536 lines
18 KiB
Python
Executable File
536 lines
18 KiB
Python
Executable File
import subprocess
|
||
import sys
|
||
import os
|
||
import requests, uuid, json
|
||
from .indictrans.indictrans import Transliterator
|
||
from om_transliterator import Transliterator as om_Transliterator
|
||
from indic_transliteration import sanscript
|
||
from indic_transliteration.sanscript import transliterate
|
||
from libindic.transliteration import getInstance
|
||
t = getInstance()
|
||
|
||
from indic_transliteration import sanscript
|
||
from indic_transliteration.sanscript import transliterate
|
||
from indicnlp.transliterate.unicode_transliterate import UnicodeIndicTransliterator
|
||
from transliterate import translit #, get_available_language_codes
|
||
from indic_transliteration.sanscript import SchemeMap, SCHEMES, transliterate
|
||
# import polyglot
|
||
# from polyglot.transliteration import Transliterator as poly
|
||
# from polyglot.text import Text
|
||
# import pinyin
|
||
# from anyascii import anyascii
|
||
from MNF.settings import BasePath
|
||
basePath = BasePath()
|
||
|
||
|
||
# -> Directly Usable azure api for transliteration
|
||
def azure_transliteration(text, source_lang, source_script, dest_script):
|
||
if source_script=="Devanagari":
|
||
source_script="Deva"
|
||
elif source_script=="Arabic":
|
||
source_script="Arab"
|
||
elif source_script=="Latin":
|
||
source_script="Latn"
|
||
elif source_script=="Kannada":
|
||
source_script="knda"
|
||
elif source_script=="Tamil":
|
||
source_script="Taml"
|
||
elif source_script=="Bengali":
|
||
source_script="Beng"
|
||
elif source_script=="Telugu":
|
||
source_script="Telu"
|
||
elif source_script=="Malayalam":
|
||
source_script="Mlym"
|
||
elif source_script=="Cyrillic":
|
||
source_script="Cyrl"
|
||
elif source_script=="Gurmukhi":
|
||
source_script="Guru"
|
||
elif source_script=="Telugu":
|
||
source_script="Telu"
|
||
elif source_script=="Gujarati":
|
||
source_script="Gujr"
|
||
elif source_script=="Oriya":
|
||
source_script="Orya"
|
||
elif source_script=="Sinhala":
|
||
source_script="Sinh"
|
||
elif source_script=="Hanji":
|
||
source_script="Hans"
|
||
elif source_script=="Thai":
|
||
source_script="Thai"
|
||
elif source_script=="Hebrew":
|
||
source_script="Hebr"
|
||
|
||
|
||
if dest_script=="Devanagari":
|
||
dest_script="Deva"
|
||
elif dest_script=="Arabic":
|
||
dest_script="Arab"
|
||
elif dest_script=="Latin":
|
||
dest_script="Latn"
|
||
elif dest_script=="Kannada":
|
||
dest_script="knda"
|
||
elif dest_script=="Tamil":
|
||
dest_script="Taml"
|
||
elif dest_script=="Cyrillic":
|
||
dest_script="Cyrl"
|
||
elif dest_script=="Malayalam":
|
||
dest_script="Mlym"
|
||
elif dest_script=="Gurmukhi":
|
||
dest_script="Guru"
|
||
elif dest_script=="Telugu":
|
||
dest_script="Telu"
|
||
elif dest_script=="Gujarati":
|
||
dest_script="Gujr"
|
||
elif dest_script=="Oriya":
|
||
dest_script="Orya"
|
||
elif dest_script=="Bengali":
|
||
dest_script="Beng"
|
||
elif dest_script=="Sinhala":
|
||
dest_script="Sinh"
|
||
elif dest_script=="Hanji":
|
||
dest_script="Hans"
|
||
elif dest_script=="Thai":
|
||
dest_script="Thai"
|
||
elif dest_script=="Hebrew":
|
||
dest_script="Hebr"
|
||
|
||
subscription_key = "959354878e73458e898a69f1f5887b69"
|
||
endpoint = "https://api.cognitive.microsofttranslator.com"
|
||
location = "eastus"
|
||
path = '/translate'
|
||
constructed_url = endpoint + path
|
||
headers = {
|
||
'Ocp-Apim-Subscription-Key': subscription_key,
|
||
'Ocp-Apim-Subscription-Region': location,
|
||
'Content-type': 'application/json',
|
||
'X-ClientTraceId': str(uuid.uuid4())
|
||
}
|
||
constructed_url1 = "https://api.cognitive.microsofttranslator.com/transliterate?api-version=3.0"
|
||
|
||
print("source_script", source_script)
|
||
print("dest_script", dest_script)
|
||
print("source_lang", source_lang)
|
||
print("text", text)
|
||
|
||
params = {'language':source_lang, 'fromScript': source_script, 'toScript': dest_script}
|
||
body = [{'text': text}]
|
||
try:
|
||
request = requests.post(constructed_url1, params=params, headers=headers, json=body)
|
||
response = request.json()
|
||
out = response[0]['text']
|
||
except Exception as e:
|
||
print("The error was ",e)
|
||
out = text
|
||
return out
|
||
|
||
|
||
# -> Directly Usable Polyglot api for transliteration
|
||
# def polyglot_trans(text, source_script, dest_script):
|
||
# # from polyglot.downloader import downloader
|
||
|
||
# if source_script=="Latin":
|
||
# source_script="en"
|
||
# elif source_script=="Arabic":
|
||
# source_script="ar"
|
||
# elif source_script=="Hanji":
|
||
# source_script="zh"
|
||
|
||
# if dest_script=="Latin":
|
||
# dest_script="en"
|
||
# elif dest_script=="Arabic":
|
||
# dest_script="ar"
|
||
# elif source_script=="Hanji":
|
||
# source_script="zh"
|
||
|
||
# new_text = ""
|
||
# text_break = Text(text)
|
||
# for x in text_break.transliterate(dest_script):
|
||
# new_text = new_text + str(x)
|
||
# return new_text
|
||
|
||
|
||
# -> Directly Usable indic_trans api for transliteration
|
||
def indic_trans(text, source_script, dest_script):
|
||
if source_script=="Devanagari":
|
||
source_script="hin"
|
||
elif source_script=="Arabic":
|
||
source_script="urd"
|
||
elif source_script=="Kannada":
|
||
source_script="kan"
|
||
elif source_script=="Tamil":
|
||
source_script="tam"
|
||
elif source_script=="Latin":
|
||
source_script="eng"
|
||
elif source_script=="Bengali":
|
||
source_script="ben"
|
||
elif source_script=="Telugu":
|
||
source_script="tel"
|
||
elif source_script=="Malayalam":
|
||
source_script="mal"
|
||
elif source_script=="Tamil":
|
||
source_script="tam"
|
||
elif source_script=="Oriya":
|
||
source_script="ori"
|
||
elif source_script=="Gujarati":
|
||
source_script="guj"
|
||
elif source_script=="Gurmukhi":
|
||
source_script="pan"
|
||
|
||
if dest_script=="Devanagari":
|
||
dest_script="hin"
|
||
elif dest_script=="Arabic":
|
||
dest_script="urd"
|
||
elif dest_script=="Kannada":
|
||
dest_script="kan"
|
||
elif dest_script=="Latin":
|
||
dest_script="eng"
|
||
elif source_script=="Tamil":
|
||
source_script="tam"
|
||
elif dest_script=="Gujarati":
|
||
dest_script="guj"
|
||
elif dest_script=="Oriya":
|
||
dest_script="ori"
|
||
elif dest_script=="Telugu":
|
||
dest_script="tel"
|
||
elif dest_script=="Malayalam":
|
||
dest_script="mal"
|
||
# elif dest_script=="Gurmukhi":
|
||
# dest_script="Guru"
|
||
elif dest_script=="Telugu":
|
||
dest_script="Telu"
|
||
elif dest_script=="Gujarati":
|
||
dest_script="Gujr"
|
||
elif dest_script=="Oriya":
|
||
dest_script="Orya"
|
||
elif dest_script=="Bengali":
|
||
dest_script="Ben"
|
||
elif dest_script=="Tamil":
|
||
dest_script="tam"
|
||
elif dest_script=="Gurmukhi":
|
||
dest_script="pan"
|
||
trn = Transliterator(source=source_script, target=dest_script, build_lookup=True)
|
||
out = trn.transform(text)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable om_translator api for transliteration
|
||
def om_transliterator(text):
|
||
transliterator = om_Transliterator()
|
||
out = transliterator.knda_to_latn(text)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable libindic api for transliteration
|
||
def libindic(text, dest_script):
|
||
if dest_script=="Devanagari":
|
||
dest_script="hi"
|
||
elif dest_script=="Latin":
|
||
dest_script="en"
|
||
elif dest_script=="Malayalam":
|
||
dest_script="ml"
|
||
elif dest_script=="Gujarati":
|
||
dest_script="gu"
|
||
elif dest_script=="Oriya":
|
||
dest_script="or"
|
||
elif dest_script=="Telugu":
|
||
dest_script="te"
|
||
elif dest_script=="Bengali":
|
||
dest_script="bn"
|
||
elif dest_script=="Tamil":
|
||
dest_script="ta"
|
||
elif dest_script=="Kannada":
|
||
dest_script="kn"
|
||
elif dest_script=="Gurmukhi":
|
||
dest_script="gu"
|
||
code = dest_script+'_IN'
|
||
out = t.transliterate(text, code)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_IAST api for transliteration
|
||
def indic_transliteration_IAST(text):
|
||
out = transliterate(text, sanscript.IAST, sanscript.DEVANAGARI)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_ITRANS api for transliteration
|
||
def indic_transliteration_ITRANS(text):
|
||
out = transliterate(text, sanscript.ITRANS, sanscript.DEVANAGARI)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable sheetal api for transliteration
|
||
def sheetal(text):
|
||
s2_out = subprocess.check_output([sys.executable, rf"{basePath}/conversion/translation/dev-rom-sheetal.py", text])
|
||
out = s2_out.decode('utf-8')
|
||
return out
|
||
|
||
|
||
# -> Directly Usable ritwik code for transliteration
|
||
def ritwik(text):
|
||
s2_out = subprocess.check_output([sys.executable, rf"{basePath}/conversion/translation/dev-rom-ritwik.py", text])
|
||
out = s2_out.decode('utf-8')
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_GURMUKHI api for transliteration
|
||
def indic_transliteration_GURMUKHI(text):
|
||
out = transliterate(text,sanscript.IAST, sanscript.GURMUKHI)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable unicode_transliteration_GURMUKHI api for transliteration
|
||
def unicode_transliteration_GURMUKHI(text):
|
||
input_text=transliterate(text, sanscript.IAST, sanscript.DEVANAGARI)
|
||
out=UnicodeIndicTransliterator.transliterate(input_text,"hi","pa")
|
||
return out
|
||
|
||
|
||
# -> Directly Usable transliteration_LATIN_CYRILLIC api for transliteration
|
||
def transliteration_LATIN_CYRILLIC(text):
|
||
out = translit(text, 'bg')
|
||
return out
|
||
|
||
|
||
# -> Directly Usable translit_CHINESE_LATIN api for transliteration
|
||
def translit_CHINESE_LATIN(text):
|
||
out = pinyin.get(text, format="strip", delimiter=" ")
|
||
return out
|
||
|
||
def translit_th_sin_mng_heb_to_latin(text):
|
||
out = anyascii(text)
|
||
return out
|
||
|
||
# -> Directly Usable indic_transliteration_TELUGU api for transliteration
|
||
def indic_transliteration_TELUGU(text):
|
||
out = transliterate(text,sanscript.IAST, sanscript.TELUGU)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_GURMUKHI_LATIN api for transliteration
|
||
def indic_transliteration_GURMUKHI_LATIN(text):
|
||
out = transliterate(text, sanscript.GURMUKHI, sanscript.ITRANS)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable unicode_transliteration_GURMUKHI_LATIN api for transliteration
|
||
def unicode_transliteration_GURMUKHI_LATIN(text):
|
||
input_text=transliterate(text, sanscript.IAST, sanscript.DEVANAGARI)
|
||
out = UnicodeIndicTransliterator.transliterate(input_text,"hi","pa")
|
||
return out
|
||
|
||
|
||
# -> Directly Usable transliteration_CYRILIC_LATIN api for transliteration
|
||
def transliteration_CYRILIC_LATIN(text):
|
||
out = translit(text, 'bg',reversed=True)
|
||
return out
|
||
|
||
|
||
# -> Some Random Code to replace special characters
|
||
def readonly(str):
|
||
str=str.replace("а", "a")
|
||
str=str.replace("б", "b")
|
||
str=str.replace("в", "v")
|
||
str=str.replace("г", "g")
|
||
str=str.replace("д", "d")
|
||
str=str.replace("е", "e")
|
||
str=str.replace("ё", "yo")
|
||
str=str.replace("ж", "zh")
|
||
str=str.replace("з", "z")
|
||
str=str.replace("и", "i")
|
||
str=str.replace("й", "j")
|
||
str=str.replace("к", "k")
|
||
str=str.replace("л", "l")
|
||
str=str.replace("м", "m")
|
||
str=str.replace("н", "n")
|
||
str=str.replace("о", "o")
|
||
str=str.replace("п", "p")
|
||
str=str.replace("р", "r")
|
||
str=str.replace("с", "s")
|
||
str=str.replace("т", "t")
|
||
str=str.replace("у", "u")
|
||
str=str.replace("ф", "f")
|
||
str=str.replace("х", "h")
|
||
str=str.replace("ц", "c")
|
||
str=str.replace("ч", "ch")
|
||
str=str.replace("ш", "sh")
|
||
str=str.replace("щ", "sch")
|
||
str=str.replace("ъ", "j")
|
||
str=str.replace("ы", "i")
|
||
str=str.replace("ь", "j")
|
||
str=str.replace("э", "e")
|
||
str=str.replace("ю", "yu")
|
||
str=str.replace("я", "ya")
|
||
str=str.replace("А", "A")
|
||
str=str.replace("Б", "B")
|
||
str=str.replace("В", "V")
|
||
str=str.replace("Г", "G")
|
||
str=str.replace("Д", "D")
|
||
str=str.replace("Е", "E")
|
||
str=str.replace("Ё", "Yo")
|
||
str=str.replace("Ж", "Zh")
|
||
str=str.replace("З", "Z")
|
||
str=str.replace("И", "I")
|
||
str=str.replace("Й", "J")
|
||
str=str.replace("К", "K")
|
||
str=str.replace("Л", "L")
|
||
str=str.replace("М", "M")
|
||
str=str.replace("Н", "N")
|
||
str=str.replace("О", "O")
|
||
str=str.replace("П", "P")
|
||
str=str.replace("Р", "R")
|
||
str=str.replace("С", "S")
|
||
str=str.replace("Т", "T")
|
||
str=str.replace("У", "U")
|
||
str=str.replace("Ф", "F")
|
||
str=str.replace("Х", "H")
|
||
str=str.replace("Ц", "C")
|
||
str=str.replace("Ч", "Ch")
|
||
str=str.replace("Ш", "Sh")
|
||
str=str.replace("Щ", "Sch")
|
||
str=str.replace("Ъ", "J")
|
||
str=str.replace("Ы", "I")
|
||
str=str.replace("Ь", "J")
|
||
str=str.replace("Э", "E")
|
||
str=str.replace("Ю", "Yu")
|
||
str=str.replace("Я", "Ya")
|
||
|
||
|
||
return str
|
||
|
||
|
||
# -> Code to Convert Letters to Latin Script
|
||
def ConvertToLatin(source):
|
||
result=''
|
||
for letter in source:
|
||
Letter = readonly(letter) ## replacemnet of word
|
||
result=result+Letter
|
||
return result
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_OTHER_DEVANAGRI api for transliteration
|
||
def indic_transliteration_OTHER_DEVANAGRI(text,src_script):
|
||
if src_script=="Malayalam":
|
||
out = transliterate(text, sanscript.MALAYALAM, sanscript.DEVANAGARI)
|
||
if src_script=="Gujarati":
|
||
out = transliterate(text, sanscript.GUJARATI, sanscript.DEVANAGARI)
|
||
if src_script=="Telugu":
|
||
out = transliterate(text, sanscript.TELUGU, sanscript.DEVANAGARI)
|
||
if src_script=="Oriya":
|
||
out = transliterate(text, sanscript.ORIYA, sanscript.DEVANAGARI)
|
||
if src_script=="Bengali":
|
||
out = transliterate(text, sanscript.BENGALI, sanscript.DEVANAGARI)
|
||
if src_script=="Kannada":
|
||
out = transliterate(text, sanscript.KANNADA, sanscript.DEVANAGARI)
|
||
if src_script=="Gurmukhi":
|
||
out = transliterate(text, sanscript.GURMUKHI, sanscript.DEVANAGARI)
|
||
if src_script=="Tamil":
|
||
out = transliterate(text, sanscript.TAMIL, sanscript.DEVANAGARI)
|
||
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_DEVANAGRI_OTHER api for transliteration
|
||
def indic_transliteration_DEVANAGRI_OTHER(text,dest_script):
|
||
if dest_script=="Malayalam":
|
||
out = transliterate(text, sanscript.DEVANAGARI, sanscript.MALAYALAM)
|
||
if dest_script=="Gujarati":
|
||
out = transliterate(text, sanscript.DEVANAGARI, sanscript.GUJARATI)
|
||
if dest_script=="Telugu":
|
||
out = transliterate(text, sanscript.DEVANAGARI, sanscript.TELUGU)
|
||
if dest_script=="Oriya":
|
||
out = transliterate(text, sanscript.DEVANAGARI, sanscript.ORIYA)
|
||
if dest_script=="Bengali":
|
||
out = transliterate(text,sanscript.DEVANAGARI,sanscript.BENGALI)
|
||
if dest_script=="Kannada":
|
||
out = transliterate(text, sanscript.DEVANAGARI, sanscript.KANNADA)
|
||
if dest_script=="Gurmukhi":
|
||
out = transliterate(text, sanscript.DEVANAGARI, sanscript.GURMUKHI)
|
||
if dest_script=="Tamil":
|
||
out = transliterate(text, sanscript.DEVANAGARI, sanscript.TAMIL)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_KANNADA_OTHER api for transliteration
|
||
def indic_transliteration_KANNADA_OTHER(text,dest_script):
|
||
if dest_script=="Malayalam":
|
||
out = transliterate(text, sanscript.KANNADA, sanscript.MALAYALAM)
|
||
if dest_script=="Telugu":
|
||
out = transliterate(text, sanscript.KANNADA, sanscript.TELUGU)
|
||
if dest_script=="Tamil":
|
||
out = transliterate(text, sanscript.KANNADA, sanscript.TAMIL)
|
||
if dest_script=="Bengali":
|
||
out = transliterate(text, sanscript.KANNADA, sanscript.BENGALI)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_OTHER_KANNADA api for transliteration
|
||
def indic_transliteration_OTHER_KANNADA(text,src_script):
|
||
if src_script=="Malayalam":
|
||
out = transliterate(text, sanscript.MALAYALAM, sanscript.KANNADA)
|
||
if src_script=="Telugu":
|
||
out = transliterate(text, sanscript.TELUGU, sanscript.KANNADA)
|
||
if src_script=="Tamil":
|
||
out = transliterate(text, sanscript.TAMIL, sanscript.KANNADA)
|
||
if src_script=="Bengali":
|
||
out = transliterate(text, sanscript.BENGALI, sanscript.KANNADA)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_TAMIL_OTHER api for transliteration
|
||
def indic_transliteration_TAMIL_OTHER(text,dest_script):
|
||
if dest_script=="Malayalam":
|
||
out = transliterate(text, sanscript.TAMIL, sanscript.MALAYALAM)
|
||
if dest_script=="Telugu":
|
||
out = transliterate(text, sanscript.TAMIL, sanscript.TELUGU)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_OTHER_TAMIL api for transliteration
|
||
def indic_transliteration_OTHER_TAMIL(text,src_script):
|
||
if src_script=="Malayalam":
|
||
out = transliterate(text, sanscript.MALAYALAM,sanscript.TAMIL)
|
||
if src_script=="Telugu":
|
||
out = transliterate(text, sanscript.TELUGU, sanscript.TAMIL)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_TELUGU_OTHER api for transliteration
|
||
def indic_transliteration_TELUGU_OTHER(text, desc_script):
|
||
if desc_script=="Malayalam":
|
||
out = transliterate(text, sanscript.TELUGU, sanscript.MALAYALAM)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_MALAYALAM_OTHER api for transliteration
|
||
def indic_transliteration_MALAYALAM_OTHER(text, desc_script):
|
||
if desc_script=="Telugu":
|
||
out = transliterate(text, sanscript.MALAYALAM, sanscript.TELUGU)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_OTHER_GUJARATI api for transliteration
|
||
def indic_transliteration_OTHER_GUJARATI(text, src_script):
|
||
if src_script=="Gurmukhi":
|
||
out = transliterate(text, sanscript.GURMUKHI, sanscript.GUJARATI)
|
||
if src_script=="Oriya":
|
||
out = transliterate(text, sanscript.ORIYA, sanscript.GUJARATI)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_OTHER_GURMUKHI api for transliteration
|
||
def indic_transliteration_OTHER_GURMUKHI(text, src_script):
|
||
if src_script=="Gujarati":
|
||
out = transliterate(text, sanscript.GUJARATI, sanscript.GURMUKHI)
|
||
if src_script=="Oriya":
|
||
out = transliterate(text, sanscript.ORIYA, sanscript.GURMUKHI)
|
||
return out
|
||
|
||
|
||
# -> Directly Usable indic_transliteration_OTHER_ORIYA api for transliteration
|
||
def indic_transliteration_OTHER_ORIYA(text, src_script):
|
||
if src_script=="Gujarati":
|
||
out = transliterate(text, sanscript.GUJARATI, sanscript.ORIYA)
|
||
if src_script=="Gurmukhi":
|
||
out = transliterate(text, sanscript.GURMUKHI, sanscript.ORIYA)
|
||
return out |