Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[translation] add tests for glossaries #19931

Merged
merged 2 commits into from
Jul 26, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
testing,essai
text,textes
Original file line number Diff line number Diff line change
Expand Up @@ -7,10 +7,12 @@
import functools
import pytest
import json
import os
from azure.core.exceptions import HttpResponseError
from testcase import DocumentTranslationTest, Document
from preparer import DocumentTranslationPreparer, \
DocumentTranslationClientPreparer as _DocumentTranslationClientPreparer
from azure.storage.blob import ContainerClient
from azure.ai.translation.document._generated.models import StartTranslationDetails as _StartTranslationDetails
from azure.ai.translation.document import (
DocumentTranslationClient,
Expand All @@ -20,6 +22,8 @@
)
DocumentTranslationClientPreparer = functools.partial(_DocumentTranslationClientPreparer, DocumentTranslationClient)

GLOSSARY_FILE_NAME = os.path.abspath(os.path.join(os.path.abspath(__file__), "..", "./glossaries-valid.csv"))


class TestTranslation(DocumentTranslationTest):

Expand Down Expand Up @@ -507,3 +511,42 @@ def test_single_input_with_kwarg_successful(self, client):
self._validate_translation_metadata(poller, status="Succeeded", total=1, succeeded=1)
for doc in result:
self._validate_doc_status(doc, target_language="fr")

@pytest.mark.live_test_only
@DocumentTranslationPreparer()
@DocumentTranslationClientPreparer()
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
maririos marked this conversation as resolved.
Show resolved Hide resolved
os.remove(document)
Original file line number Diff line number Diff line change
Expand Up @@ -7,16 +7,20 @@
import functools
import pytest
import json
import os
from testcase import Document
from asynctestcase import AsyncDocumentTranslationTest
from preparer import DocumentTranslationPreparer, \
DocumentTranslationClientPreparer as _DocumentTranslationClientPreparer
from azure.core.exceptions import HttpResponseError
from azure.storage.blob import ContainerClient
from azure.ai.translation.document._generated.models import StartTranslationDetails as _StartTranslationDetails
from azure.ai.translation.document import DocumentTranslationInput, TranslationTarget, TranslationGlossary
from azure.ai.translation.document.aio import DocumentTranslationClient
DocumentTranslationClientPreparer = functools.partial(_DocumentTranslationClientPreparer, DocumentTranslationClient)

GLOSSARY_FILE_NAME = os.path.abspath(os.path.join(os.path.abspath(__file__), "..", "./glossaries-valid.csv"))


class TestTranslation(AsyncDocumentTranslationTest):

Expand Down Expand Up @@ -506,3 +510,42 @@ async def test_single_input_with_kwarg_successful(self, client):
self._validate_translation_metadata(poller, status="Succeeded", total=1, succeeded=1)
async for doc in result:
self._validate_doc_status(doc, target_language="fr")

@pytest.mark.live_test_only
@DocumentTranslationPreparer()
@DocumentTranslationClientPreparer()
async 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
async with client:
poller = await client.begin_translation(
source_container_sas_url,
target_container_sas_url,
"es",
glossaries=[TranslationGlossary(glossary_url=glossary_file_sas_url, file_format="csv")]
)
result = await 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)
Original file line number Diff line number Diff line change
Expand Up @@ -106,28 +106,28 @@ def create_source_container(self, data):
return "dummy_string"

# for actual live tests
container_name = "src" + str(uuid.uuid4())
container_client = ContainerClient(self.storage_endpoint, container_name,
self.source_container_name = "src" + str(uuid.uuid4())
container_client = ContainerClient(self.storage_endpoint, self.source_container_name,
self.storage_key)
container_client.create_container()

self.upload_documents(data, container_client)
return self.generate_sas_url(container_name, "rl")
return self.generate_sas_url(self.source_container_name, "rl")

def create_target_container(self, data=None):
# for offline tests
if not self.is_live:
return "dummy_string"

# for actual live tests
container_name = "target" + str(uuid.uuid4())
container_client = ContainerClient(self.storage_endpoint, container_name,
self.target_container_name = "target" + str(uuid.uuid4())
container_client = ContainerClient(self.storage_endpoint, self.target_container_name,
self.storage_key)
container_client.create_container()
if data:
self.upload_documents(data, container_client)

return self.generate_sas_url(container_name, "rw")
return self.generate_sas_url(self.target_container_name, "rw")

def generate_sas_url(self, container_name, permission):

Expand Down