Modernize to Python 3.9: type hints with future annotations, exception handling, and code quality

pyproject.toml

@@ -5,7 +5,7 @@
 [tool.ruff]
 line-length = 79
 indent-width = 4
-target-version = "py310"
+target-version = "py39"
 
 [tool.ruff.format]
 quote-style = "double"

pythainlp/__init__.py

@@ -1,64 +1,63 @@
-# -*- coding: utf-8 -*-
-# SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
-# SPDX-FileType: SOURCE
-# SPDX-License-Identifier: Apache-2.0
-__version__ = "5.2.0"
-
-thai_consonants = "กขฃคฅฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรลวศษสหฬอฮ"  # 44 chars
-
-thai_vowels = (
-    "\u0e24\u0e26\u0e30\u0e31\u0e32\u0e33\u0e34\u0e35\u0e36\u0e37"
-    + "\u0e38\u0e39\u0e40\u0e41\u0e42\u0e43\u0e44\u0e45\u0e4d\u0e47"
-)  # 20
-thai_lead_vowels = "\u0e40\u0e41\u0e42\u0e43\u0e44"  # 5
-thai_follow_vowels = "\u0e30\u0e32\u0e33\u0e45"  # 4
-thai_above_vowels = "\u0e31\u0e34\u0e35\u0e36\u0e37\u0e4d\u0e47"  # 7
-thai_below_vowels = "\u0e38\u0e39"  # 2
-
-thai_tonemarks = "\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_consonants, thai_vowels, thai_tonemarks, thai_signs]
-)  # 74
-
-# Fongman, Angkhankhu, Khomut:
-# These characters are section markers
-thai_punctuations = "\u0e4f\u0e5a\u0e5b"  # 3 chars
-
-thai_digits = "๐๑๒๓๔๕๖๗๘๙"  # 10
-thai_symbols = "\u0e3f"  # Thai Bath ฿
-
-# All Thai characters that are presented in Unicode
-thai_characters = "".join(
-    [thai_letters, thai_punctuations, thai_digits, thai_symbols]
-)
-# Thai pangram by Sungsit Sawaiwan
-# CC BY-SA License
-# Source: https://fontuni.com/articles/2015-07-12-thai-poetgram.html
-thai_pangram = """กีฬาบังลังก์ ฿๑,๒๓๔,๕๖๗,๘๙๐
-๏ จับฅอคนบั่นต้อง 	อาญา
-ขุดฆ่าโคตรฃัตติยา 	ซ่านม้วย
-ธรรมฤๅผ่อนรักษา 	ใจชั่ว โฉดแฮ
-สืบอยู่เต็มศึกด้วย 	ฝุ่นฟ้ากีฬา กามฦๅ ฯ
-๏ กตัญญูไป่พร้อม 	ปฐมฌาน
-เกมส๎วัฒน์ปฏิภาณ 	ห่อนล้ำ
-ทฤษฎีถ่อยๆ สังหาร 	เกณฑ์โทษ
-โกรธจี๊ดจ๋อยจ่มถ้ำ 	อยู่เฝ้า “อตฺตา” ๚ะ๛
-๑๒ กรกฎาคม ๒๕๕๘"""
-
-from pythainlp.soundex import soundex
-from pythainlp.spell import correct, spell
-from pythainlp.tag import pos_tag
-from pythainlp.tokenize import (
-    Tokenizer,
-    sent_tokenize,
-    subword_tokenize,
-    word_tokenize,
-)
-from pythainlp.transliterate import romanize, transliterate
-from pythainlp.util import collate, thai_strftime
+# SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
+# SPDX-FileType: SOURCE
+# SPDX-License-Identifier: Apache-2.0
+__version__ = "5.2.0"
+
+thai_consonants = "กขฃคฅฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรลวศษสหฬอฮ"  # 44 chars
+
+thai_vowels = (
+    "\u0e24\u0e26\u0e30\u0e31\u0e32\u0e33\u0e34\u0e35\u0e36\u0e37"
+    + "\u0e38\u0e39\u0e40\u0e41\u0e42\u0e43\u0e44\u0e45\u0e4d\u0e47"
+)  # 20
+thai_lead_vowels = "\u0e40\u0e41\u0e42\u0e43\u0e44"  # 5
+thai_follow_vowels = "\u0e30\u0e32\u0e33\u0e45"  # 4
+thai_above_vowels = "\u0e31\u0e34\u0e35\u0e36\u0e37\u0e4d\u0e47"  # 7
+thai_below_vowels = "\u0e38\u0e39"  # 2
+
+thai_tonemarks = "\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_consonants, thai_vowels, thai_tonemarks, thai_signs]
+)  # 74
+
+# Fongman, Angkhankhu, Khomut:
+# These characters are section markers
+thai_punctuations = "\u0e4f\u0e5a\u0e5b"  # 3 chars
+
+thai_digits = "๐๑๒๓๔๕๖๗๘๙"  # 10
+thai_symbols = "\u0e3f"  # Thai Bath ฿
+
+# All Thai characters that are presented in Unicode
+thai_characters = "".join(
+    [thai_letters, thai_punctuations, thai_digits, thai_symbols]
+)
+# Thai pangram by Sungsit Sawaiwan
+# CC BY-SA License
+# Source: https://fontuni.com/articles/2015-07-12-thai-poetgram.html
+thai_pangram = """กีฬาบังลังก์ ฿๑,๒๓๔,๕๖๗,๘๙๐
+๏ จับฅอคนบั่นต้อง 	อาญา
+ขุดฆ่าโคตรฃัตติยา 	ซ่านม้วย
+ธรรมฤๅผ่อนรักษา 	ใจชั่ว โฉดแฮ
+สืบอยู่เต็มศึกด้วย 	ฝุ่นฟ้ากีฬา กามฦๅ ฯ
+๏ กตัญญูไป่พร้อม 	ปฐมฌาน
+เกมส๎วัฒน์ปฏิภาณ 	ห่อนล้ำ
+ทฤษฎีถ่อยๆ สังหาร 	เกณฑ์โทษ
+โกรธจี๊ดจ๋อยจ่มถ้ำ 	อยู่เฝ้า “อตฺตา” ๚ะ๛
+๑๒ กรกฎาคม ๒๕๕๘"""
+
+from pythainlp.soundex import soundex
+from pythainlp.spell import correct, spell
+from pythainlp.tag import pos_tag
+from pythainlp.tokenize import (
+    Tokenizer,
+    sent_tokenize,
+    subword_tokenize,
+    word_tokenize,
+)
+from pythainlp.transliterate import romanize, transliterate
+from pythainlp.util import collate, thai_strftime

pythainlp/__main__.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0

pythainlp/ancient/__init__.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0

pythainlp/ancient/aksonhan.py

@@ -1,7 +1,7 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
+from __future__ import annotations
 
 from pythainlp import thai_consonants, thai_tonemarks
 from pythainlp.corpus import thai_orst_words

pythainlp/ancient/currency.py

@@ -1,7 +1,8 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
+from __future__ import annotations
+
 
 def convert_currency(value: float, from_unit: str) -> dict:
     """
@@ -44,14 +45,14 @@ def convert_currency(value: float, from_unit: str) -> dict:
         # }
     """
     conversion_factors_to_att = {
-        'เบี้ย': 1,
-        'อัฐ': 100,  # 1 อัฐ = 100 เบี้ย
-        'ไพ': 2 * 100,  # 1 ไพ = 2 อัฐ
-        'เฟื้อง': 4 * 2 * 100,  # 1 เฟื้อง = 4 ไพ
-        'สลึง': 2 * 4 * 2 * 100,  # 1 สลึง = 2 เฟื้อง
-        'บาท': 4 * 2 * 4 * 2 * 100,  # 1 บาท = 4 สลึง
-        'ตำลึง': 4 * 4 * 2 * 4 * 2 * 100,  # 1 ตำลึง = 4 บาท
-        'ชั่ง': 20 * 4 * 4 * 2 * 4 * 2 * 100,  # 1 ชั่ง = 20 ตำลึง
+        "เบี้ย": 1,
+        "อัฐ": 100,  # 1 อัฐ = 100 เบี้ย
+        "ไพ": 2 * 100,  # 1 ไพ = 2 อัฐ
+        "เฟื้อง": 4 * 2 * 100,  # 1 เฟื้อง = 4 ไพ
+        "สลึง": 2 * 4 * 2 * 100,  # 1 สลึง = 2 เฟื้อง
+        "บาท": 4 * 2 * 4 * 2 * 100,  # 1 บาท = 4 สลึง
+        "ตำลึง": 4 * 4 * 2 * 4 * 2 * 100,  # 1 ตำลึง = 4 บาท
+        "ชั่ง": 20 * 4 * 4 * 2 * 4 * 2 * 100,  # 1 ชั่ง = 20 ตำลึง
     }
 
     if from_unit not in conversion_factors_to_att:

pythainlp/augment/__init__.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0

pythainlp/augment/lm/__init__.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0

pythainlp/augment/lm/fasttext.py

@@ -1,9 +1,9 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
+from __future__ import annotations
+
 import itertools
-from typing import List, Tuple
 
 from gensim.models.fasttext import FastText as FastText_gensim
 from gensim.models.keyedvectors import KeyedVectors
@@ -30,7 +30,7 @@ def __init__(self, model_path: str):
             self.model = FastText_gensim.load(model_path)
         self.dict_wv = list(self.model.key_to_index.keys())
 
-    def tokenize(self, text: str) -> List[str]:
+    def tokenize(self, text: str) -> list[str]:
         """
         Thai text tokenization for fastText
 
@@ -41,7 +41,7 @@ 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]]:
+    def modify_sent(self, sent: str, p: float = 0.7) -> list[list[str]]:
         """
         :param str sent: text of sentence
         :param float p: probability
@@ -61,7 +61,7 @@ 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
 

pythainlp/augment/lm/phayathaibert.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
+from __future__ import annotations
 
 import random
 import re
-from typing import List
 
 from pythainlp.phayathaibert.core import ThaiTextProcessor
 
@@ -57,7 +56,7 @@ def generate(
 
     def augment(
         self, text: str, num_augs: int = 3, sample: bool = False
-    ) -> List[str]:
+    ) -> list[str]:
         """
         Text augmentation from PhayaThaiBERT
 

pythainlp/augment/lm/wangchanberta.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-
-from typing import List
+from __future__ import annotations
 
 from transformers import (
     CamembertTokenizer,
@@ -52,7 +50,7 @@ def generate(self, sentence: str, num_replace_tokens: int = 3):
             masked_text = self.input_text
         return self.sent2
 
-    def augment(self, sentence: str, num_replace_tokens: int = 3) -> List[str]:
+    def augment(self, sentence: str, num_replace_tokens: int = 3) -> list[str]:
         """
         Text augmentation from WangchanBERTa
 

pythainlp/augment/word2vec/__init__.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0

pythainlp/augment/word2vec/bpemb_wv.py

@@ -1,8 +1,7 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-from typing import List, Tuple
+from __future__ import annotations
 
 from pythainlp.augment.word2vec.core import Word2VecAug
 
@@ -22,7 +21,7 @@ def __init__(self, lang: str = "th", vs: int = 100000, dim: int = 300):
         self.model = self.bpemb_temp.emb
         self.load_w2v()
 
-    def tokenizer(self, text: str) -> List[str]:
+    def tokenizer(self, text: str) -> list[str]:
         """
         :param str text: Thai text
         :rtype: List[str]
@@ -39,7 +38,7 @@ def load_w2v(self):
 
     def augment(
         self, sentence: str, n_sent: int = 1, p: float = 0.7
-    ) -> List[Tuple[str]]:
+    ) -> list[tuple[str]]:
         """
         Text Augment using word2vec from BPEmb
 

pythainlp/augment/word2vec/core.py

@@ -1,9 +1,9 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
+from __future__ import annotations
+
 import itertools
-from typing import List, Tuple
 
 
 class Word2VecAug:
@@ -28,7 +28,7 @@ def __init__(
             self.model = model
         self.dict_wv = list(self.model.key_to_index.keys())
 
-    def modify_sent(self, sent: str, p: float = 0.7) -> List[List[str]]:
+    def modify_sent(self, sent: str, p: float = 0.7) -> list[list[str]]:
         """
         :param str sent: text of sentence
         :param float p: probability
@@ -48,7 +48,7 @@ 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]]:
         """
         :param str sentence: text of sentence
         :param int n_sent: maximum number of synonymous sentences

pythainlp/augment/word2vec/ltw2v.py

@@ -1,8 +1,7 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-from typing import List, Tuple
+from __future__ import annotations
 
 from pythainlp.augment.word2vec.core import Word2VecAug
 from pythainlp.corpus import get_corpus_path
@@ -21,7 +20,7 @@ def __init__(self):
         self.ltw2v_wv = get_corpus_path("ltw2v")
         self.load_w2v()
 
-    def tokenizer(self, text: str) -> List[str]:
+    def tokenizer(self, text: str) -> list[str]:
         """
         :param str text: Thai text
         :rtype: List[str]
@@ -36,7 +35,7 @@ def load_w2v(self):  # insert substitute
 
     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
 

pythainlp/augment/word2vec/thai2fit.py

@@ -1,8 +1,7 @@
-# -*- coding: utf-8 -*-
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-from typing import List, Tuple
+from __future__ import annotations
 
 from pythainlp.augment.word2vec.core import Word2VecAug
 from pythainlp.corpus import get_corpus_path
@@ -21,7 +20,7 @@ def __init__(self):
         self.thai2fit_wv = get_corpus_path("thai2fit_wv")
         self.load_w2v()
 
-    def tokenizer(self, text: str) -> List[str]:
+    def tokenizer(self, text: str) -> list[str]:
         """
         :param str text: Thai text
         :rtype: List[str]
@@ -37,7 +36,7 @@ def load_w2v(self):
 
     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