108 lines
		
	
	
		
			3.7 KiB
		
	
	
	
		
			Python
		
	
	
		
			Executable File
		
	
	
			
		
		
	
	
			108 lines
		
	
	
		
			3.7 KiB
		
	
	
	
		
			Python
		
	
	
		
			Executable File
		
	
	
| from indictrans import Transliterator
 | ||
| from libindic.transliteration import getInstance
 | ||
| # import final_transliteration_only.py
 | ||
| t = getInstance()
 | ||
| from indic_transliteration import sanscript 
 | ||
| from indic_transliteration.sanscript import transliterate
 | ||
| import requests, uuid, json
 | ||
| from transliterate import translit, get_available_language_codes
 | ||
| import polyglot
 | ||
| from polyglot.text import Text
 | ||
| # from polyglot.transliteration import Transliterator
 | ||
| 
 | ||
| 
 | ||
| # translit = Transliterator(source_lang='en',target_lang='zh')
 | ||
| # text = "hello, good morning"
 | ||
| # text = Text(text)
 | ||
| # new_text = " "
 | ||
| # for x in text.transliterate("zh"):
 | ||
| #     new_text = new_text + str(x)
 | ||
| # for word in text.split():
 | ||
| #     new_text = new_text + " " + translit.transliterate(word)
 | ||
| # print(new_text)
 | ||
| # from transliterate import translit
 | ||
| # text = "Lorem ipsum dolor sit amet"
 | ||
| # blob = """Hello good morning"""
 | ||
| # text = Text(blob)
 | ||
| # final = []
 | ||
| # for x in text.transliterate("ar"):
 | ||
| #     final.append(x)
 | ||
| # final_text = " ".join(final)
 | ||
| # print(final_text)
 | ||
| # transliterator = Transliterator(source_lang="en", target_lang="ru")
 | ||
| # print(transliterator.transliterate(u"preprocessing"))
 | ||
| 
 | ||
|     # indic_src_lang = "eng"
 | ||
|     # indic_dest_lang = "urd"
 | ||
| 
 | ||
|     # # azure_src_script = ""
 | ||
| 
 | ||
| 
 | ||
|     # # #libindic-translation
 | ||
| 
 | ||
|     # # code = libindic_dest_script+'_IN' 
 | ||
|     # # lib_out = t.transliterate(text, code)
 | ||
|     # # # print("Libindic: ", lib_out)
 | ||
|     # # with open('readme.txt', 'w') as f:
 | ||
|     # #     f.write('Libindic Translierated' + "\n")
 | ||
|     # #     f.write(lib_out + "\n")
 | ||
|     # #     f.close()
 | ||
|         
 | ||
|     # # #indic-trans-IAST
 | ||
| 
 | ||
|     # # # ind_out = transliterate(text, sanscript.H, sanscript.)
 | ||
|     # # # # print("Indic-trans-IAST: ", ind_out)
 | ||
|     # # # with open('readme.txt', 'w') as f:
 | ||
|     # # #     f.write('Indic-trans IAST Translierated' + "\n")
 | ||
|     # # #     f.write(lib_out + "\n")
 | ||
|     # # #     f.close()
 | ||
| 
 | ||
|     #azure-transliteration
 | ||
| 
 | ||
| # subscription_key = "83ce6233419541929f7ab0d3035fca58"
 | ||
| # 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"
 | ||
| # azure_src_script = "Hans"
 | ||
| # azure_dest_script = "Latn"
 | ||
| # lang = "zh-Hans"
 | ||
| # text = "是的先生。"
 | ||
| # params = {'api-version': '3.0', 'language':lang, 'fromScript': azure_src_script, 'toScript': azure_dest_script}
 | ||
| # body = [{'text': text}]
 | ||
| # request = requests.post(constructed_url1, params=params, headers=headers, json=body)
 | ||
| # response = request.json()
 | ||
| # azure_out = response
 | ||
| # print(azure_out)
 | ||
| 
 | ||
| # # print(transliterate(azure_dest_script,azure_src_script,azure_src_lang,text))
 | ||
| 
 | ||
| 
 | ||
| # # azure = azure_transliteration(text, azure_src_lang, azure_dest_script)
 | ||
| # # with open('readme.txt', 'a') as f:
 | ||
| #     # f.write('Azure Translierated' + "\n")
 | ||
| #     # f.write(azure_out + "\n")
 | ||
| #     # f.close()
 | ||
| 
 | ||
| # accented_string = '''wǒ de míng zì shì tài lóng。 wǒ shì yì
 | ||
| # míng yuè nán shòu yī 。 qǐng nǐ néng
 | ||
| # shǎo zhǎo diǎn líng qián 。 wǒ de yòu
 | ||
| # yǎn bèi cì shāng , xiàn zài wǒ hé fǎ
 | ||
| # shī míng。 wǒ de qī zi gǎn rǎn le ài
 | ||
| # zī bìng dú , wǒ men xū yào qián wèi
 | ||
| # tā mǎi yào。'''
 | ||
| # # accented_string is of type 'unicode'
 | ||
| # import unidecode
 | ||
| # print(unidecode.unidecode(accented_string))
 | ||
| from anyascii import anyascii
 | ||
| 
 | ||
| s = anyascii('נתראה בקרוב')
 | ||
| y = anyascii('මට යන්න බෑ ')
 | ||
| print(s) |