def translate_text_with_glossary(
text="YOUR_TEXT_TO_TRANSLATE",
project_id="YOUR_PROJECT_ID",
glossary_id="YOUR_GLOSSARY_ID",
):
"""Translates a given text using a glossary."""
client = translate.TranslationServiceClient()
location = "us-central1"
parent = f"projects/{project_id}/locations/{location}"
glossary = client.glossary_path(
project_id,
"us-central1",
glossary_id # The location of the glossary
)
glossary_config = translate.TranslateTextGlossaryConfig(glossary=glossary)
# Supported language codes: https://cloud.google.com/translate/docs/languages
response = client.translate_text(
request={
"contents": [text],
"target_language_code": "ja",
"source_language_code": "en",
"parent": parent,
"glossary_config": glossary_config,
})
print("Translated text: \n")
for translation in response.glossary_translations:
print("\t {}".format(translation.translated_text))
def batch_translate_text_with_glossary_and_model(
input_uri="gs://YOUR_BUCKET_ID/path/to/your/file.txt",
output_uri="gs://YOUR_BUCKET_ID/path/to/save/results/",
project_id="YOUR_PROJECT_ID",
model_id="YOUR_MODEL_ID",
glossary_id="YOUR_GLOSSARY_ID",
):
"""
Batch translate text with Glossary and Translation model
"""
client = translate.TranslationServiceClient()
# Supported language codes: https://cloud.google.com/translate/docs/languages
location = "us-central1"
target_language_codes = ["ja"]
gcs_source = {"input_uri": input_uri}
# Optional. Can be "text/plain" or "text/html".
mime_type = "text/plain"
input_configs_element = {"gcs_source": gcs_source, "mime_type": mime_type}
input_configs = [input_configs_element]
gcs_destination = {"output_uri_prefix": output_uri}
output_config = {"gcs_destination": gcs_destination}
parent = f"projects/{project_id}/locations/{location}"
model_path = "projects/{}/locations/{}/models/{}".format(
project_id, "us-central1", model_id
)
models = {"ja": model_path}
glossary_path = client.glossary_path(
project_id, "us-central1", glossary_id # The location of the glossary
)
glossary_config = translate.TranslateTextGlossaryConfig(glossary=glossary_path)
glossaries = {"ja": glossary_config} # target lang as key
operation = client.batch_translate_text(
request={
"parent": parent,
"source_language_code": "en",
"target_language_codes": target_language_codes,
"input_configs": input_configs,
"output_config": output_config,
"models": models,
"glossaries": glossaries,
}
)
print("Waiting for operation to complete...")
response = operation.result()
# Display the translation for each input text provided
print("Total Characters: {}".format(response.total_characters))
print("Translated Characters: {}".format(response.translated_characters))
def batch_translate_text_with_glossary(
input_uri="gs://YOUR_BUCKET_ID/path/to/your/file.txt",
output_uri="gs://YOUR_BUCKET_ID/path/to/save/results/",
project_id="YOUR_PROJECT_ID",
glossary_id="YOUR_GLOSSARY_ID",
timeout=180,
):
"""Translates a batch of texts on GCS and stores the result in a GCS location.
Glossary is applied for translation."""
client = translate.TranslationServiceClient()
# Supported language codes: https://cloud.google.com/translate/docs/languages
location = "us-central1"
# Supported file types: https://cloud.google.com/translate/docs/supported-formats
gcs_source = {"input_uri": input_uri}
input_configs_element = {
"gcs_source": gcs_source,
"mime_type": "text/plain" # Can be "text/plain" or "text/html".
}
gcs_destination = {"output_uri_prefix": output_uri}
output_config = {"gcs_destination": gcs_destination}
parent = f"projects/{project_id}/locations/{location}"
# glossary is a custom dictionary Translation API uses
# to translate the domain-specific terminology.
glossary_path = client.glossary_path(
project_id,
"us-central1",
glossary_id # The location of the glossary
)
glossary_config = translate.TranslateTextGlossaryConfig(
glossary=glossary_path)
glossaries = {"ja": glossary_config} # target lang as key
operation = client.batch_translate_text(
request={
"parent": parent,
"source_language_code": "en",
"target_language_codes": ["ja"], # Up to 10 language codes here.
"input_configs": [input_configs_element],
"glossaries": glossaries,
"output_config": output_config
})
print(u"Waiting for operation to complete...")
response = operation.result(timeout)
print(u"Total Characters: {}".format(response.total_characters))
print(u"Translated Characters: {}".format(response.translated_characters))
def sample_batch_translate_text_with_glossary_and_model(
input_uri,
output_uri,
project_id,
location,
target_language,
source_language,
model_id,
glossary_id,
):
"""
Batch translate text with Glossary and Translation model
"""
client = translate.TranslationServiceClient()
# TODO(developer): Uncomment and set the following variables
# input_uri = 'gs://cloud-samples-data/text.txt'
# output_uri = 'gs://YOUR_BUCKET_ID/path_to_store_results/'
# project = '[Google Cloud Project ID]'
# location = 'us-central1'
# target_language = 'en'
# source_language = 'de'
# model_id = '{your-model-id}'
# glossary_id = '[YOUR_GLOSSARY_ID]'
target_language_codes = [target_language]
gcs_source = {"input_uri": input_uri}
# Optional. Can be "text/plain" or "text/html".
mime_type = "text/plain"
input_configs_element = {"gcs_source": gcs_source, "mime_type": mime_type}
input_configs = [input_configs_element]
gcs_destination = {"output_uri_prefix": output_uri}
output_config = {"gcs_destination": gcs_destination}
parent = f"projects/{project_id}/locations/{location}"
model_path = "projects/{}/locations/{}/models/{}".format(
project_id, "us-central1", model_id)
models = {target_language: model_path}
glossary_path = client.glossary_path(
project_id,
"us-central1",
glossary_id # The location of the glossary
)
glossary_config = translate.TranslateTextGlossaryConfig(
glossary=glossary_path)
glossaries = {"ja": glossary_config} # target lang as key
operation = client.batch_translate_text(
request={
"parent": parent,
"source_language_code": "en",
"target_language_codes": target_language_codes,
"input_configs": input_configs,
"output_config": output_config,
"models": models,
"glossaries": glossaries,
})
print("Waiting for operation to complete...")
response = operation.result()
# Display the translation for each input text provided
print("Total Characters: {}".format(response.total_characters))
print("Translated Characters: {}".format(response.translated_characters))