Merge pull request #1266 from PyThaiNLP/copilot/add-type-hints-to-submodules-one-more-time

Add type hints and update docstrings for compact test suite modules

Author: bact

pythainlp/classify/param_free.py

@@ -41,9 +41,11 @@ def train(self):
         return temp_list
 
     def predict(self, x1: str, k: int = 1) -> str:
-        """:param str x1: the text that we want to predict label for.
-        :param str k: k
-        :return: label
+        """Predict the label for the given text.
+
+        :param str x1: the text that we want to predict label for
+        :param int k: number of nearest neighbors to consider (default: 1)
+        :return: predicted label
         :rtype: str
 
         :Example:
@@ -80,7 +82,7 @@ def predict(self, x1: str, k: int = 1) -> str:
         sorted_idx = np.argsort(np.array(disance_from_x1))
         top_k_class = self.training_data[sorted_idx[:k], 1]
         _, counts = np.unique(top_k_class, return_counts=True)
-        predict_class = top_k_class[counts.argmax()]
+        predict_class = str(top_k_class[counts.argmax()])
 
         return predict_class
 

pythainlp/transliterate/pyicu.py

@@ -18,7 +18,9 @@
 
 def transliterate(text: str) -> str:
     """Use ICU (International Components for Unicode) for transliteration
-    :param str text: Thai text to be transliterated.
-    :return: A string of Internaitonal Phonetic Alphabets indicating how the text should be pronounced.
+
+    :param str text: Thai text to be transliterated
+    :return: A string of International Phonetic Alphabets indicating how the text should be pronounced
+    :rtype: str
     """
-    return _ICU_THAI_TO_LATIN.transliterate(text)
+    return str(_ICU_THAI_TO_LATIN.transliterate(text))

pythainlp/util/spell_words.py

@@ -5,6 +5,7 @@
 
 import re
 from functools import lru_cache
+from typing import Optional
 
 from pythainlp import (
     thai_above_vowels,
@@ -24,8 +25,12 @@
     for i, j in zip(list(thai_tonemarks), ["เอก", "โท", "ตรี", "จัตวา"])
 }
 
-rule1: list[str] = [i.replace("-", f"([{thai_letters}](thai_tonemarks)?)") for i in _r1]
-rule2: list[str] = [i.replace("–", f"([{thai_letters}])").replace(":", "") for i in _r2]
+rule1: list[str] = [
+    i.replace("-", f"([{thai_letters}](thai_tonemarks)?)") for i in _r1
+]
+rule2: list[str] = [
+    i.replace("–", f"([{thai_letters}])").replace(":", "") for i in _r2
+]
 rule3: list[str] = [
     i.replace("–", f"([{thai_letters}])").replace(":", f"([{thai_tonemarks}])")
     for i in _r2
@@ -108,12 +113,12 @@ def spell_syllable(text: str) -> list[str]:
     return c_only + v_only + t_only + [text]
 
 
-def spell_word(text: str) -> list[str]:
+def spell_word(text: Optional[str]) -> list[str]:
     """Spell out words in Thai word distribution form.
 
-    :param str w: Thai words only
-    :return: List of spelled out words
-    :rtype: List[str]
+    :param Optional[str] text: Thai words only, or None
+    :return: List of spelled out words, empty list if text is None or empty
+    :rtype: list[str]
 
     :Example:
     ::
@@ -122,7 +127,13 @@ def spell_word(text: str) -> list[str]:
 
         print(spell_word("คนดี"))
         # output: ['คอ', 'นอ', 'คน', 'ดอ', 'อี', 'ดี', 'คนดี']
+
+        print(spell_word(None))
+        # output: []
     """
+    if not text:
+        return []
+
     spellouts = []
     tokens = subword_tokenize(text, engine="han_solo")
 

pythainlp/util/thai.py

@@ -1,13 +1,13 @@
 # SPDX-FileCopyrightText: 2016-2026 PyThaiNLP Project
 # SPDX-FileType: SOURCE
 # SPDX-License-Identifier: Apache-2.0
-"""Check if it is Thai text
-"""
+"""Check if it is Thai text"""
 
 from __future__ import annotations
 
 import string
 from collections import defaultdict
+from typing import Optional
 
 from pythainlp import (
     thai_above_vowels,
@@ -215,16 +215,17 @@ def display_thai_char(ch: str) -> str:
         return ch
 
 
-def thai_word_tone_detector(word: str) -> list[tuple[str, str]]:
+def thai_word_tone_detector(word: Optional[str]) -> list[tuple[str, str]]:
     """Thai tone detector for word.
 
     It uses pythainlp.transliterate.pronunciate for converting word to\
         pronunciation.
 
-    :param str word: Thai word.
-    :return: Thai pronunciation with tones in each syllable.\
-        (l, m, h, r, f or empty if it cannot be detected)
-    :rtype: Tuple[str, str]
+    :param Optional[str] word: Thai word, or None
+    :return: List of tuples containing Thai pronunciation with tones in each syllable.\
+        Tone values: l (low), m (mid), h (high), r (rising), f (falling), or empty if it cannot be detected.\
+        Returns [] if word is None or empty.
+    :rtype: list[tuple[str, str]]
 
     :Example:
     ::
@@ -236,7 +237,13 @@ def thai_word_tone_detector(word: str) -> list[tuple[str, str]]:
 
         print(thai_word_tone_detector("มือถือ"))
         # output: [('มือ', 'm'), ('ถือ', 'r')]
+
+        print(thai_word_tone_detector(None))
+        # output: []
     """
+    if not word:
+        return []
+
     from ..transliterate import pronunciate
     from ..util.syllable import tone_detector
 

tests/compact/testc_util.py

@@ -33,5 +33,5 @@ def test_thai_word_tone_detector(self):
             thai_word_tone_detector("ราคา"), [("รา", "m"), ("คา", "m")]
         )
         # Edge cases: None and empty string
-        self.assertEqual(thai_word_tone_detector(None), [("", "")])
-        self.assertEqual(thai_word_tone_detector(""), [("", "")])
+        self.assertEqual(thai_word_tone_detector(None), [])
+        self.assertEqual(thai_word_tone_detector(""), [])