154 lines
135 KiB
Python
154 lines
135 KiB
Python
|
import ntpath
|
||
|
|
import datetime
|
||
|
|
from pytz import timezone
|
||
|
|
import os
|
||
|
|
from MNF.settings import BasePath
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# Global Variables
|
||
|
|
basePath = BasePath()
|
||
|
|
|
||
|
|
|
||
|
|
special_characters=['....', '…', '. . .', '...']
|
||
|
|
|
||
|
|
|
||
|
|
punctuations = '''!()-[]{};:'"\,<>./?@#$%^&*_~“"”'''
|
||
|
|
|
||
|
|
|
||
|
|
# -> New Data
|
||
|
|
|
||
|
|
languages = \
|
||
|
|
[
|
||
|
|
'Afrikaans', 'Albanian', 'Arabic', 'Assamese', 'Aymara', 'Azerbaijani', 'Bambara', 'Basque', 'Belarusian',
|
||
|
|
'Bengali', 'Bhojpuri', 'Bosnian', 'Bulgarian', 'Catalan', 'Cebuano', 'Chichewa', 'Chinese (Simplified)',
|
||
|
|
'Chinese (Traditional)', 'Corsican', 'Croatian', 'Czech', 'Danish', 'Dogri', 'Dutch', 'English', 'Esperanto',
|
||
|
|
'Estonian', 'Ewe', 'Filipino', 'Finnish', 'French', 'Frisian', 'Galician', 'Ganda', 'Georgian', 'German',
|
||
|
|
'Guarani', 'Gujarati', 'Haitian Creole', 'Hausa', 'Hebrew', 'Hindi', 'Hmong', 'Hungarian', 'Icelandic', 'Igbo',
|
||
|
|
'Iloko', 'Indonesian', 'Irish Gaelic', 'Italian', 'Japanese', 'Javanese', 'Kannada', 'Kazakh', 'Khmer',
|
||
|
|
'Kinyarwanda', 'Konkani', 'Korean', 'Krio', 'Kurdish (Kurmanji)', 'Kurdish (Sorani)', 'Kyrgyz', 'Lao', 'Latin',
|
||
|
|
'Latvian', 'Lingala', 'Lithuanian', 'Luxembourgish', 'Macedonian', 'Maithili', 'Malagasy', 'Malay', 'Malayalam',
|
||
|
|
'Maltese', 'Maori', 'Marathi', 'Mizo', 'Mongolian', 'Nepali', 'Northern Sotho', 'Norwegian', 'Odia (Oriya)',
|
||
|
|
'Oromo', 'Pashto', 'Persian', 'Polish', 'Portuguese', 'Punjabi', 'Quechua', 'Romanian', 'Russian', 'Samoan',
|
||
|
|
'Sanskrit', 'Serbian', 'Sesotho', 'Shona', 'Sindhi', 'Sinhala', 'Slovak', 'Slovenian', 'Somali', 'Spanish',
|
||
|
|
'Sundanese', 'Swahili', 'Swedish', 'Tajik', 'Tamil', 'Tatar', 'Telugu', 'Thai', 'Tsonga', 'Turkish', 'Turkmen',
|
||
|
|
'Twi', 'Ukrainian', 'Urdu', 'Uyghur', 'Uzbek', 'Vietnamese', 'Welsh', 'Xhosa', 'Yiddish', 'Yoruba', 'Zulu']
|
||
|
|
codes = [
|
||
|
|
'af', 'sq', 'ar', 'as', 'ay', 'az', 'bm', 'eu', 'be', 'bn', 'bho', 'bs', 'bg', 'ca', 'ceb', 'ny', 'zh-CN', 'zh-TW', 'co', 'hr', 'cs', 'da', 'doi', 'nl', 'en', 'eo', 'et', 'ee', 'tl', 'fi', 'fr', 'fy', 'gl', 'lg', 'ka', 'de', 'gn', 'gu', 'ht', 'ha', 'he', 'hi', 'hmn', 'hu', 'is', 'ig', 'ilo', 'id', 'ga', 'it', 'ja', 'jv', 'kn', 'kk', 'km', 'rw', 'gom', 'ko', 'kri', 'ku', 'ckb', 'ky', 'lo', 'la', 'lv', 'ln', 'lt', 'lb', 'mk', 'mai', 'mg', 'ms', 'ml', 'mt', 'mi', 'mr', 'lus', 'mn', 'ne', 'nso', 'no', 'or', 'om', 'ps', 'fa', 'pl', 'pt', 'pa', 'qu', 'ro', 'ru', 'sm', 'sa', 'sr', 'st', 'sn', 'sd', 'si', 'sk', 'sl', 'so', 'es', 'su', 'sw', 'sv', 'tg', 'ta', 'tt', 'te', 'th', 'ts', 'tr', 'tk', 'ak', 'uk', 'ur', 'ug', 'uz', 'vi', 'cy', 'xh', 'yi', 'yo', 'zu']
|
||
|
|
language_2_code = {
|
||
|
|
'':'', 'Afrikaans': 'af', 'Albanian': 'sq', 'Arabic': 'ar', 'Assamese': 'as', 'Aymara': 'ay', 'Azerbaijani': 'az', 'Bambara': 'bm', 'Basque': 'eu', 'Belarusian': 'be', 'Bengali': 'bn', 'Bhojpuri': 'bho', 'Bosnian': 'bs', 'Bulgarian': 'bg', 'Catalan': 'ca', 'Cebuano': 'ceb', 'Chichewa': 'ny', 'Chinese (Simplified)': 'zh-CN', 'Chinese (Traditional)': 'zh-TW', 'Corsican': 'co', 'Croatian': 'hr', 'Czech': 'cs', 'Danish': 'da', 'Dogri': 'doi', 'Dutch': 'nl', 'English': 'en', 'Esperanto': 'eo', 'Estonian': 'et', 'Ewe': 'ee', 'Filipino': 'fil', 'Finnish': 'fi', 'French': 'fr', 'Frisian': 'fy', 'Galician': 'gl', 'Ganda': 'lg', 'Georgian': 'ka', 'German': 'de', 'Guarani': 'gn', 'Gujarati': 'gu', 'Haitian Creole': 'ht', 'Hausa': 'ha', 'Hebrew': 'he', 'Hindi': 'hi', 'Hmong': 'hmn', 'Hungarian': 'hu', 'Icelandic': 'is', 'Igbo': 'ig', 'Iloko': 'ilo', 'Indonesian': 'id', 'Irish Gaelic': 'ga', 'Italian': 'it', 'Japanese': 'ja', 'Javanese': 'jv', 'Kannada': 'kn', 'Kazakh': 'kk', 'Khmer': 'km', 'Kinyarwanda': 'rw', 'Konkani': 'gom', 'Korean': 'ko', 'Krio': 'kri', 'Kurdish (Kurmanji)': 'ku', 'Kurdish (Sorani)': 'ckb', 'Kyrgyz': 'ky', 'Lao': 'lo', 'Latin': 'la', 'Latvian': 'lv', 'Lingala': 'ln', 'Lithuanian': 'lt', 'Luxembourgish': 'lb', 'Macedonian': 'mk', 'Maithili': 'mai', 'Malagasy': 'mg', 'Malay': 'ms', 'Malayalam': 'ml', 'Maltese': 'mt', 'Maori': 'mi', 'Marathi': 'mr', 'Mizo': 'lus', 'Mongolian': 'mn', 'Nepali': 'ne', 'Northern Sotho': 'nso', 'Norwegian': 'no', 'Odia (Oriya)': 'or', 'Oromo': 'om', 'Pashto': 'ps', 'Persian': 'fa', 'Polish': 'pl', 'Portuguese': 'pt', 'Punjabi': 'pa', 'Quechua': 'qu', 'Romanian': 'ro', 'Russian': 'ru', 'Samoan': 'sm', 'Sanskrit': 'sa', 'Serbian': 'sr', 'Sesotho': 'st', 'Shona': 'sn', 'Sindhi': 'sd', 'Sinhala': 'si', 'Slovak': 'sk', 'Slovenian': 'sl', 'Somali': 'so', 'Spanish': 'es', 'Sundanese': 'su', 'Swahili': 'sw', 'Swedish': 'sv', 'Tajik': 'tg', 'Tamil': 'ta', 'Tatar': 'tt', 'Telugu': 'te', 'Thai': 'th', 'Tsonga': 'ts', 'Turkish': 'tr', 'Turkmen': 'tk', 'Twi': 'ak', 'Ukrainian': 'uk', 'Urdu': 'ur', 'Uyghur': 'ug', 'Uzbek': 'uz', 'Vietnamese': 'vi', 'Welsh': 'cy', 'Xhosa': 'xh', 'Yiddish': 'yi', 'Yoruba': 'yo', 'Zulu': 'zu'}
|
||
|
|
code_2_language = {
|
||
|
|
'': '', 'af': 'Afrikaans', 'sq': 'Albanian', 'ar': 'Arabic', 'as': 'Assamese', 'ay': 'Aymara', 'az': 'Azerbaijani', 'bm': 'Bambara', 'eu': 'Basque', 'be': 'Belarusian', 'bn': 'Bengali', 'bho': 'Bhojpuri', 'bs': 'Bosnian', 'bg': 'Bulgarian', 'ca': 'Catalan', 'ceb': 'Cebuano', 'ny': 'Chichewa', 'zh-CN': 'Chinese (Simplified)', 'zh-TW': 'Chinese (Traditional)', 'co': 'Corsican', 'hr': 'Croatian', 'cs': 'Czech', 'da': 'Danish', 'doi': 'Dogri', 'nl': 'Dutch', 'en': 'English', 'eo': 'Esperanto', 'et': 'Estonian', 'ee': 'Ewe', 'fil': 'Filipino', 'fi': 'Finnish', 'fr': 'French', 'fy': 'Frisian', 'gl': 'Galician', 'lg': 'Ganda', 'ka': 'Georgian', 'de': 'German', 'gn': 'Guarani', 'gu': 'Gujarati', 'ht': 'Haitian Creole', 'ha': 'Hausa', 'he': 'Hebrew', 'hi': 'Hindi', 'hmn': 'Hmong', 'hu': 'Hungarian', 'is': 'Icelandic', 'ig': 'Igbo', 'ilo': 'Iloko', 'id': 'Indonesian', 'ga': 'Irish Gaelic', 'it': 'Italian', 'ja': 'Japanese', 'jv': 'Javanese', 'kn': 'Kannada', 'kk': 'Kazakh', 'km': 'Khmer', 'rw': 'Kinyarwanda', 'gom': 'Konkani', 'ko': 'Korean', 'kri': 'Krio', 'ku': 'Kurdish (Kurmanji)', 'ckb': 'Kurdish (Sorani)', 'ky': 'Kyrgyz', 'lo': 'Lao', 'la': 'Latin', 'lv': 'Latvian', 'ln': 'Lingala', 'lt': 'Lithuanian', 'lb': 'Luxembourgish', 'mk': 'Macedonian', 'mai': 'Maithili', 'mg': 'Malagasy', 'ms': 'Malay', 'ml': 'Malayalam', 'mt': 'Maltese', 'mi': 'Maori', 'mr': 'Marathi', 'lus': 'Mizo', 'mn': 'Mongolian', 'ne': 'Nepali', 'nso': 'Northern Sotho', 'no': 'Norwegian', 'or': 'Odia (Oriya)', 'om': 'Oromo', 'ps': 'Pashto', 'fa': 'Persian', 'pl': 'Polish', 'pt': 'Portuguese', 'pa': 'Punjabi', 'qu': 'Quechua', 'ro': 'Romanian', 'ru': 'Russian', 'sm': 'Samoan', 'sa': 'Sanskrit', 'sr': 'Serbian', 'st': 'Sesotho', 'sn': 'Shona', 'sd': 'Sindhi', 'si': 'Sinhala', 'sk': 'Slovak', 'sl': 'Slovenian', 'so': 'Somali', 'es': 'Spanish', 'su': 'Sundanese', 'sw': 'Swahili', 'sv': 'Swedish', 'tg': 'Tajik', 'ta': 'Tamil', 'tt': 'Tatar', 'te': 'Telugu', 'th': 'Thai', 'ts': 'Tsonga', 'tr': 'Turkish', 'tk': 'Turkmen', 'ak': 'Twi', 'uk': 'Ukrainian', 'ur': 'Urdu', 'ug': 'Uyghur', 'uz': 'Uzbek', 'vi': 'Vietnamese', 'cy': 'Welsh', 'xh': 'Xhosa', 'yi': 'Yiddish', 'yo': 'Yoruba', 'zu': 'Zulu'}
|
||
|
|
language_dict = {
|
||
|
|
'Afrikaans': ['Afrikaans', 'Albanian', 'Arabic', 'Azerbaijani', 'Basque', 'Bengali', 'Bosnian', 'Bulgarian', 'Catalan', 'Chinese (Simplified)', 'Chinese (Traditional)', 'Croatian', 'Czech', 'Danish', 'Dutch', 'English', 'Estonian', 'Filipino', 'Finnish', 'French', 'Galician', 'Georgian', 'German', 'Gujarati', 'Haitian Creole', 'Hausa', 'Hebrew', 'Hindi', 'Hungarian', 'Icelandic', 'Igbo', 'Indonesian', 'Irish Gaelic', 'Italian', 'Japanese', 'Kannada', 'Kazakh', 'Khmer', 'Kinyarwanda', 'Korean', 'Kurdish (Kurmanji)', 'Kyrgyz', 'Lao', 'Latvian', 'Lithuanian', 'Macedonian', 'Malagasy', 'Malay', 'Malayalam', 'Maltese', 'Maori', 'Marathi', 'Mongolian', 'Nepali', 'Norwegian', 'Odia (Oriya)', 'Pashto', 'Persian', 'Polish', 'Portuguese', 'Punjabi', 'Romanian', 'Russian', 'Samoan', 'Serbian', 'Sesotho', 'Shona', 'Sindhi', 'Sinhala', 'Slovak', 'Slovenian', 'Somali', 'Spanish', 'Swahili', 'Swedish', 'Tamil', 'Tatar', 'Telugu', 'Thai', 'Turkish', 'Turkmen', 'Ukrainian', 'Urdu', 'Uyghur', 'Uzbek', 'Vietnamese', 'Welsh', 'Xhosa', 'Yoruba', 'Zulu'], 'Albanian': ['Albanian', 'Afrikaans', 'Arabic', 'Azerbaijani', 'Basque', 'Bengali', 'Bosnian', 'Bulgarian', 'Catalan', 'Chinese (Simplified)', 'Chinese (Traditional)', 'Croatian', 'Czech', 'Danish', 'Dutch', 'English', 'Estonian', 'Filipino', 'Finnish', 'French', 'Galician', 'Georgian', 'German', 'Gujarati', 'Haitian Creole', 'Hausa', 'Hebrew', 'Hindi', 'Hungarian', 'Icelandic', 'Igbo', 'Indonesian', 'Irish Gaelic', 'Italian', 'Japanese', 'Kannada', 'Kazakh', 'Khmer', 'Kinyarwanda', 'Korean', 'Kurdish (Kurmanji)', 'Kyrgyz', 'Lao', 'Latvian', 'Lithuanian', 'Macedonian', 'Malagasy', 'Malay', 'Malayalam', 'Maltese', 'Maori', 'Marathi', 'Mongolian', 'Nepali', 'Norwegian', 'Odia (Oriya)', 'Pashto', 'Persian', 'Polish', 'Portuguese', 'Punjabi', 'Romanian', 'Russian', 'Samoan', 'Serbian', 'Sesotho', 'Shona', 'Sindhi', 'Sinhala', 'Slovak', 'Slovenian', 'Somali', 'Spanish', 'Swahili', 'Swedish', 'Tamil', 'Tatar', 'Telugu', 'Thai', 'Turkish', 'Turkmen', 'Ukrainian', 'Urdu', 'Uyghur', 'Uzbek', 'Vietnamese', 'Welsh', 'Xhosa', 'Yoruba', 'Zulu'], 'Arabic': ['Arabic', 'Afrikaans', 'Albanian', 'Azerbaijani', 'Basque', 'Bengali', 'Bosnian', 'Bulgarian', 'Catalan', 'Chinese (Simplified)', 'Chinese (Traditional)', 'Croatian', 'Czech', 'Danish', 'Dutch', 'English', 'Estonian', 'Filipino', 'Finnish', 'French', 'Galician', 'Georgian', 'German', 'Gujarati', 'Haitian Creole', 'Hausa', 'Hebrew', 'Hindi', 'Hungarian', 'Icelandic', 'Igbo', 'Indonesian', 'Irish Gaelic', 'Italian', 'Japanese', 'Kannada', 'Kazakh', 'Khmer', 'Kinyarwanda', 'Korean', 'Kurdish (Kurmanji)', 'Kyrgyz', 'Lao', 'Latvian', 'Lithuanian', 'Macedonian', 'Malagasy', 'Malay', 'Malayalam', 'Maltese', 'Maori', 'Marathi', 'Mongolian', 'Nepali', 'Norwegian', 'Odia (Oriya)', 'Pashto', 'Persian', 'Polish', 'Portuguese', 'Punjabi', 'Romanian', 'Russian', 'Samoan', 'Serbian', 'Sesotho', 'Shona', 'Sindhi', 'Sinhala', 'Slovak', 'Slovenian', 'Somali', 'Spanish', 'Swahili', 'Swedish', 'Tamil', 'Tatar', 'Telugu', 'Thai', 'Turkish', 'Turkmen', 'Ukrainian', 'Urdu', 'Uyghur', 'Uzbek', 'Vietnamese', 'Welsh', 'Xhosa', 'Yoruba', 'Zulu'], 'Assamese': ['Assamese', 'Afrikaans', 'Albanian', 'Arabic', 'Azerbaijani', 'Basque', 'Bengali', 'Bosnian', 'Bulgarian', 'Catalan', 'Croatian', 'Czech', 'Danish', 'Dutch', 'English', 'Estonian', 'Finnish', 'French', 'Galician', 'Georgian', 'German', 'Gujarati', 'Haitian Creole', 'Hausa', 'Hebrew', 'Hindi', 'Hungarian', 'Icelandic', 'Igbo', 'Indonesian', 'Irish Gaelic', 'Italian', 'Japanese', 'Kannada', 'Kazakh', 'Khmer', 'Kinyarwanda', 'Korean', 'Kurdish (Kurmanji)', 'Kyrgyz', 'Lao', 'Latvian', 'Lithuanian', 'Macedonian', 'Malagasy', 'Malay', 'Malayalam', 'Maltese', 'Maori', 'Marathi', 'Mongolian', 'Nepali', 'Norwegian', 'Odia (Oriya)', 'Pashto', 'Persian', 'Polish', 'Portuguese', 'Punjabi', 'Romanian', 'Russian', 'Samoan', 'Sesotho', 'Shona', 'Sindhi', 'Sinhala', 'Slovak', 'Slovenian', 'Somali', 'Spanish', 'Swahili', 'Swedish', 'Tamil', 'Tatar', 'Telugu', 'Thai', 'Turkish', 'Turkmen', 'Ukrainian', 'Urdu', 'Uyghur', 'Uzbek', 'Vietna
|
||
|
|
language_script = {
|
||
|
|
'Afrikaans': 'Latin', 'Albanian': 'Latin', 'Arabic': 'Arabic', 'Assamese': 'Bengali', 'Aymara': 'Latin', 'Azerbaijani': 'Latin', 'Bambara': 'Latin', 'Basque': 'Latin', 'Belarusian': 'Cyrillic', 'Bengali': 'Bengali', 'Bhojpuri': 'Devanagari', 'Bosnian': 'Latin', 'Bulgarian': 'Cyrillic', 'Catalan': 'Latin', 'Cebuano': 'Latin', 'Chichewa': 'Latin', 'Chinese (Simplified)': 'Hanji', 'Chinese (Traditional)': 'Hanji', 'Corsican': 'Latin', 'Croatian': 'Latin', 'Czech': 'Latin', 'Danish': 'Latin', 'Dogri': 'Devanagari', 'Dutch': 'Latin', 'English': 'Latin', 'Esperanto': 'Latin', 'Estonian': 'Latin', 'Ewe': 'Latin', 'Filipino': 'Latin', 'Finnish': 'Latin', 'French': 'Latin', 'Frisian': 'Latin', 'Galician': 'Latin', 'Ganda': 'Latin', 'Georgian': 'Georgian', 'German': 'Latin', 'Guarani': 'Latin', 'Gujarati': 'Gujarati', 'Haitian Creole': 'Latin', 'Hausa': 'Latin', 'Hebrew': 'Hebrew', 'Hindi': 'Devanagari', 'Hmong': 'Latin', 'Hungarian': 'Latin', 'Icelandic': 'Latin', 'Igbo': 'Latin', 'Iloko': 'Latin', 'Indonesian': 'Latin', 'Irish Gaelic': 'Latin', 'Italian': 'Latin', 'Japanese': 'Hanji', 'Javanese': 'Latin', 'Kannada': 'Kannada', 'Kazakh': 'Cyrillic', 'Khmer': 'Khmer', 'Kinyarwanda': 'Latin', 'Konkani': 'Devanagari', 'Korean': 'Hangul', 'Krio': 'Latin', 'Kurdish (Kurmanji)': 'Latin', 'Kurdish (Sorani)': 'Arabic', 'Kyrgyz': 'Cyrillic', 'Lao': 'Lao', 'Latin': 'Latin', 'Latvian': 'Latin', 'Lingala': 'Latin', 'Lithuanian': 'Latin', 'Luxembourgish': 'Latin', 'Macedonian': 'Cyrillic', 'Maithili': 'Devanagari', 'Malagasy': 'Latin', 'Malay': 'Latin', 'Malayalam': 'Malayalam', 'Maltese': 'Latin', 'Maori': 'Latin', 'Marathi': 'Devanagari', 'Mizo': 'Latin', 'Mongolian': 'Cyrillic', 'Nepali': 'Devanagari', 'Northern Sotho': 'Latin', 'Norwegian': 'Latin', 'Odia (Oriya)': 'Oriya', 'Oromo': 'Latin', 'Pashto': 'Arabic', 'Persian': 'Arabic', 'Polish': 'Latin', 'Portuguese': 'Latin', 'Punjabi': 'Gurmukhi', 'Quechua': 'Latin', 'Romanian': 'Latin', 'Russian': 'Cyrillic', 'Samoan': 'Latin', 'Sanskrit': 'Devanagari', 'Serbian': 'Cyrillic', 'Sesotho': 'Latin', 'Shona': 'Latin', 'Sindhi': 'Arabic', 'Sinhala': 'Sinhala', 'Slovak': 'Latin', 'Slovenian': 'Latin', 'Somali': 'Latin', 'Spanish': 'Latin', 'Sundanese': 'Latin', 'Swahili': 'Latin', 'Swedish': 'Latin', 'Tajik': 'Cyrillic', 'Tamil': 'Tamil', 'Tatar': 'Cyrillic', 'Telugu': 'Telugu', 'Thai': 'Thai', 'Tsonga': 'Latin', 'Turkish': 'Latin', 'Turkmen': 'Latin', 'Twi': 'Latin', 'Ukrainian': 'Cyrillic', 'Urdu': 'Arabic', 'Uyghur': 'Arabic', 'Uzbek': 'Latin', 'Vietnamese': 'Latin', 'Welsh': 'Latin', 'Xhosa': 'Latin', 'Yiddish': 'Hebrew', 'Yoruba': 'Latin', 'Zulu': 'Latin'}
|
||
|
|
code_script = {
|
||
|
|
'af': 'Latin', 'sq': 'Latin', 'ar': 'Arabic', 'as': 'Bengali', 'ay': 'Latin', 'az': 'Latin', 'bm': 'Latin', 'eu': 'Latin', 'be': 'Cyrillic', 'bn': 'Bengali', 'bho': 'Devanagari', 'bs': 'Latin', 'bg': 'Cyrillic', 'ca': 'Latin', 'ceb': 'Latin', 'ny': 'Latin', 'zh-CN': 'Hanji', 'zh-TW': 'Hanji', 'co': 'Latin', 'hr': 'Latin', 'cs': 'Latin', 'da': 'Latin', 'doi': 'Devanagari', 'nl': 'Latin', 'en': 'Latin', 'eo': 'Latin', 'et': 'Latin', 'ee': 'Latin', 'fil': 'Latin', 'fi': 'Latin', 'fr': 'Latin', 'fy': 'Latin', 'gl': 'Latin', 'lg': 'Latin', 'ka': 'Georgian', 'de': 'Latin', 'gn': 'Latin', 'gu': 'Gujarati', 'ht': 'Latin', 'ha': 'Latin', 'he': 'Hebrew', 'hi': 'Devanagari', 'hmn': 'Latin', 'hu': 'Latin', 'is': 'Latin', 'ig': 'Latin', 'ilo': 'Latin', 'id': 'Latin', 'ga': 'Latin', 'it': 'Latin', 'ja': 'Hanji', 'jv': 'Latin', 'kn': 'Kannada', 'kk': 'Cyrillic', 'km': 'Khmer', 'rw': 'Latin', 'gom': 'Devanagari', 'ko': 'Hangul', 'kri': 'Latin', 'ku': 'Latin', 'ckb': 'Arabic', 'ky': 'Cyrillic', 'lo': 'Lao', 'la': 'Latin', 'lv': 'Latin', 'ln': 'Latin', 'lt': 'Latin', 'lb': 'Latin', 'mk': 'Cyrillic', 'mai': 'Devanagari', 'mg': 'Latin', 'ms': 'Latin', 'ml': 'Malayalam', 'mt': 'Latin', 'mi': 'Latin', 'mr': 'Devanagari', 'lus': 'Latin', 'mn': 'Cyrillic', 'ne': 'Devanagari', 'nso': 'Latin', 'no': 'Latin', 'or': 'Oriya', 'om': 'Latin', 'ps': 'Arabic', 'fa': 'Arabic', 'pl': 'Latin', 'pt': 'Latin', 'pa': 'Gurmukhi', 'qu': 'Latin', 'ro': 'Latin', 'ru': 'Cyrillic', 'sm': 'Latin', 'sa': 'Devanagari', 'sr': 'Cyrillic', 'st': 'Latin', 'sn': 'Latin', 'sd': 'Arabic', 'si': 'Sinhala', 'sk': 'Latin', 'sl': 'Latin', 'so': 'Latin', 'es': 'Latin', 'su': 'Latin', 'sw': 'Latin', 'sv': 'Latin', 'tg': 'Cyrillic', 'ta': 'Tamil', 'tt': 'Cyrillic', 'te': 'Telugu', 'th': 'Thai', 'ts': 'Latin', 'tr': 'Latin', 'tk': 'Latin', 'ak': 'Latin', 'uk': 'Cyrillic', 'ur': 'Arabic', 'ug': 'Arabic', 'uz': 'Latin', 'vi': 'Latin', 'cy': 'Latin', 'xh': 'Latin', 'yi': 'Hebrew', 'yo': 'Latin', 'zu': 'Latin'}
|
||
|
|
script_dict = {
|
||
|
|
"Devanagari": ["Devanagari", "Latin", "Oriya", "Malayalam", "Telugu", "Gujarati", "Tamil", "Arabic", "Bengali","Kannada", "Cyrillic"],
|
||
|
|
"Arabic": ["Arabic", "Latin", "Gurmukhi", "Devanagari", "Gujarati", "Cyrillic", "Kannada", "Telugu", "Tamil",
|
||
|
|
"Malayalam", "Bengali", "Oriya"],
|
||
|
|
"Malayalam": ["Malayalam", "Latin", "Devanagari", "Kannada", "Tamil", "Telugu"],
|
||
|
|
"Telugu": ["Telugu", "Latin", "Devanagari", "Kannada", "Tamil", "Malayalam"],
|
||
|
|
"Bengali": ["Bengali", "Latin", "Kannada", "Tamil", "Telugu", "Malayalam"],
|
||
|
|
"Kannada":["Kannada", "Latin", "Devanagari", "Tamil", "Telugu", "Malayalam", "Bengali", "Cyrillic", "Telugu", "Gujarati", "Gurmukhi", "Oriya"],
|
||
|
|
"Hanji": ["Hanji", "Latin", "Devanagari", "Arabic", "Gurmukhi", "Gujarati", "Oriya"],
|
||
|
|
"Gurmukhi": ["Gurmukhi", "Latin", "Gujarati", "Oriya", "Arabic"],
|
||
|
|
"Gujarati": ["Gujarati", "Latin", "Devanagari", "Gurmukhi", "Oriya", "Arabic"],
|
||
|
|
"Oriya": ["Oriya", "Latin", "Devanagari", "Gujarati", "Gurmukhi"],
|
||
|
|
"Kana": ["Kana"],
|
||
|
|
"Javanese": ["Javanese"],
|
||
|
|
"Hangul": ["Hangul"],
|
||
|
|
"Burmese": ["Burmese"],
|
||
|
|
"Thai": ["Thai", "Latin"],
|
||
|
|
"Sundanese": ["Sundanese"],
|
||
|
|
"Lao": ["Lao"],
|
||
|
|
"Amharic": ["Amharic"],
|
||
|
|
"Sinhala": ["Sinhala", "Latin"],
|
||
|
|
"Hebrew": ["Hebrew", "Latin"],
|
||
|
|
"Cyrillic": ["Cyrillic", "Latin", "Tamil", "Arabic"],
|
||
|
|
"Armanian": ["Armanian"],
|
||
|
|
"Khmer": ["Khmer"],
|
||
|
|
"Georgian": ["Georgian"],
|
||
|
|
"Mongolian": ["Mongolian", "Latin"],
|
||
|
|
"Tamil": ["Tamil", "Latin", "Kannada", "Telugu", "Devanagari", "Malayalam", "Cyrillic", "Gujarati", "Gurmukhi",
|
||
|
|
"Bengali", "Oriya"],
|
||
|
|
"Latin": ["Latin", "Bengali", "Devanagari", "Gurmukhi", "Cyrillic", "Gujarati", "Malayalam", "Oriya", "Tamil",
|
||
|
|
"Telugu", "Kannada", "Arabic"],
|
||
|
|
}
|
||
|
|
|
||
|
|
language_code = code_2_language
|
||
|
|
script_code = language_script
|
||
|
|
translation_list = codes
|
||
|
|
|
||
|
|
|
||
|
|
def get_language_script(language):
|
||
|
|
''' Getting Default Script of a Language '''
|
||
|
|
return language_script.get(language)
|
||
|
|
|
||
|
|
|
||
|
|
def get_language_script_code(language):
|
||
|
|
''' Getting Default Script code of a Language '''
|
||
|
|
return language_script.get(code_2_language.get(language))
|
||
|
|
|
||
|
|
|
||
|
|
def original_script(text):
|
||
|
|
''' returns language for a lang code '''
|
||
|
|
def get_expansion(lang):
|
||
|
|
return code_2_language.get(lang)
|
||
|
|
|
||
|
|
|
||
|
|
def get_expansion(lang):
|
||
|
|
''' returns language for a lang code '''
|
||
|
|
return code_2_language.get(lang)
|
||
|
|
|
||
|
|
|
||
|
|
def is_in_translation_list(lan_code):
|
||
|
|
''' checks if a language code is in available languages for translation '''
|
||
|
|
return lan_code in codes
|
||
|
|
|
||
|
|
|
||
|
|
def is_a_special_characters(char):
|
||
|
|
''' checks if a char is special character or not '''
|
||
|
|
return char in special_characters
|
||
|
|
|
||
|
|
|
||
|
|
def get_list_special_character():
|
||
|
|
''' returns all special characters '''
|
||
|
|
return special_characters
|
||
|
|
|
||
|
|
|
||
|
|
def set_google_application_credentials():
|
||
|
|
''' will set google application credentials if called '''
|
||
|
|
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = rf"{basePath}/MNF/json_keys/authentication.json"
|
||
|
|
|
||
|
|
|
||
|
|
def get_user_script_data(script_id):
|
||
|
|
''' Useless Function '''
|
||
|
|
pass
|
||
|
|
|
||
|
|
|
||
|
|
def get_pdf_save_dir():
|
||
|
|
''' returns conversion pdf saving directory '''
|
||
|
|
return rf'{basePath}/media/scripts/translated'
|
||
|
|
|
||
|
|
|
||
|
|
def get_doc_file(dial_dest_lang, script_path, data=[]):
|
||
|
|
file_name = str((((script_path.split("/"))[-1]).split("."))[0]) + ".docx"
|
||
|
|
''' will return a doc file name for saving the translation '''
|
||
|
|
|
||
|
|
if len(data) > 0:
|
||
|
|
print("id kya hai be",script_path)
|
||
|
|
doc_file = basePath+f"/media/scripts/sample_script_translations/{data[7]}/{str(data[0])}_{dial_dest_lang}_{str(data[1])}_{str(data[2])}_{str(data[3])}_{str(data[4])}_{str(data[5])}_{str(data[6])}_" + file_name
|
||
|
|
return doc_file
|
||
|
|
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_' + file_name
|
||
|
|
|
||
|
|
|
||
|
|
return doc_file
|
||
|
|
|
||
|
|
|
||
|
|
|