Skip to content

Fix KeyError when transliterating text containing obsolete Thai letter ฅ #1187

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bact merged 2 commits into from
Jan 11, 2026
Merged

Fix KeyError when transliterating text containing obsolete Thai letter ฅ #1187

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
52942dc
Initial plan
Copilot Jan 10, 2026
621e15d
Fix: Replace ฅ with ค in tltk transliterate functions to avoid KeyError
Copilot Jan 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions pythainlp/transliterate/tltk.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,15 +16,21 @@ def romanize(text: str) -> str:
:return: A string of Thai words rendered in the Latin alphabet.
:rtype: str
"""
# Replace ฅ with ค to avoid KeyError in tltk (out-of-vocabulary issue)
text = text.replace("ฅ", "ค")
_temp = th2roman(text)
return _temp[: _temp.rfind(" <s/>")].replace("<s/>", "")


def tltk_g2p(text: str) -> str:
# Replace ฅ with ค to avoid KeyError in tltk (out-of-vocabulary issue)
text = text.replace("ฅ", "ค")
_temp = g2p(text).split("<tr/>")[1].replace("|<s/>", "").replace("|", " ")
return _temp.replace("<s/>", "")


def tltk_ipa(text: str) -> str:
# Replace ฅ with ค to avoid KeyError in tltk (out-of-vocabulary issue)
text = text.replace("ฅ", "ค")
_temp = th2ipa(text)
return _temp[: _temp.rfind(" <s/>")].replace("<s/>", "")
5 changes: 5 additions & 0 deletions tests/extra/testx_transliterate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@
class TransliterateTestCaseX(unittest.TestCase):
def test_romanize(self):
self.assertEqual(romanize("แมว", engine="tltk"), "maeo")
# Test for character ฅ (issue: Transliterator cannot handle ฅ)
self.assertIsNotNone(romanize("ภาษาไวคาลีฅ", engine="tltk"))

def test_romanize_thai2rom(self):
self.assertEqual(romanize("แมว", engine="thai2rom"), "maeo")
Expand Down Expand Up @@ -146,6 +148,9 @@ def test_transliterate(self):
self.assertIsNotNone(transliterate("แมว", engine="tltk_g2p"))
self.assertIsNotNone(transliterate("คน", engine="tltk_ipa"))
self.assertIsNotNone(transliterate("แมว", engine="tltk_ipa"))
# Test for character ฅ (issue: Transliterator cannot handle ฅ)
self.assertIsNotNone(transliterate("ภาษาไวคาลีฅ", engine="tltk_g2p"))
self.assertIsNotNone(transliterate("ภาษาไวคาลีฅ", engine="tltk_ipa"))

self.assertIsNotNone(trans_list("คน"))
self.assertIsNotNone(xsampa_list("คน"))
Expand Down
Loading