Spaces:
Sleeping
Sleeping
File size: 4,495 Bytes
e8510d3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 | import unicodedata
import logging
logger = logging.getLogger(__name__)
def strip_diacritics(text):
"""
Removes diacritics from Unicode characters to get the base letter and outputs warnings
for actually unknown characters.
"""
stripped_text = ''
for char in unicodedata.normalize('NFD', text):
if unicodedata.category(char) not in ['Mn', 'Cf']:
stripped_text += char
return stripped_text
def letter_to_value(letter):
"""
Converts a single letter to its Gematria value, ignores spaces
and non-letter characters.
"""
values = {
# Latin letters
'a': 1, 'b': 2, 'c': 3, 'd': 4, 'e': 5, 'f': 6, 'g': 7, 'h': 8, 'i': 9, 'j': 600,
'k': 10, 'l': 20, 'm': 30, 'n': 40, 'o': 50, 'p': 60, 'q': 70, 'r': 80, 's': 90,
't': 100, 'u': 200, 'v': 700, 'w': 900, 'x': 300, 'y': 400, 'z': 500,
'A': 1, 'B': 2, 'C': 3, 'D': 4, 'E': 5, 'F': 6, 'G': 7, 'H': 8, 'I': 9, 'J': 600,
'K': 10, 'L': 20, 'M': 30, 'N': 40, 'O': 50, 'P': 60, 'Q': 70, 'R': 80, 'S': 90,
'T': 100, 'U': 200, 'V': 700, 'W': 900, 'X': 300, 'Y': 400, 'Z': 500,
# Base letters and some already mentioned variants
'ا': 1, 'أ': 1, 'إ': 1, 'آ': 1, 'ب': 2, 'ج': 3, 'د': 4, 'ه': 5, 'و': 6, 'ز': 7, 'ح': 8, 'ط': 9,
'ي': 10, 'ى': 10, 'ك': 20, 'ک': 20, 'ل': 30, 'م': 40, 'ن': 50, 'س': 60, 'ع': 70, 'ف': 80,
'ص': 90, 'ق': 100, 'ر': 200, 'ش': 300, 'ت': 400, 'ث': 500, 'خ': 600, 'ذ': 700, 'ض': 800, 'ظ': 900, 'غ': 1000,
'ٱ': 1, # Alif Wasla
'ـ': 0, # Tatweel
# Additional variants and special characters
'ة': 400, # Taa Marbuta
'ؤ': 6, # Waw with Hamza above
'ئ': 10, # Ya with Hamza above
'ء': 1, # Hamza
'ى': 10, # Alif Maqsurah
'ٹ': 400, # Taa' marbuta goal
'پ': 2, # Pe (Persian/Urdu)
'چ': 3, # Che (Persian/Urdu)
'ژ': 7, # Zhe (Persian/Urdu)
'گ': 20, # Gaf (Persian/Urdu)
'ڭ': 20, # Ngaf (Kazakh, Uyghur, Uzbek, and in some Arabic dialects)
'ں': 50, # Noon Ghunna (Persian/Urdu)
'ۀ': 5, # Heh with Yeh above (Persian/Urdu)
'ے': 10, # Barree Yeh (Persian/Urdu)
'؋': 0, # Afghani Sign
# Hebrew letters (base and final forms)
'א': 1, 'ב': 2, 'ג': 3, 'ד': 4, 'ה': 5, 'ו': 6, 'ז': 7, 'ח': 8, 'ט': 9, 'י': 10,
'כ': 20, 'ך': 500, 'ל': 30, 'מ': 40, 'ם': 600, 'נ': 50, 'ן': 700, 'ס': 60, 'ע': 70, 'פ': 80, 'ף': 800,
'צ': 90, 'ץ': 900, 'ק': 100, 'ר': 200, 'ש': 300, 'ת': 400,
# Greek letters
'α': 1, 'β': 2, 'γ': 3, 'δ': 4, 'ε': 5, 'ϝ': 6, 'ζ': 7, 'η': 8, 'θ': 9, 'ι': 10,
'κ': 20, 'λ': 30, 'μ': 40, 'ν': 50, 'ξ': 60, 'ο': 70, 'π': 80, 'ϟ': 90, 'ρ': 100,
'σ': 200, 'τ': 300, 'υ': 400, 'φ': 500, 'χ': 600, 'ψ': 700, 'ω': 800, 'ϡ': 900,
# Greek uppercase letters
'Α': 1, 'Β': 2, 'Γ': 3, 'Δ': 4, 'Ε': 5, 'Ϝ': 6, 'Ζ': 7, 'Η': 8, 'Θ': 9, 'Ι': 10,
'Κ': 20, 'Λ': 30, 'Μ': 40, 'Ν': 50, 'Ξ': 60, 'Ο': 70, 'Π': 80, 'Ϟ': 90, 'Ρ': 100,
'Σ': 200, 'Τ': 300, 'Υ': 400, 'Φ': 500, 'Χ': 600, 'Ψ': 700, 'Ω': 800, 'Ϡ': 900,
'σ': 200, # Sigma
'ς': 200, # Final Sigma
'ϲ': 200, # Lunate Sigma (Greek)
'Ϲ': 200, # Uppercase Lunate Sigma (Greek)
# Katapayadi System
'क': 1, 'ख': 2, 'ग': 3, 'घ': 4, 'ङ': 5,
'च': 6, 'छ': 7, 'ज': 8, 'झ': 9, 'ञ': 0,
'ट': 1, 'ठ': 2, 'ड': 3, 'ढ': 4, 'ण': 5,
'त': 6, 'थ': 7, 'द': 8, 'ध': 9, 'न': 0,
'प': 1, 'फ': 2, 'ब': 3, 'भ': 4, 'म': 5,
'य': 1, 'र': 2, 'ल': 3, 'व': 4, 'श': 5, 'ष': 6, 'स': 7, 'ह': 8,
# Half forms (same values)
'क्': 1, 'ख्': 2, 'ग्': 3, 'घ्': 4, 'ङ्': 5,
'च्': 6, 'छ्': 7, 'ज्': 8, 'झ्': 9, 'ञ्': 0,
'ट्': 1, 'ठ्': 2, 'ड्': 3, 'ढ्': 4, 'ण्': 5,
'त्': 6, 'थ्': 7, 'द्': 8, 'ध्': 9, 'न्': 0,
'प्': 1, 'फ्': 2, 'ब्': 3, 'भ्': 4, 'म्': 5,
'य्': 1, 'र्': 2, 'ल्': 3, 'व्': 4, 'श्': 5, 'ष्': 6, 'स्': 7, 'ह्': 8,
}
# Return the value if found, otherwise 0
return values.get(letter, 0)
def calculate_gematria(text):
"""
Calculates the gematria value of a text by summing the values of each letter.
"""
if not text:
return 0
total = 0
for char in text:
value = letter_to_value(char)
total += value
return total
|