Merge pull request #1264 from PyThaiNLP/copilot/add-type-hints-to-submodules-yet-again

Add type hints to core modules (stdlib-only)

Author: bact

pythainlp/generate/core.py

@@ -88,7 +88,7 @@ def _next_word(
         output_str: bool,
         prob: float,
         duplicate: bool = False,
-    ):
+    ) -> Union[list[str], str]:
         words = []
         words.append(text)
         word_list = list(self._word_prob.keys())
@@ -230,7 +230,7 @@ def prob(self, t1: str, t2: str, t3: str) -> float:
 
     def gen_sentence(
         self,
-        start_seq: str = "",
+        start_seq: Union[str, tuple[str, str]] = "",
         N: int = 4,
         prob: float = 0.001,
         output_str: bool = True,
@@ -254,14 +254,15 @@ def gen_sentence(
             gen.gen_sentence()
             # output: 'ยังทำตัวเป็นเซิร์ฟเวอร์คือ'
         """
+        late_word: Union[str, tuple[str, str]]
         if not start_seq:
             # Non-cryptographic use, pseudo-random generator is acceptable here
             start_seq = random.choice(self.bi_keys)  # noqa: S311
         late_word = start_seq
-        list_word = []
+        list_word: list[Union[str, tuple[str, str]]] = []
         list_word.append(start_seq)
 
-        for i in range(N):
+        for _ in range(N):
             if duplicate:
                 temp = [j for j in self.ti_keys if j[:2] == late_word]
             else:
@@ -279,11 +280,14 @@ def gen_sentence(
             late_word = items[1:]
             list_word.append(late_word)
 
-        listdata = []
-        for i in list_word:
-            for j in i:
-                if j not in listdata:
-                    listdata.append(j)
+        listdata: list[str] = []
+        for item in list_word:
+            if isinstance(item, tuple):
+                for j in item:
+                    if j not in listdata:
+                        listdata.append(j)
+            elif isinstance(item, str) and item not in listdata:
+                listdata.append(item)
 
         if output_str:
             return "".join(listdata)

pythainlp/generate/thai2fit.py

@@ -136,9 +136,10 @@ def gen_sentence(
     if not start_seq:
         # Non-cryptographic use, pseudo-random generator is acceptable here
         start_seq = random.choice(list(thwiki_itos))  # noqa: S311
-    list_word = learn.predict(
+    predicted_text: str = learn.predict(
         start_seq, N, temperature=0.8, min_p=prob, sep="-*-"
-    ).split("-*-")
+    )
+    list_word = predicted_text.split("-*-")
 
     if output_str:
         return "".join(list_word)

pythainlp/khavee/core.py

@@ -4,7 +4,7 @@
 # ruff: noqa: C901
 from __future__ import annotations
 
-from typing import List, Union
+from typing import Union
 
 from pythainlp import thai_consonants
 from pythainlp.tokenize import subword_tokenize
@@ -383,7 +383,7 @@ def check_karu_lahu(self, text):
         else:
             return "lahu"
 
-    def check_klon(self, text: str, k_type: int = 8) -> Union[List[str], str]:
+    def check_klon(self, text: str, k_type: int = 8) -> Union[list[str], str]:
         """
         Check the suitability of the poem according to Thai principles.
 
@@ -627,8 +627,8 @@ def check_klon(self, text: str, k_type: int = 8) -> Union[List[str], str]:
             return "Something went wrong. Make sure you enter it in the correct form."
 
     def check_aek_too(
-        self, text: Union[List[str], str], dead_syllable_as_aek: bool = False
-    ) -> Union[List[bool], List[str], bool, str]:
+        self, text: Union[list[str], str], dead_syllable_as_aek: bool = False
+    ) -> Union[list[Union[bool, str]], bool, str]:
         """
         Checker of Thai tonal words
 
@@ -657,7 +657,7 @@ def check_aek_too(
             # -> [False, 'aek', 'too']
         """
         if isinstance(text, list):
-            return [self.check_aek_too(t, dead_syllable_as_aek) for t in text]
+            return [self.check_aek_too(t, dead_syllable_as_aek) for t in text]  # type: ignore[misc]
 
         if not isinstance(text, str):
             raise TypeError("text must be str or iterable list[str]")

pythainlp/soundex/sound.py

@@ -71,7 +71,7 @@ def audio_vector(word: str) -> list[list[int]]:
         audio_vector("น้ำ")
         # output : [[-1, 1, 1, -1, -1, -1, ...]]
     """
-    return _ft.word_to_vector_list(word2audio(word), numeric=True)
+    return _ft.word_to_vector_list(word2audio(word), numeric=True)  # type: ignore[no-any-return]
 
 
 def word_approximation(word: str, list_word: list[str]) -> list[float]:

pythainlp/util/abbreviation.py

@@ -45,4 +45,4 @@ def abbreviation_to_full_text(
             pip install pythainlp[abbreviation].
             """
         )
-    return _replace(text, top_k=top_k)
+    return _replace(text, top_k=top_k)  # type: ignore[no-any-return]

pythainlp/util/keyboard.py

@@ -220,7 +220,7 @@ def get_char_coord(
 
     coord1 = get_char_coord(c1)
     coord2 = get_char_coord(c2)
-    distance = (
+    distance: float = (
         (coord1[0] - coord2[0]) ** 2 + (coord1[1] - coord2[1]) ** 2
     ) ** (0.5)
     if distance == 0 and c1 != c2:

pythainlp/util/numtoword.py

@@ -10,6 +10,8 @@
 
 from __future__ import annotations
 
+from typing import Optional
+
 __all__ = ["bahttext", "num_to_thaiword"]
 
 _VALUES = [
@@ -77,7 +79,7 @@ def bahttext(number: float) -> str:
     return ret
 
 
-def num_to_thaiword(number: int) -> str:
+def num_to_thaiword(number: Optional[int]) -> str:
     """Converts a number to Thai text.
 
     :param int number: an integer number to be converted to Thai text
@@ -95,11 +97,12 @@ def num_to_thaiword(number: int) -> str:
         num_to_thaiword(11)
         # output: สิบเอ็ด
     """
-    output = ""
-    number_temp = number
     if number is None:
         return ""
-    elif number == 0:
+
+    output = ""
+    number_temp = number
+    if number == 0:
         output = "ศูนย์"
 
     number_str = str(abs(number))

pythainlp/util/time.py

@@ -314,7 +314,7 @@ def thaiword_to_time(text: str, padding: bool = True) -> str:
     text += ":"
 
     # determine minute
-    if minute:
+    if minute and isinstance(minute, list):
         n = 0
         for affix in minute:
             if affix in keys_dict: