.. role:: raw-html-m2r(raw)
   :format: html


Azure Document Translation client library for Python
====================================================

Azure Cognitive Services Document Translation is a cloud service that translates documents to and from 90 languages 
and dialects while preserving document structure and data format. Use the client library for Document Translation to:


* Translate numerous, large files from an Azure Blob Storage container to a target container in your language of choice.
* Check the translation status and progress of each document in the translation job.
* Apply a custom translation model or glossaries to tailor translation to your specific case.

`Source code <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/azure/ai/translation/document>`_ | `Package (PyPI) <https://aka.ms/azsdk/python/texttranslation/pypi>`_ | `API reference documentation <https://aka.ms/azsdk/python/documenttranslation/docs>`_ | `Product documentation <https://docs.microsoft.com/azure/cognitive-services/translator/document-translation/overview>`_ | `Samples <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples>`_

Getting started
---------------

Prerequisites
^^^^^^^^^^^^^


* Python 2.7, or 3.6 or later is required to use this package.
* You must have an `Azure subscription <https://azure.microsoft.com/free/>`_ and a
  `Document Translation resource <https://docs.microsoft.com/azure/cognitive-services/translator/document-translation/get-started-with-document-translation?tabs=python>`_ to use this package.

Install the package
^^^^^^^^^^^^^^^^^^^

Install the Azure Document Translation client library for Python with `pip <https://pypi.org/project/pip/>`_\ :

.. code-block:: bash

   pip install azure-ai-translation-document --pre

..

   Note: This version of the client library defaults to the v1.0-preview.1 version of the service


Create a Document Translation resource
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Document Translation supports `single-service access <https://docs.microsoft.com/azure/cognitive-services/cognitive-services-apis-create-account?tabs=singleservice%2Cwindows>`_ only.
To access the service, create a Translator resource.

You can create the resource using

**Option 1:** `Azure Portal <https://ms.portal.azure.com/#create/Microsoft.CognitiveServicesTextTranslation>`_

**Option 2:** `Azure CLI <https://docs.microsoft.com/azure/cognitive-services/cognitive-services-apis-create-account-cli?tabs=windows>`_.
Below is an example of how you can create a Document Translation resource using the CLI:

.. code-block:: bash

   # Create a new resource group to hold the document translation resource -
   # if using an existing resource group, skip this step
   az group create --name my-resource-group --location westus2

.. code-block:: bash

   # Create document translation
   az cognitiveservices account create \
       --name document-translation-resource \
       --custom-domain document-translation-resource \
       --resource-group my-resource-group \
       --kind TextTranslation \
       --sku S1 \
       --location westus2 \
       --yes

Authenticate the client
^^^^^^^^^^^^^^^^^^^^^^^

In order to interact with the Document Translation service, you will need to create an instance of a client.
An **endpoint** and **credential** are necessary to instantiate the client object.

Looking up the endpoint
~~~~~~~~~~~~~~~~~~~~~~~

You can find the endpoint for your Document Translation resource using the
`Azure Portal <https://docs.microsoft.com/azure/cognitive-services/translator/document-translation/get-started-with-document-translation?tabs=csharp#get-your-custom-domain-name-and-subscription-key>`_.

..

   Note that the service requires a custom domain endpoint. Follow the instructions in the above link to format your endpoint:
   https://{NAME-OF-YOUR-RESOURCE}.cognitiveservices.azure.com/


Get the API key
~~~~~~~~~~~~~~~

The API key can be found in the Azure Portal or by running the following Azure CLI command:

``az cognitiveservices account keys list --name "resource-name" --resource-group "resource-group-name"``

Create the client with AzureKeyCredential
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

To use an `API key <https://docs.microsoft.com/azure/cognitive-services/translator/document-translation/get-started-with-document-translation?tabs=csharp#get-your-subscription-key>`_ as the ``credential`` parameter,
pass the key as a string into an instance of `AzureKeyCredential <https://aka.ms/azsdk/python/core/azurekeycredential>`_.

.. code-block:: python

   from azure.core.credentials import AzureKeyCredential
   from azure.ai.translation.document import DocumentTranslationClient

   endpoint = "https://<resource-name>.cognitiveservices.azure.com/"
   credential = AzureKeyCredential("<api_key>")
   document_translation_client = DocumentTranslationClient(endpoint, credential)

Key concepts
------------

The Document Translation service requires that you upload your files to an Azure Blob Storage source container and provide
a target container where the translated documents can be written. SAS tokens to the containers (or files) are used to
access the documents and create the translated documents in the target container. Additional information about setting this up can be found in
the service documentation:


* `Set up Azure Blob Storage containers <https://docs.microsoft.com/azure/cognitive-services/translator/document-translation/get-started-with-document-translation?tabs=csharp#create-your-azure-blob-storage-containers>`_ with your documents
* Optionally apply `glossaries <https://docs.microsoft.com/azure/cognitive-services/translator/document-translation/overview#supported-glossary-formats>`_ or a `custom model for translation <https://docs.microsoft.com/azure/cognitive-services/translator/custom-translator/quickstart-build-deploy-custom-model>`_
* Generate `SAS tokens <https://docs.microsoft.com/azure/cognitive-services/translator/document-translation/create-sas-tokens?tabs=Containers#create-your-sas-tokens-with-azure-storage-explorer>`_ to your containers (or files) with the appropriate `permissions <https://docs.microsoft.com/azure/cognitive-services/translator/document-translation/get-started-with-document-translation?tabs=csharp#create-sas-access-tokens-for-document-translation>`_

DocumentTranslationClient
^^^^^^^^^^^^^^^^^^^^^^^^^

Interaction with the Document Translation client library begins with an instance of the ``DocumentTranslationClient``.
The client provides operations for:


* Creating a translation job to translate documents in your source container(s) and write results to you target container(s).
* Checking the status of individual documents in the translation job and monitoring each document's progress.
* Enumerating all past and current translation jobs with the option to wait until the job(s) finish.
* Identifying supported glossary and document formats.

Translation Input
^^^^^^^^^^^^^^^^^

To create a translation job, pass a list of ``DocumentTranslationInput`` into the ``create_translation_job`` client method.
Constructing a ``DocumentTranslationInput`` requires that you pass the SAS URLs to your source and target containers (or files)
and the target language(s) for translation.

A single source container with documents can be translated to many different languages:

.. code-block:: python

   from azure.ai.translation.document import DocumentTranslationInput, TranslationTarget

   my_input = [
       DocumentTranslationInput(
           source_url="<sas_url_to_source>",
           targets=[
               TranslationTarget(target_url="<sas_url_to_target_fr>", language_code="fr"),
               TranslationTarget(target_url="<sas_url_to_target_de>", language_code="de")
           ]
       )
   ]

Or multiple different sources can be provided each with their own targets.

.. code-block:: python

   from azure.ai.translation.document import DocumentTranslationInput, TranslationTarget

   my_input = [
       DocumentTranslationInput(
           source_url="<sas_url_to_source_A>",
           targets=[
               TranslationTarget(target_url="<sas_url_to_target_fr>", language_code="fr"),
               TranslationTarget(target_url="<sas_url_to_target_de>", language_code="de")
           ]
       ),
       DocumentTranslationInput(
           source_url="<sas_url_to_source_B>",
           targets=[
               TranslationTarget(target_url="<sas_url_to_target_fr>", language_code="fr"),
               TranslationTarget(target_url="<sas_url_to_target_de>", language_code="de")
           ]
       ),
       DocumentTranslationInput(
           source_url="<sas_url_to_source_C>",
           targets=[
               TranslationTarget(target_url="<sas_url_to_target_fr>", language_code="fr"),
               TranslationTarget(target_url="<sas_url_to_target_de>", language_code="de")
           ]
       )
   ]

..

   Note: the target_url for each target language must be unique.


See the service documentation for all `supported languages <https://docs.microsoft.com/azure/cognitive-services/translator/language-support#translate>`_.

Return value
^^^^^^^^^^^^

There are primarily two types of return values when checking on the result of a translation job - ``JobStatusResult`` and ``DocumentStatusResult``.


* A ``JobStatusResult`` will contain the details of the entire job, such as it's status, ID, any errors, and status summaries of the documents in the job.
* A ``DocumentStatusResult`` will contain the details of an individual document, such as it's status, translation progress, any errors,
  and the URLs to the source document and translated document.

Examples
--------

The following section provides several code snippets covering some of the most common Document Translation tasks, including:


* :raw-html-m2r:`<a href="#translate-your-documents" title="Translate Your Documents">Translate your documents</a>`
* :raw-html-m2r:`<a href="#check-status-on-individual-documents" title="Check Status On Individual Documents">Check status on individual documents</a>`
* :raw-html-m2r:`<a href="#list-translation-jobs" title="List Translation Jobs">List translation jobs</a>`

Translate your documents
^^^^^^^^^^^^^^^^^^^^^^^^

Translate the documents in your source container to the target containers.

.. code-block:: python

   from azure.core.credentials import AzureKeyCredential
   from azure.ai.translation.document import DocumentTranslationClient, DocumentTranslationInput, TranslationTarget

   endpoint = "https://<resource-name>.cognitiveservices.azure.com/"
   credential = AzureKeyCredential("<api_key>")
   source_container_sas_url_en = "<sas-url-en>"
   target_container_sas_url_es = "<sas-url-es>"
   target_container_sas_url_fr = "<sas-url-fr>"

   document_translation_client = DocumentTranslationClient(endpoint, credential)

   job = document_translation_client.create_translation_job(
       [
           DocumentTranslationInput(
               source_url=source_container_sas_url_en,
               targets=[
                   TranslationTarget(target_url=target_container_sas_url_es, language_code="es"),
                   TranslationTarget(target_url=target_container_sas_url_fr, language_code="fr"),
               ],
           )
       ]
   )  # type: JobStatusResult

   job_result = document_translation_client.wait_until_done(job.id)  # type: JobStatusResult

   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("Of total documents...")
   print("{} failed".format(job_result.documents_failed_count))
   print("{} succeeded".format(job_result.documents_succeeded_count))

   if job_result.status == "Succeeded":
       print("Our translation job succeeded")

   if job_result.status == "Failed":
       print("All documents failed in the translation job")

   # check document statuses... see next sample

Check status on individual documents
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Check status and translation progress of each document under a job.

.. code-block:: python

   from azure.core.credentials import AzureKeyCredential
   from azure.ai.translation.document import DocumentTranslationClient

   endpoint = "https://<resource-name>.cognitiveservices.azure.com/"
   credential = AzureKeyCredential("<api_key>")
   job_id = "<job-id>"

   document_translation_client = DocumentTranslationClient(endpoint, credential)

   documents =  document_translation_client.list_all_document_statuses(job_id)  # type: ItemPaged[DocumentStatusResult]

   for doc in documents:
       if doc.status == "Succeeded":
           print("Document at {} was translated to {} language".format(
               doc.translated_document_url, doc.translate_to
           ))
       if doc.status == "Running":
           print("Document ID: {}, translation progress is {} percent".format(
               doc.id, doc.translation_progress*100
           ))
       if doc.status == "Failed":
           print("Document ID: {}, Error Code: {}, Message: {}".format(
               doc.id, doc.error.code, doc.error.message
           ))

List translation jobs
^^^^^^^^^^^^^^^^^^^^^

Enumerate over the translation jobs submitted for the resource.

.. code-block:: python

   from azure.core.credentials import AzureKeyCredential
   from azure.ai.translation.document import DocumentTranslationClient

   endpoint = "https://<resource-name>.cognitiveservices.azure.com/"
   credential = AzureKeyCredential("<api_key>")

   document_translation_client = DocumentTranslationClient(endpoint, credential)

   jobs = document_translation_client.list_submitted_jobs()  # type: ItemPaged[JobStatusResult]

   for job in jobs:
       if not job.has_completed:
           job = document_translation_client.wait_until_done(job.id)

       print("Job ID: {}".format(job.id))
       print("Job status: {}".format(job.status))
       print("Job created on: {}".format(job.created_on))
       print("Job last updated on: {}".format(job.last_updated_on))
       print("Total number of translations on documents: {}".format(job.documents_total_count))
       print("Total number of characters charged: {}".format(job.total_characters_charged))

       print("Of total documents...")
       print("{} failed".format(job.documents_failed_count))
       print("{} succeeded".format(job.documents_succeeded_count))
       print("{} cancelled".format(job.documents_cancelled_count))

To see how to use the Document Translation client library with Azure Storage Blob to upload documents, create SAS tokens
for your containers, and download the finished translated documents, see this `sample <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/sample_translation_with_azure_blob.py>`_. 
Note that you will need to install the `azure-storage-blob <https://pypi.org/project/azure-storage-blob/>`_ library to run this sample.

Troubleshooting
---------------

General
^^^^^^^

Document Translation client library will raise exceptions defined in `Azure Core <https://aka.ms/azsdk/python/core/docs#module-azure.core.exceptions>`_.

Logging
^^^^^^^

This library uses the standard
`logging <https://docs.python.org/3/library/logging.html>`_ library for logging.

Basic information about HTTP sessions (URLs, headers, etc.) is logged at ``INFO`` level.

Detailed ``DEBUG`` level logging, including request/response bodies and **unredacted**
headers, can be enabled on the client or per-operation with the ``logging_enable`` keyword argument.

See full SDK logging documentation with examples `here <https://docs.microsoft.com/azure/developer/python/azure-sdk-logging>`_.

Optional Configuration
^^^^^^^^^^^^^^^^^^^^^^

Optional keyword arguments can be passed in at the client and per-operation level.
The azure-core `reference documentation <https://aka.ms/azsdk/python/core/docs>`_
describes available configurations for retries, logging, transport protocols, and more.

Next steps
----------

The following section provides several code snippets illustrating common patterns used in the Document Translation Python client library.

More sample code
^^^^^^^^^^^^^^^^

These code samples show common scenario operations with the Azure Document Translation client library.


* Client authentication: `sample_authentication.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/sample_authentication.py>`_
* Create a translation job: `sample_create_translation_job.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/sample_create_translation_job.py>`_
* Check the status of documents: `sample_check_document_statuses.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/sample_check_document_statuses.py>`_
* List all submitted translation jobs: `sample_list_all_submitted_jobs.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/sample_list_all_submitted_jobs.py>`_
* Apply a custom glossary to translation: `sample_translation_with_glossaries.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/sample_translation_with_glossaries.py>`_
* Use Azure Blob Storage to set up translation resources: `sample_translation_with_azure_blob.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/sample_translation_with_azure_blob.py>`_

Async samples
^^^^^^^^^^^^^

This library also includes a complete async API supported on Python 3.6+. To use it, you must
first install an async transport, such as `aiohttp <https://pypi.org/project/aiohttp/>`_. Async clients
are found under the ``azure.ai.translation.document.aio`` namespace.


* Client authentication: `sample_authentication_async.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/async_samples/sample_authentication_async.py>`_
* Create a translation job: `sample_create_translation_job_async.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/async_samples/sample_create_translation_job_async.py>`_
* Check the status of documents: `sample_check_document_statuses_async.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/async_samples/sample_check_document_statuses_async.py>`_
* List all submitted translation jobs: `sample_list_all_submitted_jobs_async.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/async_samples/sample_list_all_submitted_jobs_async.py>`_
* Apply a custom glossary to translation: `sample_translation_with_glossaries_async.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/async_samples/sample_translation_with_glossaries_async.py>`_
* Use Azure Blob Storage to set up translation resources: `sample_translation_with_azure_blob_async.py <https://github.com/Azure/azure-sdk-for-python/tree/master/sdk/translation/azure-ai-translation-document/samples/async_samples/sample_translation_with_azure_blob_async.py>`_

Additional documentation
^^^^^^^^^^^^^^^^^^^^^^^^

For more extensive documentation on Azure Cognitive Services Document Translation, see the `Document Translation documentation <https://docs.microsoft.com/azure/cognitive-services/translator/document-translation/overview>`_ on docs.microsoft.com.

Contributing
------------

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit `cla.microsoft.com <https://cla.microsoft.com>`_.

When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the `Microsoft Open Source Code of Conduct <https://opensource.microsoft.com/codeofconduct/>`_. For more information see the `Code of Conduct FAQ <https://opensource.microsoft.com/codeofconduct/faq/>`_ or contact `opencode@microsoft.com <mailto:opencode@microsoft.com>`_ with any additional questions or comments.


.. raw:: html

   <!-- LINKS -->




Indices and tables
------------------

* :ref:`genindex`
* :ref:`modindex`
* :ref:`search`

.. toctree::
  :maxdepth: 5
  :glob:
  :caption: Developer Documentation

  azure.ai.translation.document.rst