Merge pull request #1238 from PyThaiNLP/copilot/check-docs-comments-code

Fix spelling errors in comments and docstrings

Author: bact

examples/khavee.py

@@ -67,8 +67,8 @@
     )
 )
 # -> [
-# "Cant find rhyme between paragraphs ('สอน', 'ไป') in paragraph 4",
-# "Cant find rhyme between paragraphs ('มี่', ['เกม', 'เอ่อ', 'เก่ง', 'กาจ']) in paragraph 5"
+# "Can't find rhyme between paragraphs ('สอน', 'ไป') in paragraph 4",
+# "Can't find rhyme between paragraphs ('มี่', ['เกม', 'เอ่อ', 'เก่ง', 'กาจ']) in paragraph 5"
 # ]
 
 
@@ -95,8 +95,8 @@
     )
 )
 # -> [
-# "Cant find rhyme between paragraphs ('หมา', 'จอง') in paragraph 2",
-# "Cant find rhyme between paragraphs ('หมา', 'ทอง') in paragraph 2"
+# "Can't find rhyme between paragraphs ('หมา', 'จอง') in paragraph 2",
+# "Can't find rhyme between paragraphs ('หมา', 'ทอง') in paragraph 2"
 # ]
 
 # การเช็คคำเอกโท

pythainlp/khavee/core.py

@@ -314,7 +314,7 @@ def check_marttra(self, word: str) -> str:
             if "็" in word:
                 return "กา"
             else:
-                return "Cant find Marttra in this word"
+                return "Can't find Marttra in this word"
 
     def is_sumpus(self, word1: str, word2: str) -> bool:
         """

pythainlp/transliterate/core.py

@@ -22,7 +22,7 @@ def romanize(
 
     :param str text: A Thai word to be romanized. \
         The input should not include whitespace because \
-        the function is support subwords by spliting whitespace.
+        the function is support subwords by splitting whitespace.
     :param str engine: One of 'royin' (default), 'thai2rom', 'thai2rom_onnx,
         'tltk', and 'lookup'. See more in options for engine section.
     :param str fallback_engine: If engine equals 'lookup',

pythainlp/transliterate/iso_11940.py

@@ -98,7 +98,7 @@
 
 _punctuation_and_digits = {
     # ฯ can has two meanings in ISO 11940.
-    # If it is for abbrevation, it is paiyan noi.
+    # If it is for abbreviation, it is paiyan noi.
     # If it is for sentence termination, it is angkhan diao.
     # Without semantic analysis, they cannot be distinguished from each other.
     # In this simple implementation, we decided to always treat ฯ as paiyan noi.

pythainlp/util/remove_trailing_repeat_consonants.py

@@ -79,7 +79,7 @@ def remove_trailing_repeat_consonants(
     if has_dictionary_updated:
         _update_consonant_repeaters(custom_dict)
 
-    # seperate by newline
+    # separate by newline
     modified_lines = []
     for line in text.split("\n"):
         segments = line.split(" ")
@@ -144,7 +144,7 @@ def _remove_repeat_trailing_consonants_from_segment(segment: str) -> str:
         # the chance is that the correct is one character,
         # or it's not in the dictionary.
 
-        # make the repition to once
+        # make the repetition to once
         segment = segment_head + (dup * 1)
 
     return segment