def test_translation_with_glossary(self, client):
doc = Document(data=b'testing')
source_container_sas_url = self.create_source_container(data=[doc])
target_container_sas_url = self.create_target_container()
container_client = ContainerClient(self.storage_endpoint, self.source_container_name,
self.storage_key)
with open(GLOSSARY_FILE_NAME, "rb") as fd:
container_client.upload_blob(name=GLOSSARY_FILE_NAME, data=fd.read())
prefix, suffix = source_container_sas_url.split("?")
glossary_file_sas_url = prefix + "/" + GLOSSARY_FILE_NAME + "?" + suffix
poller = client.begin_translation(
source_container_sas_url,
target_container_sas_url,
"es",
glossaries=[TranslationGlossary(glossary_url=glossary_file_sas_url, file_format="csv")]
)
result = poller.result()
container_client = ContainerClient(self.storage_endpoint, self.target_container_name,
self.storage_key)
# download translated file and assert that translation reflects glossary changes
document = doc.name + doc.suffix
with open(document, "wb") as my_blob:
download_stream = container_client.download_blob(document)
my_blob.write(download_stream.readall())
with open(document, "rb") as fd:
translated = fd.readline()
assert b'essai' in translated # glossary worked
os.remove(document)
async def sample_translation_with_glossaries_async():
import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.translation.document.aio import DocumentTranslationClient
from azure.ai.translation.document import (DocumentTranslationInput,
TranslationTarget,
TranslationGlossary)
endpoint = os.environ["AZURE_DOCUMENT_TRANSLATION_ENDPOINT"]
key = os.environ["AZURE_DOCUMENT_TRANSLATION_KEY"]
source_container_url = os.environ["AZURE_SOURCE_CONTAINER_URL"]
target_container_url = os.environ["AZURE_TARGET_CONTAINER_URL"]
glossary_url = os.environ["AZURE_TRANSLATION_GLOSSARY_URL"]
client = DocumentTranslationClient(endpoint, AzureKeyCredential(key))
inputs = DocumentTranslationInput(
source_url=source_container_url,
targets=[
TranslationTarget(target_url=target_container_url,
language_code="es",
glossaries=[
TranslationGlossary(
glossary_url=glossary_url,
file_format="TSV")
])
])
async with client:
job = await client.create_translation_job(inputs=[inputs]
) # type: JobStatusResult
job_result = await client.wait_until_done(job.id
) # type: JobStatusResult
print("Job status: {}".format(job_result.status))
print("Job created on: {}".format(job_result.created_on))
print("Job last updated on: {}".format(job_result.last_updated_on))
print("Total number of translations on documents: {}".format(
job_result.documents_total_count))
print("\nOf total documents...")
print("{} failed".format(job_result.documents_failed_count))
print("{} succeeded".format(job_result.documents_succeeded_count))
doc_results = client.list_all_document_statuses(
job_result.id) # type: AsyncItemPaged[DocumentStatusResult]
async for document in doc_results:
print("Document ID: {}".format(document.id))
print("Document status: {}".format(document.status))
if document.status == "Succeeded":
print("Source document location: {}".format(
document.source_document_url))
print("Translated document location: {}".format(
document.translated_document_url))
print("Translated to language: {}\n".format(
document.translate_to))
else:
print("Error Code: {}, Message: {}\n".format(
document.error.code, document.error.message))
async def sample_translation_with_glossaries_async():
import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.translation.document.aio import DocumentTranslationClient
from azure.ai.translation.document import (DocumentTranslationInput,
TranslationTarget,
TranslationGlossary)
endpoint = os.environ["AZURE_DOCUMENT_TRANSLATION_ENDPOINT"]
key = os.environ["AZURE_DOCUMENT_TRANSLATION_KEY"]
source_container_url = os.environ["AZURE_SOURCE_CONTAINER_URL"]
target_container_url = os.environ["AZURE_TARGET_CONTAINER_URL"]
glossary_url = os.environ["AZURE_TRANSLATION_GLOSSARY_URL"]
client = DocumentTranslationClient(endpoint, AzureKeyCredential(key))
inputs = DocumentTranslationInput(
source_url=source_container_url,
targets=[
TranslationTarget(target_url=target_container_url,
language_code="es",
glossaries=[
TranslationGlossary(
glossary_url=glossary_url,
file_format="TSV")
])
])
async with client:
poller = await client.begin_translation(inputs=[inputs])
result = await poller.result()
print("Status: {}".format(poller.status()))
print("Created on: {}".format(poller.details.created_on))
print("Last updated on: {}".format(poller.details.last_updated_on))
print("Total number of translations on documents: {}".format(
poller.details.documents_total_count))
print("\nOf total documents...")
print("{} failed".format(poller.details.documents_failed_count))
print("{} succeeded".format(poller.details.documents_succeeded_count))
async for document in result:
print("Document ID: {}".format(document.id))
print("Document status: {}".format(document.status))
if document.status == "Succeeded":
print("Source document location: {}".format(
document.source_document_url))
print("Translated document location: {}".format(
document.translated_document_url))
print("Translated to language: {}\n".format(
document.translated_to))
else:
print("Error Code: {}, Message: {}\n".format(
document.error.code, document.error.message))
def sample_translation_with_glossaries():
import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.translation.document import (DocumentTranslationClient,
TranslationGlossary)
endpoint = os.environ["AZURE_DOCUMENT_TRANSLATION_ENDPOINT"]
key = os.environ["AZURE_DOCUMENT_TRANSLATION_KEY"]
source_container_url = os.environ["AZURE_SOURCE_CONTAINER_URL"]
target_container_url = os.environ["AZURE_TARGET_CONTAINER_URL"]
glossary_url = os.environ["AZURE_TRANSLATION_GLOSSARY_URL"]
client = DocumentTranslationClient(endpoint, AzureKeyCredential(key))
poller = client.begin_translation(source_container_url,
target_container_url,
"es",
glossaries=[
TranslationGlossary(
glossary_url=glossary_url,
file_format="TSV")
])
result = poller.result()
print(f"Status: {poller.status()}")
print(f"Created on: {poller.details.created_on}")
print(f"Last updated on: {poller.details.last_updated_on}")
print(
f"Total number of translations on documents: {poller.details.documents_total_count}"
)
print("\nOf total documents...")
print(f"{poller.details.documents_failed_count} failed")
print(f"{poller.details.documents_succeeded_count} succeeded")
for document in result:
print(f"Document ID: {document.id}")
print(f"Document status: {document.status}")
if document.status == "Succeeded":
print(f"Source document location: {document.source_document_url}")
print(
f"Translated document location: {document.translated_document_url}"
)
print(f"Translated to language: {document.translated_to}\n")
else:
print(
f"Error Code: {document.error.code}, Message: {document.error.message}\n"
)
def test_single_input_with_kwargs(self, **kwargs):
client = kwargs.pop("client")
variables = kwargs.pop("variables", {})
# prepare containers and test data
source_container_sas_url = self.create_source_container(
data=Document(data=b'hello world'), variables=variables)
target_container_sas_url = self.create_target_container(
variables=variables)
def callback(request):
req = _StartTranslationDetails.deserialize(
json.loads(request.http_request.body))
input = req.inputs[0]
assert input.source.source_url == source_container_sas_url
assert input.source.language == "en"
assert input.source.filter.prefix == ""
assert input.source.filter.suffix == ".txt"
assert input.storage_type == "File"
assert input.targets[0].category == "fake"
assert input.targets[0].glossaries[0].format == "txt"
assert input.targets[0].glossaries[
0].glossary_url == "https://glossaryfile.txt"
assert input.targets[0].language == "es"
assert input.targets[0].target_url == target_container_sas_url
try:
poller = client.begin_translation(
source_container_sas_url,
target_container_sas_url,
"es",
storage_type="File",
source_language_code="en",
prefix="",
suffix=".txt",
category_id="fake",
glossaries=[
TranslationGlossary(
glossary_url="https://glossaryfile.txt",
file_format="txt")
],
raw_response_hook=callback)
poller.result()
except HttpResponseError as e:
pass
return variables