/usr/local/lib/python3.6/site-packages/sacremoses
Edit: /usr/local/lib/python3.6/site-packages/sacremoses/indic.py (2517B)
#
# Created by: Thamme Gowda ; June 2020
#
# https://en.wikipedia.org/wiki/Virama
VIRAMAS = [
"\u094D", # Devanagari ◌्
"\u09CD", # Bengali ◌্
"\u0A4D", # Gurmukhi ◌੍
"\u0ACD", # Gujarati ◌્
"\u0B4D", # Oriya ◌୍
"\u0BCD", # Tamil ◌்
"\u0C4D", # Telugu ◌్
"\u0CCD", # Kannada ◌್
"\u0D3B", # Malayalam Sign Vertical Bar ◌഻
"\u0D3C", # Malayalam Sign Circular ◌഻
"\u0D4D", # Malayalam ◌്
"\u0EBA", # Lao Sign Pali ◌຺
"\u1039", # Myanmar ◌္
"\u1714", # Tagalog ◌᜔
"\u1BAB", # Sundanese ◌᮫
"\uA8C4", # Saurashtra ◌꣄
"\uA8F3", # Devanagari Sign Candrabindu ꣳ
"\uA8F4", # Devanagari Sign Double Candrabindu ꣴ
"\uA953", # Rejang ꥓
"\uAAF6", # Meetei Mayek ◌꫶
"\U00010A3F", # Kharoshthi ◌𐨿
"\U00011046", # Brahmi ◌𑁆
"\U000110B9", # Kaithi ◌𑂹
"\U00011133", # Chakma ◌𑄳
"\U000111C0", # Sharada 𑇀
"\U00011235", # Khojki 𑈵
"\U000112EA", # Khudawadi ◌𑋪
"\U0001134D", # Grantha 𑍍
"\U00011442", # Newa ◌𑑂
"\U000114C2", # Tirhuta ◌𑓂
"\U000115BF", # Siddham ◌𑖿
"\U0001163F", # Modi ◌𑘿
"\U000116B6", # Takri 𑚶
"\U00011839", # Dogra ◌𑠹
"\U000119E0", # Nandinagari ◌𑧠
"\U00011A34", # Zanabazar Square ◌𑨴
"\U00011C3F", # Bhaiksuki ◌𑰿
"\U00011D45", # Masaram Gondi ◌𑵅
"\U00011D97", # Gunjala Gondi ◌𑶗
"\u0DCA", # Sinhala hal kirīma ්
]
# https://en.wikipedia.org/wiki/Nuqta
NUKTAS = [
"\u093C", # Devanagari ◌़
"\u09BC", # Bengali ◌়
"\u0A3C", # Gurmukhi ◌਼
"\u0ABC", # Gujarati ◌઼
"\u0AFD", # Gujarati Sign Three-Dot Above ◌૽
"\u0AFE", # Gujarati Sign Circle Above ◌૾
"\u0AFF", # Gujarati Sign Two-Circle Above ◌૿
"\u0B3C", # Oriya ◌଼
"\u0CBC", # Kannada ◌಼
"\u1C37", # Lepcha ◌᰷
"\U000110BA", # Kaithi ◌𑂺
"\U00011173", # Mahajani ◌𑅳
"\U000111CA", # Sharada ◌𑇊
"\U00011236", # Khojki ◌𑈶
"\U000112E9", # Khudawadi ◌𑋩
"\U0001133C", # Grantha ◌𑌼
"\U00011446", # Newa ◌𑑆
"\U000114C3", # Tirhuta ◌𑓃
"\U000115C0", # Siddham ◌𑗀
"\U000116B7", # Takri ◌𑚷
"\U0001183A", # Dogra ◌𑠺
"\U00011D42", # Masaram Gondi ◌𑵂
"\U0001E94A", # Adlam ◌𞥊
]