from .translation_resources import google, aws, azure, yandex
from nltk.tokenize import regexp_tokenize
from .script_writing import default_script
from narration.vectorcode.code.functions import ScriptBreakdown
from .transliteration_resources import azure_transliteration, om_transliterator, libindic, indic_transliteration_IAST, indic_transliteration_ITRANS, sheetal, ritwik
from .script_reading import breaksen, getRefined, getSlugAndNonSlug, getSpeakers, getScenes
from .script_writing import addSlugLine, addActionLine, addSpeaker, addParenthetical, addDialogue, dual_script, addTransition, dial_checker, non_dial_checker
from .selection_source import selection_source, function5, function41, function311, function221, function2111, function11111, selection_source_transliteration, two_sources_two_outputs
from .translation_metric import manual_diff_score, bleu_diff_score, gleu_diff_score, meteor_diff_score, rouge_diff_score, diff_score, critera4_5
from .buck_2_unicode import buck_2_unicode
from .script_detector import script_cat
from google.cloud import translate_v2 as Translate
from google.cloud import translate
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
import uuid
import 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
import statistics
from statistics import mode
from indicnlp.tokenize import sentence_tokenize
import nltk
try:
print("time9999")
nltk.data.find('tokenizers/punkt')
except LookupError:
# nltk.download('punkt')
pass
try:
nltk.data.find('wordnet')
except LookupError:
###nltk.download('wordnet')
print("error in finding wordnet6666666")
from nltk.tokenize import sent_tokenize
print("7777777")
from .all_transliteration import all_transliteration
print("88")
from MNF.settings import BasePath
basePath = BasePath()
#basePath = '/home/user/mnf/project/MNF'
# google
# os.environ["GOOGLE_APPLICATION_CREDENTIALS"]="gifted-mountain-318504-0a5f94cda0c8.json"
#os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = rf"{basePath}/conversion/My First Project-2573112d5326.json"
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = rf"{basePath}/MNF/json_keys/authentication.json"
# os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = rf"{basePath}/conversion/gifted-mountain-318504-4f001d5f08db.json"
translate_client = Translate.Client()
print("9999")
client = translate.TranslationServiceClient()
print("101010")
project_id = 'authentic-bongo-272808'
location = "global"
parent = f"projects/{project_id}/locations/{location}"
print("11111")
def action_line_english(script_path):
filename1 = script_path
translation_list = ['en', 'ta', 'hi', 'ar', 'ur', 'kn', 'gu', 'bg', 'bn', 'te', 'ml', 'ru', 'sr', 'uk', 'hr', 'ga', 'sq', 'mr',
'fa', 'tr', 'hu', 'it', 'ro', 'pa', 'gu', 'or', 'zh-CN', 'zh-TW', 'ne', 'fr', 'es', 'id', 'el', 'ja', 'ko', 'be', 'uz', 'sd', 'af', 'de', 'is',
'ig', 'la', 'pt', 'my', 'th', 'su', 'lo', 'am', 'si', 'az', 'kk', 'mk', 'bs', 'ps', 'mg', 'ms', 'yo', 'cs', 'da', 'nl', 'tl', 'no', 'sl', 'sv',
'vi', 'cy', 'he', 'hy', 'km', 'ka', 'mn', 'ku', 'ky', 'tk', 'he', 'hy', 'km', 'ka', 'mn', 'ku', 'ky', 'tk', 'fi', 'ht', 'haw', 'lt', 'lb', 'mt',
'pl', 'eo', 'tt', 'ug', 'ha', 'so', 'sw', 'yi', 'eu', 'ca', 'ceb', 'co', 'et', 'fy', 'gl', 'hmn', 'rw', 'lv', 'mi', 'sm', 'gd', 'st', 'sn', 'sk',
'xh', 'zu']
# create an instance of a word document
doc = docx.Document()
doc_file = BasePath()+"/conversion/translation/translated/" + "actionline" + \
"trans" + '_of_' + ntpath.basename(filename1)
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
# process the input script and return scenes
refined, total_scenes = getRefined(filename1)
# print(refined)
# log.debug(refined)
sluglines, without_slug = getSlugAndNonSlug(refined)
# print(sluglines)
# log.debug(sluglines)
characters = getSpeakers(without_slug)
# log.debug(characters)
scenes, actionline, parenthetical_lis, speakers, dialogues = getScenes(
refined, total_scenes, characters)
# refined, total_scenes = ScriptBreakdown().getRefined(filename1)
# sluglines, without_slug = ScriptBreakdown().getSlugAndNonSlug(refined)
# characters = ScriptBreakdown().getSpeakers(without_slug)
# scenes, actionline, parenthetical_lis, speakers, dialogues = ScriptBreakdown().getScenes(
# refined, total_scenes, characters)
print(scenes)
# to detect the language
def language_detector(text):
result = translate_client.translate(text, target_language='hi')
det_lang = result["detectedSourceLanguage"]
return det_lang
class myDict(dict):
def __init__(self):
self = dict()
def add(self, key, value):
self[key] = value
def all_translator(sentence, source_lang, target_lang):
i = 0
trans = myDict()
sources_name = myDict()
try:
globals()['t%s' % i] = google(sentence, source_lang, target_lang)
trans.add(str(i), globals()['t%s' % i])
sources_name.add(str(i), "GOOGLE")
i = i+1
except:
pass
try:
globals()['t%s' % i] = ibm_watson(
sentence, source_lang, target_lang)
trans.add(str(i), globals()['t%s' % i])
sources_name.add(str(i), "IBM_WATSON")
i = i+1
except:
pass
try:
globals()['t%s' % i] = aws(sentence, source_lang, target_lang)
trans.add(str(i), globals()['t%s' % i])
sources_name.add(str(i), "AWS")
i = i+1
except:
pass
try:
globals()['t%s' % i] = azure(sentence, target_lang)
trans.add(str(i), globals()['t%s' % i])
sources_name.add(str(i), "AZURE")
i = i+1
except:
pass
try:
globals()['t%s' % i] = lingvanex(
sentence, source_lang, target_lang)
trans.add(str(i), globals()['t%s' % i])
sources_name.add(str(i), "LINGVANEX")
i = i+1
except:
pass
try:
globals()['t%s' % i] = yandex(sentence, source_lang, target_lang)
trans.add(str(i), globals()['t%s' % i])
sources_name.add(str(i), "YANDEX")
i = i+1
except:
pass
trans_text = compare_outputs(
sentence, trans["0"], trans, sources_name, target_lang)
return trans_text
def recursive_dots(Sentence, source_lang, target_lang):
special_characters = ['....', '…', '. . .', '...']
translated_text = []
for i in special_characters:
if i not in Sentence:
continue
Sentences = Sentence.split(i)
for Sentence in Sentences:
if Sentence == "" or Sentence == " ":
continue
if any(ext in Sentence for ext in special_characters):
trans_text = translation_with_spcecial_dots(
Sentence, source_lang, target_lang)
else:
if Sentence != Sentences[-1]:
trans_text = all_translator(
Sentence, source_lang, target_lang) + i
else:
trans_text = all_translator(
Sentence, source_lang, target_lang)
translated_text.append(trans_text)
return " ".join(translated_text)
def translation_with_spcecial_dots(Sentence, source_lang, target_lang):
special_characters = ['....', '…', '. . .', '...']
translated_text = []
for ext in special_characters:
if ext in Sentence:
splitter = ext
break
Sentences = Sentence.split(splitter)
for Sentence in Sentences:
if Sentence == "" or Sentence == " ":
continue
if any(ext in Sentence for ext in special_characters):
trans_text = recursive_dots(Sentence, source_lang, target_lang)
else:
if Sentence != Sentences[-1]:
trans_text = all_translator(
Sentence, source_lang, target_lang) + splitter
else:
trans_text = all_translator(
Sentence, source_lang, target_lang)
translated_text.append(trans_text)
return " ".join(translated_text)
def translate_comparison(text, source_lang, target_lang):
sentences = sent_tokenize(text)
special_characters = ['....', '…', '. . .', '...']
translated_text = []
for sentence in sentences:
if any(ext in sentence for ext in special_characters):
trans_text = translation_with_spcecial_dots(
sentence, source_lang, target_lang)
translated_text.append(trans_text)
else:
trans_text = all_translator(sentence, source_lang, target_lang)
translated_text.append(trans_text)
return " ".join(translated_text)
def script_det(text):
punctuations = '''!()-[]{};:'"\,<>./?@#$%^&*_~“"”'''
no_punct = ""
for char in text:
if char not in punctuations:
no_punct = char
break
#print("alphabet", no_punct)
script = script_cat(no_punct)[0]
#print("script", script)
return script
def punct_remover(string):
# punctuations = '''!()-[]{};:'"\,<>./?@#$%^&*_~…।“”'''
punctuations = '''!()-[]{};:'"\,<>./?@#$%^&*_~…।1234567890“”"'''
for x in string.lower():
if x in punctuations:
string = string.replace(x, " ")
return string
def word_transliterate(sentence, dest_script):
return sentence
def final_out(output1, output2, output3, dest_lang):
temp_output1 = punct_remover(output1)
temp_output2 = punct_remover(output2)
temp_output3 = punct_remover(output3)
# for word in regexp_tokenize(output1, "[\w']+")
for word in temp_output1.split():
#print("word", word)
if script_det(word) != default_script[dest_lang]:
for word in temp_output2.split():
if script_det(word) != default_script[dest_lang]:
for word in temp_output3.split():
if script_det(word) != default_script[dest_lang]:
# print("in3")
output1 = word_transliterate(
output1, default_script[dest_lang])
return output1
return output3
return output2
return output1
# take a sentence and give translated sentence by comparing outputs from different resources
def compare_outputs(sentence, t0, trans, sources_name, target_lang):
k = []
s = []
methods_name = {'0': 'MNF', '1': 'Gleu',
'2': 'Meteor', '3': 'Rougen', '4': 'Rougel'}
google_output = t0
#print("google", google_output)
output1, source1 = manual_diff_score(trans, sources_name)
#print("MNF", output1)
output2, source2 = gleu_diff_score(trans, sources_name)
#print("gleu", output2)
output3, source3 = meteor_diff_score(trans, sources_name)
#print("meteor", output3)
output4, source4, output5, source5 = rouge_diff_score(
trans, sources_name)
#print("rougen", output4)
#print("rougel", output5)
if google_output == output1 == output2 == output3 == output4 == output5:
#print("all output are same as google")
return google_output
else:
if google_output != output1:
k.append(output1)
s.append(source1)
else:
k.append(" ")
s.append(" ")
if google_output != output2:
k.append(output2)
s.append(source2)
else:
k.append(" ")
s.append(" ")
if google_output != output3:
k.append(output3)
s.append(source3)
else:
k.append(" ")
s.append(" ")
if google_output != output4:
k.append(output4)
s.append(source4)
else:
k.append(" ")
s.append(" ")
if google_output != output5:
k.append(output5)
s.append(source5)
else:
k.append(" ")
s.append(" ")
k.insert(0, sentence)
k.insert(1, google_output)
s1ANDm1, s2ANDm2, s3ANDm3 = selection_source(
s, sources_name, trans, methods_name)
# print("s1", s1ANDm1)
# print("s2", s2ANDm2)
# print("s3", s3ANDm3)
# print(s1ANDm1[0])
# print(sources_name)
#add_dial_comparison_doc2(doc2, table2, sentence, s1ANDm1, s2ANDm2, s3ANDm3, sources_name, trans)
for a, b in sources_name.items():
if b == s1ANDm1[0]:
k = a
output1 = trans[str(k)]
if s2ANDm2[0] != "":
for c, d in sources_name.items():
if d == s2ANDm2[0]:
l = c
output2 = trans[str(l)]
else:
output2 = output1
if s3ANDm3[0] != "":
for e, f in sources_name.items():
if f == s3ANDm3[0]:
m = e
output3 = trans[str(m)]
else:
output3 = output1
# print("output1", output1)
# print("output2", output2)
# print("output3", output3)
output = final_out(output1, output2, output3, target_lang)
# print("output", output)
return output
# to return the table with best 3 outputs
def add_dial_comparison_doc2(doc2, table2, sentence, s1ANDm1, s2ANDm2, s3ANDm3, sources_name, trans):
row_Cells = table2.add_row().cells
for a, b in sources_name.items():
if b == s1ANDm1[0]:
k = a
output1 = trans[str(k)]
row_Cells[0].text = sentence
row_Cells[1].text = output1
row_Cells[1].paragraphs[0].add_run('(Source : '+str(s1ANDm1[0])+')')
row_Cells[1].paragraphs[0].add_run('(Methods : '+str(s1ANDm1[1])+')')
if s2ANDm2[0] == "":
row_Cells[2].text = ""
else:
for a, b in sources_name.items():
if b == s2ANDm2[0]:
k = a
output2 = trans[str(k)]
row_Cells[2].text = output2
row_Cells[2].paragraphs[0].add_run(
'(Source : '+str(s2ANDm2[0])+')')
row_Cells[2].paragraphs[0].add_run(
'(Methods : '+str(s2ANDm2[1])+')')
if s3ANDm3[0] == "":
row_Cells[3].text = ""
else:
for a, b in sources_name.items():
if b == s3ANDm3[0]:
k = a
output3 = trans[str(k)]
row_Cells[3].text = output3
row_Cells[3].paragraphs[0].add_run(
'(Source : '+str(s3ANDm3[0])+')')
row_Cells[3].paragraphs[0].add_run(
'(Methods : '+str(s3ANDm3[1])+')')
def actionline_translation(text, non_dial_src_lang, non_dial_dest_lang):
if non_dial_src_lang in translation_list and non_dial_dest_lang in translation_list:
trans_text = translate_comparison(
text, non_dial_src_lang, non_dial_dest_lang)
addActionLine(doc, trans_text, non_dial_dest_lang)
else:
addActionLine(doc, text, non_dial_dest_lang)
# def all_transliterator(text, source_script, dest_script):
# return text
count = 0
for scene in tqdm(scenes[:]):
for i, line in enumerate(scene):
if i == 0:
continue
if type(line) == type(""):
if count == 0:
non_dial_src_lang = language_detector(line)
non_dial_script = script_det(line)
count += 1
else:
pass
if count != 0:
break
print("non_dial_src_lang", non_dial_src_lang)
print("non_dial_script", non_dial_script)
non_dial_dest_lang = "en"
for scene in tqdm(scenes[:]):
for i, line in enumerate(scene):
if i == 0:
addSlugLine(doc, line)
continue
if type(line) == type(""):
if non_dial_src_lang == non_dial_dest_lang:
# print("here1")
addActionLine(doc, line, non_dial_dest_lang)
else:
# print("here2")
if non_dial_script == default_script[non_dial_src_lang]:
# print("here3")
actionline_translation(
line, non_dial_src_lang, non_dial_dest_lang)
else:
transliterated_text = all_transliteration(line, script_det(
non_dial_src_lang), default_script[non_dial_src_lang])
actionline_translation(
transliterated_text, non_dial_src_lang, non_dial_dest_lang)
else:
[speaker] = line.keys()
if speaker == 'Transition':
addTransition(doc, line[speaker])
continue
addSpeaker(doc, speaker)
if line[speaker][0] != 'NONE':
addParenthetical(doc, line[speaker][0])
if line[speaker][2] == "":
continue
addDialogue(doc, line[speaker][2], non_dial_dest_lang)
doc.save(doc_file)
return doc_file
# doc2.save("....")