Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/sacremoses/indic.py: 67%

Shortcuts on this page

r m x   toggle line displays

j k   next/prev highlighted chunk

0   (zero) top of page

1   (one) first highlighted chunk

3 statements  

1# 

2# Created by: Thamme Gowda ; June 2020 

3# 

4# https://en.wikipedia.org/wiki/Virama 

5VIRAMAS = [ 

6 "\u094D", # Devanagari ◌् 

7 "\u09CD", # Bengali ◌্ 

8 "\u0A4D", # Gurmukhi ◌੍ 

9 "\u0ACD", # Gujarati ◌્ 

10 "\u0B4D", # Oriya ◌୍ 

11 "\u0BCD", # Tamil ◌் 

12 "\u0C4D", # Telugu ◌్ 

13 "\u0CCD", # Kannada ◌್ 

14 "\u0D3B", # Malayalam Sign Vertical Bar ◌഻ 

15 "\u0D3C", # Malayalam Sign Circular ◌഻ 

16 "\u0D4D", # Malayalam ◌് 

17 "\u0EBA", # Lao Sign Pali ◌຺ 

18 "\u1039", # Myanmar ◌္ 

19 "\u1714", # Tagalog ◌᜔ 

20 "\u1BAB", # Sundanese ◌᮫ 

21 "\uA8C4", # Saurashtra ◌꣄ 

22 "\uA8F3", # Devanagari Sign Candrabindu ꣳ 

23 "\uA8F4", # Devanagari Sign Double Candrabindu ꣴ 

24 "\uA953", # Rejang ꥓ 

25 "\uAAF6", # Meetei Mayek ◌꫶ 

26 "\U00010A3F", # Kharoshthi ◌𐨿 

27 "\U00011046", # Brahmi ◌𑁆 

28 "\U000110B9", # Kaithi ◌𑂹 

29 "\U00011133", # Chakma ◌𑄳 

30 "\U000111C0", # Sharada 𑇀 

31 "\U00011235", # Khojki 𑈵 

32 "\U000112EA", # Khudawadi ◌𑋪 

33 "\U0001134D", # Grantha 𑍍 

34 "\U00011442", # Newa ◌𑑂 

35 "\U000114C2", # Tirhuta ◌𑓂 

36 "\U000115BF", # Siddham ◌𑖿 

37 "\U0001163F", # Modi ◌𑘿 

38 "\U000116B6", # Takri 𑚶 

39 "\U00011839", # Dogra ◌𑠹 

40 "\U000119E0", # Nandinagari ◌𑧠 

41 "\U00011A34", # Zanabazar Square ◌𑨴 

42 "\U00011C3F", # Bhaiksuki ◌𑰿 

43 "\U00011D45", # Masaram Gondi ◌𑵅 

44 "\U00011D97", # Gunjala Gondi ◌𑶗 

45 "\u0DCA", # Sinhala hal kirīma ් 

46] 

47 

48# https://en.wikipedia.org/wiki/Nuqta 

49NUKTAS = [ 

50 "\u093C", # Devanagari ◌़ 

51 "\u09BC", # Bengali ◌় 

52 "\u0A3C", # Gurmukhi ◌਼ 

53 "\u0ABC", # Gujarati ◌઼ 

54 "\u0AFD", # Gujarati Sign Three-Dot Above ◌૽ 

55 "\u0AFE", # Gujarati Sign Circle Above ◌૾ 

56 "\u0AFF", # Gujarati Sign Two-Circle Above ◌૿ 

57 "\u0B3C", # Oriya ◌଼ 

58 "\u0CBC", # Kannada ◌಼ 

59 "\u1C37", # Lepcha ◌᰷ 

60 "\U000110BA", # Kaithi ◌𑂺 

61 "\U00011173", # Mahajani ◌𑅳 

62 "\U000111CA", # Sharada ◌𑇊 

63 "\U00011236", # Khojki ◌𑈶 

64 "\U000112E9", # Khudawadi ◌𑋩 

65 "\U0001133C", # Grantha ◌𑌼 

66 "\U00011446", # Newa ◌𑑆 

67 "\U000114C3", # Tirhuta ◌𑓃 

68 "\U000115C0", # Siddham ◌𑗀 

69 "\U000116B7", # Takri ◌𑚷 

70 "\U0001183A", # Dogra ◌𑠺 

71 "\U00011D42", # Masaram Gondi ◌𑵂 

72 "\U0001E94A", # Adlam ◌𞥊 

73]