Fix few lint issues

Author: bact

pythainlp/augment/word2vec/core.py

@@ -55,9 +55,9 @@ def augment(
         :return: list of synonyms
         :rtype: list[tuple[str, ...]]
         """
-        self.sentence = self.tokenizer(sentence)
-        self.list_synonym = self.modify_sent(self.sentence, p=p)
+        _sentence = self.tokenizer(sentence)
+        _list_synonym = self.modify_sent(_sentence, p=p)
         new_sentences = []
-        for x in list(itertools.product(*self.list_synonym))[0:n_sent]:
+        for x in list(itertools.product(*_list_synonym))[0:n_sent]:
             new_sentences.append(x)
         return new_sentences

pythainlp/corpus/common.py

@@ -8,7 +8,7 @@
 from __future__ import annotations
 
 import ast
-from typing import Any, Union
+from typing import Union
 
 __all__ = [
     "countries",

pythainlp/corpus/core.py

@@ -40,7 +40,7 @@ def json(self) -> dict:
         try:
             return json.loads(self._content.decode("utf-8"))
         except (json.JSONDecodeError, UnicodeDecodeError) as err:
-            raise ValueError(f"Failed to parse JSON response: {err}")
+            raise ValueError(f"Failed to parse JSON response: {err}") from err
 
 
 def get_corpus_db(url: str) -> Optional[_ResponseWrapper]:

pythainlp/tag/_tag_perceptron.py

@@ -203,9 +203,9 @@ def load(self, loc: str) -> None:
         try:
             with open(loc, encoding="utf-8-sig") as f:
                 w_td_c = json.load(f)
-        except OSError:
+        except OSError as ex:
             msg = "Missing trontagger.json file."
-            raise OSError(msg)
+            raise OSError(msg) from ex
         self.model.weights = w_td_c["weights"]
         self.tagdict = w_td_c["tagdict"]
         self.classes = w_td_c["classes"]

pythainlp/tokenize/core.py

@@ -30,7 +30,6 @@
 _RE_WORD_CHAR = re.compile(r"\w")
 
 
-
 def word_detokenize(
     segments: Union[list[list[str]], list[str]], output: str = "str"
 ) -> Union[list[str], str]:
@@ -483,16 +482,13 @@ def sent_tokenize(
     if not text or not isinstance(text, (str, list)):
         return []
 
-    is_list_input = isinstance(text, list)
-
-    if is_list_input:
+    if isinstance(text, list):
         try:
             original_text = "".join(text)
         except ValueError:
             return []
-
     else:
-        original_text = text
+        original_text = str(text)
 
     segments = []
 
@@ -501,13 +497,13 @@ def sent_tokenize(
 
         segments = segment(original_text)
 
-        if is_list_input:
+        if isinstance(text, list):
             word_indices = indices_words(text)
             result = map_indices_to_words(word_indices, [original_text])
             return result
     elif engine == "whitespace":
         segments = re.split(r" +", original_text, flags=re.U)
-        if is_list_input:
+        if isinstance(text, list):
             result = []
             _temp: list[str] = []
             for i, w in enumerate(text):
@@ -523,7 +519,7 @@ def sent_tokenize(
             return result
     elif engine == "whitespace+newline":
         segments = original_text.split()
-        if is_list_input:
+        if isinstance(text, list):
             result = []
             _temp = []
             for i, w in enumerate(text):
@@ -538,24 +534,22 @@ def sent_tokenize(
                     result.append(_temp)
             return result
     elif engine == "tltk":
-        from pythainlp.tokenize.tltk import sent_tokenize as segment
+        from pythainlp.tokenize.tltk import sent_tokenize as tltk_sent_tokenize
 
-        segments = segment(original_text)
+        segments = tltk_sent_tokenize(original_text)
     elif engine == "thaisum":
-        from pythainlp.tokenize.thaisumcut import (
-            ThaiSentenceSegmentor as segmentor,
-        )
+        from pythainlp.tokenize.thaisumcut import ThaiSentenceSegmentor
 
-        segment = segmentor()
-        segments = segment.split_into_sentences(original_text)
+        segmentor = ThaiSentenceSegmentor()
+        segments = segmentor.split_into_sentences(original_text)
     elif engine.startswith("wtp"):
         if "-" not in engine:
             _size = "mini"
         else:
             _size = engine.split("-")[-1]
-        from pythainlp.tokenize.wtsplit import tokenize as segment
+        from pythainlp.tokenize.wtsplit import tokenize
 
-        segments = segment(original_text, size=_size, tokenize="sentence")
+        segments = tokenize(text=original_text, size=_size, tokenize="sentence")
     else:
         raise ValueError(
             f"""Tokenizer \"{engine}\" not found.
@@ -565,7 +559,7 @@ def sent_tokenize(
     if not keep_whitespace:
         segments = strip_whitespace(segments)
 
-    if is_list_input and engine not in ["crfcut"]:
+    if isinstance(text, list) and engine not in ["crfcut"]:
         word_indices = indices_words(text)
         result = map_indices_to_words(word_indices, segments)
         return result
@@ -914,7 +908,7 @@ class Tokenizer:
 
     def __init__(
         self,
-        custom_dict: Union[Trie, Iterable[str], str] = [],
+        custom_dict: Union[Trie, Iterable[str], str, None] = None,
         engine: str = "newmm",
         keep_whitespace: bool = True,
         join_broken_num: bool = True,
@@ -937,10 +931,8 @@ def __init__(
         self.__engine = engine
         if self.__engine not in ["newmm", "mm", "longest", "deepcut"]:
             raise NotImplementedError(
-                """
-                The Tokenizer class is not support %s for custom tokenizer
-                """
-                % self.__engine
+                "The Tokenizer class does not support "
+                f"{self.__engine} for custom tokenizer."
             )
         self.__keep_whitespace = keep_whitespace
         self.__join_broken_num = join_broken_num

pythainlp/tokenize/longest.py

@@ -52,6 +52,8 @@ def __init__(self, trie: Trie):
     @staticmethod
     def __search_nonthai(text: str) -> Optional[str]:
         match = _RE_NONTHAI.search(text)
+        if not match:
+            return None
         if match.group(0):
             return match.group(0).lower()
         return None

pythainlp/util/date.py

@@ -26,12 +26,7 @@
 
 import re
 from datetime import datetime, timedelta
-
-try:
-    from zoneinfo import ZoneInfo
-except ImportError:
-    from backports.zoneinfo import ZoneInfo  # type: ignore[no-redef]
-
+from zoneinfo import ZoneInfo
 
 thai_abbr_weekdays = ["จ", "อ", "พ", "พฤ", "ศ", "ส", "อา"]
 thai_full_weekdays = [
@@ -290,19 +285,19 @@ def thai_strptime(
     y_matches = re.findall(fmt, text)
 
     data = {i: "".join(list(j)) for i, j in zip(keys, y_matches[0])}
-    H: Union[int, str] = 0
-    M: Union[int, str] = 0
-    S: Union[int, str] = 0
+    hour: Union[int, str] = 0
+    minute: Union[int, str] = 0
+    second: Union[int, str] = 0
     f: Union[int, str] = 0
     d = data["d"]
     m = _find_month(data["B"])
     y = data["Y"]
     if "H" in keys:
-        H = data["H"]
+        hour = data["H"]
     if "M" in keys:
-        M = data["M"]
+        minute = data["M"]
     if "S" in keys:
-        S = data["S"]
+        second = data["S"]
     if "f" in keys:
         f = data["f"]
     if int(y) < 100 and year == "be":
@@ -321,9 +316,9 @@ def thai_strptime(
         year=int(y),
         month=int(m),
         day=int(d),
-        hour=int(H),
-        minute=int(M),
-        second=int(S),
+        hour=int(hour),
+        minute=int(minute),
+        second=int(second),
         microsecond=int(f),
         tzinfo=tzinfo,
     )
@@ -376,6 +371,7 @@ def reign_year_to_ad(reign_year: int, reign: int) -> int:
             reign_year_to_ad(1, 9))
         # output: The 4th reign year of the King Rama X is in 1946
     """
+    ad = 0
     if int(reign) == 10:
         ad = int(reign_year) + 2015
     elif int(reign) == 9: