Add whitespace check

.github/workflows/lint.yml

@@ -26,4 +26,4 @@ jobs:
       uses: astral-sh/ruff-action@v3
       with:
         src: "./pythainlp"
-        args: check --verbose --line-length 79 --select C901
+        args: check --fix --verbose --line-length 79 --select I,W,C901,W291,W293

docs/conf.py

@@ -9,8 +9,8 @@
 import os
 import sys
 import traceback
-from datetime import datetime
-from datetime import date
+from datetime import date, datetime
+
 import pythainlp
 
 # -- Path setup --------------------------------------------------------------
@@ -34,7 +34,7 @@
 # -- Get version information and date from Git ----------------------------
 
 try:
-    from subprocess import check_output, STDOUT
+    from subprocess import STDOUT, check_output
 
     current_branch = (
         os.environ["CURRENT_BRANCH"]
@@ -69,7 +69,7 @@
     #     .decode()
     #     .strip()
     # )
-except Exception as e:
+except Exception:
     traceback.print_exc()
     release = pythainlp.__version__
     # today = "<unknown date>"

examples/khavee.py

@@ -2,13 +2,11 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""
-Example of using KhaveeVerifier from pythainlp.khavee
+"""Example of using KhaveeVerifier from pythainlp.khavee
 """
 
 from pythainlp.khavee import KhaveeVerifier
 
-
 kv = KhaveeVerifier()
 
 # การเช็คสระ
@@ -64,7 +62,7 @@
 เรื่องวิศวะเก่งกาจประหลาดใจ เรื่องฟิสิกส์ไร้ผู้ใดมาต่อไป
 นริศราอีฟเก่งกว่าใครเพื่อน คอยช่วยเตือนเรื่องงานคอยสั่งสอน
 อ่านตำราหาความรู้ไม่ละทอน เป็นคนดีศรีนครของจิตรลดา
-ภัสนันท์นาคลออหรือมีมี่ เรื่องเกมเอ่อเก่งกาจไม่กังขา 
+ภัสนันท์นาคลออหรือมีมี่ เรื่องเกมเอ่อเก่งกาจไม่กังขา
 เกมอะไรก็เล่นได้ไม่ลดวา สุดฉลาดมากปัญญามาครบครัน""",
         k_type=8,
     )

notebooks/convert_thai2rom_to_onnx.ipynb

@@ -75,6 +75,7 @@
    "outputs": [],
    "source": [
     "import torch\n",
+    "\n",
     "from pythainlp.corpus import get_corpus_path\n",
     "from pythainlp.transliterate.thai2rom import _MODEL_NAME\n",
     "\n",
@@ -115,7 +116,6 @@
    "outputs": [],
    "source": [
     "import torch\n",
-    "import numpy as np\n",
     "\n",
     "input_tensor = torch.Tensor([[30, 19, 8, 30, 38, 37, 10, 3]]).long()\n",
     "\n",

notebooks/create_words.ipynb

@@ -6,8 +6,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from pythainlp.transliterate import pronunciate\n",
-    "from pythainlp import thai_consonants"
+    "from pythainlp import thai_consonants\n",
+    "from pythainlp.transliterate import pronunciate"
    ]
   },
   {

notebooks/test_chat.ipynb

@@ -9,8 +9,9 @@
    },
    "outputs": [],
    "source": [
-    "from pythainlp.chat.core import ChatBotModel\n",
-    "import torch"
+    "import torch\n",
+    "\n",
+    "from pythainlp.chat.core import ChatBotModel"
    ]
   },
   {

notebooks/test_el.ipynb

@@ -8,6 +8,7 @@
    "outputs": [],
    "source": [
     "import os\n",
+    "\n",
     "os.environ[\"CUDA_VISIBLE_DEVICES\"]=\"1\""
    ]
   },

notebooks/test_wangchanglm.ipynb

@@ -9,8 +9,9 @@
    },
    "outputs": [],
    "source": [
-    "from pythainlp.generate.wangchanglm import WangChanGLM\n",
-    "import torch"
+    "import torch\n",
+    "\n",
+    "from pythainlp.generate.wangchanglm import WangChanGLM"
    ]
   },
   {

notebooks/test_wsd.ipynb

@@ -80,7 +80,7 @@
    },
    "outputs": [],
    "source": [
-    "from pythainlp.corpus import get_corpus_path, thai_wsd_dict"
+    "from pythainlp.corpus import thai_wsd_dict"
    ]
   },
   {

pyproject.toml

@@ -301,4 +301,4 @@ docstring-code-format = true
 [tool.ruff.lint.mccabe]
 # Flag errors (`C901`) whenever the complexity level exceeds 5. Default is 10.
 # We should aim to gradually reduce this to 10.
-max-complexity = 40
+max-complexity = 38

pythainlp/__init__.py

@@ -50,6 +50,21 @@
 โกรธจี๊ดจ๋อยจ่มถ้ำ 	อยู่เฝ้า “อตฺตา” ๚ะ๛
 ๑๒ กรกฎาคม ๒๕๕๘"""
 
+__all__ = [
+    "collate",
+    "correct",
+    "pos_tag",
+    "romanize",
+    "spell",
+    "sent_tokenize",
+    "subword_tokenize",
+    "soundex",
+    "thai_strftime",
+    "transliterate",
+    "Tokenizer",
+    "word_tokenize",
+]
+
 from pythainlp.soundex import soundex
 from pythainlp.spell import correct, spell
 from pythainlp.tag import pos_tag

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/ancient/aksonhan.py

@@ -23,8 +23,7 @@
 
 
 def aksonhan_to_current(word: str) -> str:
-    """
-    Convert AksonHan words to current Thai words
+    """Convert AksonHan words to current Thai words
 
     AksonHan (อักษรหัน) writes down two consonants for the \
     spelling of the /a/ vowels. (สระ อะ).

pythainlp/ancient/currency.py

@@ -5,8 +5,7 @@
 
 
 def convert_currency(value: float, from_unit: str) -> dict:
-    """
-    Convert ancient Thai currency to other units
+    """Convert ancient Thai currency to other units
 
     * เบี้ย (Bia)
     * อัฐ (At)

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__ = [

pythainlp/augment/lm/fasttext.py

@@ -12,15 +12,13 @@
 
 
 class FastTextAug:
-    """
-    Text Augment from fastText
+    """Text Augment from fastText
 
     :param str model_path: path of model file
     """
 
     def __init__(self, model_path: str):
-        """
-        :param str model_path: path of model file
+        """:param str model_path: path of model file
         """
         if model_path.endswith(".bin"):
             self.model = FastText_gensim.load_facebook_vectors(model_path)
@@ -31,8 +29,7 @@ def __init__(self, model_path: str):
         self.dict_wv = list(self.model.key_to_index.keys())
 
     def tokenize(self, text: str) -> list[str]:
-        """
-        Thai text tokenization for fastText
+        """Thai text tokenization for fastText
 
         :param str text: Thai text
 
@@ -42,8 +39,7 @@ 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
+        """:param str sent: text of sentence
         :param float p: probability
         :rtype: List[List[str]]
         """
@@ -62,8 +58,7 @@ 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]]:
-        """
-        Text Augment from fastText
+        """Text Augment from fastText
 
         You may want to download the Thai model
         from https://fasttext.cc/docs/en/crawl-vectors.html.

pythainlp/augment/lm/phayathaibert.py

@@ -57,8 +57,7 @@ def generate(
     def augment(
         self, text: str, num_augs: int = 3, sample: bool = False
     ) -> list[str]:
-        """
-        Text augmentation from PhayaThaiBERT
+        """Text augmentation from PhayaThaiBERT
 
         :param str text: Thai text
         :param int num_augs: an amount of augmentation text needed as an output

pythainlp/augment/lm/wangchanberta.py

@@ -51,8 +51,7 @@ def generate(self, sentence: str, num_replace_tokens: int = 3):
         return self.sent2
 
     def augment(self, sentence: str, num_replace_tokens: int = 3) -> list[str]:
-        """
-        Text augmentation from WangchanBERTa
+        """Text augmentation from WangchanBERTa
 
         :param str sentence: Thai sentence
         :param int num_replace_tokens: number replace tokens

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

@@ -7,8 +7,7 @@
 
 
 class BPEmbAug:
-    """
-    Thai Text Augment using word2vec from BPEmb
+    """Thai Text Augment using word2vec from BPEmb
 
     BPEmb:
     `github.com/bheinzerling/bpemb <https://github.com/bheinzerling/bpemb>`_
@@ -22,15 +21,13 @@ def __init__(self, lang: str = "th", vs: int = 100000, dim: int = 300):
         self.load_w2v()
 
     def tokenizer(self, text: str) -> list[str]:
-        """
-        :param str text: Thai text
+        """:param str text: Thai text
         :rtype: List[str]
         """
         return self.bpemb_temp.encode(text)
 
     def load_w2v(self):
-        """
-        Load BPEmb model
+        """Load BPEmb model
         """
         self.aug = Word2VecAug(
             self.model, tokenize=self.tokenizer, type="model"
@@ -39,8 +36,7 @@ def load_w2v(self):
     def augment(
         self, sentence: str, n_sent: int = 1, p: float = 0.7
     ) -> list[tuple[str]]:
-        """
-        Text Augment using word2vec from BPEmb
+        """Text Augment using word2vec from BPEmb
 
         :param str sentence: Thai sentence
         :param int n_sent: number of sentence

pythainlp/augment/word2vec/core.py

@@ -10,8 +10,7 @@ class Word2VecAug:
     def __init__(
         self, model: str, tokenize: object, type: str = "file"
     ) -> None:
-        """
-        :param str model: path of model
+        """:param str model: path of model
         :param object tokenize: tokenize function
         :param str type: model type (file, binary)
         """
@@ -29,8 +28,7 @@ def __init__(
         self.dict_wv = list(self.model.key_to_index.keys())
 
     def modify_sent(self, sent: str, p: float = 0.7) -> list[list[str]]:
-        """
-        :param str sent: text of sentence
+        """:param str sent: text of sentence
         :param float p: probability
         :rtype: List[List[str]]
         """
@@ -49,8 +47,7 @@ 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]]:
-        """
-        :param str sentence: text of sentence
+        """:param str sentence: text of sentence
         :param int n_sent: maximum number of synonymous sentences
         :param int p: probability
 

pythainlp/augment/word2vec/ltw2v.py

@@ -9,8 +9,7 @@
 
 
 class LTW2VAug:
-    """
-    Text Augment using word2vec from LTW2V
+    """Text Augment using word2vec from LTW2V
 
     LTW2V:
     `github.com/PyThaiNLP/large-thaiword2vec <https://github.com/PyThaiNLP/large-thaiword2vec>`_
@@ -21,23 +20,20 @@ def __init__(self):
         self.load_w2v()
 
     def tokenizer(self, text: str) -> list[str]:
-        """
-        :param str text: Thai text
+        """:param str text: Thai text
         :rtype: List[str]
         """
         return word_tokenize(text, engine="newmm")
 
     def load_w2v(self):  # insert substitute
-        """
-        Load LTW2V's word2vec model
+        """Load LTW2V's word2vec model
         """
         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]]:
-        """
-        Text Augment using word2vec from Thai2Fit
+        """Text Augment using word2vec from Thai2Fit
 
         :param str sentence: Thai sentence
         :param int n_sent: number of sentence