Using glossaries with tts and vision tutorial sample code

translate/cloud-client/hybrid_glossaries/hybrid_tutorial.py

@@ -0,0 +1,257 @@
+# Copyright 2019 Google Inc. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+# [START hybrid_imports]
+# Imports the Google Cloud client libraries
+from google.cloud import translate_v3beta1 as translate
+from google.cloud import vision
+from google.cloud import texttospeech
+
+import io
+import os
+# [END hybrid_imports]
+
+# [START hybrid_project_id]
+# extract GCP project id
+PROJECT_ID = os.environ['GCLOUD_PROJECT']
+# [END hybrid_project_id]
+
+
+# [START hybrid_vision]
+def pic_to_text(infile):
+    # Detects text in an image file
+    #
+    # ARGS
+    # infile: path to image file
+    #
+    # RETURNS
+    # String of text detected in image
+
+    # Instantiates a client
+    client = vision.ImageAnnotatorClient()
+
+    # Opens the input image file
+    with io.open(infile, 'rb') as image_file:
+        content = image_file.read()
+
+    image = vision.types.Image(content=content)
+
+    # For dense text, use document_text_detection
+    # For less dense text, use text_detection
+    response = client.document_text_detection(image=image)
+    text = response.full_text_annotation.text
+
+    return text
+    # [END hybrid_vision]
+
+
+# [START hybrid_create_glossary]
+def create_glossary(languages, project_id, glossary_name, glossary_uri):
+    # Creates a GCP glossary resource
+    # Assumes you've already manually uploaded a glossary to Cloud Storage
+    #
+    # ARGS
+    # languages: list of languages in the glossary
+    # project_id: GCP project id
+    # glossary_name: name you want to give this glossary resource
+    # glossary_uri: the uri of the glossary you uploaded to Cloud Storage
+    #
+    # RETURNS
+    # nothing if glossary creation is successful
+
+    # Instantiates a client
+    client = translate.TranslationServiceClient()
+
+    # Defines the languages in the glossary
+    # This list must match the languages in the glossary
+    #   Here, the glossary includes French and English
+    languages = ['fr', 'en']
+    # Set information to access
+    glossary_uri = 'gs://cloud-samples-data/translation/bistro_glossary.csv'
+    # Designates the data center location that you want to use
+    location = 'us-central1'
+
+    # Set glossary resource name
+    name = client.glossary_path(
+        project_id,
+        location,
+        glossary_name)
+
+    # Set language codes
+    language_codes_set = translate.types.Glossary.LanguageCodesSet(
+        language_codes=languages)
+
+    gcs_source = translate.types.GcsSource(
+        input_uri=glossary_uri)
+
+    input_config = translate.types.GlossaryInputConfig(
+        gcs_source=gcs_source)
+
+    # Set glossary resource information
+    glossary = translate.types.Glossary(
+        name=name,
+        language_codes_set=language_codes_set,
+        input_config=input_config)
+
+    resource = client.location_path(project_id, location)
+
+    # Create glossary resource
+    operation = client.create_glossary(parent=resource, glossary=glossary)
+
+    return operation.result(timeout=90)
+
+
+# [START hybrid_translate]
+def translate_text(text, prev_lang, new_lang, project_id, glossary_name):
+    # Translates text to a given language using a glossary
+    #
+    # ARGS
+    # text: String of text to translate
+    # prev_lang: language of input text
+    # new_lang: language of output text
+    # project_id: GCP project id
+    # glossary_name: name you gave your project's glossary
+    #  resource when you created it
+    #
+    # RETURNS
+    # String of translated text
+
+    # Instantiates a client
+    client = translate.TranslationServiceClient()
+
+    # Designates the data center location that you want to use
+    location = 'us-central1'
+
+    glossary = client.glossary_path(
+        project_id,
+        location,
+        glossary_name)
+
+    glossary_config = translate.types.TranslateTextGlossaryConfig(
+        glossary=glossary)
+
+    resource = client.location_path(project_id, location)
+
+    result = client.translate_text(
+        parent=resource,
+        contents=[text],
+        mime_type='text/plain',  # mime types: text/plain, text/html
+        source_language_code=prev_lang,
+        target_language_code=new_lang,
+        glossary_config=glossary_config)
+
+    # Returns translated text
+    return result.glossary_translations[0].translated_text
+    # [END hybrid_translate]
+
+
+# [START hybrid_glossary_delete]
+def delete_glossary(project_id, glossary_name):
+    # Deletes a GCP glossary resource
+    #
+    # ARGS
+    # project_id: GCP project id
+    # glossary_name: name you gave your project's glossary
+    #   resource when you created it
+    #
+    # RETURNS
+    # nothing
+
+    # Designates the data center location that you want to use
+    location = 'us-central1'
+
+    # Instantiates a client
+    client = translate.TranslationServiceClient()
+
+    resource = client.glossary_path(
+        project_id,
+        location,
+        glossary_name)
+
+    operation = client.delete_glossary(resource)
+    result = operation.result(timeout=90)
+
+    print('Deleted: {}'.format(result.name))
+    # [END hybrid_glossary_delete]
+
+
+# [START hybrid_tts]
+def text_to_speech(text, outfile):
+    # Generates synthetic audio from plaintext
+    #
+    # ARGS
+    # text: text to synthesize
+    # outfile: filename to use to store synthetic audio
+    #
+    # RETURNS
+    # nothing
+
+    # Instantiates a client
+    client = texttospeech.TextToSpeechClient()
+
+    # Sets the text input to be synthesized
+    synthesis_input = texttospeech.types.SynthesisInput(text=text)
+
+    # Builds the voice request, selects the language code ("en-US") and
+    # the SSML voice gender ("MALE")
+    voice = texttospeech.types.VoiceSelectionParams(
+        language_code='en-US',
+        ssml_gender=texttospeech.enums.SsmlVoiceGender.MALE)
+
+    # Selects the type of audio file to return
+    audio_config = texttospeech.types.AudioConfig(
+        audio_encoding=texttospeech.enums.AudioEncoding.MP3)
+
+    # Performs the text-to-speech request on the text input with the selected
+    # voice parameters and audio file type
+    response = client.synthesize_speech(synthesis_input, voice, audio_config)
+
+    # Writes the synthetic audio to the output file.
+    with open(outfile, 'wb') as out:
+        out.write(response.audio_content)
+        print('Audio content written to file ' + outfile)
+    # [END hybrid_tts]
+
+
+# [START hybrid_integration]
+def main():
+
+    # Photo from which to extract text
+    infile = "resources/example.png"
+    # Name of file that will hold synthetic speech
+    outfile = "resources/example.mp3"
+
+    # Name that will be assigned to your project's glossary resource
+    glossary_name = 'bistro-glossary'
+    # URI of glossary uploaded to Cloud Storage
+    glossary_uri = 'gs://cloud-samples-data/translation/bistro_glossary.csv'
+    # List of languages in the glossary
+    glossary_langs = ['fr', 'en']
+
+    # delete_glossary(PROJECT_ID, glossary_name)
+    create_glossary(glossary_langs, PROJECT_ID,  glossary_name, glossary_uri)
+
+    # photo -> detected text
+    text_to_translate = pic_to_text(infile)
+    # detected text -> translated text
+    text_to_speak = translate_text(text_to_translate, 'fr', 'en',
+                                   PROJECT_ID, glossary_name)
+    # translated text -> synthetic audio
+    text_to_speech(text_to_speak, outfile)
+    # [END hybrid_integration]
+
+
+if __name__ == '__main__':
+    main()

translate/cloud-client/hybrid_glossaries/hybrid_tutorial_tests.py

@@ -0,0 +1,117 @@
+# Copyright 2019 Google Inc. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from hybrid_tutorial import pic_to_text
+from hybrid_tutorial import create_glossary
+from hybrid_tutorial import delete_glossary
+from hybrid_tutorial import translate_text
+from hybrid_tutorial import text_to_speech
+
+import filecmp
+import os
+
+PROJECT_ID = os.environ['GCLOUD_PROJECT']
+
+# VISION TESTS
+
+
+def test_vision_standard_format():
+
+    expected_text = 'This is\na test!\n'
+    alt_expected_text = 'This\nis\na test!\n'
+
+    # Generate text using Vision API
+    text = pic_to_text('resources/standard_format.jpeg')
+
+    assert (text == expected_text) or (text == alt_expected_text)
+
+
+def test_vision_non_standard_format():
+
+    # Generate text
+    text = pic_to_text('resources/non_standard_format.png')
+
+    # Read expected text
+    with open('resources/non_standard_format.txt') as f:
+        expected_text = f.read()
+
+    assert text == expected_text
+
+
+# TRANSLATE TESTS
+
+
+def test_create_and_delete_glossary():
+    languages = ['fr', 'en']
+    glossary_name = 'test-glossary'
+    glossary_uri = 'gs://cloud-samples-data/translation/bistro_glossary.csv'
+
+    # create_glossary will raise an exception if creation fails
+    create_glossary(languages, PROJECT_ID, glossary_name,
+                    glossary_uri)
+
+    # Delete glossary so that future tests will pass
+    # delete_glossary will raise an exception if deletion fails
+    delete_glossary(PROJECT_ID, glossary_name)
+
+
+def test_translate_standard():
+
+    expected_text = 'Hello'
+
+    text = translate_text('Bonjour', 'fr', 'en', PROJECT_ID,
+                          'bistro-glossary')
+
+    assert text == expected_text
+
+
+def test_translate_glossary():
+
+    expected_text = 'I eat goat cheese'
+    input_text = 'Je mange du chevre'
+
+    text = translate_text(input_text, 'fr', 'en', PROJECT_ID,
+                          'bistro-glossary')
+
+    assert text == expected_text
+
+
+# TEXT-TO-SPEECH TESTS
+
+
+def test_tts_standard(capsys):
+    outfile = 'resources/test_standard_text.mp3'
+    expected_outfile = 'resources/expected_standard_text.mp3'
+    textfile = 'resources/standard_format.txt'
+
+    with open(textfile, 'r') as f:
+        text = f.read()
+
+    text_to_speech(text, outfile)
+
+    # Assert audio file generated
+    assert os.path.isfile(outfile)
+
+    # Assert audio file generated correctly
+    assert filecmp.cmp(outfile,
+                       expected_outfile,
+                       shallow=True)
+
+    out, err = capsys.readouterr()
+
+    # Assert success message printed
+    assert 'Audio content written to file ' + outfile in out
+
+    # Delete test file
+    os.remove(outfile)

translate/cloud-client/hybrid_glossaries/requirements.txt

@@ -0,0 +1,3 @@
+google-cloud-translate==1.4.0
+google-cloud-vision==0.35.2
+google-cloud-texttospeech==0.4.0

translate/cloud-client/hybrid_glossaries/resources/bistro_glossary.csv

@@ -0,0 +1,13 @@
+fr,en,
+chevre,goat cheese,
+Chevre,Goat cheese,
+chèvre,goat cheese,
+Chèvre,Goat cheese,
+crème brulée,crème brulée,
+Crème brulée,Crème brulée,
+Crème Brulée,Crème Brulée,
+bouillabaisse,fish stew,
+Bouillabaisse,Fish stew,
+steak frites,steak with french fries,
+Steak frites,Steak with french fries,
+Steak Frites,Steak with French Fries,