def test_normalize(self):
self.assertIsNotNone(normalize("พรรค์จันทร์ab์"))
# normalize sara e + sara e
self.assertEqual(normalize("เเปลก"), "แปลก")
# normalize consonant + nikhahit + sara aa
self.assertEqual(normalize("นํา"), "นำ")
self.assertEqual(normalize("\u0e01\u0e4d\u0e32"), "\u0e01\u0e33")
# normalize consonant + tone mark + nikhahit + sara aa
self.assertEqual(normalize("\u0e01\u0e48\u0e4d\u0e32"),
"\u0e01\u0e48\u0e33")
# reorder consonant + follow vowel + tone mark
self.assertEqual(normalize("\u0e01\u0e30\u0e48"), "\u0e01\u0e48\u0e30")
# reorder consonant + nikhahit + tone mark + sara aa
self.assertEqual(normalize("\u0e01\u0e4d\u0e48\u0e32"),
"\u0e01\u0e48\u0e33")
# reorder consonant + follow vowel + tone mark
self.assertEqual(normalize("\u0e01\u0e32\u0e48"), "\u0e01\u0e48\u0e32")
# remove repeating following vowels
self.assertEqual(normalize("กาา"), "กา")
self.assertEqual(normalize("กา า า า"), "กา")
self.assertEqual(normalize("กา าาะา"), "กาะา")
# remove epeating tone marks
self.assertEqual(normalize("\u0e01\u0e48\u0e48"), "\u0e01\u0e48")
# remove repeating different ton emarks
self.assertEqual(normalize("\u0e01\u0e48\u0e49"), "\u0e01\u0e49")
self.assertEqual(normalize("\u0e01\u0e48\u0e49\u0e48\u0e49"),
"\u0e01\u0e49")
# remove tone mark at the beginning of text
self.assertEqual(remove_dangling("\u0e48\u0e01"), "\u0e01")
self.assertEqual(remove_dangling("\u0e48\u0e48\u0e01"), "\u0e01")
self.assertEqual(remove_dangling("\u0e48\u0e49\u0e01"), "\u0e01")
self.assertEqual(remove_dangling("\u0e48\u0e01\u0e48"), "\u0e01\u0e48")
# remove duplicate spaces
self.assertEqual(remove_dup_spaces(" ab c d "), "ab c d")
self.assertEqual(remove_dup_spaces("\nab c \n d \n"), "ab c\nd")
# remove tone marks
self.assertEqual(remove_tonemark("จิ้น"), "จิน")
self.assertEqual(remove_tonemark("เก๋า"), "เกา")
self.assertEqual(delete_tone("เจ๋งเป้ง"), remove_tonemark("เจ๋งเป้ง"))
with self.assertWarns(DeprecationWarning):
delete_tone("ค้าบ")
# remove zero width chars
self.assertEqual(remove_zw("กา\u200b"), "กา")
self.assertEqual(remove_zw("ก\u200cา"), "กา")
self.assertEqual(remove_zw("\u200bกา"), "กา")
self.assertEqual(remove_zw("กา\u200b\u200c\u200b"), "กา")
def lk82(text: str) -> str:
"""
This function converts Thai text into phonetic code with the a
Thai soundex algorithm named **LK82** [#lk82]_.
:param str text: Thai word
:return: LK82 soundex of the given Thai word
:rtype: str
:Example:
::
from pythainlp.soundex import lk82
lk82("ลัก")
# output: 'ร1000'
lk82("รัก")
# output: 'ร1000'
lk82("รักษ์")
# output: 'ร1000'
lk82("บูรณการ")
# output: 'บE419'
lk82("ปัจจุบัน")
# output: 'ป3E54'
"""
if not text or not isinstance(text, str):
return ""
text = remove_tonemark(text) # 4. remove tone marks
text = _RE_KARANT.sub("", text) # 4. remove "karat" characters
text = _RE_SIGN.sub("", text) # 5. remove Mai tai khu,
if not text:
return ""
# 6. encode the first character
res = []
if "ก" <= text[0] <= "ฮ":
res.append(text[0].translate(_TRANS1))
text = text[1:]
else:
if len(text) > 1:
res.append(text[1].translate(_TRANS1))
res.append(text[0].translate(_TRANS2))
text = text[2:]
# encode the rest
i_v = None # ตำแหน่งตัวคั่นล่าสุด (สระ)
len_text = len(text)
for i, c in enumerate(text):
if (
c in "\u0e30\u0e31\u0e34\u0e35"
): # 7. ตัวคั่นเฉยๆ/ Sara A, Mai Han-Akat, Sara I, Sara II
i_v = i
res.append("")
elif (
c in "\u0e32\u0e36\u0e37\u0e39\u0e45"
): # 8. คั่นและใส่/ Sara Aa, Sara Ue, Sara Uee, Sara Uu, Lankkhangyao
i_v = i
res.append(c.translate(_TRANS2))
elif c == "\u0e38": # 9. สระอุ / Sara U
i_v = i
if i == 0 or (text[i - 1] not in "ตธ"):
res.append(c.translate(_TRANS2))
else:
res.append("")
elif c in "\u0e2b\u0e2d": # หอ
if i + 1 < len_text and (
text[i + 1] in "\u0e36\u0e37\u0e38\u0e39"
): # Sara Ue, Sara Uee, Sara U, Sara Uu
res.append(c.translate(_TRANS2))
elif c in "\u0e22\u0e23\u0e24\u0e26\u0e27":
if i_v == i - 1 or (
i + 1 < len_text
and (text[i + 1] in "\u0e36\u0e37\u0e38\u0e39")
): # Sara Ue, Sara Uee, Sara U, Sara Uu
res.append(c.translate(_TRANS2))
else:
res.append(c.translate(_TRANS2)) # 12.
# 13. remove repetitives
res2 = [res[0]]
for i in range(1, len(res)):
if res[i] != res[i - 1]:
res2.append(res[i])
# 14. fill zeros
return ("".join(res2) + "0000")[:5]