Spaces:
Sleeping
Sleeping
nos
commited on
Commit
•
f16a65c
1
Parent(s):
fceca92
Update lib/torah.py
Browse files- lib/torah.py +197 -3
lib/torah.py
CHANGED
@@ -1,7 +1,201 @@
|
|
1 |
-
import json
|
2 |
-
import os
|
3 |
-
import re
|
4 |
from deep_translator import GoogleTranslator
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
|
6 |
def process_json_files(start, end, step, length=0, tlang="en", spaces_include=False, strip_in_braces=True, strip_diacritics=True):
|
7 |
base_path = "resources/texts"
|
|
|
|
|
|
|
|
|
1 |
from deep_translator import GoogleTranslator
|
2 |
+
import torahcodes.resources.func.utils as util
|
3 |
+
from hebrew_numbers import gematria_to_int
|
4 |
+
from textblob import TextBlob
|
5 |
+
from os import listdir
|
6 |
+
from os.path import isfile, join
|
7 |
+
import re
|
8 |
+
import time
|
9 |
+
import random
|
10 |
+
import os
|
11 |
+
import json
|
12 |
+
|
13 |
+
BLUE, RED, WHITE, YELLOW, MAGENTA, GREEN, END = '\33[1;94m', '\033[1;91m', '\33[1;97m', '\33[1;93m', '\033[1;35m', '\033[1;32m', '\033[0m'
|
14 |
+
ORANGE = '\033[1;33m' # orange
|
15 |
+
|
16 |
+
|
17 |
+
data_dir = "resources/texts"
|
18 |
+
|
19 |
+
class BibleBooks():
|
20 |
+
def __init__(self):
|
21 |
+
self.folder = data_dir
|
22 |
+
self.book = {}
|
23 |
+
def load(self):
|
24 |
+
|
25 |
+
for f in listdir(self.folder):
|
26 |
+
if isfile(join(self.folder, f)) and f.endswith(".json"):
|
27 |
+
fn = f.split('.')
|
28 |
+
#print('Load', fn[0])
|
29 |
+
with open(self.folder+f, encoding="utf-8-sig") as File:
|
30 |
+
self.book[fn[0]] = File.read()
|
31 |
+
|
32 |
+
def rawdata(self, bookname):
|
33 |
+
return self.book[bookname]
|
34 |
+
|
35 |
+
def booklist(self):
|
36 |
+
return list(self.book.keys())
|
37 |
+
|
38 |
+
books = BibleBooks()
|
39 |
+
|
40 |
+
class Torah():
|
41 |
+
def __init__(self):
|
42 |
+
self.book = ''
|
43 |
+
self.gcode = {
|
44 |
+
'a': 1, 'b': 2, 'c': 3, 'd': 4, 'e': 5, 'f': 6, 'g': 7, 'h': 8, 'i': 9, 'j': 600,
|
45 |
+
'k': 10, 'l': 20, 'm': 30, 'n': 40, 'o': 50, 'p': 60, 'q': 70, 'r': 80, 's': 90,
|
46 |
+
't': 100, 'u': 200, 'v': 700, 'w': 900, 'x': 300, 'y': 400, 'z': 500
|
47 |
+
}
|
48 |
+
|
49 |
+
def loadbooks(self):
|
50 |
+
books.load()
|
51 |
+
|
52 |
+
def func_getnumber(self, listL, listW):
|
53 |
+
return util.fn_GetNumberValues(listL, listW)
|
54 |
+
|
55 |
+
def func_checklang(self, word, lang):
|
56 |
+
b = TextBlob(word)
|
57 |
+
|
58 |
+
try:
|
59 |
+
b.detect_language()
|
60 |
+
if (b.detect_language() == lang):
|
61 |
+
return True
|
62 |
+
except:
|
63 |
+
return True
|
64 |
+
return False
|
65 |
+
|
66 |
+
def numtobook(self, number):
|
67 |
+
for x in books.booklist():
|
68 |
+
xt = re.findall("[-+]?[.]?[\d]+(?:,\d\d\d)*[\.]?\d*(?:[eE][-+]?\d+)?", x)
|
69 |
+
if xt[0] == str(number):
|
70 |
+
return x
|
71 |
+
|
72 |
+
def func_translate(self, lang_in, lang_out, data):
|
73 |
+
translated = GoogleTranslator(source=lang_in, target=lang_out).translate(data.strip())
|
74 |
+
return translated
|
75 |
+
|
76 |
+
def gematria(self, word: str) -> int:
|
77 |
+
try:
|
78 |
+
if word.isdigit():
|
79 |
+
return int(word)
|
80 |
+
|
81 |
+
# Aufteilen des Wortes in Buchstaben und Zahlen
|
82 |
+
letters = [char for char in word if char.isalpha()]
|
83 |
+
numbers = [int(char) for char in word if char.isdigit()]
|
84 |
+
|
85 |
+
# Berechnen des Gematria-Werts für die Buchstaben
|
86 |
+
letters_value = sum([self.gcode[char] for char in letters if char in self.gcode])
|
87 |
+
|
88 |
+
|
89 |
+
# Hinzufügen der Summe der Zahlen zum Gematria-Wert der Buchstaben
|
90 |
+
total_value = letters_value + sum(numbers)
|
91 |
+
|
92 |
+
return total_value
|
93 |
+
except:
|
94 |
+
print(word)
|
95 |
+
raise ValueError
|
96 |
+
|
97 |
+
|
98 |
+
def gematrix(self, phrase: str) -> int:
|
99 |
+
phrase = self.strip_accents(phrase.lower())
|
100 |
+
phrase = ''.join([i for i in phrase if i.isalpha() or i.isdigit() or i.isspace()])
|
101 |
+
|
102 |
+
# Aufteilen der Eingabe in separate Wörter und Zahlen
|
103 |
+
elements = phrase.split()
|
104 |
+
total_value = 0
|
105 |
+
|
106 |
+
for element in elements:
|
107 |
+
if element.isalpha():
|
108 |
+
# Berechne den Wert für Buchstaben
|
109 |
+
total_value += sum([self.gcode[char] for char in element if char in self.gcode])
|
110 |
+
elif element.isdigit():
|
111 |
+
# Addiere Zahlen direkt zum Gesamtwert
|
112 |
+
total_value += int(element)
|
113 |
+
|
114 |
+
return total_value
|
115 |
+
|
116 |
+
|
117 |
+
|
118 |
+
|
119 |
+
|
120 |
+
|
121 |
+
def strip_accents(self, s):
|
122 |
+
try:
|
123 |
+
return ''.join(
|
124 |
+
c for c in unicodedata.normalize('NFD', s)
|
125 |
+
if unicodedata.category(c) != 'Mn'
|
126 |
+
)
|
127 |
+
except:
|
128 |
+
return s
|
129 |
+
|
130 |
+
|
131 |
+
def gematria_iw_int(text):
|
132 |
+
return gematria_to_int(text)
|
133 |
+
|
134 |
+
|
135 |
+
def func_ParseTranslation(self, translated, lang, active):
|
136 |
+
abd = 'abcdefghijklmnñopqrstuvwxyz1234567890'
|
137 |
+
str_split = translated.split(' ')
|
138 |
+
str_final = ''
|
139 |
+
for word in str_split:
|
140 |
+
try:
|
141 |
+
if word[0].lower() in abd:
|
142 |
+
if active == 'true':
|
143 |
+
if self.func_checklang(word, lang) == True:
|
144 |
+
str_final = str_final+ word+' '
|
145 |
+
else:
|
146 |
+
str_final = str_final+ word+' '
|
147 |
+
except:
|
148 |
+
pass
|
149 |
+
|
150 |
+
if not str_final == '':
|
151 |
+
return str_final
|
152 |
+
else:
|
153 |
+
return 0
|
154 |
+
def els(self, namebook, number, tracert='false', visualice=False):
|
155 |
+
space = number
|
156 |
+
abd = 'abcdefghijklmnñopqrstuvwxyz'
|
157 |
+
i=1
|
158 |
+
rese=""
|
159 |
+
totalvalue = 0
|
160 |
+
D = self.GetDataBook(namebook)
|
161 |
+
for (z,b,y) in D:
|
162 |
+
try:
|
163 |
+
charnum = 0
|
164 |
+
res=""
|
165 |
+
|
166 |
+
for char in D[z,b,y]:
|
167 |
+
charnum = charnum+1
|
168 |
+
if (i % int(space)) == 0:
|
169 |
+
if tracert == 'true':
|
170 |
+
totalvalue = totalvalue + int(charnum)
|
171 |
+
print('Source:',int(z),'chapter:', int(b),'Verse:', int(y),'CharNum:',int(charnum),'Char:', char)
|
172 |
+
|
173 |
+
res=res+char
|
174 |
+
|
175 |
+
i=i+1
|
176 |
+
rese=rese+" "+res
|
177 |
+
except:
|
178 |
+
pass
|
179 |
+
#print('Total', totalvalue)
|
180 |
+
ret = re.sub('\s+', ' ', rese.strip())
|
181 |
+
return ret, totalvalue
|
182 |
+
|
183 |
+
def GetDataBook(self, bibleNumberBook):
|
184 |
+
|
185 |
+
|
186 |
+
JSON = books.rawdata(bibleNumberBook)
|
187 |
+
ListOfJSONStringsParsed, ListOfJSONStringsParsedWithSpaces = util.fn_TextFilePreprocess(JSON)
|
188 |
+
ListOfDictsOfJSONStringsParsed, ListOfDictsOfJSONStringsParsedWithSpaces = util.fn_ConvertJSONStringsToDicts(ListOfJSONStringsParsed, ListOfJSONStringsParsedWithSpaces)
|
189 |
+
SearchTextChosen = util.fn_GetNumberOfTextChosen(ListOfDictsOfJSONStringsParsed)
|
190 |
+
ZippedTupleNoSpaces, ZippedTupleWithSpaces = util.fn_ZippedTupleCreate(ListOfDictsOfJSONStringsParsed, ListOfDictsOfJSONStringsParsedWithSpaces, SearchTextChosen)
|
191 |
+
D, DS = util.fn_DictionaryOfVersesCreate(ZippedTupleNoSpaces, ZippedTupleWithSpaces)
|
192 |
+
S, L, DL, D5, ListOfWords = util.fn_DataObjectsCreate(D, DS)
|
193 |
+
N, NW = util.fn_GetNumberValues(S, ListOfWords)
|
194 |
+
ListOfIndexesCustom = util.fn_ListOfIndexesCustomCreate(D5)
|
195 |
+
W = util.fn_TupleOfWordsAndGematriaValuesCreate(ListOfWords, NW)
|
196 |
+
|
197 |
+
return D
|
198 |
+
|
199 |
|
200 |
def process_json_files(start, end, step, length=0, tlang="en", spaces_include=False, strip_in_braces=True, strip_diacritics=True):
|
201 |
base_path = "resources/texts"
|