Nearly finished Polly implementation

getmoto · Sep 26, 2017 · fcacecb · fcacecb
1 parent b17136e
commit fcacecb
Show file tree

Hide file tree

Showing 12 changed files with 520 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -100,6 +100,8 @@ It gets even better! Moto isn't just for Python code and it isn't just for S3. L
 |------------------------------------------------------------------------------|
 | KMS                   | @mock_kms        | basic endpoints done              |
 |------------------------------------------------------------------------------|
+| Polly                 | @mock_polly      | all endpoints done                |
+|------------------------------------------------------------------------------|
 | RDS                   | @mock_rds        | core endpoints done               |
 |------------------------------------------------------------------------------|
 | RDS2                  | @mock_rds2       | core endpoints done               |

diff --git a/moto/__init__.py b/moto/__init__.py
@@ -22,10 +22,11 @@
 from .emr import mock_emr, mock_emr_deprecated  # flake8: noqa
 from .events import mock_events  # flake8: noqa
 from .glacier import mock_glacier, mock_glacier_deprecated  # flake8: noqa
-from .opsworks import mock_opsworks, mock_opsworks_deprecated  # flake8: noqa
 from .iam import mock_iam, mock_iam_deprecated  # flake8: noqa
 from .kinesis import mock_kinesis, mock_kinesis_deprecated  # flake8: noqa
 from .kms import mock_kms, mock_kms_deprecated  # flake8: noqa
+from .opsworks import mock_opsworks, mock_opsworks_deprecated  # flake8: noqa
+from .polly import mock_polly  # flake8: noqa
 from .rds import mock_rds, mock_rds_deprecated  # flake8: noqa
 from .rds2 import mock_rds2, mock_rds2_deprecated  # flake8: noqa
 from .redshift import mock_redshift, mock_redshift_deprecated  # flake8: noqa

diff --git a/moto/backends.py b/moto/backends.py
@@ -23,6 +23,7 @@
 from moto.kinesis import kinesis_backends
 from moto.kms import kms_backends
 from moto.opsworks import opsworks_backends
+from moto.polly import polly_backends
 from moto.rds2 import rds2_backends
 from moto.redshift import redshift_backends
 from moto.route53 import route53_backends
@@ -54,9 +55,10 @@
     'iam': iam_backends,
     'moto_api': moto_api_backends,
     'instance_metadata': instance_metadata_backends,
-    'opsworks': opsworks_backends,
     'kinesis': kinesis_backends,
     'kms': kms_backends,
+    'opsworks': opsworks_backends,
+    'polly': polly_backends,
     'redshift': redshift_backends,
     'rds': rds2_backends,
     's3': s3_backends,

diff --git a/moto/polly/__init__.py b/moto/polly/__init__.py
@@ -0,0 +1,6 @@
+from __future__ import unicode_literals
+from .models import polly_backends
+from ..core.models import base_decorator
+
+polly_backend = polly_backends['us-east-1']
+mock_polly = base_decorator(polly_backends)
diff --git a/moto/polly/models.py b/moto/polly/models.py
@@ -0,0 +1,114 @@
+from __future__ import unicode_literals
+from xml.etree import ElementTree as ET
+import datetime
+
+import boto3
+from moto.core import BaseBackend, BaseModel
+
+from .resources import VOICE_DATA
+from .utils import make_arn_for_lexicon
+
+DEFAULT_ACCOUNT_ID = 123456789012
+
+
+class Lexicon(BaseModel):
+    def __init__(self, name, content, region_name):
+        self.name = name
+        self.content = content
+        self.size = 0
+        self.alphabet = None
+        self.last_modified = None
+        self.language_code = None
+        self.lexemes_count = 0
+        self.arn = make_arn_for_lexicon(DEFAULT_ACCOUNT_ID, name, region_name)
+
+        self.update()
+
+    def update(self, content=None):
+        if content is not None:
+            self.content = content
+
+        # Probably a very naive approach, but it'll do for now.
+        try:
+            root = ET.fromstring(self.content)
+            self.size = len(self.content)
+            self.last_modified = int((datetime.datetime.now() -
+                                      datetime.datetime(1970, 1, 1)).total_seconds())
+            self.lexemes_count = len(root.findall('.'))
+
+            for key, value in root.attrib.items():
+                if key.endswith('alphabet'):
+                    self.alphabet = value
+                elif key.endswith('lang'):
+                    self.language_code = value
+
+        except Exception as err:
+            raise ValueError('Failure parsing XML: {0}'.format(err))
+
+    def to_dict(self):
+        return {
+            'Attributes': {
+                'Alphabet': self.alphabet,
+                'LanguageCode': self.language_code,
+                'LastModified': self.last_modified,
+                'LexemesCount': self.lexemes_count,
+                'LexiconArn': self.arn,
+                'Size': self.size
+            }
+        }
+
+    def __repr__(self):
+        return '<Lexicon {0}>'.format(self.name)
+
+
+class PollyBackend(BaseBackend):
+    def __init__(self, region_name=None):
+        super(PollyBackend, self).__init__()
+        self.region_name = region_name
+
+        self._lexicons = {}
+
+    def reset(self):
+        region_name = self.region_name
+        self.__dict__ = {}
+        self.__init__(region_name)
+
+    def describe_voices(self, language_code, next_token):
+        if language_code is None:
+            return VOICE_DATA
+
+        return [item for item in VOICE_DATA if item['LanguageCode'] == language_code]
+
+    def delete_lexicon(self, name):
+        # implement here
+        del self._lexicons[name]
+
+    def get_lexicon(self, name):
+        # Raises KeyError
+        return self._lexicons[name]
+
+    def list_lexicons(self, next_token):
+
+        result = []
+
+        for name, lexicon in self._lexicons.items():
+            lexicon_dict = lexicon.to_dict()
+            lexicon_dict['Name'] = name
+
+            result.append(lexicon_dict)
+
+        return result
+
+    def put_lexicon(self, name, content):
+        # If lexicon content is bad, it will raise ValueError
+        if name in self._lexicons:
+            # Regenerated all the stats from the XML
+            # but keeps the ARN
+            self._lexicons.update(content)
+        else:
+            lexicon = Lexicon(name, content, region_name=self.region_name)
+            self._lexicons[name] = lexicon
+
+
+available_regions = boto3.session.Session().get_available_regions("polly")
+polly_backends = {region: PollyBackend(region_name=region) for region in available_regions}
diff --git a/moto/polly/resources.py b/moto/polly/resources.py
@@ -0,0 +1,61 @@
+VOICE_DATA = [
+    {'Id': 'Joanna', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Gender': 'Female', 'Name': 'Joanna'},
+    {'Id': 'Mizuki', 'LanguageCode': 'ja-JP', 'LanguageName': 'Japanese', 'Gender': 'Female', 'Name': 'Mizuki'},
+    {'Id': 'Filiz', 'LanguageCode': 'tr-TR', 'LanguageName': 'Turkish', 'Gender': 'Female', 'Name': 'Filiz'},
+    {'Id': 'Astrid', 'LanguageCode': 'sv-SE', 'LanguageName': 'Swedish', 'Gender': 'Female', 'Name': 'Astrid'},
+    {'Id': 'Tatyana', 'LanguageCode': 'ru-RU', 'LanguageName': 'Russian', 'Gender': 'Female', 'Name': 'Tatyana'},
+    {'Id': 'Maxim', 'LanguageCode': 'ru-RU', 'LanguageName': 'Russian', 'Gender': 'Male', 'Name': 'Maxim'},
+    {'Id': 'Carmen', 'LanguageCode': 'ro-RO', 'LanguageName': 'Romanian', 'Gender': 'Female', 'Name': 'Carmen'},
+    {'Id': 'Ines', 'LanguageCode': 'pt-PT', 'LanguageName': 'Portuguese', 'Gender': 'Female', 'Name': 'Inês'},
+    {'Id': 'Cristiano', 'LanguageCode': 'pt-PT', 'LanguageName': 'Portuguese', 'Gender': 'Male', 'Name': 'Cristiano'},
+    {'Id': 'Vitoria', 'LanguageCode': 'pt-BR', 'LanguageName': 'Brazilian Portuguese', 'Gender': 'Female', 'Name': 'Vitória'},
+    {'Id': 'Ricardo', 'LanguageCode': 'pt-BR', 'LanguageName': 'Brazilian Portuguese', 'Gender': 'Male', 'Name': 'Ricardo'},
+    {'Id': 'Maja', 'LanguageCode': 'pl-PL', 'LanguageName': 'Polish', 'Gender': 'Female', 'Name': 'Maja'},
+    {'Id': 'Jan', 'LanguageCode': 'pl-PL', 'LanguageName': 'Polish', 'Gender': 'Male', 'Name': 'Jan'},
+    {'Id': 'Ewa', 'LanguageCode': 'pl-PL', 'LanguageName': 'Polish', 'Gender': 'Female', 'Name': 'Ewa'},
+    {'Id': 'Ruben', 'LanguageCode': 'nl-NL', 'LanguageName': 'Dutch', 'Gender': 'Male', 'Name': 'Ruben'},
+    {'Id': 'Lotte', 'LanguageCode': 'nl-NL', 'LanguageName': 'Dutch', 'Gender': 'Female', 'Name': 'Lotte'},
+    {'Id': 'Liv', 'LanguageCode': 'nb-NO', 'LanguageName': 'Norwegian', 'Gender': 'Female', 'Name': 'Liv'},
+    {'Id': 'Giorgio', 'LanguageCode': 'it-IT', 'LanguageName': 'Italian', 'Gender': 'Male', 'Name': 'Giorgio'},
+    {'Id': 'Carla', 'LanguageCode': 'it-IT', 'LanguageName': 'Italian', 'Gender': 'Female', 'Name': 'Carla'},
+    {'Id': 'Karl', 'LanguageCode': 'is-IS', 'LanguageName': 'Icelandic', 'Gender': 'Male', 'Name': 'Karl'},
+    {'Id': 'Dora', 'LanguageCode': 'is-IS', 'LanguageName': 'Icelandic', 'Gender': 'Female', 'Name': 'Dóra'},
+    {'Id': 'Mathieu', 'LanguageCode': 'fr-FR', 'LanguageName': 'French', 'Gender': 'Male', 'Name': 'Mathieu'},
+    {'Id': 'Celine', 'LanguageCode': 'fr-FR', 'LanguageName': 'French', 'Gender': 'Female', 'Name': 'Céline'},
+    {'Id': 'Chantal', 'LanguageCode': 'fr-CA', 'LanguageName': 'Canadian French', 'Gender': 'Female', 'Name': 'Chantal'},
+    {'Id': 'Penelope', 'LanguageCode': 'es-US', 'LanguageName': 'US Spanish', 'Gender': 'Female', 'Name': 'Penélope'},
+    {'Id': 'Miguel', 'LanguageCode': 'es-US', 'LanguageName': 'US Spanish', 'Gender': 'Male', 'Name': 'Miguel'},
+    {'Id': 'Enrique', 'LanguageCode': 'es-ES', 'LanguageName': 'Castilian Spanish', 'Gender': 'Male', 'Name': 'Enrique'},
+    {'Id': 'Conchita', 'LanguageCode': 'es-ES', 'LanguageName': 'Castilian Spanish', 'Gender': 'Female', 'Name': 'Conchita'},
+    {'Id': 'Geraint', 'LanguageCode': 'en-GB-WLS', 'LanguageName': 'Welsh English', 'Gender': 'Male', 'Name': 'Geraint'},
+    {'Id': 'Salli', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Gender': 'Female', 'Name': 'Salli'},
+    {'Id': 'Kimberly', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Gender': 'Female', 'Name': 'Kimberly'},
+    {'Id': 'Kendra', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Gender': 'Female', 'Name': 'Kendra'},
+    {'Id': 'Justin', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Gender': 'Male', 'Name': 'Justin'},
+    {'Id': 'Joey', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Gender': 'Male', 'Name': 'Joey'},
+    {'Id': 'Ivy', 'LanguageCode': 'en-US', 'LanguageName': 'US English', 'Gender': 'Female', 'Name': 'Ivy'},
+    {'Id': 'Raveena', 'LanguageCode': 'en-IN', 'LanguageName': 'Indian English', 'Gender': 'Female', 'Name': 'Raveena'},
+    {'Id': 'Emma', 'LanguageCode': 'en-GB', 'LanguageName': 'British English', 'Gender': 'Female', 'Name': 'Emma'},
+    {'Id': 'Brian', 'LanguageCode': 'en-GB', 'LanguageName': 'British English', 'Gender': 'Male', 'Name': 'Brian'},
+    {'Id': 'Amy', 'LanguageCode': 'en-GB', 'LanguageName': 'British English', 'Gender': 'Female', 'Name': 'Amy'},
+    {'Id': 'Russell', 'LanguageCode': 'en-AU', 'LanguageName': 'Australian English', 'Gender': 'Male', 'Name': 'Russell'},
+    {'Id': 'Nicole', 'LanguageCode': 'en-AU', 'LanguageName': 'Australian English', 'Gender': 'Female', 'Name': 'Nicole'},
+    {'Id': 'Vicki', 'LanguageCode': 'de-DE', 'LanguageName': 'German', 'Gender': 'Female', 'Name': 'Vicki'},
+    {'Id': 'Marlene', 'LanguageCode': 'de-DE', 'LanguageName': 'German', 'Gender': 'Female', 'Name': 'Marlene'},
+    {'Id': 'Hans', 'LanguageCode': 'de-DE', 'LanguageName': 'German', 'Gender': 'Male', 'Name': 'Hans'},
+    {'Id': 'Naja', 'LanguageCode': 'da-DK', 'LanguageName': 'Danish', 'Gender': 'Female', 'Name': 'Naja'},
+    {'Id': 'Mads', 'LanguageCode': 'da-DK', 'LanguageName': 'Danish', 'Gender': 'Male', 'Name': 'Mads'},
+    {'Id': 'Gwyneth', 'LanguageCode': 'cy-GB', 'LanguageName': 'Welsh', 'Gender': 'Female', 'Name': 'Gwyneth'},
+    {'Id': 'Jacek', 'LanguageCode': 'pl-PL', 'LanguageName': 'Polish', 'Gender': 'Male', 'Name': 'Jacek'}
+]
+
+# {...} is also shorthand set syntax
+LANGUAGE_CODES = {'cy-GB', 'da-DK', 'de-DE', 'en-AU', 'en-GB', 'en-GB-WLS', 'en-IN', 'en-US', 'es-ES', 'es-US',
+                  'fr-CA', 'fr-FR', 'is-IS', 'it-IT', 'ja-JP', 'nb-NO', 'nl-NL', 'pl-PL', 'pt-BR', 'pt-PT', 'ro-RO',
+                  'ru-RU', 'sv-SE', 'tr-TR'}
+
+VOICE_IDS = {'Geraint', 'Gwyneth', 'Mads', 'Naja', 'Hans', 'Marlene', 'Nicole', 'Russell', 'Amy', 'Brian', 'Emma',
+             'Raveena', 'Ivy', 'Joanna', 'Joey', 'Justin', 'Kendra', 'Kimberly', 'Salli', 'Conchita', 'Enrique',
+             'Miguel', 'Penelope', 'Chantal', 'Celine', 'Mathieu', 'Dora', 'Karl', 'Carla', 'Giorgio', 'Mizuki',
+             'Liv', 'Lotte', 'Ruben', 'Ewa', 'Jacek', 'Jan', 'Maja', 'Ricardo', 'Vitoria', 'Cristiano', 'Ines',
+             'Carmen', 'Maxim', 'Tatyana', 'Astrid', 'Filiz'}