import os
import sys
import docx
import re
# import textract
from tqdm import tqdm
from collections import Counter
import ntpath
from docx.shared import Inches, Cm, Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.enum.table import WD_TABLE_ALIGNMENT, WD_ALIGN_VERTICAL
import requests, uuid, json
import nltk.translate.bleu_score as bleu
import nltk.translate.gleu_score as gleu
from rouge_score import rouge_scorer
import numpy as np
from indicnlp.tokenize import sentence_tokenize
import nltk
# try: nltk.data.find('tokenizers/punkt')
# except LookupError: nltk.download('punkt')
# try: nltk.data.find('wordnet')
# except LookupError: ###nltk.download('wordnet')
# print("error in finding wordnet")
# import logging
# from logger import get_module_logger
# log = get_module_logger(__name__)
# log.info('Logger working')
from MNF.settings import BasePath
basePath = BasePath()
#google
from google.cloud import translate
from google.cloud import translate_v2 as Translate
import datetime
from pytz import timezone
from .script_detector import script_cat
from .buck_2_unicode import buck_2_unicode
from .translation_metric import manual_diff_score, bleu_diff_score, gleu_diff_score, meteor_diff_score, rouge_diff_score, diff_score, critera4_5
from .selection_source import selection_source, function5, function41, function311, function221, function2111, function11111, selection_source_transliteration, two_sources_two_outputs
from .script_writing import addSlugLine, addActionLine, addSpeaker, addParenthetical, addDialogue, dual_script, addTransition, dial_checker, non_dial_checker
from .script_reading import breaksen, getRefined, getSlugAndNonSlug, getSpeakers, getScenes
from .translation_resources import ibm_watson, google, aws, azure, yandex ,lingvanex
from .transliteration_resources import azure_transliteration, indic_trans, om_transliterator, libindic, indic_transliteration_IAST, indic_transliteration_ITRANS, sheetal,unicode_transliteration_GURMUKHI,indic_transliteration_GURMUKHI,transliteration_LATIN_CYRILLIC,indic_transliteration_TELUGU,unicode_transliteration_GURMUKHI_LATIN,indic_transliteration_GURMUKHI_LATIN,transliteration_CYRILIC_LATIN,ConvertToLatin,readonly
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = rf"{basePath}/MNF/json_keys/authentication.json"
def makeTransliteration_only(**kwargs):
dial_dest_script=kwargs.get('dial_dest_script')
dual_dial_script=kwargs.get('dual_dial_script')
original_file=kwargs.get('original_file')
dial_dest_lang=kwargs.get('dial_dest_lang')
is_dialogue_transliteration_required=kwargs.get("is_dialogue_transliteration_required")
is_action_line_transliteration_required=kwargs.get("is_action_line_transliteration_required")
action_line_dest_script=kwargs.get("action_line_dest_script")
action_line_src_lang=kwargs.get("action_line_src_lang")
action_line_src_script=kwargs.get("action_line_src_script")
scenes_original=kwargs.get("scenes_original")
restrict_to_five=kwargs.get("restrict_to_five")
# os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = rf"{basePath}/conversion/gifted-mountain-318504-4f001d5f08db.json"
translate_client = Translate.Client()
client = translate.TranslationServiceClient()
project_id = 'authentic-bongo-272808'
location = "global"
parent = f"projects/{project_id}/locations/{location}"
dial_dest_script = dial_dest_script
dual_dial_script = dual_dial_script
filename2 = original_file
dial_dest_lang = dial_dest_lang
if is_dialogue_transliteration_required==False and is_action_line_transliteration_required==False and dual_dial_script=="No":
return original_file,scenes_original
# filename1 = sys.argv[1] # get translated file from UI-1(translation)
# dial_dest_script = sys.argv[2]
# dual_dial_script = sys.argv[3] #Yes/No
# translation_and_transliteration = sys.argv[4] #Yes/No
# filename2 = sys.argv[5] # original file or take input as scenes from final translation
# create an instance of a word document
doc = docx.Document()
x = datetime.datetime.now(timezone('UTC')).astimezone(timezone('Asia/Kolkata'))
doc_file = basePath+"/media/scripts/translated/" + "trans_"+str(dial_dest_lang)+"_"+str(x.strftime("%d"))+ "_"+ str(x.strftime("%b"))+ "_"+ str(x.strftime("%H"))+ str(x.strftime("%I")) + "_" + "trans" + '_of_' + ntpath.basename(filename2)
print(doc_file)
doc2 = docx.Document()
sections = doc2.sections
for section in sections:
section.top_margin = Inches(0.2)
section.bottom_margin = Inches(0.2)
section.left_margin = Inches(0.2)
section.right_margin = Inches(0.2)
section = doc2.sections[-1]
new_height = section.page_width
section.page_width = section.page_height
section.page_height = new_height
name = 'Final table '+doc_file
doc2.add_heading(name, 0)
doc_para = doc2.add_paragraph()
doc_para.add_run('Translation resources used : Google, IBM watson, AWS, Azure, Lingvanex, Yandex').bold = True
table2 = doc2.add_table(rows=1,cols=4)
table2.style = 'TableGrid'
hdr_Cells = table2.rows[0].cells
hdr_Cells[0].paragraphs[0].add_run("Input").bold=True
hdr_Cells[1].paragraphs[0].add_run("Output1").bold=True
hdr_Cells[2].paragraphs[0].add_run("Output2").bold=True
hdr_Cells[3].paragraphs[0].add_run("Output3").bold=True
refined,total_scenes = getRefined(filename2)
sluglines,without_slug = getSlugAndNonSlug(refined)
characters = getSpeakers(without_slug)
scenes1,actionline,parenthetical_lis,speakers,dialogues = getScenes(refined,total_scenes,characters)
if restrict_to_five == 'yes':
scenes1=scenes1[:5]
def language_detector(text):
result = translate_client.translate(text, target_language='hi')
det_lang = result["detectedSourceLanguage"]
return det_lang
def script_det(text):
punctuations = '''!()-[]{};:'"\,<>./?@#$%^&*_~'''
no_punct = ""
for char in text:
if char not in punctuations:
no_punct = char
break
script = script_cat(no_punct)[0]
return script
def punct_remover(string):
punctuations = '''!()-[]{};:'"\,<>./?@#$%^&*_~…।'''
for x in string.lower():
if x in punctuations:
string = string.replace(x, " ")
return string
def space_after_punct(text):
#text = text.replace('...',' ... ')
text = text.replace('. . .',' ... ')
text = re.sub('([,!?()…-])', r'\1 ', text)
text = re.sub('\s{2,}', ' ', text)
return text
def final_transliterated_sentence(original, transliterated):
original = space_after_punct(original)
punct_list = ['!', '"', '#', '$', '%', '&', "'", '(', ')', '*', '+', ',', ' ', '-', '.', '/', ':', ';',
'<', '=', '>', '?', '@', '[', '\\', ']', '^', '_', '`', '{', '|', '}', '~', '…', '...', '।']
sentence = []
j = 0
for i in range(len(original.split())):
if original.split()[i] in punct_list:
sentence.append(original.split()[i])
elif original.split()[i][-1] in punct_list:
temp = transliterated.split()[j] + original.split()[i][-1]
sentence.append(temp)
j = j+1
elif original.split()[i][-1] not in punct_list:
temp = transliterated.split()[j]
sentence.append(temp)
j = j+1
transliterated_sentence = " ".join(sentence)
transliterated_sentence.replace(' ... ','...')
transliterated_sentence.replace('… ', '…')
return transliterated_sentence
def MNF_translate(text, dest_lang):
result = translate_client.translate(text, target_language = dest_lang)
translated_text = result['translatedText']
return translated_text
def google_length_checker(t, temp_sentence, t0):
if len(t.split()) >= len(temp_sentence.split()):
return t
elif len(t.split()) == len(temp_sentence.split())-1:
final_t = t+ " " + t0.split()[-1]
return final_t
elif len(t.split()) == len(temp_sentence.split())-2:
final_t = t+ " " + t0.split()[-2] + " " + t0.split()[-1]
return final_t
else:
return t
def Halant_remover(T3):
if T3[-1] == "्":
return T3[:-1]
else: return T3
def dial_comparison_transliteration_rom_dev_ph1(text, source_lang, source_script, dest_script):
source_lang = "hi"
source_script = "Latin"
dest_script = "Devanagari"
sources_name = {'0':'Azure', '1':'indic_trans', '2':'google', '3':'indic_trans_IAST'}
sentences=sentence_tokenize.sentence_split(text, lang='en')
priority_list =['Azure', 'indic_trans', 'google', 'indic_trans_IAST', ]
transliterated_text=[]
for sentence in sentences:
if sentence == "" or sentence == " . . ." or sentence == " . ." or sentence ==" . . ”":
continue
print(sentence)
OUT=[]
for word in sentence.split():
if word==".":
continue
print(word)
t0 = azure_transliteration(word, source_lang, source_script, dest_script)
#print(t0)
t1 = indic_trans(word, source_script, dest_script)
#print(t1)
t2 = google(word, 'en', 'hi')
#print(t2)
t3 = indic_transliteration_IAST(word)
#print(t3)
outputs=[t0, t1, t2, t3]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
OUT.append(out)
transliterated_text.append(" ".join(OUT))
return " ".join(transliterated_text)
def dial_comparison_transliteration_rom_dev_ph1_sentence_wise(text, source_lang, source_script, dest_script):
source_lang = "hi"
sources_name = {'0':'Azure', '1':'indic_trans', '2':'google', '3':'indic_trans_IAST'}
etc_punctuation =["", " . . .", " . .", " . . ”"]
sentences=sentence_tokenize.sentence_split(text, lang='en')
priority_list =['Azure', 'indic_trans', 'google', 'indic_trans_IAST']
transliterated_text=[]
for sentence in sentences:
if sentence in etc_punctuation:
continue
print("original_sentence", sentence)
temp_sentence = punct_remover(sentence)
print("sentence_without_punctuation", temp_sentence)
t00 = azure_transliteration(temp_sentence, source_lang, source_script, dest_script)
print(t00)
t11 = indic_trans(temp_sentence, source_script, dest_script)
print(t11)
t = google(temp_sentence, 'en', 'hi')
#print("btw", t)
t22 = google_length_checker(t, temp_sentence, t00)
print("T22 transliteration",t22)
t33 = indic_transliteration_IAST(temp_sentence)
print(t33)
Out= []
outputs = []
for i in range(len(temp_sentence.split())):
word = temp_sentence.split()[i]
# print("test of trasnliteration",i)
T0 = t00.split()[i]
# print("test of trasnliteration T0",T0)
# print("test of trasnliteration T11",t11)
T1 = t11.split()[i]
# print("test of trasnliteration T1",T1)
# print("test of trasnliteration T22",t22)
T2 = t22.split()[i]
# print("test of trasnliteration T2",T2)
T3 = t33.split()[i]
T3 = Halant_remover(T3)
outputs=[T0, T1, T2, T3]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
Out.append(out)
trans_sent_wo_punct = " ".join(Out)
print("trans_sent_wo_punct", trans_sent_wo_punct)
transliterated_sentence = final_transliterated_sentence(sentence, trans_sent_wo_punct)
print("trans_sent_w_punct", transliterated_sentence)
transliterated_text.append(transliterated_sentence)
return " ".join(transliterated_text)
def dial_comparison_transliteration_dev_rom_ph1_sentence_wise(text, source_lang, source_script, dest_script):
# sources_name = {'0':'indic_trans', '1':'Azure', '2':'libindic', '3':'sheetal', '4':'ritwik'}
sources_name = {'0':'indic_trans', '1':'Azure', '2':'libindic', '3':'sheetal'}
# priority_list =['indic_trans', 'Azure', 'ritwik', 'sheetal', 'libindic']
priority_list =['indic_trans', 'Azure', 'sheetal', 'libindic']
etc_punctuation =["", " . . .", " . .", " . . ”"]
sentences=sentence_tokenize.sentence_split(text, lang='hi')
transliterated_text=[]
for sentence in sentences:
#if sentence == "" or sentence == " . . ." or sentence == " . ." or sentence ==" . . ”":
if sentence in etc_punctuation:
continue
print("original_sentence", sentence)
temp_sentence = punct_remover(sentence)
print("sentence_without_punctuation", temp_sentence)
t0 = indic_trans(temp_sentence, source_script, dest_script)
print(t0)
t1 = azure_transliteration(temp_sentence, source_lang, source_script, dest_script)
print(t1)
t2 = libindic(temp_sentence, dest_script).rstrip()
print(t2)
t3 = sheetal(temp_sentence).replace('\n','')
print(t3)
# t4 = ritwik(temp_sentence).replace('\n','').rstrip()
# print(t4)
Out= []
outputs = []
for i in range(len(temp_sentence.split())):
word = temp_sentence.split()[i]
T0 = t0.split()[i]
T1 = t1.split()[i]
T2 = t2.split()[i]
T3 = t3.split()[i]
# T4 = t4.split()[i]
# outputs=[T0, T1, T2, T3, T4]
outputs=[T0, T1, T2, T3]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
Out.append(out)
trans_sent_wo_punct = " ".join(Out)
print("trans_sent_wo_punct", trans_sent_wo_punct)
transliterated_sentence = final_transliterated_sentence(sentence, trans_sent_wo_punct)
print("trans_sent_w_punct", transliterated_sentence)
transliterated_text.append(transliterated_sentence)
return " ".join(transliterated_text)
def dial_comparison_transliteration_dev_rom_ph1(text, source_lang, source_script, dest_script):
#sources_name = {'0':'indic_trans', '1':'Azure', '2':'libindic', '3':'sheetal', '4':'ritwik'}
sources_name = {'0':'indic_trans', '1':'Azure', '2':'libindic', '3':'sheetal'}
sentences=sentence_tokenize.sentence_split(text, lang='hi')
#priority_list =['indic_trans', 'Azure', 'ritwik, 'sheetal', 'libindic']
priority_list =['indic_trans', 'Azure', 'sheetal', 'libindic']
transliterated_text=[]
for sentence in sentences:
if sentence == "" or sentence == " . . ." or sentence == " . ." or sentence ==" . . ”":
continue
print(sentence)
OUT=[]
for word in sentence.split():
if word==".":
continue
print(word)
t0 = indic_trans(word, source_script, dest_script)
#print(t0)
t1 = azure_transliteration(word, source_lang, source_script, dest_script)
#print(t1)
t2 = libindic(word, dest_script).rstrip()
#print(t2)
t3 = sheetal(word).replace('\n','')
#print(t3)
#t4 = ritwik(word).replace('\n','').rstrip()
#print(t4)
# outputs=[t0, t1, t2, t3, t4]
outputs=[t0, t1, t2, t3]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
OUT.append(out)
transliterated_text.append(" ".join(OUT))
return " ".join(transliterated_text)
def dial_comparison_transliteration_arbic_to_rom_ph1(text, source_lang, source_script, dest_script):
print("hello")
sources_name = {'0':'indic_trans', '1':'Azure', '2':'buck_2_unicode'}
sentences=sentence_tokenize.sentence_split(text, lang='en')
priority_list =['indic_trans', 'Azure', 'buck_2_unicode' ]
transliterated_text=[]
for sentence in sentences:
if sentence == "" or sentence == " . . ." or sentence == " . ." or sentence ==" . . ”":
continue
print(sentence)
OUT=[]
for word in sentence.split():
if word==".":
continue
print(word)
t0 = indic_trans(word, source_script, dest_script)
t1 = azure_transliteration(word, source_lang, source_script, dest_script)
t2 = buck_2_unicode(word)
outputs=[t0, t1, t2]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
OUT.append(out)
transliterated_text.append(" ".join(OUT))
return " ".join(transliterated_text)
def dial_comparison_transliteration_kann_to_rom_ph1(text, source_lang, source_script, dest_script):
print("hello")
sources_name = {'0':'om_transliteration', '1':'indic_trans', '2':'libindic', '3':'Azure'}
sentences=sentence_tokenize.sentence_split(text, lang='en')
priority_list =['om_transliteration', 'indic_trans', 'libindic', 'Azure']
transliterated_text=[]
for sentence in sentences:
if sentence == "" or sentence == " . . ." or sentence == " . ." or sentence ==" . . ”":
continue
print(sentence)
OUT=[]
for word in sentence.split():
if word==".":
continue
print(word)
t0 = om_transliterator(word)
t1 = indic_trans(word, source_script, dest_script)
t2 = libindic(word, dest_script)
t3 = azure_transliteration(word, source_lang, source_script, dest_script)
outputs=[t0, t1, t2, t3]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
OUT.append(out)
transliterated_text.append(" ".join(OUT))
return " ".join(transliterated_text)
def dial_comparison_transliteration_tamil_to_rom_ph1(text, source_lang, source_script, dest_script):
print("hello")
sources_name = {'0':'Azure', '1':'libindic', '2':'indic_trans', }
sentences=sentence_tokenize.sentence_split(text, lang='en')
priority_list =['Azure', 'libindic', 'indic_trans']
transliterated_text=[]
for sentence in sentences:
if sentence == "" or sentence == " . . ." or sentence == " . ." or sentence ==" . . ”":
continue
print(sentence)
OUT=[]
for word in sentence.split():
if word==".":
continue
print(word)
t0 = azure_transliteration(word, source_lang, source_script, dest_script)
t2 = libindic(word, dest_script)
t1 = indic_trans(word, source_script, dest_script)
outputs=[t0, t1, t2]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
OUT.append(out)
transliterated_text.append(" ".join(OUT))
return " ".join(transliterated_text)
def dial_comparison_transliteration_beng_tel_mal_to_rom_ph1(text, source_lang, source_script, dest_script):
print("hello gujarati to latin")
sources_name = {'0':'Azure', '1':'indic_trans', '2':'libindic'}
sentences=sentence_tokenize.sentence_split(text, lang='en')
priority_list =['Azure', 'indic_trans', 'libindic']
transliterated_text=[]
for sentence in sentences:
if sentence == "" or sentence == " . . ." or sentence == " . ." or sentence ==" . . ”":
continue
#print(sentence)
OUT=[]
for word in sentence.split():
if word==".":
continue
print(word)
t0 = azure_transliteration(word, source_lang, source_script, dest_script)
t1 = indic_trans(word, source_script, dest_script)
t2 = libindic(word, dest_script)
outputs=[t0, t1, t2]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
OUT.append(out)
transliterated_text.append(" ".join(OUT))
return " ".join(transliterated_text)
def dial_comparison_transliteration_latin_gurmukhi(text,source_lang, source_script, dest_script):
source_lang = "pa"
sources_name = {'0':'Azure', '1':'indic_trans', '2':'indic_trans_IAST'}
etc_punctuation =["", " . . .", " . .", " . . ”"]
sentences=sentence_tokenize.sentence_split(text, lang='en')
priority_list =['Azure', 'indic_trans', 'indic_trans_IAST']
transliterated_text=[]
for sentence in sentences:
if sentence in etc_punctuation:
continue
temp_sentence = punct_remover(sentence)
t00 = azure_transliteration(temp_sentence, source_lang, source_script, dest_script)
t11 = indic_transliteration_GURMUKHI(temp_sentence)
t22 = unicode_transliteration_GURMUKHI(temp_sentence)
Out= []
outputs = []
for i in range(len(temp_sentence.split())):
word = temp_sentence.split()[i]
T0 = t00.split()[i]
T1 = t11.split()[i]
T2 = t22.split()[i]
outputs=[T0, T1, T2]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
Out.append(out)
trans_sent_wo_punct = " ".join(Out)
transliterated_sentence = final_transliterated_sentence(sentence, trans_sent_wo_punct)
transliterated_text.append(transliterated_sentence)
return " ".join(transliterated_text)
def dial_comparison_transliteration_latin_cyrillic(text,source_lang, source_script, dest_script):
source_lang = "bg"
sources_name = {'0':'Azure', '1':'indic_trans'}
etc_punctuation =["", " . . .", " . .", " . . ”"]
sentences=sentence_tokenize.sentence_split(text, lang='en')
priority_list =['Azure', 'indic_trans']
transliterated_text=[]
for sentence in sentences:
if sentence in etc_punctuation:
continue
temp_sentence = punct_remover(sentence)
t00 = azure_transliteration(temp_sentence, source_lang, source_script, dest_script)
t11 = transliteration_LATIN_CYRILLIC(temp_sentence)
#t22 = polygot(text)
Out= []
outputs = []
for i in range(len(temp_sentence.split())):
word = temp_sentence.split()[i]
T0 = t00.split()[i]
T1 = t11.split()[i]
#T2 = t22.split()[i]
outputs=[T0, T1]
#outputs=[T0, T1, T2]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
Out.append(out)
trans_sent_wo_punct = " ".join(Out)
transliterated_sentence = final_transliterated_sentence(sentence, trans_sent_wo_punct)
transliterated_text.append(transliterated_sentence)
return " ".join(transliterated_text)
def dial_comparison_transliteration_latin_telugu_sentence_wise(text, source_lang, source_script, dest_script):
source_lang = "te"
sources_name = {'0':'indic_trans', '1':'Azure'}
priority_list =['indic_trans', 'Azure',]
etc_punctuation =["", " . . .", " . .", " . . ”"]
sentences=sentence_tokenize.sentence_split(text, lang='hi')
transliterated_text=[]
for sentence in sentences:
#if sentence == "" or sentence == " . . ." or sentence == " . ." or sentence ==" . . ”":
if sentence in etc_punctuation:
continue
print("original_sentence", sentence)
temp_sentence = punct_remover(sentence)
print("sentence_without_punctuation", temp_sentence)
t0 = indic_transliteration_TELUGU(temp_sentence)
print(t0)
t1 = azure_transliteration(temp_sentence, source_lang, source_script, dest_script)
print(t1)
Out= []
outputs = []
for i in range(len(temp_sentence.split())):
word = temp_sentence.split()[i]
T0 = t0.split()[i]
T1 = t1.split()[i]
outputs=[T0, T1]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
Out.append(out)
trans_sent_wo_punct = " ".join(Out)
print("trans_sent_wo_punct", trans_sent_wo_punct)
transliterated_sentence = final_transliterated_sentence(sentence, trans_sent_wo_punct)
print("trans_sent_w_punct", transliterated_sentence)
transliterated_text.append(transliterated_sentence)
return " ".join(transliterated_text)
def dial_comparison_transliteration_gurmukhi_latin_sentence_wise(text, source_lang, source_script, dest_script):
source_lang = "pa"
sources_name = {'0':'indic_trans', '1':'Azure', '2':'unicode'}
priority_list =['indic_trans', 'Azure', 'unicode']
etc_punctuation =["", " . . .", " . .", " . . ”"]
sentences=sentence_tokenize.sentence_split(text, lang='hi')
transliterated_text=[]
for sentence in sentences:
#if sentence == "" or sentence == " . . ." or sentence == " . ." or sentence ==" . . ”":
if sentence in etc_punctuation:
continue
print("original_sentence", sentence)
temp_sentence = punct_remover(sentence)
print("sentence_without_punctuation", temp_sentence)
t0 = indic_transliteration_GURMUKHI_LATIN(temp_sentence)
# print(t0)
t1 = azure_transliteration(temp_sentence, source_lang, source_script, dest_script)
# print(t1)
t2 = unicode_transliteration_GURMUKHI_LATIN(temp_sentence).rstrip()
# print(t2)
Out= []
outputs = []
for i in range(len(temp_sentence.split())):
word = temp_sentence.split()[i]
T0 = t0.split()[i]
T1 = t1.split()[i]
T2 = t2.split()[i]
outputs=[T0, T1, T2]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
Out.append(out)
trans_sent_wo_punct = " ".join(Out)
print("trans_sent_wo_punct", trans_sent_wo_punct)
transliterated_sentence = final_transliterated_sentence(sentence, trans_sent_wo_punct)
print("trans_sent_w_punct", transliterated_sentence)
transliterated_text.append(transliterated_sentence)
return " ".join(transliterated_text)
def dial_comparison_transliteration_cyrilic_latin_sentence_wise(text, source_lang, source_script, dest_script):
print("cyrillic to latin")
source_lang = "bg"
sources_name = {'0':'indic_trans', '1':'Azure', '2':'unicode'}
priority_list =['indic_trans', 'Azure', 'unicode']
etc_punctuation =["", " . . .", " . .", " . . ”"]
sentences=sentence_tokenize.sentence_split(text, lang='hi')
transliterated_text=[]
for sentence in sentences:
#if sentence == "" or sentence == " . . ." or sentence == " . ." or sentence ==" . . ”":
if sentence in etc_punctuation:
continue
print("original_sentence", sentence)
temp_sentence = punct_remover(sentence)
print("sentence_without_punctuation", temp_sentence)
t0 = azure_transliteration(temp_sentence, source_lang, source_script, dest_script)
# print("t0",t0)
t1 = transliteration_CYRILIC_LATIN(temp_sentence)
# print("t1",t1)
t2 = ConvertToLatin(temp_sentence)
# print("t2",t2)
Out= []
outputs = []
for i in range(len(temp_sentence.split())):
word = temp_sentence.split()[i]
T0 = t0.split()[i]
T1 = t1.split()[i]
T2 = t2.split()[i]
outputs=[T0, T1, T2]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
Out.append(out)
trans_sent_wo_punct = " ".join(Out)
print("trans_sent_wo_punct", trans_sent_wo_punct)
transliterated_sentence = final_transliterated_sentence(sentence, trans_sent_wo_punct)
print("trans_sent_w_punct", transliterated_sentence)
transliterated_text.append(transliterated_sentence)
return " ".join(transliterated_text)
def dial_comparison_transliteration_latin_to_gu_or_ml_ta_bn(text,source_lang, source_script, dest_script):
print("destin script",dest_script)
if dest_script=="Gujarati":
source_lang="gu"
if dest_script=="Oriya":
source_lang="or"
if dest_script=="Malayalam":
source_lang="ml"
if dest_script=="Tamil":
source_lang="ta"
if dest_script=="Bengali":
source_lang="bn"
sources_name = {'0':'Azure', '1':'indic_trans', '2':'indic_trans_IAST'}
etc_punctuation =["", " . . .", " . .", " . . ”"]
sentences=sentence_tokenize.sentence_split(text, lang='en')
priority_list =['Azure', 'indic_trans', 'indic_trans_IAST']
transliterated_text=[]
for sentence in sentences:
if sentence in etc_punctuation:
continue
temp_sentence = punct_remover(sentence)
t00= azure_transliteration(temp_sentence, source_lang, source_script, dest_script)
t11 = libindic(temp_sentence, dest_script)
t22 = indic_trans(temp_sentence, source_script, dest_script)
Out= []
outputs = []
for i in range(len(temp_sentence.split())):
word = temp_sentence.split()[i]
T0 = t00.split()[i]
T1 = t11.split()[i]
T2 = t22.split()[i]
outputs=[T0, T1, T2]
out = compare_outputs_transliteration(word, outputs, sources_name, priority_list)
Out.append(out)
trans_sent_wo_punct = " ".join(Out)
transliterated_sentence = final_transliterated_sentence(sentence, trans_sent_wo_punct)
transliterated_text.append(transliterated_sentence)
return " ".join(transliterated_text)
def compare_outputs_transliteration(word, outputs, sources_name, priority_list):
#print(outputs)
O1ANDS1, O2ANDS2 = selection_source_transliteration(sources_name, outputs, priority_list)
print(O1ANDS1)
add_dial_comparison_doc2_transliteration(doc2, table2, word, O1ANDS1, O2ANDS2, sources_name)
return O1ANDS1[0]
def add_dial_comparison_doc2_transliteration(doc2, table2, word, O1ANDS1, O2ANDS2, sources_name):
row_Cells = table2.add_row().cells
row_Cells[0].text= word
row_Cells[1].text= O1ANDS1[0]
row_Cells[1].paragraphs[0].add_run('(Source : '+str(O1ANDS1[1])+')')
row_Cells[2].text= O2ANDS2[0]
row_Cells[2].paragraphs[0].add_run('(Source : '+str(O2ANDS2[1])+')')
def transliterate(dest_script,src_script,src_lang,text):
trans_text=text
if dest_script == "Latin" and src_script == "Devanagari":
# trans_text = dial_comparison_transliteration_dev_rom_ph1(text, src_lang, src_script,dest_script)
trans_text=dial_comparison_transliteration_dev_rom_ph1_sentence_wise(text, src_lang, src_script,dest_script)
elif dest_script == "Devanagari" and src_script == "Latin":
trans_text = dial_comparison_transliteration_rom_dev_ph1(text, src_lang, src_script,dest_script)
#trans_text=dial_comparison_transliteration_rom_dev_ph1_sentence_wise(text, src_lang, src_script,dest_script)
elif dest_script == "Latin" and src_script == "Arabic":
trans_text = dial_comparison_transliteration_arbic_to_rom_ph1(text, src_lang, src_script,dest_script )
elif dest_script == "Latin" and src_script == "Kannada":
trans_text = dial_comparison_transliteration_kann_to_rom_ph1(text, src_lang, src_script,dest_script )
elif dest_script == "Latin" and src_script == "Tamil":
trans_text = dial_comparison_transliteration_tamil_to_rom_ph1(text, src_lang, src_script,dest_script )
elif dest_script == "Latin" and src_script == "Bengali":
trans_text = dial_comparison_transliteration_beng_tel_mal_to_rom_ph1(text, src_lang, src_script,dest_script )
elif dest_script == "Latin" and src_script == "Telugu":
trans_text = dial_comparison_transliteration_beng_tel_mal_to_rom_ph1(text, src_lang, src_script,dest_script )
elif dest_script == "Latin" and src_script == "Malayalam":
trans_text = dial_comparison_transliteration_beng_tel_mal_to_rom_ph1(text, src_lang, src_script,dest_script )
elif dest_script == "Gurmukhi" and src_script == "Latin":
trans_text = dial_comparison_transliteration_latin_gurmukhi(text, src_lang, src_script,dest_script )
elif dest_script == "Cyrillic" and src_script == "Latin":
trans_text = dial_comparison_transliteration_latin_cyrillic(text, src_lang, src_script,dest_script )
elif dest_script == "Telugu" and src_script == "Latin":
trans_text = dial_comparison_transliteration_latin_telugu_sentence_wise(text, src_lang, src_script,dest_script )
elif dest_script == "Latin" and src_script == "Gurmukhi":
trans_text = dial_comparison_transliteration_gurmukhi_latin_sentence_wise(text, src_lang, src_script,dest_script )
elif dest_script == "Latin" and src_script == "Cyrillic":
trans_text = dial_comparison_transliteration_cyrilic_latin_sentence_wise(text, src_lang, src_script,dest_script )
elif dest_script == "Latin" and src_script == "Gujarati":
trans_text = dial_comparison_transliteration_beng_tel_mal_to_rom_ph1(text, src_lang, src_script,dest_script )
elif dest_script == "Latin" and src_script == "Oriya":
trans_text = dial_comparison_transliteration_beng_tel_mal_to_rom_ph1(text, src_lang, src_script,dest_script )
elif dest_script == "Gujarati" and src_script == "Latin":
trans_text = dial_comparison_transliteration_latin_to_gu_or_ml_ta_bn(text, src_lang, src_script,dest_script )
elif dest_script == "Oriya" and src_script == "Latin":
trans_text = dial_comparison_transliteration_latin_to_gu_or_ml_ta_bn(text, src_lang, src_script,dest_script )
elif dest_script == "Tamil" and src_script == "Latin":
trans_text = dial_comparison_transliteration_latin_to_gu_or_ml_ta_bn(text, src_lang, src_script,dest_script )
elif dest_script == "Malayalam" and src_script == "Latin":
trans_text =dial_comparison_transliteration_latin_to_gu_or_ml_ta_bn(text, src_lang, src_script,dest_script )
elif dest_script == "Bengali" and src_script == "Latin":
print("Bengali me aya hain :")
trans_text = dial_comparison_transliteration_latin_to_gu_or_ml_ta_bn(text, src_lang, src_script,dest_script )
return trans_text
#....
# print(scenes1)
for scene in tqdm(scenes1):
x = "False"
y = "False"
for i,line in enumerate(scene):
if i == 0:
continue
if type(line)==type(""):
x = "True"
non_dial_src_lang = language_detector(line)
else:
[speaker] = line.keys()
if speaker == 'Transition':
continue
if line[speaker][0] != 'NONE':
continue
if line[speaker][2] == "":
continue
y = "True"
dial_src_lang = language_detector(line[speaker][2])
dial_src_script = script_det(line[speaker][2])
print("dial_src_lang", dial_src_lang)
print("dial_src_script", dial_src_script)
if x == "True" and y == "True":
break
print("non_dial_src_lang", non_dial_src_lang)
# print("dial_src_lang", dial_src_lang)
print("dial_src_script", dial_src_script)
scenes_current=scenes1
if scenes_original:
scenes1=zip(scenes1,scenes_original)
else:
scenes1=zip(scenes1,scenes1)
for scene,scene_original in tqdm(scenes1):
for i,(line,line_original) in enumerate(zip(scene , scene_original)):
if i == 0:
addSlugLine(doc,line)
continue
if type(line)==type(""):
trans_text=line
if is_action_line_transliteration_required:
trans_text=transliterate(action_line_dest_script,action_line_src_script,action_line_src_lang,line)
addActionLine(doc, trans_text, non_dial_src_lang)
else:
print("In dialogue")
[speaker] = line.keys()
if speaker == 'Transition':
# if want to translate transition also along with action line use addTransition(doc,translator.translate(speaker,dest = gtrans_dict[actionline_dest_lang]).text)
addTransition(doc,line[speaker])
continue
addSpeaker(doc,speaker)
if line[speaker][0] != 'NONE': # In parenthitical part
addParenthetical(doc,line[speaker][0])
print("dialogue to be transliterated ", line[speaker][2])
if line[speaker][2] == "":
continue
trans_text=line[speaker][2]
if is_dialogue_transliteration_required:
trans_text=transliterate(dial_dest_script,dial_src_script,dial_src_lang,trans_text)
if dual_dial_script == "Yes":
print(line_original[speaker][2],trans_text)
dual_script(doc, line_original[speaker][2], trans_text, dial_src_lang)
else:
addDialogue(doc, trans_text, dial_src_lang)
doc.save(doc_file)
# file_tr = rf"{basePath}/media/scripts/Final_Table" + str(forFinal.split('.')[0])+"_trans_to_"+str(dial_dest_lang)+'_'+"final.docx"
# doc2.save(file_tr)
print('done file is saved')
return doc_file,scenes_current