Merge pull request #1245 from PyThaiNLP/copilot/validate-example-code-docstrings

bact · web-flow · commit 7029234d0f93 · 2026-01-30T13:44:49.000Z
[WIP] Recheck example code for accuracy in PyThaiNLP
diff --git a/docs/notes/command_line.rst b/docs/notes/command_line.rst
@@ -26,7 +26,7 @@ You can use some `thainlp` functions directly from the command line.
 
 **Part-of-speech tagging**::
 
-    pythainlp tagg pos [-s SEPARATOR] TEXT
+    thainlp tag pos [-s SEPARATOR] TEXT
 
 *Example*::
 
diff --git a/examples/khavee.py b/examples/khavee.py
@@ -32,7 +32,7 @@
 print("ชิชะ", kv.check_karu_lahu("ชิชะ"))
 # lahu
 
-# การตรวจสอบกลอน 8 ที่ถูกฉันทลักษณ์
+# การตรวจสอบกลอน 8 ที่มีข้อผิดพลาดเล็กน้อย
 print(
     kv.check_klon(
         """ณรงค์วุฒิผู้เปี่ยมวุฒิสมสง่า มากวิชาหาความรู้ไปสู่ผล
@@ -48,7 +48,7 @@
         k_type=8,
     )
 )
-# -> The poem is correct according to the principle.
+# -> ["Can't find rhyme between paragraphs ('ผล', 'ทน') in paragraph 1"]
 
 # การตรวจสอบกลอน 8 ที่ผิดฉันทลักษณ์
 print(
@@ -67,6 +67,7 @@
     )
 )
 # -> [
+# "Can't find rhyme between paragraphs ('ผล', 'ทน') in paragraph 1",
 # "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"
 # ]
diff --git a/pythainlp/corpus/wordnet.py b/pythainlp/corpus/wordnet.py
@@ -53,7 +53,7 @@ def synsets(word: str, pos: Optional[str] = None, lang: str = "tha") -> list[wor
         [Synset('function.v.01'), Synset('work.v.02'),
          Synset('work.v.01'), Synset('work.v.08')]
         >>>
-        >>> synsets("บ้าน", lang="tha"))
+        >>> synsets("บ้าน", lang="tha")
         [Synset('duplex_house.n.01'), Synset('dwelling.n.01'),
          Synset('house.n.01'), Synset('family.n.01'), Synset('home.n.03'),
          Synset('base.n.14'), Synset('home.n.01'),
diff --git a/pythainlp/phayathaibert/core.py b/pythainlp/phayathaibert/core.py
@@ -39,7 +39,7 @@ def replace_url(self, text: str) -> str:
         :rtype: str
         :Example:
             >>> replace_url("go to https://github.com")
-            go to <url>
+            'go to <url>'
         """
         return re.sub(_PAT_URL, self._TK_URL, text)
 
@@ -50,7 +50,7 @@ def rm_brackets(self, text: str) -> str:
         :rtype: str
         :Example:
             >>> rm_brackets("hey() whats[;] up{*&} man(hey)")
-            hey whats up man(hey)
+            'hey whats up man(hey)'
         """
         # remove empty brackets
         new_line = re.sub(r"\(\)", "", text)
diff --git a/pythainlp/tag/_tag_perceptron.py b/pythainlp/tag/_tag_perceptron.py
@@ -108,7 +108,7 @@ class PerceptronTagger:
             [("นก", "N"), ("บิน", "V")],
         ]
     >>> tagger.train(data)
-    >>> tagger.tag(["นก", "เดิน])
+    >>> tagger.tag(["นก", "เดิน"])
     [('นก', 'N'), ('เดิน', 'V')]
 
     """
diff --git a/pythainlp/tag/named_entity.py b/pythainlp/tag/named_entity.py
@@ -84,7 +84,7 @@ def tag(
             >>> ner = NER("thainer")
             >>> ner.tag("ทดสอบ นายวรรณพงษ์ ภัททิยไพบูลย์")
             [('ทดสอบ', 'O'),
-            [(' ', 'O'),
+            (' ', 'O'),
             ('นาย', 'B-PERSON'),
             ('วรรณ', 'I-PERSON'),
             ('พงษ์', 'I-PERSON'),
diff --git a/pythainlp/tag/thainer.py b/pythainlp/tag/thainer.py
@@ -173,8 +173,7 @@ def get_ner(
             ('น.', 'I-TIME')]
             >>> ner.get_ner("วันที่ 15 ก.ย. 61 ทดสอบระบบเวลา 14:49 น.",
                             tag=True)
-            'วันที่ <DATE>15 ก.ย. 61</DATE> ทดสอบระบบเวลา <TIME>
-            14:49 น.</TIME>'
+            'วันที่ <DATE>15 ก.ย. 61</DATE> ทดสอบระบบเวลา <TIME>14:49 น.</TIME>'
         """
         tokens = word_tokenize(text, engine=_TOKENIZER_ENGINE)
         pos_tags = pos_tag(
diff --git a/pythainlp/ulmfit/core.py b/pythainlp/ulmfit/core.py
@@ -132,7 +132,7 @@ def process_thai(
         >>> from pythainlp.ulmfit import process_thai
         >>> text = "บ้านนนนน () อยู่นานนานนาน 😂🤣😃😄😅 PyThaiNLP amp;     "
         >>> process_thai(text)
-        [บ้าน', 'xxrep', '   ', 'อยู่', 'xxwrep', 'นาน', '😂', '🤣',
+        ['บ้าน', 'xxrep', '   ', 'อยู่', 'xxwrep', 'นาน', '😂', '🤣',
         '😃', '😄', '😅', 'pythainlp', '&']
 
         2. Modify pre_rules and post_rules arguments with
diff --git a/pythainlp/ulmfit/preprocess.py b/pythainlp/ulmfit/preprocess.py
@@ -32,7 +32,7 @@ def replace_url(text: str) -> str:
 
         >>> from pythainlp.ulmfit import replace_url
         >>> replace_url("go to github.com")
-        go to xxurl
+        'go to xxurl'
     """
     URL_PATTERN = r"""(?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)\b/?(?!@)))"""
     return re.sub(URL_PATTERN, _TK_URL, text)
@@ -50,7 +50,7 @@ def fix_html(text: str) -> str:
 
         >>> from pythainlp.ulmfit import fix_html
         >>> fix_html("Anbsp;amp;nbsp;B @.@ ")
-        A & B.
+        'A & B.'
     """
     re1 = re.compile(r"  +")
     text = (
diff --git a/pythainlp/word_vector/core.py b/pythainlp/word_vector/core.py
@@ -92,7 +92,7 @@ def doesnt_match(self, words: list[str]) -> str:
         >>> wv = WordVector()
         >>> words = ["อาหารเช้า", "อาหารเที่ยง", "อาหารเย็น", "พริกไทย"]
         >>> wv.doesnt_match(words)
-        พริกไทย
+        'พริกไทย'
 
         Pick the word "เรือ" (name of vehicle) out of the list of words
         related to occupation ("ดีไซน์เนอร์", "พนักงานเงินเดือน", "หมอ").
@@ -102,7 +102,7 @@ def doesnt_match(self, words: list[str]) -> str:
         >>> wv = WordVector()
         >>> words = ["ดีไซน์เนอร์", "พนักงานเงินเดือน", "หมอ", "เรือ"]
         >>> wv.doesnt_match(words)
-        เรือ
+        'เรือ'
         """
         return self.model.doesnt_match(words)
 

Original file line number	Diff line number	Diff line change
`@@ -32,7 +32,7 @@`
`32`	`32`	`print("ชิชะ", kv.check_karu_lahu("ชิชะ"))`
`33`	`33`	`# lahu`
`34`	`34`
`35`		`-# การตรวจสอบกลอน 8 ที่ถูกฉันทลักษณ์`
	`35`	`+# การตรวจสอบกลอน 8 ที่มีข้อผิดพลาดเล็กน้อย`
`36`	`36`	`print(`
`37`	`37`	`kv.check_klon(`
`38`	`38`	`"""ณรงค์วุฒิผู้เปี่ยมวุฒิสมสง่า มากวิชาหาความรู้ไปสู่ผล`
`@@ -48,7 +48,7 @@`
`48`	`48`	`k_type=8,`
`49`	`49`	`)`
`50`	`50`	`)`
`51`		`-# -> The poem is correct according to the principle.`
	`51`	`+# -> ["Can't find rhyme between paragraphs ('ผล', 'ทน') in paragraph 1"]`
`52`	`52`
`53`	`53`	`# การตรวจสอบกลอน 8 ที่ผิดฉันทลักษณ์`
`54`	`54`	`print(`
`@@ -67,6 +67,7 @@`
`67`	`67`	`)`
`68`	`68`	`)`
`69`	`69`	`# -> [`
	`70`	`+# "Can't find rhyme between paragraphs ('ผล', 'ทน') in paragraph 1",`
`70`	`71`	`# "Can't find rhyme between paragraphs ('สอน', 'ไป') in paragraph 4",`
`71`	`72`	`# "Can't find rhyme between paragraphs ('มี่', ['เกม', 'เอ่อ', 'เก่ง', 'กาจ']) in paragraph 5"`
`72`	`73`	`# ]`
Original file line number	Diff line number	Diff line change
`@@ -108,7 +108,7 @@ class PerceptronTagger:`
`108`	`108`	`[("นก", "N"), ("บิน", "V")],`
`109`	`109`	`]`
`110`	`110`	`>>> tagger.train(data)`
`111`		`- >>> tagger.tag(["นก", "เดิน])`
	`111`	`+ >>> tagger.tag(["นก", "เดิน"])`
`112`	`112`	`[('นก', 'N'), ('เดิน', 'V')]`
`113`	`113`
`114`	`114`	`"""`