cloudlanguagetools 11.1.0__tar.gz → 11.2.1__tar.gz

{cloudlanguagetools-11.1.0 → cloudlanguagetools-11.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cloudlanguagetools
-Version: 11.1.0
+Version: 11.2.1
 Summary: Interface with various cloud APIs for language processing such as translation, text to speech
 Home-page: https://github.com/Language-Tools/cloud-language-tools-core
 Author: Luc

{cloudlanguagetools-11.1.0 → cloudlanguagetools-11.2.1}/cloudlanguagetools/cereproc.py

@@ -50,7 +50,7 @@ class CereProcVoice(cloudlanguagetools.ttsvoice.TtsVoice):
 
 class CereProcService(cloudlanguagetools.service.Service):
     def __init__(self):
-        pass
+        self.service = cloudlanguagetools.constants.Service.CereProc
 
     def configure(self, config):
         self.username = config['username']
@@ -98,27 +98,13 @@ class CereProcService(cloudlanguagetools.service.Service):
         return result
 
     def get_tts_audio(self, text, voice_key, options):
-        output_temp_file = tempfile.NamedTemporaryFile()
-        output_temp_filename = output_temp_file.name
-
         voice_name = voice_key['name']
         url = f'https://api.cerevoice.com/v2/speak?voice={voice_name}&audio_format=mp3'
 
-
         ssml_text = f"""<?xml version="1.0" encoding="UTF-8"?>
 <speak xmlns="http://www.w3.org/2001/10/synthesis">{text}</speak>""".encode(encoding='utf-8')
 
-        # logging.debug(f'querying url: {url}')
-        response = requests.post(url, data=ssml_text, headers=self.get_auth_headers(), timeout=cloudlanguagetools.constants.RequestTimeout)
-
-        if response.status_code == 200:
-            with open(output_temp_filename, 'wb') as audio:
-                audio.write(response.content)
-            return output_temp_file
-
-        # otherwise, an error occured
-        error_message = f"Status code: {response.status_code} reason: {response.reason} voice: [{voice_name}]]"
-        raise cloudlanguagetools.errors.RequestError(error_message)
+        return self.get_tts_audio_base_post_request(url, data=ssml_text, headers=self.get_auth_headers())
 
 
     def get_transliteration_language_list(self):

{cloudlanguagetools-11.1.0 → cloudlanguagetools-11.2.1}/cloudlanguagetools/deepl.py

@@ -3,15 +3,16 @@ import requests
 import tempfile
 import logging
 import os
+import pprint
 
 import cloudlanguagetools.service
 import cloudlanguagetools.constants
 import cloudlanguagetools.languages
-import cloudlanguagetools.ttsvoice
 import cloudlanguagetools.translationlanguage
 import cloudlanguagetools.transliterationlanguage
 import cloudlanguagetools.errors
 
+logger = logging.getLogger(__name__)
 
 class DeepLTranslationLanguage(cloudlanguagetools.translationlanguage.TranslationLanguage):
     def __init__(self, language, language_id):
@@ -34,42 +35,43 @@ class DeepLService(cloudlanguagetools.service.Service):
     def get_tts_voice_list(self):
         return []
 
+    def get_headers(self):
+        return {
+            'Authorization': f'DeepL-Auth-Key {self.api_key}'
+        }
 
-    def get_translation_language_list(self):
+    def get_language_enum(self, deepl_language_code):
+        lowercase_str = deepl_language_code.lower()
+        override_map = {
+            'id': 'id_',
+            'zh': 'zh_cn',
+            'pt': 'pt_pt'
+        }
+        lowercase_str = override_map.get(lowercase_str, lowercase_str)
         language = cloudlanguagetools.languages.Language
-        result = [
-            DeepLTranslationLanguage(language.bg, 'BG'),
-            DeepLTranslationLanguage(language.cs, 'CS'),
-            DeepLTranslationLanguage(language.da, 'DA'),
-            DeepLTranslationLanguage(language.de, 'DE'),
-            DeepLTranslationLanguage(language.el, 'EL'),
-            DeepLTranslationLanguage(language.en, 'EN'),
-            DeepLTranslationLanguage(language.es, 'ES'),
-            DeepLTranslationLanguage(language.et, 'ET'),
-            DeepLTranslationLanguage(language.fi, 'FI'),
-            DeepLTranslationLanguage(language.fr, 'FR'),
-            DeepLTranslationLanguage(language.hu, 'HU'),
-            DeepLTranslationLanguage(language.id_, 'ID'),
-            DeepLTranslationLanguage(language.it, 'IT'),
-            DeepLTranslationLanguage(language.ja, 'JA'),
-            DeepLTranslationLanguage(language.lt, 'LT'),
-            DeepLTranslationLanguage(language.lv, 'LV'),
-            DeepLTranslationLanguage(language.nl, 'NL'),
-            DeepLTranslationLanguage(language.pl, 'PL'),
-            DeepLTranslationLanguage(language.pt_pt, 'PT-PT'),
-            DeepLTranslationLanguage(language.pt_br, 'PT-BR'),
-            DeepLTranslationLanguage(language.ro, 'RO'),
-            DeepLTranslationLanguage(language.ru, 'RU'),
-            DeepLTranslationLanguage(language.sk, 'SK'),
-            DeepLTranslationLanguage(language.sl, 'SL'),
-            DeepLTranslationLanguage(language.sv, 'SV'),
-            DeepLTranslationLanguage(language.tr, 'TR'),
-            DeepLTranslationLanguage(language.uk, 'UK'),
-            DeepLTranslationLanguage(language.zh_cn, 'ZH'),
-        ]
-        return result        
+        return language[lowercase_str]
 
 
+    def get_translation_language_list(self):
+        language = cloudlanguagetools.languages.Language
+        url = 'https://api.deepl.com/v2/languages'
+        response = requests.get(url, headers=self.get_headers(), timeout=cloudlanguagetools.constants.RequestTimeout)
+        response.raise_for_status()
+        # pprint.pprint(response.json())
+        results = []
+        for language_entry in response.json():
+            try:
+                # pprint.pprint(language_entry)
+                deepl_language_code = language_entry['language']
+                language_enum = self.get_language_enum(deepl_language_code)
+                results.append(DeepLTranslationLanguage(language_enum, deepl_language_code))
+                # if it's portuguese, replicate the entry for PT-PT and PT-BR
+                if language_enum == language.pt_pt:
+                    results.append(DeepLTranslationLanguage(language.pt_br, deepl_language_code))
+            except Exception as e:
+                logger.exception(f'could not process Deepl language entry: {language_entry}')
+        return results
+
     def get_tts_voice_list(self):
         result = []
         return result

{cloudlanguagetools-11.1.0 → cloudlanguagetools-11.2.1}/cloudlanguagetools/easypronunciation.py

@@ -1,6 +1,8 @@
 import os
 import requests
 import urllib.parse
+import json
+import logging
 
 import cloudlanguagetools.service
 import cloudlanguagetools.constants
@@ -10,6 +12,8 @@ import cloudlanguagetools.transliterationlanguage
 VARIANT_JAPANESE_ROMAJI = 'Romaji'
 VARIANT_JAPANESE_KANA = 'Kana'
 
+logger = logging.getLogger(__name__)
+
 class EasyPronunciationTransliterationLanguage(cloudlanguagetools.transliterationlanguage.TransliterationLanguage):
     def __init__(self, url_path, language, api_params, api_key, variant = None):
         self.service = cloudlanguagetools.constants.Service.EasyPronunciation
@@ -209,27 +213,41 @@ class EasyPronunciationService(cloudlanguagetools.service.Service):
         full_url = f'{api_url}?{encoded_parameters}'
 
         # print(full_url)
-        request = requests.get(full_url)
-        result = request.json()
-
-        # print(request)
-        # print(result)
-
-        if 'phonetic_transcription' in result:
-            phonetic_transcription = result['phonetic_transcription']
-            result_components = []
-            for entry in phonetic_transcription:
-                result_components.append(entry['transcriptions'][0])
-
-            if 'variant' in transliteration_key:
-                if transliteration_key['variant'] == VARIANT_JAPANESE_ROMAJI:
-                    result_components = [x['romaji'] for x in result_components]
-                if transliteration_key['variant'] == VARIANT_JAPANESE_KANA:
-                    result_components = [x['kana'] for x in result_components]
-
-            # print(result_components)
-            return ' '.join(result_components)
-
-        # an error occured
-        error_message = f'EasyPronunciation: could not perform conversion: {str(result)}'
-        raise cloudlanguagetools.errors.RequestError(error_message)
+        try:
+            response = requests.get(full_url)
+            response.raise_for_status()
+            result = response.json()
+
+            # print(request)
+            # print(result)
+
+            if 'phonetic_transcription' in result:
+                phonetic_transcription = result['phonetic_transcription']
+                result_components = []
+                for entry in phonetic_transcription:
+                    result_components.append(entry['transcriptions'][0])
+
+                if 'variant' in transliteration_key:
+                    if transliteration_key['variant'] == VARIANT_JAPANESE_ROMAJI:
+                        result_components = [x['romaji'] for x in result_components]
+                    if transliteration_key['variant'] == VARIANT_JAPANESE_KANA:
+                        result_components = [x['kana'] for x in result_components]
+
+                # print(result_components)
+                return ' '.join(result_components)
+
+            # an error occured
+            error_message = f'EasyPronunciation: could not perform conversion: {str(result)}'
+            raise cloudlanguagetools.errors.RequestError(error_message)
+
+        except requests.exceptions.ReadTimeout as exception:
+            raise cloudlanguagetools.errors.TimeoutError(f'timeout while retrieving EasyPronouncation transliteration')
+        # handle json decode error
+        except json.decoder.JSONDecodeError as exception:
+            logger.error(f'could not decode json response from EasyPronounciation: {response.content}')
+            raise cloudlanguagetools.errors.RequestError('Unable to retrieve transliteration from EasyPronounciation')
+        except Exception as exception:
+            # make sure not to leak url and key
+            msg = 'could not retrieve EasyPronouncation transliteration'
+            logger.exception(msg)
+            raise cloudlanguagetools.errors.RequestError(msg)

{cloudlanguagetools-11.1.0 → cloudlanguagetools-11.2.1}/cloudlanguagetools/elevenlabs.py

@@ -67,7 +67,7 @@ class ElevenLabsVoice(cloudlanguagetools.ttsvoice.TtsVoice):
 
 class ElevenLabsService(cloudlanguagetools.service.Service):
     def __init__(self):
-        pass
+        self.service = cloudlanguagetools.constants.Service.ElevenLabs
 
     def configure(self, config):
         self.api_key = config['api_key']
@@ -79,16 +79,12 @@ class ElevenLabsService(cloudlanguagetools.service.Service):
         }
 
     def get_tts_audio(self, text, voice_key, options):
-        import requests
-
-        CHUNK_SIZE = 1024
         voice_id = voice_key['voice_id']
         url = f'https://api.elevenlabs.io/v1/text-to-speech/{voice_id}'
 
         headers = self.get_headers()
         headers['Accept'] = "audio/mpeg"
 
-
         data = {
             "text": text,
             "model_id": voice_key['model_id'],
@@ -98,24 +94,7 @@ class ElevenLabsService(cloudlanguagetools.service.Service):
             }
         }
 
-        response = requests.post(url, json=data, headers=headers, timeout=cloudlanguagetools.constants.RequestTimeout)
-        if response.status_code != 200:
-            error_message = f'ElevenLabs: error processing TTS request: {response.status_code} {response.text}'
-            logger.error(error_message)
-            raise cloudlanguagetools.errors.RequestError(error_message)
-
-
-        response.raise_for_status()
-        
-        output_temp_file = tempfile.NamedTemporaryFile()
-        output_temp_filename = output_temp_file.name
-
-        with open(output_temp_filename, 'wb') as f:
-            for chunk in response.iter_content(chunk_size=CHUNK_SIZE):
-                if chunk:
-                    f.write(chunk)
-
-        return output_temp_file
+        return self.get_tts_audio_base_post_request(url, json=data, headers=headers)
 
 
 

{cloudlanguagetools-11.1.0 → cloudlanguagetools-11.2.1}/cloudlanguagetools/forvo.py

@@ -105,6 +105,10 @@ class ForvoService(cloudlanguagetools.service.Service):
             raise cloudlanguagetools.errors.TimeoutError(f'timeout while retrieving forvo audio')
         except cloudlanguagetools.errors.NotFoundError as exception:
             raise exception
+        # handle json decode error
+        except json.decoder.JSONDecodeError as exception:
+            logger.error(f'could not decode json response from forvo: {response.content}')
+            raise cloudlanguagetools.errors.RequestError('Unable to retrieve audio from Forvo')
         except Exception as exception:
             # make sure not to leak url and key
             logger.exception('could not retrieve forvo audio')

{cloudlanguagetools-11.1.0 → cloudlanguagetools-11.2.1}/cloudlanguagetools/languages.py

@@ -65,6 +65,7 @@ class Language(enum.Enum):
     id_ = ("Indonesian")
     ilo = ("Iloko")
     ga = ("Irish")
+    hne = ("Chhattisgarhi")
     it = ("Italian")
     ja = ("Japanese")
     jw = ("Javanese")

cloudlanguagetools-11.2.1/cloudlanguagetools/service.py

@@ -0,0 +1,53 @@
+import requests
+import tempfile
+import logging
+
+import cloudlanguagetools.constants
+
+logger = logging.getLogger(__name__)
+
+class Service():
+    def __init__(self):
+        pass
+
+    def get_service_name(self):
+        return self.service.name
+
+    def post_request(self, url, **kwargs):
+        kwargs['timeout'] = cloudlanguagetools.constants.RequestTimeout
+        return requests.post(url, **kwargs)
+
+    def get_tts_audio_base_post_request(self, url, **kwargs):
+        try:
+            response = self.post_request(url, **kwargs)
+            response.raise_for_status()
+            output_temp_file = tempfile.NamedTemporaryFile()
+            output_temp_filename = output_temp_file.name            
+            with open(output_temp_filename, 'wb') as audio:
+                audio.write(response.content)
+            return output_temp_file            
+        except requests.exceptions.ReadTimeout as exception:
+            raise cloudlanguagetools.errors.TimeoutError(f'timeout while retrieving {self.get_service_name()} audio')
+        except Exception as exception:
+            error_message = f'could not retrieve audio from {self.get_service_name()}'
+            logger.exception(error_message)
+            raise cloudlanguagetools.errors.RequestError(error_message)
+
+    # used for pre-loading models
+    def load_data(self):
+        pass
+
+    def get_tts_voice_list(self):
+        return []
+
+    def get_translation_language_list(self):
+        return []
+
+    def get_transliteration_language_list(self):
+        return []
+
+    def get_tokenization_options(self):
+        return []
+
+    def get_dictionary_lookup_list(self):
+        return []

{cloudlanguagetools-11.1.0 → cloudlanguagetools-11.2.1}/cloudlanguagetools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cloudlanguagetools
-Version: 11.1.0
+Version: 11.2.1
 Summary: Interface with various cloud APIs for language processing such as translation, text to speech
 Home-page: https://github.com/Language-Tools/cloud-language-tools-core
 Author: Luc

{cloudlanguagetools-11.1.0 → cloudlanguagetools-11.2.1}/setup.py

@@ -6,7 +6,7 @@ from setuptools.command.install import install
 # twine upload dist/*
 
 setup(name='cloudlanguagetools',
-      version='11.1.0',
+      version='11.2.1',
       description='Interface with various cloud APIs for language processing such as translation, text to speech',
       long_description=open('README.rst', encoding='utf-8').read(),
       url='https://github.com/Language-Tools/cloud-language-tools-core',

cloudlanguagetools-11.1.0/cloudlanguagetools/service.py

@@ -1,23 +0,0 @@
-
-class Service():
-    def __init__(self):
-        pass
-
-    # used for pre-loading models
-    def load_data(self):
-        pass
-
-    def get_tts_voice_list(self):
-        return []
-
-    def get_translation_language_list(self):
-        return []
-
-    def get_transliteration_language_list(self):
-        return []
-
-    def get_tokenization_options(self):
-        return []
-
-    def get_dictionary_lookup_list(self):
-        return []