Use map/filter with built-in functions for performance

pythainlp/soundex/prayut_and_somchaip.py

@@ -89,5 +89,5 @@ def prayut_and_somchaip(text: str, length: int = 4) -> str:
         else:
             chars[i] = None  # type: ignore[call-overload]
         i += 1
-    chars = list("".join([i for i in chars if i is not None]))
+    chars = list("".join(filter(None, chars)))
     return "".join(chars[-length:])

pythainlp/spell/words_spelling_correction.py

@@ -236,7 +236,7 @@ def __init__(self):
                 self.model_name, "list_word-spelling-correction-char2vec.txt"
             )
         ) as f:
-            self.list_word = [i.strip() for i in f.readlines()]
+            self.list_word = list(map(str.strip, f.readlines()))
         super().__init__(self.model_path, self.model_onnx, self.list_word)
 
 

pythainlp/tokenize/thaisumcut.py

@@ -77,7 +77,7 @@ def middle_cut(sentences: list[str]) -> list[str]:
     # Split all result parts by <stop> and filter
     all_sentences = (s.strip() for part in result_parts for s in part.split("<stop>"))
 
-    return [s for s in all_sentences if s]
+    return list(filter(None, all_sentences))
 
 
 class ThaiSentenceSegmentor:
@@ -358,9 +358,7 @@ def split_into_sentences(self, text: str, isMiddleCut: bool = False) -> list[str
         text = text.replace("!", "!<stop>")
         text = text.replace("<prd>", ".")
         sentences = text.split("<stop>")
-        sentences = [s.strip() for s in sentences]
-        if "" in sentences:
-            sentences.remove("")
+        sentences = list(map(str.strip, sentences))
         if "nan" in sentences:
             sentences.remove("nan")
 

pythainlp/ulmfit/preprocess.py

@@ -142,7 +142,7 @@ def replace_wrep_post(toks: Collection[str]) -> list[str]:
         else:
             res.append(previous_word)
         previous_word = current_word
-    return [x for x in res[1:] if x is not None]
+    return list(filter(None, res[1:]))
 
 
 def rm_useless_newlines(text: str) -> str:
@@ -201,7 +201,7 @@ def lowercase_all(toks: Collection[str]) -> list[str]:
     """Lowercase all English words;
     English words in Thai texts don't usually have nuances of capitalization.
     """
-    return [tok.lower() for tok in toks]
+    return list(map(str.lower, toks))
 
 
 def replace_rep_nonum(text: str) -> str:
@@ -264,7 +264,7 @@ def replace_wrep_post_nonum(toks: Collection[str]) -> list[str]:
         else:
             res.append(previous_word)
         previous_word = current_word
-    return [x for x in res[1:] if x is not None]
+    return list(filter(None, res[1:]))
 
 
 def remove_space(toks: Collection[str]) -> list[str]:

pythainlp/util/date.py

@@ -88,7 +88,7 @@
 dates_list = (
     "("
     + "|".join(
-        [str(i) for i in range(32, 0, -1)]
+        list(map(str, range(32, 0, -1)))
         + ["0" + str(i) for i in range(1, 10)]
     )
     + ")"

pythainlp/util/normalize.py

@@ -346,7 +346,7 @@ def expand_maiyamok(sent: Union[str, list[str]]) -> list[str]:
     temp_toks: list[str] = []
     for token in sent:
         toks = re_yamok.split(token)
-        toks = [tok for tok in toks if tok]  # remove empty string ("")
+        toks = list(filter(None, toks))  # remove empty string ("")
         temp_toks.extend(toks)
     sent = temp_toks
     del temp_toks