     _content: bytes
 
     def __init__(self, response: HTTPResponse) -> None:

pythainlp/el/_multiel.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any, Union
+from typing import TYPE_CHECKING, Union
 
 if TYPE_CHECKING:
     from multiel import BELA

pythainlp/morpheme/thaiwordcheck.py

@@ -17,7 +17,6 @@
 from __future__ import annotations
 
 import re
-from typing import Pattern
 
 _THANTHAKHAT_CHAR: str = "\u0e4c"  # Thanthakhat (cancellation of sound)
 

pythainlp/parse/transformers_ud.py

@@ -16,8 +16,8 @@
 
 if TYPE_CHECKING:
     from transformers import (
-        AutoTokenizer,
         AutoModelForQuestionAnswering,
+        AutoTokenizer,
         TokenClassificationPipeline,
     )
 

pythainlp/spell/__init__.py

@@ -13,9 +13,10 @@
     "get_words_spell_suggestion",
 ]
 
-from pythainlp.spell.pn import NorvigSpellChecker
 from typing import Type
 
+from pythainlp.spell.pn import NorvigSpellChecker
+
 DEFAULT_SPELL_CHECKER: Type[NorvigSpellChecker] = NorvigSpellChecker
 
 # these imports are placed here to avoid circular imports

pythainlp/spell/words_spelling_correction.py

@@ -58,11 +58,13 @@ def __init__(
 
         """
         try:
-            import numpy as np
+            import numpy as np  # noqa: F401
         except ModuleNotFoundError:
-            raise ModuleNotFoundError("""
+            raise ModuleNotFoundError(
+                """
             Please installing the package via 'pip install numpy onnxruntime'.
-            """)
+            """
+            )
         except Exception as e:
             raise RuntimeError(f"An unexpected error occurred: {e}") from e
         self.model_dir = model_dir
@@ -81,7 +83,7 @@ def __init__(
     def _load_embeddings(self) -> tuple[list[str], NDArray[np.float32]]:
         """Loads embeddings matrix and vocabulary list."""
         import numpy as np
-        
+
         input_matrix = np.load(
             os.path.join(self.model_dir, "embeddings.npy")
         )
@@ -95,7 +97,7 @@ def _load_embeddings(self) -> tuple[list[str], NDArray[np.float32]]:
     def _load_suggestion_words(self, words_list: list[str]) -> NDArray[np.str_]:
         """Loads the list of words used for suggestions."""
         import numpy as np
-        
+
         words = np.array(words_list)
         return words
 
@@ -152,7 +154,7 @@ def _get_subwords(self, word: str) -> tuple[list[str], NDArray[np.int_]]:
     def get_word_vector(self, word: str) -> NDArray[np.float32]:
         """Computes the normalized vector for a single word."""
         import numpy as np
-        
+
         # subword_ids[1] contains the array of indices for the word and its subwords
         subword_ids = self._get_subwords(word)[1]
 
@@ -193,7 +195,7 @@ def _tokenize(self, sentence: str) -> list[str]:
     def get_sentence_vector(self, line: str) -> NDArray[np.float32]:
         """Computes the mean vector for a sentence."""
         import numpy as np
-        
+
         tokens = self._tokenize(line)
         vectors = []
         for t in tokens:

pythainlp/translate/small100.py

@@ -6,8 +6,8 @@
 from typing import TYPE_CHECKING, Optional
 
 if TYPE_CHECKING:
-    from transformers import M2M100ForConditionalGeneration
     import torch
+    from transformers import M2M100ForConditionalGeneration
 
 from .tokenization_small100 import SMALL100Tokenizer
 

pythainlp/translate/th_fr.py

@@ -14,11 +14,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
-    from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
     import torch
+    from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
 
 class ThFrTranslator:

pythainlp/translate/tokenization_small100.py

@@ -27,7 +27,7 @@
 import os
 from pathlib import Path
 from shutil import copyfile
-from typing import TYPE_CHECKING, Optional, Union, cast
+from typing import TYPE_CHECKING, Any, Optional, Union, cast
 
 if TYPE_CHECKING:
     from sentencepiece import SentencePieceProcessor
@@ -439,7 +439,7 @@ def load_spm(
     path: str, sp_model_kwargs: dict[str, str]
 ) -> SentencePieceProcessor:
     import sentencepiece
-    
+
     spm = sentencepiece.SentencePieceProcessor(**sp_model_kwargs)
     spm.Load(str(path))
     return spm

pythainlp/translate/zh_th.py

@@ -11,11 +11,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
-    from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
     import torch
+    from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
 
 class ThZhTranslator:

pythainlp/transliterate/thaig2p_v2.py

@@ -9,7 +9,7 @@
 # Use a pipeline as a high-level helper
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
     from transformers import Pipeline

pythainlp/transliterate/umt5_thaig2p.py

@@ -9,7 +9,7 @@
 # Use a pipeline as a high-level helper
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
     from transformers import Pipeline

pythainlp/util/emojiconv.py

@@ -7,7 +7,6 @@
 from __future__ import annotations
 
 import re
-from typing import Pattern
 
 _emoji_th: dict[str, str] = {
     "😀": "หน้ายิ้มยิงฟัน",

pythainlp/util/syllable.py

@@ -6,7 +6,6 @@
 from __future__ import annotations
 
 import re
-
 from typing import Pattern
 
 from pythainlp import thai_consonants, thai_tonemarks

pythainlp/wangchanberta/core.py

@@ -8,7 +8,11 @@
 from typing import TYPE_CHECKING, Union
 
 if TYPE_CHECKING:
-    from transformers import CamembertTokenizer, PreTrainedModel, PreTrainedTokenizerBase
+    from transformers import (
+        CamembertTokenizer,
+        PreTrainedModel,
+        PreTrainedTokenizerBase,
+    )
     from transformers.pipelines import TokenClassificationPipeline
 
 from pythainlp.tokenize import word_tokenize