diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS index b4c980836dfd..15f794713c6a 100644 --- a/.github/CODEOWNERS +++ b/.github/CODEOWNERS @@ -412,6 +412,10 @@ # PRLabel: %Cognitive - Text Analytics /sdk/textanalytics/ @quentinRobinson @wangyuantao +# ServiceLabel: %Health Deidentification +# PRLabel: %Health Deidentification +/sdk/healthdataaiservices/ @GrahamMThomas @danielszaniszlo + # AzureSdkOwners: @YalinLi0312 # ServiceLabel: %Cognitive - Form Recognizer # ServiceOwners: @bojunehsu @vkurpad diff --git a/.vscode/cspell.json b/.vscode/cspell.json index 683a2f6649cd..812b93d73d4e 100644 --- a/.vscode/cspell.json +++ b/.vscode/cspell.json @@ -244,6 +244,7 @@ "guids", "hanaonazure", "hdinsight", + "healthdataaiservices", "heapq", "hexlify", "himds", @@ -402,6 +403,7 @@ "unpad", "unpadder", "unpartial", + "uniquifier", "unredacted", "unseekable", "unsubscriptable", @@ -440,6 +442,7 @@ "BUILDID", "documentdb", "chdir", + "radiculopathy", "reqs", "rgpy", "swaggertosdk", @@ -1840,6 +1843,17 @@ "words": [ "dcid" ] + }, + { + "filename": "sdk/healthdataaiservices/azure-health-deidentification/**", + "words": [ + "deid", + "deidservices", + "deidentification", + "healthdataaiservices", + "deidentify", + "deidentified" + ] } ], "allowCompoundWords": true diff --git a/sdk/healthdataaiservices/azure-health-deidentification/CHANGELOG.md b/sdk/healthdataaiservices/azure-health-deidentification/CHANGELOG.md new file mode 100644 index 000000000000..ef45e51211b9 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/CHANGELOG.md @@ -0,0 +1,9 @@ +# Release History + +## 1.0.0b1 (1970-01-01) + +- Initial version + +### Features Added + +- Initial Code \ No newline at end of file diff --git a/sdk/healthdataaiservices/azure-health-deidentification/LICENSE b/sdk/healthdataaiservices/azure-health-deidentification/LICENSE new file mode 100644 index 000000000000..63447fd8bbbf --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/LICENSE @@ -0,0 +1,21 @@ +Copyright (c) Microsoft Corporation. + +MIT License + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED *AS IS*, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. \ No newline at end of file diff --git a/sdk/healthdataaiservices/azure-health-deidentification/MANIFEST.in b/sdk/healthdataaiservices/azure-health-deidentification/MANIFEST.in new file mode 100644 index 000000000000..9f9ff90e4267 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/MANIFEST.in @@ -0,0 +1,7 @@ +include *.md +include LICENSE +include azure/health/deidentification/py.typed +recursive-include tests *.py +recursive-include samples *.py *.md +include azure/__init__.py +include azure/health/__init__.py \ No newline at end of file diff --git a/sdk/healthdataaiservices/azure-health-deidentification/README.md b/sdk/healthdataaiservices/azure-health-deidentification/README.md new file mode 100644 index 000000000000..462f005e6278 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/README.md @@ -0,0 +1,108 @@ + + +# Azure Health Deidentification client library for Python +Azure.Health.Deidentification is a managed service that enables users to tag, redact, or surrogate health data. + +## Getting started + +### Install the package + +```bash +python -m pip install azure-health-deidentification +``` + +#### Prequisites + +- Python 3.8 or later is required to use this package. +- You need an [Azure subscription][azure_sub] to use this package. +- An existing Azure Health Deidentification instance. +#### Create with an Azure Active Directory Credential +To use an [Azure Active Directory (AAD) token credential][authenticate_with_token], +provide an instance of the desired credential type obtained from the +[azure-identity][azure_identity_credentials] library. + +To authenticate with AAD, you must first [pip][pip] install [`azure-identity`][azure_identity_pip] + +After setup, you can choose which type of [credential][azure_identity_credentials] from azure.identity to use. +As an example, [DefaultAzureCredential][default_azure_credential] can be used to authenticate the client: + +Set the values of the client ID, tenant ID, and client secret of the AAD application as environment variables: +`AZURE_CLIENT_ID`, `AZURE_TENANT_ID`, `AZURE_CLIENT_SECRET` + +Use the returned token credential to authenticate the client: + +```python +>>> from azure.health.deidentification import DeidentificationClient +>>> from azure.identity import DefaultAzureCredential +>>> client = DeidentificationClient(endpoint='', credential=DefaultAzureCredential()) +``` + +## Key concepts + +**Operation Modes** +- Tag: Will return a structure of offset and length with the PHI category of the related text spans. +- Redact: Will return output text with placeholder stubbed text. ex. `[name]` +- Surrogate: Will return output text with synthetic replacements. + - `My name is John Smith` + - `My name is Tom Jones` + +**Job Integration with Azure Storage** +Instead of sending text, you can send an Azure Storage Location to the service. We will asynchronously +process the list of files and output the deidentified files to a location of your choice. + +Limitations: +- Maximum file count per job: 1000 documents +- Maximum file size per file: 2 MB + +## Examples + +```python +>>> from azure.health.deidentification import DeidentificationClient +>>> from azure.identity import DefaultAzureCredential +>>> from azure.core.exceptions import HttpResponseError + +>>> client = DeidentificationClient(endpoint='', credential=DefaultAzureCredential()) +>>> try: + + except HttpResponseError as e: + print('service responds error: {}'.format(e.response.json())) + +``` + +## Next steps + +- Find a bug, or have feedback? Raise an issue with "Health Deidentification" Label. + + +## Troubleshooting + +- **Unabled to Access Source or Target Storage** + - Ensure you create your deid service with a system assigned managed identity + - Ensure your storage account has given permissions to that managed identity + +## 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 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][code_of_conduct]. For more information, +see the Code of Conduct FAQ or contact opencode@microsoft.com with any +additional questions or comments. + + +[code_of_conduct]: https://opensource.microsoft.com/codeofconduct/ +[authenticate_with_token]: https://docs.microsoft.com/azure/cognitive-services/authentication?tabs=powershell#authenticate-with-an-authentication-token +[azure_identity_credentials]: https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/identity/azure-identity#credentials +[azure_identity_pip]: https://pypi.org/project/azure-identity/ +[default_azure_credential]: https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/identity/azure-identity#defaultazurecredential +[pip]: https://pypi.org/project/pip/ +[azure_sub]: https://azure.microsoft.com/free/ + diff --git a/sdk/healthdataaiservices/azure-health-deidentification/assets.json b/sdk/healthdataaiservices/azure-health-deidentification/assets.json new file mode 100644 index 000000000000..b3c9831d2065 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/assets.json @@ -0,0 +1,6 @@ +{ + "AssetsRepo": "Azure/azure-sdk-assets", + "AssetsRepoPrefixPath": "python", + "TagPrefix": "python/healthdataaiservices/azure-health-deidentification", + "Tag": "python/healthdataaiservices/azure-health-deidentification_a8eed6d322" +} diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/__init__.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/__init__.py new file mode 100644 index 000000000000..d55ccad1f573 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/__init__.py @@ -0,0 +1 @@ +__path__ = __import__("pkgutil").extend_path(__path__, __name__) # type: ignore diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/__init__.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/__init__.py new file mode 100644 index 000000000000..d55ccad1f573 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/__init__.py @@ -0,0 +1 @@ +__path__ = __import__("pkgutil").extend_path(__path__, __name__) # type: ignore diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/__init__.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/__init__.py new file mode 100644 index 000000000000..01d9492ed4f6 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/__init__.py @@ -0,0 +1,26 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from ._client import DeidentificationClient +from ._version import VERSION + +__version__ = VERSION + +try: + from ._patch import __all__ as _patch_all + from ._patch import * # pylint: disable=unused-wildcard-import +except ImportError: + _patch_all = [] +from ._patch import patch_sdk as _patch_sdk + +__all__ = [ + "DeidentificationClient", +] +__all__.extend([p for p in _patch_all if p not in __all__]) + +_patch_sdk() diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_client.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_client.py new file mode 100644 index 000000000000..787817c317d9 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_client.py @@ -0,0 +1,103 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from copy import deepcopy +from typing import Any, TYPE_CHECKING +from typing_extensions import Self + +from azure.core import PipelineClient +from azure.core.pipeline import policies +from azure.core.rest import HttpRequest, HttpResponse + +from ._configuration import DeidentificationClientConfiguration +from ._operations import DeidentificationClientOperationsMixin +from ._serialization import Deserializer, Serializer + +if TYPE_CHECKING: + # pylint: disable=unused-import,ungrouped-imports + from azure.core.credentials import TokenCredential + + +class DeidentificationClient( + DeidentificationClientOperationsMixin +): # pylint: disable=client-accepts-api-version-keyword + """DeidentificationClient. + + :param endpoint: Url of your De-identification Service. Required. + :type endpoint: str + :param credential: Credential used to authenticate requests to the service. Required. + :type credential: ~azure.core.credentials.TokenCredential + :keyword api_version: The API version to use for this operation. Default value is + "2024-07-12-preview". Note that overriding this default value may result in unsupported + behavior. + :paramtype api_version: str + :keyword int polling_interval: Default waiting time between two polls for LRO operations if no + Retry-After header is present. + """ + + def __init__(self, endpoint: str, credential: "TokenCredential", **kwargs: Any) -> None: + _endpoint = "https://{endpoint}" + self._config = DeidentificationClientConfiguration(endpoint=endpoint, credential=credential, **kwargs) + _policies = kwargs.pop("policies", None) + if _policies is None: + _policies = [ + policies.RequestIdPolicy(**kwargs), + self._config.headers_policy, + self._config.user_agent_policy, + self._config.proxy_policy, + policies.ContentDecodePolicy(**kwargs), + self._config.redirect_policy, + self._config.retry_policy, + self._config.authentication_policy, + self._config.custom_hook_policy, + self._config.logging_policy, + policies.DistributedTracingPolicy(**kwargs), + policies.SensitiveHeaderCleanupPolicy(**kwargs) if self._config.redirect_policy else None, + self._config.http_logging_policy, + ] + self._client: PipelineClient = PipelineClient(base_url=_endpoint, policies=_policies, **kwargs) + + self._serialize = Serializer() + self._deserialize = Deserializer() + self._serialize.client_side_validation = False + + def send_request(self, request: HttpRequest, *, stream: bool = False, **kwargs: Any) -> HttpResponse: + """Runs the network request through the client's chained policies. + + >>> from azure.core.rest import HttpRequest + >>> request = HttpRequest("GET", "https://www.example.org/") + + >>> response = client.send_request(request) + + + For more information on this code flow, see https://aka.ms/azsdk/dpcodegen/python/send_request + + :param request: The network request you want to make. Required. + :type request: ~azure.core.rest.HttpRequest + :keyword bool stream: Whether the response payload will be streamed. Defaults to False. + :return: The response of your network call. Does not do error handling on your response. + :rtype: ~azure.core.rest.HttpResponse + """ + + request_copy = deepcopy(request) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + + request_copy.url = self._client.format_url(request_copy.url, **path_format_arguments) + return self._client.send_request(request_copy, stream=stream, **kwargs) # type: ignore + + def close(self) -> None: + self._client.close() + + def __enter__(self) -> Self: + self._client.__enter__() + return self + + def __exit__(self, *exc_details: Any) -> None: + self._client.__exit__(*exc_details) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_configuration.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_configuration.py new file mode 100644 index 000000000000..35237a99ba8f --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_configuration.py @@ -0,0 +1,65 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from typing import Any, TYPE_CHECKING + +from azure.core.pipeline import policies + +from ._version import VERSION + +if TYPE_CHECKING: + # pylint: disable=unused-import,ungrouped-imports + from azure.core.credentials import TokenCredential + + +class DeidentificationClientConfiguration: # pylint: disable=too-many-instance-attributes,name-too-long + """Configuration for DeidentificationClient. + + Note that all parameters used to create this instance are saved as instance + attributes. + + :param endpoint: Url of your De-identification Service. Required. + :type endpoint: str + :param credential: Credential used to authenticate requests to the service. Required. + :type credential: ~azure.core.credentials.TokenCredential + :keyword api_version: The API version to use for this operation. Default value is + "2024-07-12-preview". Note that overriding this default value may result in unsupported + behavior. + :paramtype api_version: str + """ + + def __init__(self, endpoint: str, credential: "TokenCredential", **kwargs: Any) -> None: + api_version: str = kwargs.pop("api_version", "2024-07-12-preview") + + if endpoint is None: + raise ValueError("Parameter 'endpoint' must not be None.") + if credential is None: + raise ValueError("Parameter 'credential' must not be None.") + + self.endpoint = endpoint + self.credential = credential + self.api_version = api_version + self.credential_scopes = kwargs.pop("credential_scopes", ["https://deid.azure.com/.default"]) + kwargs.setdefault("sdk_moniker", "health-deidentification/{}".format(VERSION)) + self.polling_interval = kwargs.get("polling_interval", 30) + self._configure(**kwargs) + + def _configure(self, **kwargs: Any) -> None: + self.user_agent_policy = kwargs.get("user_agent_policy") or policies.UserAgentPolicy(**kwargs) + self.headers_policy = kwargs.get("headers_policy") or policies.HeadersPolicy(**kwargs) + self.proxy_policy = kwargs.get("proxy_policy") or policies.ProxyPolicy(**kwargs) + self.logging_policy = kwargs.get("logging_policy") or policies.NetworkTraceLoggingPolicy(**kwargs) + self.http_logging_policy = kwargs.get("http_logging_policy") or policies.HttpLoggingPolicy(**kwargs) + self.custom_hook_policy = kwargs.get("custom_hook_policy") or policies.CustomHookPolicy(**kwargs) + self.redirect_policy = kwargs.get("redirect_policy") or policies.RedirectPolicy(**kwargs) + self.retry_policy = kwargs.get("retry_policy") or policies.RetryPolicy(**kwargs) + self.authentication_policy = kwargs.get("authentication_policy") + if self.credential and not self.authentication_policy: + self.authentication_policy = policies.BearerTokenCredentialPolicy( + self.credential, *self.credential_scopes, **kwargs + ) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_model_base.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_model_base.py new file mode 100644 index 000000000000..43fd8c7e9b1b --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_model_base.py @@ -0,0 +1,888 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for +# license information. +# -------------------------------------------------------------------------- +# pylint: disable=protected-access, arguments-differ, signature-differs, broad-except + +import copy +import calendar +import decimal +import functools +import sys +import logging +import base64 +import re +import typing +import enum +import email.utils +from datetime import datetime, date, time, timedelta, timezone +from json import JSONEncoder +from typing_extensions import Self +import isodate +from azure.core.exceptions import DeserializationError +from azure.core import CaseInsensitiveEnumMeta +from azure.core.pipeline import PipelineResponse +from azure.core.serialization import _Null + +if sys.version_info >= (3, 9): + from collections.abc import MutableMapping +else: + from typing import MutableMapping + +_LOGGER = logging.getLogger(__name__) + +__all__ = ["SdkJSONEncoder", "Model", "rest_field", "rest_discriminator"] + +TZ_UTC = timezone.utc +_T = typing.TypeVar("_T") + + +def _timedelta_as_isostr(td: timedelta) -> str: + """Converts a datetime.timedelta object into an ISO 8601 formatted string, e.g. 'P4DT12H30M05S' + + Function adapted from the Tin Can Python project: https://github.com/RusticiSoftware/TinCanPython + + :param timedelta td: The timedelta to convert + :rtype: str + :return: ISO8601 version of this timedelta + """ + + # Split seconds to larger units + seconds = td.total_seconds() + minutes, seconds = divmod(seconds, 60) + hours, minutes = divmod(minutes, 60) + days, hours = divmod(hours, 24) + + days, hours, minutes = list(map(int, (days, hours, minutes))) + seconds = round(seconds, 6) + + # Build date + date_str = "" + if days: + date_str = "%sD" % days + + if hours or minutes or seconds: + # Build time + time_str = "T" + + # Hours + bigger_exists = date_str or hours + if bigger_exists: + time_str += "{:02}H".format(hours) + + # Minutes + bigger_exists = bigger_exists or minutes + if bigger_exists: + time_str += "{:02}M".format(minutes) + + # Seconds + try: + if seconds.is_integer(): + seconds_string = "{:02}".format(int(seconds)) + else: + # 9 chars long w/ leading 0, 6 digits after decimal + seconds_string = "%09.6f" % seconds + # Remove trailing zeros + seconds_string = seconds_string.rstrip("0") + except AttributeError: # int.is_integer() raises + seconds_string = "{:02}".format(seconds) + + time_str += "{}S".format(seconds_string) + else: + time_str = "" + + return "P" + date_str + time_str + + +def _serialize_bytes(o, format: typing.Optional[str] = None) -> str: + encoded = base64.b64encode(o).decode() + if format == "base64url": + return encoded.strip("=").replace("+", "-").replace("/", "_") + return encoded + + +def _serialize_datetime(o, format: typing.Optional[str] = None): + if hasattr(o, "year") and hasattr(o, "hour"): + if format == "rfc7231": + return email.utils.format_datetime(o, usegmt=True) + if format == "unix-timestamp": + return int(calendar.timegm(o.utctimetuple())) + + # astimezone() fails for naive times in Python 2.7, so make make sure o is aware (tzinfo is set) + if not o.tzinfo: + iso_formatted = o.replace(tzinfo=TZ_UTC).isoformat() + else: + iso_formatted = o.astimezone(TZ_UTC).isoformat() + # Replace the trailing "+00:00" UTC offset with "Z" (RFC 3339: https://www.ietf.org/rfc/rfc3339.txt) + return iso_formatted.replace("+00:00", "Z") + # Next try datetime.date or datetime.time + return o.isoformat() + + +def _is_readonly(p): + try: + return p._visibility == ["read"] # pylint: disable=protected-access + except AttributeError: + return False + + +class SdkJSONEncoder(JSONEncoder): + """A JSON encoder that's capable of serializing datetime objects and bytes.""" + + def __init__(self, *args, exclude_readonly: bool = False, format: typing.Optional[str] = None, **kwargs): + super().__init__(*args, **kwargs) + self.exclude_readonly = exclude_readonly + self.format = format + + def default(self, o): # pylint: disable=too-many-return-statements + if _is_model(o): + if self.exclude_readonly: + readonly_props = [p._rest_name for p in o._attr_to_rest_field.values() if _is_readonly(p)] + return {k: v for k, v in o.items() if k not in readonly_props} + return dict(o.items()) + try: + return super(SdkJSONEncoder, self).default(o) + except TypeError: + if isinstance(o, _Null): + return None + if isinstance(o, decimal.Decimal): + return float(o) + if isinstance(o, (bytes, bytearray)): + return _serialize_bytes(o, self.format) + try: + # First try datetime.datetime + return _serialize_datetime(o, self.format) + except AttributeError: + pass + # Last, try datetime.timedelta + try: + return _timedelta_as_isostr(o) + except AttributeError: + # This will be raised when it hits value.total_seconds in the method above + pass + return super(SdkJSONEncoder, self).default(o) + + +_VALID_DATE = re.compile(r"\d{4}[-]\d{2}[-]\d{2}T\d{2}:\d{2}:\d{2}" + r"\.?\d*Z?[-+]?[\d{2}]?:?[\d{2}]?") +_VALID_RFC7231 = re.compile( + r"(Mon|Tue|Wed|Thu|Fri|Sat|Sun),\s\d{2}\s" + r"(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\s\d{4}\s\d{2}:\d{2}:\d{2}\sGMT" +) + + +def _deserialize_datetime(attr: typing.Union[str, datetime]) -> datetime: + """Deserialize ISO-8601 formatted string into Datetime object. + + :param str attr: response string to be deserialized. + :rtype: ~datetime.datetime + :returns: The datetime object from that input + """ + if isinstance(attr, datetime): + # i'm already deserialized + return attr + attr = attr.upper() + match = _VALID_DATE.match(attr) + if not match: + raise ValueError("Invalid datetime string: " + attr) + + check_decimal = attr.split(".") + if len(check_decimal) > 1: + decimal_str = "" + for digit in check_decimal[1]: + if digit.isdigit(): + decimal_str += digit + else: + break + if len(decimal_str) > 6: + attr = attr.replace(decimal_str, decimal_str[0:6]) + + date_obj = isodate.parse_datetime(attr) + test_utc = date_obj.utctimetuple() + if test_utc.tm_year > 9999 or test_utc.tm_year < 1: + raise OverflowError("Hit max or min date") + return date_obj + + +def _deserialize_datetime_rfc7231(attr: typing.Union[str, datetime]) -> datetime: + """Deserialize RFC7231 formatted string into Datetime object. + + :param str attr: response string to be deserialized. + :rtype: ~datetime.datetime + :returns: The datetime object from that input + """ + if isinstance(attr, datetime): + # i'm already deserialized + return attr + match = _VALID_RFC7231.match(attr) + if not match: + raise ValueError("Invalid datetime string: " + attr) + + return email.utils.parsedate_to_datetime(attr) + + +def _deserialize_datetime_unix_timestamp(attr: typing.Union[float, datetime]) -> datetime: + """Deserialize unix timestamp into Datetime object. + + :param str attr: response string to be deserialized. + :rtype: ~datetime.datetime + :returns: The datetime object from that input + """ + if isinstance(attr, datetime): + # i'm already deserialized + return attr + return datetime.fromtimestamp(attr, TZ_UTC) + + +def _deserialize_date(attr: typing.Union[str, date]) -> date: + """Deserialize ISO-8601 formatted string into Date object. + :param str attr: response string to be deserialized. + :rtype: date + :returns: The date object from that input + """ + # This must NOT use defaultmonth/defaultday. Using None ensure this raises an exception. + if isinstance(attr, date): + return attr + return isodate.parse_date(attr, defaultmonth=None, defaultday=None) # type: ignore + + +def _deserialize_time(attr: typing.Union[str, time]) -> time: + """Deserialize ISO-8601 formatted string into time object. + + :param str attr: response string to be deserialized. + :rtype: datetime.time + :returns: The time object from that input + """ + if isinstance(attr, time): + return attr + return isodate.parse_time(attr) + + +def _deserialize_bytes(attr): + if isinstance(attr, (bytes, bytearray)): + return attr + return bytes(base64.b64decode(attr)) + + +def _deserialize_bytes_base64(attr): + if isinstance(attr, (bytes, bytearray)): + return attr + padding = "=" * (3 - (len(attr) + 3) % 4) # type: ignore + attr = attr + padding # type: ignore + encoded = attr.replace("-", "+").replace("_", "/") + return bytes(base64.b64decode(encoded)) + + +def _deserialize_duration(attr): + if isinstance(attr, timedelta): + return attr + return isodate.parse_duration(attr) + + +def _deserialize_decimal(attr): + if isinstance(attr, decimal.Decimal): + return attr + return decimal.Decimal(str(attr)) + + +_DESERIALIZE_MAPPING = { + datetime: _deserialize_datetime, + date: _deserialize_date, + time: _deserialize_time, + bytes: _deserialize_bytes, + bytearray: _deserialize_bytes, + timedelta: _deserialize_duration, + typing.Any: lambda x: x, + decimal.Decimal: _deserialize_decimal, +} + +_DESERIALIZE_MAPPING_WITHFORMAT = { + "rfc3339": _deserialize_datetime, + "rfc7231": _deserialize_datetime_rfc7231, + "unix-timestamp": _deserialize_datetime_unix_timestamp, + "base64": _deserialize_bytes, + "base64url": _deserialize_bytes_base64, +} + + +def get_deserializer(annotation: typing.Any, rf: typing.Optional["_RestField"] = None): + if rf and rf._format: + return _DESERIALIZE_MAPPING_WITHFORMAT.get(rf._format) + return _DESERIALIZE_MAPPING.get(annotation) + + +def _get_type_alias_type(module_name: str, alias_name: str): + types = { + k: v + for k, v in sys.modules[module_name].__dict__.items() + if isinstance(v, typing._GenericAlias) # type: ignore + } + if alias_name not in types: + return alias_name + return types[alias_name] + + +def _get_model(module_name: str, model_name: str): + models = {k: v for k, v in sys.modules[module_name].__dict__.items() if isinstance(v, type)} + module_end = module_name.rsplit(".", 1)[0] + models.update({k: v for k, v in sys.modules[module_end].__dict__.items() if isinstance(v, type)}) + if isinstance(model_name, str): + model_name = model_name.split(".")[-1] + if model_name not in models: + return model_name + return models[model_name] + + +_UNSET = object() + + +class _MyMutableMapping(MutableMapping[str, typing.Any]): # pylint: disable=unsubscriptable-object + def __init__(self, data: typing.Dict[str, typing.Any]) -> None: + self._data = data + + def __contains__(self, key: typing.Any) -> bool: + return key in self._data + + def __getitem__(self, key: str) -> typing.Any: + return self._data.__getitem__(key) + + def __setitem__(self, key: str, value: typing.Any) -> None: + self._data.__setitem__(key, value) + + def __delitem__(self, key: str) -> None: + self._data.__delitem__(key) + + def __iter__(self) -> typing.Iterator[typing.Any]: + return self._data.__iter__() + + def __len__(self) -> int: + return self._data.__len__() + + def __ne__(self, other: typing.Any) -> bool: + return not self.__eq__(other) + + def keys(self) -> typing.KeysView[str]: + return self._data.keys() + + def values(self) -> typing.ValuesView[typing.Any]: + return self._data.values() + + def items(self) -> typing.ItemsView[str, typing.Any]: + return self._data.items() + + def get(self, key: str, default: typing.Any = None) -> typing.Any: + try: + return self[key] + except KeyError: + return default + + @typing.overload + def pop(self, key: str) -> typing.Any: ... + + @typing.overload + def pop(self, key: str, default: _T) -> _T: ... + + @typing.overload + def pop(self, key: str, default: typing.Any) -> typing.Any: ... + + def pop(self, key: str, default: typing.Any = _UNSET) -> typing.Any: + if default is _UNSET: + return self._data.pop(key) + return self._data.pop(key, default) + + def popitem(self) -> typing.Tuple[str, typing.Any]: + return self._data.popitem() + + def clear(self) -> None: + self._data.clear() + + def update(self, *args: typing.Any, **kwargs: typing.Any) -> None: + self._data.update(*args, **kwargs) + + @typing.overload + def setdefault(self, key: str, default: None = None) -> None: ... + + @typing.overload + def setdefault(self, key: str, default: typing.Any) -> typing.Any: ... + + def setdefault(self, key: str, default: typing.Any = _UNSET) -> typing.Any: + if default is _UNSET: + return self._data.setdefault(key) + return self._data.setdefault(key, default) + + def __eq__(self, other: typing.Any) -> bool: + try: + other_model = self.__class__(other) + except Exception: + return False + return self._data == other_model._data + + def __repr__(self) -> str: + return str(self._data) + + +def _is_model(obj: typing.Any) -> bool: + return getattr(obj, "_is_model", False) + + +def _serialize(o, format: typing.Optional[str] = None): # pylint: disable=too-many-return-statements + if isinstance(o, list): + return [_serialize(x, format) for x in o] + if isinstance(o, dict): + return {k: _serialize(v, format) for k, v in o.items()} + if isinstance(o, set): + return {_serialize(x, format) for x in o} + if isinstance(o, tuple): + return tuple(_serialize(x, format) for x in o) + if isinstance(o, (bytes, bytearray)): + return _serialize_bytes(o, format) + if isinstance(o, decimal.Decimal): + return float(o) + if isinstance(o, enum.Enum): + return o.value + try: + # First try datetime.datetime + return _serialize_datetime(o, format) + except AttributeError: + pass + # Last, try datetime.timedelta + try: + return _timedelta_as_isostr(o) + except AttributeError: + # This will be raised when it hits value.total_seconds in the method above + pass + return o + + +def _get_rest_field( + attr_to_rest_field: typing.Dict[str, "_RestField"], rest_name: str +) -> typing.Optional["_RestField"]: + try: + return next(rf for rf in attr_to_rest_field.values() if rf._rest_name == rest_name) + except StopIteration: + return None + + +def _create_value(rf: typing.Optional["_RestField"], value: typing.Any) -> typing.Any: + if not rf: + return _serialize(value, None) + if rf._is_multipart_file_input: + return value + if rf._is_model: + return _deserialize(rf._type, value) + return _serialize(value, rf._format) + + +class Model(_MyMutableMapping): + _is_model = True + + def __init__(self, *args: typing.Any, **kwargs: typing.Any) -> None: + class_name = self.__class__.__name__ + if len(args) > 1: + raise TypeError(f"{class_name}.__init__() takes 2 positional arguments but {len(args) + 1} were given") + dict_to_pass = { + rest_field._rest_name: rest_field._default + for rest_field in self._attr_to_rest_field.values() + if rest_field._default is not _UNSET + } + if args: + dict_to_pass.update( + {k: _create_value(_get_rest_field(self._attr_to_rest_field, k), v) for k, v in args[0].items()} + ) + else: + non_attr_kwargs = [k for k in kwargs if k not in self._attr_to_rest_field] + if non_attr_kwargs: + # actual type errors only throw the first wrong keyword arg they see, so following that. + raise TypeError(f"{class_name}.__init__() got an unexpected keyword argument '{non_attr_kwargs[0]}'") + dict_to_pass.update( + { + self._attr_to_rest_field[k]._rest_name: _create_value(self._attr_to_rest_field[k], v) + for k, v in kwargs.items() + if v is not None + } + ) + super().__init__(dict_to_pass) + + def copy(self) -> "Model": + return Model(self.__dict__) + + def __new__(cls, *args: typing.Any, **kwargs: typing.Any) -> Self: # pylint: disable=unused-argument + # we know the last three classes in mro are going to be 'Model', 'dict', and 'object' + mros = cls.__mro__[:-3][::-1] # ignore model, dict, and object parents, and reverse the mro order + attr_to_rest_field: typing.Dict[str, _RestField] = { # map attribute name to rest_field property + k: v for mro_class in mros for k, v in mro_class.__dict__.items() if k[0] != "_" and hasattr(v, "_type") + } + annotations = { + k: v + for mro_class in mros + if hasattr(mro_class, "__annotations__") # pylint: disable=no-member + for k, v in mro_class.__annotations__.items() # pylint: disable=no-member + } + for attr, rf in attr_to_rest_field.items(): + rf._module = cls.__module__ + if not rf._type: + rf._type = rf._get_deserialize_callable_from_annotation(annotations.get(attr, None)) + if not rf._rest_name_input: + rf._rest_name_input = attr + cls._attr_to_rest_field: typing.Dict[str, _RestField] = dict(attr_to_rest_field.items()) + + return super().__new__(cls) # pylint: disable=no-value-for-parameter + + def __init_subclass__(cls, discriminator: typing.Optional[str] = None) -> None: + for base in cls.__bases__: + if hasattr(base, "__mapping__"): # pylint: disable=no-member + base.__mapping__[discriminator or cls.__name__] = cls # type: ignore # pylint: disable=no-member + + @classmethod + def _get_discriminator(cls, exist_discriminators) -> typing.Optional[str]: + for v in cls.__dict__.values(): + if ( + isinstance(v, _RestField) and v._is_discriminator and v._rest_name not in exist_discriminators + ): # pylint: disable=protected-access + return v._rest_name # pylint: disable=protected-access + return None + + @classmethod + def _deserialize(cls, data, exist_discriminators): + if not hasattr(cls, "__mapping__"): # pylint: disable=no-member + return cls(data) + discriminator = cls._get_discriminator(exist_discriminators) + exist_discriminators.append(discriminator) + mapped_cls = cls.__mapping__.get(data.get(discriminator), cls) # pyright: ignore # pylint: disable=no-member + if mapped_cls == cls: + return cls(data) + return mapped_cls._deserialize(data, exist_discriminators) # pylint: disable=protected-access + + def as_dict(self, *, exclude_readonly: bool = False) -> typing.Dict[str, typing.Any]: + """Return a dict that can be JSONify using json.dump. + + :keyword bool exclude_readonly: Whether to remove the readonly properties. + :returns: A dict JSON compatible object + :rtype: dict + """ + + result = {} + if exclude_readonly: + readonly_props = [p._rest_name for p in self._attr_to_rest_field.values() if _is_readonly(p)] + for k, v in self.items(): + if exclude_readonly and k in readonly_props: # pyright: ignore + continue + is_multipart_file_input = False + try: + is_multipart_file_input = next( + rf for rf in self._attr_to_rest_field.values() if rf._rest_name == k + )._is_multipart_file_input + except StopIteration: + pass + result[k] = v if is_multipart_file_input else Model._as_dict_value(v, exclude_readonly=exclude_readonly) + return result + + @staticmethod + def _as_dict_value(v: typing.Any, exclude_readonly: bool = False) -> typing.Any: + if v is None or isinstance(v, _Null): + return None + if isinstance(v, (list, tuple, set)): + return type(v)(Model._as_dict_value(x, exclude_readonly=exclude_readonly) for x in v) + if isinstance(v, dict): + return {dk: Model._as_dict_value(dv, exclude_readonly=exclude_readonly) for dk, dv in v.items()} + return v.as_dict(exclude_readonly=exclude_readonly) if hasattr(v, "as_dict") else v + + +def _deserialize_model(model_deserializer: typing.Optional[typing.Callable], obj): + if _is_model(obj): + return obj + return _deserialize(model_deserializer, obj) + + +def _deserialize_with_optional(if_obj_deserializer: typing.Optional[typing.Callable], obj): + if obj is None: + return obj + return _deserialize_with_callable(if_obj_deserializer, obj) + + +def _deserialize_with_union(deserializers, obj): + for deserializer in deserializers: + try: + return _deserialize(deserializer, obj) + except DeserializationError: + pass + raise DeserializationError() + + +def _deserialize_dict( + value_deserializer: typing.Optional[typing.Callable], + module: typing.Optional[str], + obj: typing.Dict[typing.Any, typing.Any], +): + if obj is None: + return obj + return {k: _deserialize(value_deserializer, v, module) for k, v in obj.items()} + + +def _deserialize_multiple_sequence( + entry_deserializers: typing.List[typing.Optional[typing.Callable]], + module: typing.Optional[str], + obj, +): + if obj is None: + return obj + return type(obj)(_deserialize(deserializer, entry, module) for entry, deserializer in zip(obj, entry_deserializers)) + + +def _deserialize_sequence( + deserializer: typing.Optional[typing.Callable], + module: typing.Optional[str], + obj, +): + if obj is None: + return obj + return type(obj)(_deserialize(deserializer, entry, module) for entry in obj) + + +def _sorted_annotations(types: typing.List[typing.Any]) -> typing.List[typing.Any]: + return sorted( + types, + key=lambda x: hasattr(x, "__name__") and x.__name__.lower() in ("str", "float", "int", "bool"), + ) + + +def _get_deserialize_callable_from_annotation( # pylint: disable=R0911, R0915, R0912 + annotation: typing.Any, + module: typing.Optional[str], + rf: typing.Optional["_RestField"] = None, +) -> typing.Optional[typing.Callable[[typing.Any], typing.Any]]: + if not annotation or annotation in [int, float]: + return None + + # is it a type alias? + if isinstance(annotation, str): + if module is not None: + annotation = _get_type_alias_type(module, annotation) + + # is it a forward ref / in quotes? + if isinstance(annotation, (str, typing.ForwardRef)): + try: + model_name = annotation.__forward_arg__ # type: ignore + except AttributeError: + model_name = annotation + if module is not None: + annotation = _get_model(module, model_name) + + try: + if module and _is_model(annotation): + if rf: + rf._is_model = True + + return functools.partial(_deserialize_model, annotation) # pyright: ignore + except Exception: + pass + + # is it a literal? + try: + if annotation.__origin__ is typing.Literal: # pyright: ignore + return None + except AttributeError: + pass + + # is it optional? + try: + if any(a for a in annotation.__args__ if a == type(None)): # pyright: ignore + if len(annotation.__args__) <= 2: # pyright: ignore + if_obj_deserializer = _get_deserialize_callable_from_annotation( + next(a for a in annotation.__args__ if a != type(None)), module, rf # pyright: ignore + ) + + return functools.partial(_deserialize_with_optional, if_obj_deserializer) + # the type is Optional[Union[...]], we need to remove the None type from the Union + annotation_copy = copy.copy(annotation) + annotation_copy.__args__ = [a for a in annotation_copy.__args__ if a != type(None)] # pyright: ignore + return _get_deserialize_callable_from_annotation(annotation_copy, module, rf) + except AttributeError: + pass + + # is it union? + if getattr(annotation, "__origin__", None) is typing.Union: + # initial ordering is we make `string` the last deserialization option, because it is often them most generic + deserializers = [ + _get_deserialize_callable_from_annotation(arg, module, rf) + for arg in _sorted_annotations(annotation.__args__) # pyright: ignore + ] + + return functools.partial(_deserialize_with_union, deserializers) + + try: + if annotation._name == "Dict": # pyright: ignore + value_deserializer = _get_deserialize_callable_from_annotation( + annotation.__args__[1], module, rf # pyright: ignore + ) + + return functools.partial( + _deserialize_dict, + value_deserializer, + module, + ) + except (AttributeError, IndexError): + pass + try: + if annotation._name in ["List", "Set", "Tuple", "Sequence"]: # pyright: ignore + if len(annotation.__args__) > 1: # pyright: ignore + + entry_deserializers = [ + _get_deserialize_callable_from_annotation(dt, module, rf) + for dt in annotation.__args__ # pyright: ignore + ] + return functools.partial(_deserialize_multiple_sequence, entry_deserializers, module) + deserializer = _get_deserialize_callable_from_annotation( + annotation.__args__[0], module, rf # pyright: ignore + ) + + return functools.partial(_deserialize_sequence, deserializer, module) + except (TypeError, IndexError, AttributeError, SyntaxError): + pass + + def _deserialize_default( + deserializer, + obj, + ): + if obj is None: + return obj + try: + return _deserialize_with_callable(deserializer, obj) + except Exception: + pass + return obj + + if get_deserializer(annotation, rf): + return functools.partial(_deserialize_default, get_deserializer(annotation, rf)) + + return functools.partial(_deserialize_default, annotation) + + +def _deserialize_with_callable( + deserializer: typing.Optional[typing.Callable[[typing.Any], typing.Any]], + value: typing.Any, +): + try: + if value is None or isinstance(value, _Null): + return None + if deserializer is None: + return value + if isinstance(deserializer, CaseInsensitiveEnumMeta): + try: + return deserializer(value) + except ValueError: + # for unknown value, return raw value + return value + if isinstance(deserializer, type) and issubclass(deserializer, Model): + return deserializer._deserialize(value, []) + return typing.cast(typing.Callable[[typing.Any], typing.Any], deserializer)(value) + except Exception as e: + raise DeserializationError() from e + + +def _deserialize( + deserializer: typing.Any, + value: typing.Any, + module: typing.Optional[str] = None, + rf: typing.Optional["_RestField"] = None, + format: typing.Optional[str] = None, +) -> typing.Any: + if isinstance(value, PipelineResponse): + value = value.http_response.json() + if rf is None and format: + rf = _RestField(format=format) + if not isinstance(deserializer, functools.partial): + deserializer = _get_deserialize_callable_from_annotation(deserializer, module, rf) + return _deserialize_with_callable(deserializer, value) + + +class _RestField: + def __init__( + self, + *, + name: typing.Optional[str] = None, + type: typing.Optional[typing.Callable] = None, # pylint: disable=redefined-builtin + is_discriminator: bool = False, + visibility: typing.Optional[typing.List[str]] = None, + default: typing.Any = _UNSET, + format: typing.Optional[str] = None, + is_multipart_file_input: bool = False, + ): + self._type = type + self._rest_name_input = name + self._module: typing.Optional[str] = None + self._is_discriminator = is_discriminator + self._visibility = visibility + self._is_model = False + self._default = default + self._format = format + self._is_multipart_file_input = is_multipart_file_input + + @property + def _class_type(self) -> typing.Any: + return getattr(self._type, "args", [None])[0] + + @property + def _rest_name(self) -> str: + if self._rest_name_input is None: + raise ValueError("Rest name was never set") + return self._rest_name_input + + def __get__(self, obj: Model, type=None): # pylint: disable=redefined-builtin + # by this point, type and rest_name will have a value bc we default + # them in __new__ of the Model class + item = obj.get(self._rest_name) + if item is None: + return item + if self._is_model: + return item + return _deserialize(self._type, _serialize(item, self._format), rf=self) + + def __set__(self, obj: Model, value) -> None: + if value is None: + # we want to wipe out entries if users set attr to None + try: + obj.__delitem__(self._rest_name) + except KeyError: + pass + return + if self._is_model: + if not _is_model(value): + value = _deserialize(self._type, value) + obj.__setitem__(self._rest_name, value) + return + obj.__setitem__(self._rest_name, _serialize(value, self._format)) + + def _get_deserialize_callable_from_annotation( + self, annotation: typing.Any + ) -> typing.Optional[typing.Callable[[typing.Any], typing.Any]]: + return _get_deserialize_callable_from_annotation(annotation, self._module, self) + + +def rest_field( + *, + name: typing.Optional[str] = None, + type: typing.Optional[typing.Callable] = None, # pylint: disable=redefined-builtin + visibility: typing.Optional[typing.List[str]] = None, + default: typing.Any = _UNSET, + format: typing.Optional[str] = None, + is_multipart_file_input: bool = False, +) -> typing.Any: + return _RestField( + name=name, + type=type, + visibility=visibility, + default=default, + format=format, + is_multipart_file_input=is_multipart_file_input, + ) + + +def rest_discriminator( + *, + name: typing.Optional[str] = None, + type: typing.Optional[typing.Callable] = None, # pylint: disable=redefined-builtin + visibility: typing.Optional[typing.List[str]] = None, +) -> typing.Any: + return _RestField(name=name, type=type, is_discriminator=True, visibility=visibility) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_operations/__init__.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_operations/__init__.py new file mode 100644 index 000000000000..f30b11092e89 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_operations/__init__.py @@ -0,0 +1,19 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from ._operations import DeidentificationClientOperationsMixin + +from ._patch import __all__ as _patch_all +from ._patch import * # pylint: disable=unused-wildcard-import +from ._patch import patch_sdk as _patch_sdk + +__all__ = [ + "DeidentificationClientOperationsMixin", +] +__all__.extend([p for p in _patch_all if p not in __all__]) +_patch_sdk() diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_operations/_operations.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_operations/_operations.py new file mode 100644 index 000000000000..f1aea8456604 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_operations/_operations.py @@ -0,0 +1,1499 @@ +# pylint: disable=too-many-lines,too-many-statements +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- +from io import IOBase +import json +import sys +from typing import Any, Callable, Dict, IO, Iterable, Iterator, List, Optional, Type, TypeVar, Union, cast, overload +import urllib.parse + +from azure.core.exceptions import ( + ClientAuthenticationError, + HttpResponseError, + ResourceExistsError, + ResourceNotFoundError, + ResourceNotModifiedError, + map_error, +) +from azure.core.paging import ItemPaged +from azure.core.pipeline import PipelineResponse +from azure.core.polling import LROPoller, NoPolling, PollingMethod +from azure.core.polling.base_polling import LROBasePolling +from azure.core.rest import HttpRequest, HttpResponse +from azure.core.tracing.decorator import distributed_trace +from azure.core.utils import case_insensitive_dict + +from .. import models as _models +from .._model_base import SdkJSONEncoder, _deserialize +from .._serialization import Serializer +from .._vendor import DeidentificationClientMixinABC + +if sys.version_info >= (3, 9): + from collections.abc import MutableMapping +else: + from typing import MutableMapping # type: ignore # pylint: disable=ungrouped-imports +JSON = MutableMapping[str, Any] # pylint: disable=unsubscriptable-object +T = TypeVar("T") +ClsType = Optional[Callable[[PipelineResponse[HttpRequest, HttpResponse], T, Dict[str, Any]], Any]] + +_SERIALIZER = Serializer() +_SERIALIZER.client_side_validation = False + + +def build_deidentification_get_job_request(name: str, **kwargs: Any) -> HttpRequest: + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = case_insensitive_dict(kwargs.pop("params", {}) or {}) + + api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2024-07-12-preview")) + accept = _headers.pop("Accept", "application/json") + + # Construct URL + _url = "/jobs/{name}" + path_format_arguments = { + "name": _SERIALIZER.url("name", name, "str"), + } + + _url: str = _url.format(**path_format_arguments) # type: ignore + + # Construct parameters + _params["api-version"] = _SERIALIZER.query("api_version", api_version, "str") + + # Construct headers + _headers["Accept"] = _SERIALIZER.header("accept", accept, "str") + + return HttpRequest(method="GET", url=_url, params=_params, headers=_headers, **kwargs) + + +def build_deidentification_create_job_request(name: str, **kwargs: Any) -> HttpRequest: # pylint: disable=name-too-long + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = case_insensitive_dict(kwargs.pop("params", {}) or {}) + + content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("Content-Type", None)) + api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2024-07-12-preview")) + accept = _headers.pop("Accept", "application/json") + + # Construct URL + _url = "/jobs/{name}" + path_format_arguments = { + "name": _SERIALIZER.url("name", name, "str"), + } + + _url: str = _url.format(**path_format_arguments) # type: ignore + + # Construct parameters + _params["api-version"] = _SERIALIZER.query("api_version", api_version, "str") + + # Construct headers + if content_type is not None: + _headers["Content-Type"] = _SERIALIZER.header("content_type", content_type, "str") + _headers["Accept"] = _SERIALIZER.header("accept", accept, "str") + + return HttpRequest(method="PUT", url=_url, params=_params, headers=_headers, **kwargs) + + +def build_deidentification_list_jobs_request( + *, maxpagesize: Optional[int] = None, continuation_token_parameter: Optional[str] = None, **kwargs: Any +) -> HttpRequest: + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = case_insensitive_dict(kwargs.pop("params", {}) or {}) + + api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2024-07-12-preview")) + accept = _headers.pop("Accept", "application/json") + + # Construct URL + _url = "/jobs" + + # Construct parameters + _params["api-version"] = _SERIALIZER.query("api_version", api_version, "str") + if maxpagesize is not None: + _params["maxpagesize"] = _SERIALIZER.query("maxpagesize", maxpagesize, "int") + if continuation_token_parameter is not None: + _params["continuationToken"] = _SERIALIZER.query( + "continuation_token_parameter", continuation_token_parameter, "str" + ) + + # Construct headers + _headers["Accept"] = _SERIALIZER.header("accept", accept, "str") + + return HttpRequest(method="GET", url=_url, params=_params, headers=_headers, **kwargs) + + +def build_deidentification_list_job_documents_request( # pylint: disable=name-too-long + name: str, *, maxpagesize: Optional[int] = None, continuation_token_parameter: Optional[str] = None, **kwargs: Any +) -> HttpRequest: + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = case_insensitive_dict(kwargs.pop("params", {}) or {}) + + api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2024-07-12-preview")) + accept = _headers.pop("Accept", "application/json") + + # Construct URL + _url = "/jobs/{name}/documents" + path_format_arguments = { + "name": _SERIALIZER.url("name", name, "str"), + } + + _url: str = _url.format(**path_format_arguments) # type: ignore + + # Construct parameters + _params["api-version"] = _SERIALIZER.query("api_version", api_version, "str") + if maxpagesize is not None: + _params["maxpagesize"] = _SERIALIZER.query("maxpagesize", maxpagesize, "int") + if continuation_token_parameter is not None: + _params["continuationToken"] = _SERIALIZER.query( + "continuation_token_parameter", continuation_token_parameter, "str" + ) + + # Construct headers + _headers["Accept"] = _SERIALIZER.header("accept", accept, "str") + + return HttpRequest(method="GET", url=_url, params=_params, headers=_headers, **kwargs) + + +def build_deidentification_cancel_job_request(name: str, **kwargs: Any) -> HttpRequest: # pylint: disable=name-too-long + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = case_insensitive_dict(kwargs.pop("params", {}) or {}) + + api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2024-07-12-preview")) + accept = _headers.pop("Accept", "application/json") + + # Construct URL + _url = "/jobs/{name}:cancel" + path_format_arguments = { + "name": _SERIALIZER.url("name", name, "str"), + } + + _url: str = _url.format(**path_format_arguments) # type: ignore + + # Construct parameters + _params["api-version"] = _SERIALIZER.query("api_version", api_version, "str") + + # Construct headers + _headers["Accept"] = _SERIALIZER.header("accept", accept, "str") + + return HttpRequest(method="POST", url=_url, params=_params, headers=_headers, **kwargs) + + +def build_deidentification_delete_job_request(name: str, **kwargs: Any) -> HttpRequest: # pylint: disable=name-too-long + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = case_insensitive_dict(kwargs.pop("params", {}) or {}) + + api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2024-07-12-preview")) + accept = _headers.pop("Accept", "application/json") + + # Construct URL + _url = "/jobs/{name}" + path_format_arguments = { + "name": _SERIALIZER.url("name", name, "str"), + } + + _url: str = _url.format(**path_format_arguments) # type: ignore + + # Construct parameters + _params["api-version"] = _SERIALIZER.query("api_version", api_version, "str") + + # Construct headers + _headers["Accept"] = _SERIALIZER.header("accept", accept, "str") + + return HttpRequest(method="DELETE", url=_url, params=_params, headers=_headers, **kwargs) + + +def build_deidentification_deidentify_request(**kwargs: Any) -> HttpRequest: # pylint: disable=name-too-long + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = case_insensitive_dict(kwargs.pop("params", {}) or {}) + + content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("Content-Type", None)) + api_version: str = kwargs.pop("api_version", _params.pop("api-version", "2024-07-12-preview")) + accept = _headers.pop("Accept", "application/json") + + # Construct URL + _url = "/deid" + + # Construct parameters + _params["api-version"] = _SERIALIZER.query("api_version", api_version, "str") + + # Construct headers + if content_type is not None: + _headers["Content-Type"] = _SERIALIZER.header("content_type", content_type, "str") + _headers["Accept"] = _SERIALIZER.header("accept", accept, "str") + + return HttpRequest(method="POST", url=_url, params=_params, headers=_headers, **kwargs) + + +class DeidentificationClientOperationsMixin(DeidentificationClientMixinABC): + + @distributed_trace + def get_job(self, name: str, **kwargs: Any) -> _models.DeidentificationJob: + """Get a de-identification job. + + Resource read operation template. + + :param name: The name of a job. Required. + :type name: str + :return: DeidentificationJob. The DeidentificationJob is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationJob + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + _headers = kwargs.pop("headers", {}) or {} + _params = kwargs.pop("params", {}) or {} + + cls: ClsType[_models.DeidentificationJob] = kwargs.pop("cls", None) + + _request = build_deidentification_get_job_request( + name=name, + api_version=self._config.api_version, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + _stream = kwargs.pop("stream", False) + pipeline_response: PipelineResponse = self._client._pipeline.run( # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + + response = pipeline_response.http_response + + if response.status_code not in [200]: + if _stream: + response.read() # Load the body in memory and close the socket + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + response_headers = {} + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + + if _stream: + deserialized = response.iter_bytes() + else: + deserialized = _deserialize(_models.DeidentificationJob, response.json()) + + if cls: + return cls(pipeline_response, deserialized, response_headers) # type: ignore + + return deserialized # type: ignore + + def _create_job_initial( + self, name: str, resource: Union[_models.DeidentificationJob, JSON, IO[bytes]], **kwargs: Any + ) -> Iterator[bytes]: + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = kwargs.pop("params", {}) or {} + + content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("Content-Type", None)) + cls: ClsType[Iterator[bytes]] = kwargs.pop("cls", None) + + content_type = content_type or "application/json" + _content = None + if isinstance(resource, (IOBase, bytes)): + _content = resource + else: + _content = json.dumps(resource, cls=SdkJSONEncoder, exclude_readonly=True) # type: ignore + + _request = build_deidentification_create_job_request( + name=name, + content_type=content_type, + api_version=self._config.api_version, + content=_content, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + _stream = True + pipeline_response: PipelineResponse = self._client._pipeline.run( # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + + response = pipeline_response.http_response + + if response.status_code not in [200, 201]: + response.read() # Load the body in memory and close the socket + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + response_headers = {} + if response.status_code == 200: + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + response_headers["Operation-Location"] = self._deserialize( + "str", response.headers.get("Operation-Location") + ) + + deserialized = response.iter_bytes() + + if response.status_code == 201: + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + response_headers["Operation-Location"] = self._deserialize( + "str", response.headers.get("Operation-Location") + ) + + deserialized = response.iter_bytes() + + if cls: + return cls(pipeline_response, deserialized, response_headers) # type: ignore + + return deserialized # type: ignore + + @overload + def begin_create_job( + self, name: str, resource: _models.DeidentificationJob, *, content_type: str = "application/json", **kwargs: Any + ) -> LROPoller[_models.DeidentificationJob]: + """Create a de-identification job. + + Long-running resource create or replace operation template. + + :param name: The name of a job. Required. + :type name: str + :param resource: The resource instance. Required. + :type resource: ~azure.health.deidentification.models.DeidentificationJob + :keyword content_type: Body Parameter content-type. Content type parameter for JSON body. + Default value is "application/json". + :paramtype content_type: str + :return: An instance of LROPoller that returns DeidentificationJob. The DeidentificationJob is + compatible with MutableMapping + :rtype: + ~azure.core.polling.LROPoller[~azure.health.deidentification.models.DeidentificationJob] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # JSON input template you can fill out and use as your body input. + resource = { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + + # response body for status code(s): 201, 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + + @overload + def begin_create_job( + self, name: str, resource: JSON, *, content_type: str = "application/json", **kwargs: Any + ) -> LROPoller[_models.DeidentificationJob]: + """Create a de-identification job. + + Long-running resource create or replace operation template. + + :param name: The name of a job. Required. + :type name: str + :param resource: The resource instance. Required. + :type resource: JSON + :keyword content_type: Body Parameter content-type. Content type parameter for JSON body. + Default value is "application/json". + :paramtype content_type: str + :return: An instance of LROPoller that returns DeidentificationJob. The DeidentificationJob is + compatible with MutableMapping + :rtype: + ~azure.core.polling.LROPoller[~azure.health.deidentification.models.DeidentificationJob] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 201, 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + + @overload + def begin_create_job( + self, name: str, resource: IO[bytes], *, content_type: str = "application/json", **kwargs: Any + ) -> LROPoller[_models.DeidentificationJob]: + """Create a de-identification job. + + Long-running resource create or replace operation template. + + :param name: The name of a job. Required. + :type name: str + :param resource: The resource instance. Required. + :type resource: IO[bytes] + :keyword content_type: Body Parameter content-type. Content type parameter for binary body. + Default value is "application/json". + :paramtype content_type: str + :return: An instance of LROPoller that returns DeidentificationJob. The DeidentificationJob is + compatible with MutableMapping + :rtype: + ~azure.core.polling.LROPoller[~azure.health.deidentification.models.DeidentificationJob] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 201, 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + + @distributed_trace + def begin_create_job( + self, name: str, resource: Union[_models.DeidentificationJob, JSON, IO[bytes]], **kwargs: Any + ) -> LROPoller[_models.DeidentificationJob]: + """Create a de-identification job. + + Long-running resource create or replace operation template. + + :param name: The name of a job. Required. + :type name: str + :param resource: The resource instance. Is one of the following types: DeidentificationJob, + JSON, IO[bytes] Required. + :type resource: ~azure.health.deidentification.models.DeidentificationJob or JSON or IO[bytes] + :return: An instance of LROPoller that returns DeidentificationJob. The DeidentificationJob is + compatible with MutableMapping + :rtype: + ~azure.core.polling.LROPoller[~azure.health.deidentification.models.DeidentificationJob] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # JSON input template you can fill out and use as your body input. + resource = { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + + # response body for status code(s): 201, 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = kwargs.pop("params", {}) or {} + + content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("Content-Type", None)) + cls: ClsType[_models.DeidentificationJob] = kwargs.pop("cls", None) + polling: Union[bool, PollingMethod] = kwargs.pop("polling", True) + lro_delay = kwargs.pop("polling_interval", self._config.polling_interval) + cont_token: Optional[str] = kwargs.pop("continuation_token", None) + if cont_token is None: + raw_result = self._create_job_initial( + name=name, + resource=resource, + content_type=content_type, + cls=lambda x, y, z: x, + headers=_headers, + params=_params, + **kwargs + ) + raw_result.http_response.read() # type: ignore + kwargs.pop("error_map", None) + + def get_long_running_output(pipeline_response): + response_headers = {} + response = pipeline_response.http_response + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + response_headers["Operation-Location"] = self._deserialize( + "str", response.headers.get("Operation-Location") + ) + + deserialized = _deserialize(_models.DeidentificationJob, response.json()) + if cls: + return cls(pipeline_response, deserialized, response_headers) # type: ignore + return deserialized + + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + + if polling is True: + polling_method: PollingMethod = cast( + PollingMethod, LROBasePolling(lro_delay, path_format_arguments=path_format_arguments, **kwargs) + ) + elif polling is False: + polling_method = cast(PollingMethod, NoPolling()) + else: + polling_method = polling + if cont_token: + return LROPoller[_models.DeidentificationJob].from_continuation_token( + polling_method=polling_method, + continuation_token=cont_token, + client=self._client, + deserialization_callback=get_long_running_output, + ) + return LROPoller[_models.DeidentificationJob]( + self._client, raw_result, get_long_running_output, polling_method # type: ignore + ) + + @distributed_trace + def list_jobs( + self, *, continuation_token_parameter: Optional[str] = None, **kwargs: Any + ) -> Iterable["_models.DeidentificationJob"]: + """List de-identification jobs. + + Resource list operation template. + + :keyword continuation_token_parameter: Token to continue a previous query. Default value is + None. + :paramtype continuation_token_parameter: str + :return: An iterator like instance of DeidentificationJob + :rtype: ~azure.core.paging.ItemPaged[~azure.health.deidentification.models.DeidentificationJob] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + _headers = kwargs.pop("headers", {}) or {} + _params = kwargs.pop("params", {}) or {} + + maxpagesize = kwargs.pop("maxpagesize", None) + cls: ClsType[List[_models.DeidentificationJob]] = kwargs.pop("cls", None) + + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + def prepare_request(next_link=None): + if not next_link: + + _request = build_deidentification_list_jobs_request( + maxpagesize=maxpagesize, + continuation_token_parameter=continuation_token_parameter, + api_version=self._config.api_version, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + else: + # make call to next link with the client's api-version + _parsed_next_link = urllib.parse.urlparse(next_link) + _next_request_params = case_insensitive_dict( + { + key: [urllib.parse.quote(v) for v in value] + for key, value in urllib.parse.parse_qs(_parsed_next_link.query).items() + } + ) + _next_request_params["api-version"] = self._config.api_version + _request = HttpRequest( + "GET", urllib.parse.urljoin(next_link, _parsed_next_link.path), params=_next_request_params + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + return _request + + def extract_data(pipeline_response): + deserialized = pipeline_response.http_response.json() + list_of_elem = _deserialize(List[_models.DeidentificationJob], deserialized["value"]) + if cls: + list_of_elem = cls(list_of_elem) # type: ignore + return deserialized.get("nextLink") or None, iter(list_of_elem) + + def get_next(next_link=None): + _request = prepare_request(next_link) + + _stream = False + pipeline_response: PipelineResponse = self._client._pipeline.run( # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + response = pipeline_response.http_response + + if response.status_code not in [200]: + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + return pipeline_response + + return ItemPaged(get_next, extract_data) + + @distributed_trace + def list_job_documents( + self, name: str, *, continuation_token_parameter: Optional[str] = None, **kwargs: Any + ) -> Iterable["_models.DocumentDetails"]: + """List processed documents within a job. + + Resource list operation template. + + :param name: The name of a job. Required. + :type name: str + :keyword continuation_token_parameter: Token to continue a previous query. Default value is + None. + :paramtype continuation_token_parameter: str + :return: An iterator like instance of DocumentDetails + :rtype: ~azure.core.paging.ItemPaged[~azure.health.deidentification.models.DocumentDetails] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "id": "str", + "input": { + "etag": "str", + "path": "str" + }, + "status": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "output": { + "etag": "str", + "path": "str" + } + } + """ + _headers = kwargs.pop("headers", {}) or {} + _params = kwargs.pop("params", {}) or {} + + maxpagesize = kwargs.pop("maxpagesize", None) + cls: ClsType[List[_models.DocumentDetails]] = kwargs.pop("cls", None) + + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + def prepare_request(next_link=None): + if not next_link: + + _request = build_deidentification_list_job_documents_request( + name=name, + maxpagesize=maxpagesize, + continuation_token_parameter=continuation_token_parameter, + api_version=self._config.api_version, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + else: + # make call to next link with the client's api-version + _parsed_next_link = urllib.parse.urlparse(next_link) + _next_request_params = case_insensitive_dict( + { + key: [urllib.parse.quote(v) for v in value] + for key, value in urllib.parse.parse_qs(_parsed_next_link.query).items() + } + ) + _next_request_params["api-version"] = self._config.api_version + _request = HttpRequest( + "GET", urllib.parse.urljoin(next_link, _parsed_next_link.path), params=_next_request_params + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + return _request + + def extract_data(pipeline_response): + deserialized = pipeline_response.http_response.json() + list_of_elem = _deserialize(List[_models.DocumentDetails], deserialized["value"]) + if cls: + list_of_elem = cls(list_of_elem) # type: ignore + return deserialized.get("nextLink") or None, iter(list_of_elem) + + def get_next(next_link=None): + _request = prepare_request(next_link) + + _stream = False + pipeline_response: PipelineResponse = self._client._pipeline.run( # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + response = pipeline_response.http_response + + if response.status_code not in [200]: + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + return pipeline_response + + return ItemPaged(get_next, extract_data) + + @distributed_trace + def cancel_job(self, name: str, **kwargs: Any) -> _models.DeidentificationJob: + """Cancel a de-identification job. + + Cancels a job that is in progress. + + The job will be marked as canceled and the service will stop processing the job. The service + will not delete any documents that have already been processed. + + If the job is already complete, this will have no effect. + + :param name: The name of a job. Required. + :type name: str + :return: DeidentificationJob. The DeidentificationJob is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationJob + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + _headers = kwargs.pop("headers", {}) or {} + _params = kwargs.pop("params", {}) or {} + + cls: ClsType[_models.DeidentificationJob] = kwargs.pop("cls", None) + + _request = build_deidentification_cancel_job_request( + name=name, + api_version=self._config.api_version, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + _stream = kwargs.pop("stream", False) + pipeline_response: PipelineResponse = self._client._pipeline.run( # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + + response = pipeline_response.http_response + + if response.status_code not in [200]: + if _stream: + response.read() # Load the body in memory and close the socket + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + response_headers = {} + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + + if _stream: + deserialized = response.iter_bytes() + else: + deserialized = _deserialize(_models.DeidentificationJob, response.json()) + + if cls: + return cls(pipeline_response, deserialized, response_headers) # type: ignore + + return deserialized # type: ignore + + @distributed_trace + def delete_job(self, name: str, **kwargs: Any) -> None: # pylint: disable=inconsistent-return-statements + """Delete a de-identification job. + + Removes the record of the job from the service. Does not delete any documents. + + :param name: The name of a job. Required. + :type name: str + :return: None + :rtype: None + :raises ~azure.core.exceptions.HttpResponseError: + """ + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + _headers = kwargs.pop("headers", {}) or {} + _params = kwargs.pop("params", {}) or {} + + cls: ClsType[None] = kwargs.pop("cls", None) + + _request = build_deidentification_delete_job_request( + name=name, + api_version=self._config.api_version, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + _stream = False + pipeline_response: PipelineResponse = self._client._pipeline.run( # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + + response = pipeline_response.http_response + + if response.status_code not in [204]: + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + response_headers = {} + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + + if cls: + return cls(pipeline_response, None, response_headers) # type: ignore + + @overload + def deidentify( + self, body: _models.DeidentificationContent, *, content_type: str = "application/json", **kwargs: Any + ) -> _models.DeidentificationResult: + """De-identify text. + + A remote procedure call (RPC) operation. + + :param body: Request body for de-identification operation. Required. + :type body: ~azure.health.deidentification.models.DeidentificationContent + :keyword content_type: Body Parameter content-type. Content type parameter for JSON body. + Default value is "application/json". + :paramtype content_type: str + :return: DeidentificationResult. The DeidentificationResult is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationResult + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # JSON input template you can fill out and use as your body input. + body = { + "inputText": "str", + "dataType": "str", + "operation": "str", + "redactionFormat": "str" + } + + # response body for status code(s): 200 + response == { + "outputText": "str", + "taggerResult": { + "entities": [ + { + "category": "str", + "length": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "offset": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "confidenceScore": 0.0, + "text": "str" + } + ], + "etag": "str", + "path": "str" + } + } + """ + + @overload + def deidentify( + self, body: JSON, *, content_type: str = "application/json", **kwargs: Any + ) -> _models.DeidentificationResult: + """De-identify text. + + A remote procedure call (RPC) operation. + + :param body: Request body for de-identification operation. Required. + :type body: JSON + :keyword content_type: Body Parameter content-type. Content type parameter for JSON body. + Default value is "application/json". + :paramtype content_type: str + :return: DeidentificationResult. The DeidentificationResult is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationResult + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "outputText": "str", + "taggerResult": { + "entities": [ + { + "category": "str", + "length": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "offset": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "confidenceScore": 0.0, + "text": "str" + } + ], + "etag": "str", + "path": "str" + } + } + """ + + @overload + def deidentify( + self, body: IO[bytes], *, content_type: str = "application/json", **kwargs: Any + ) -> _models.DeidentificationResult: + """De-identify text. + + A remote procedure call (RPC) operation. + + :param body: Request body for de-identification operation. Required. + :type body: IO[bytes] + :keyword content_type: Body Parameter content-type. Content type parameter for binary body. + Default value is "application/json". + :paramtype content_type: str + :return: DeidentificationResult. The DeidentificationResult is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationResult + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "outputText": "str", + "taggerResult": { + "entities": [ + { + "category": "str", + "length": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "offset": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "confidenceScore": 0.0, + "text": "str" + } + ], + "etag": "str", + "path": "str" + } + } + """ + + @distributed_trace + def deidentify( + self, body: Union[_models.DeidentificationContent, JSON, IO[bytes]], **kwargs: Any + ) -> _models.DeidentificationResult: + """De-identify text. + + A remote procedure call (RPC) operation. + + :param body: Request body for de-identification operation. Is one of the following types: + DeidentificationContent, JSON, IO[bytes] Required. + :type body: ~azure.health.deidentification.models.DeidentificationContent or JSON or IO[bytes] + :return: DeidentificationResult. The DeidentificationResult is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationResult + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # JSON input template you can fill out and use as your body input. + body = { + "inputText": "str", + "dataType": "str", + "operation": "str", + "redactionFormat": "str" + } + + # response body for status code(s): 200 + response == { + "outputText": "str", + "taggerResult": { + "entities": [ + { + "category": "str", + "length": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "offset": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "confidenceScore": 0.0, + "text": "str" + } + ], + "etag": "str", + "path": "str" + } + } + """ + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = kwargs.pop("params", {}) or {} + + content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("Content-Type", None)) + cls: ClsType[_models.DeidentificationResult] = kwargs.pop("cls", None) + + content_type = content_type or "application/json" + _content = None + if isinstance(body, (IOBase, bytes)): + _content = body + else: + _content = json.dumps(body, cls=SdkJSONEncoder, exclude_readonly=True) # type: ignore + + _request = build_deidentification_deidentify_request( + content_type=content_type, + api_version=self._config.api_version, + content=_content, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + _stream = kwargs.pop("stream", False) + pipeline_response: PipelineResponse = self._client._pipeline.run( # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + + response = pipeline_response.http_response + + if response.status_code not in [200]: + if _stream: + response.read() # Load the body in memory and close the socket + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + if _stream: + deserialized = response.iter_bytes() + else: + deserialized = _deserialize(_models.DeidentificationResult, response.json()) + + if cls: + return cls(pipeline_response, deserialized, {}) # type: ignore + + return deserialized # type: ignore diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_operations/_patch.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_operations/_patch.py new file mode 100644 index 000000000000..f7dd32510333 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_operations/_patch.py @@ -0,0 +1,20 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ +"""Customize generated code here. + +Follow our quickstart for examples: https://aka.ms/azsdk/python/dpcodegen/python/customize +""" +from typing import List + +__all__: List[str] = [] # Add all objects you want publicly available to users at this package level + + +def patch_sdk(): + """Do not remove from this file. + + `patch_sdk` is a last resort escape hatch that allows you to do customizations + you can't accomplish using the techniques described in + https://aka.ms/azsdk/python/dpcodegen/python/customize + """ diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_patch.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_patch.py new file mode 100644 index 000000000000..f7dd32510333 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_patch.py @@ -0,0 +1,20 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ +"""Customize generated code here. + +Follow our quickstart for examples: https://aka.ms/azsdk/python/dpcodegen/python/customize +""" +from typing import List + +__all__: List[str] = [] # Add all objects you want publicly available to users at this package level + + +def patch_sdk(): + """Do not remove from this file. + + `patch_sdk` is a last resort escape hatch that allows you to do customizations + you can't accomplish using the techniques described in + https://aka.ms/azsdk/python/dpcodegen/python/customize + """ diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_serialization.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_serialization.py new file mode 100644 index 000000000000..8139854b97bb --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_serialization.py @@ -0,0 +1,2000 @@ +# -------------------------------------------------------------------------- +# +# Copyright (c) Microsoft Corporation. All rights reserved. +# +# The MIT License (MIT) +# +# Permission is hereby granted, free of charge, to any person obtaining a copy +# of this software and associated documentation files (the ""Software""), to +# deal in the Software without restriction, including without limitation the +# rights to use, copy, modify, merge, publish, distribute, sublicense, and/or +# sell copies of the Software, and to permit persons to whom the Software is +# furnished to do so, subject to the following conditions: +# +# The above copyright notice and this permission notice shall be included in +# all copies or substantial portions of the Software. +# +# THE SOFTWARE IS PROVIDED *AS IS*, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS +# IN THE SOFTWARE. +# +# -------------------------------------------------------------------------- + +# pylint: skip-file +# pyright: reportUnnecessaryTypeIgnoreComment=false + +from base64 import b64decode, b64encode +import calendar +import datetime +import decimal +import email +from enum import Enum +import json +import logging +import re +import sys +import codecs +from typing import ( + Dict, + Any, + cast, + Optional, + Union, + AnyStr, + IO, + Mapping, + Callable, + TypeVar, + MutableMapping, + Type, + List, + Mapping, +) + +try: + from urllib import quote # type: ignore +except ImportError: + from urllib.parse import quote +import xml.etree.ElementTree as ET + +import isodate # type: ignore + +from azure.core.exceptions import DeserializationError, SerializationError +from azure.core.serialization import NULL as CoreNull + +_BOM = codecs.BOM_UTF8.decode(encoding="utf-8") + +ModelType = TypeVar("ModelType", bound="Model") +JSON = MutableMapping[str, Any] + + +class RawDeserializer: + + # Accept "text" because we're open minded people... + JSON_REGEXP = re.compile(r"^(application|text)/([a-z+.]+\+)?json$") + + # Name used in context + CONTEXT_NAME = "deserialized_data" + + @classmethod + def deserialize_from_text(cls, data: Optional[Union[AnyStr, IO]], content_type: Optional[str] = None) -> Any: + """Decode data according to content-type. + + Accept a stream of data as well, but will be load at once in memory for now. + + If no content-type, will return the string version (not bytes, not stream) + + :param data: Input, could be bytes or stream (will be decoded with UTF8) or text + :type data: str or bytes or IO + :param str content_type: The content type. + """ + if hasattr(data, "read"): + # Assume a stream + data = cast(IO, data).read() + + if isinstance(data, bytes): + data_as_str = data.decode(encoding="utf-8-sig") + else: + # Explain to mypy the correct type. + data_as_str = cast(str, data) + + # Remove Byte Order Mark if present in string + data_as_str = data_as_str.lstrip(_BOM) + + if content_type is None: + return data + + if cls.JSON_REGEXP.match(content_type): + try: + return json.loads(data_as_str) + except ValueError as err: + raise DeserializationError("JSON is invalid: {}".format(err), err) + elif "xml" in (content_type or []): + try: + + try: + if isinstance(data, unicode): # type: ignore + # If I'm Python 2.7 and unicode XML will scream if I try a "fromstring" on unicode string + data_as_str = data_as_str.encode(encoding="utf-8") # type: ignore + except NameError: + pass + + return ET.fromstring(data_as_str) # nosec + except ET.ParseError as err: + # It might be because the server has an issue, and returned JSON with + # content-type XML.... + # So let's try a JSON load, and if it's still broken + # let's flow the initial exception + def _json_attemp(data): + try: + return True, json.loads(data) + except ValueError: + return False, None # Don't care about this one + + success, json_result = _json_attemp(data) + if success: + return json_result + # If i'm here, it's not JSON, it's not XML, let's scream + # and raise the last context in this block (the XML exception) + # The function hack is because Py2.7 messes up with exception + # context otherwise. + _LOGGER.critical("Wasn't XML not JSON, failing") + raise DeserializationError("XML is invalid") from err + elif content_type.startswith("text/"): + return data_as_str + raise DeserializationError("Cannot deserialize content-type: {}".format(content_type)) + + @classmethod + def deserialize_from_http_generics(cls, body_bytes: Optional[Union[AnyStr, IO]], headers: Mapping) -> Any: + """Deserialize from HTTP response. + + Use bytes and headers to NOT use any requests/aiohttp or whatever + specific implementation. + Headers will tested for "content-type" + """ + # Try to use content-type from headers if available + content_type = None + if "content-type" in headers: + content_type = headers["content-type"].split(";")[0].strip().lower() + # Ouch, this server did not declare what it sent... + # Let's guess it's JSON... + # Also, since Autorest was considering that an empty body was a valid JSON, + # need that test as well.... + else: + content_type = "application/json" + + if body_bytes: + return cls.deserialize_from_text(body_bytes, content_type) + return None + + +_LOGGER = logging.getLogger(__name__) + +try: + _long_type = long # type: ignore +except NameError: + _long_type = int + + +class UTC(datetime.tzinfo): + """Time Zone info for handling UTC""" + + def utcoffset(self, dt): + """UTF offset for UTC is 0.""" + return datetime.timedelta(0) + + def tzname(self, dt): + """Timestamp representation.""" + return "Z" + + def dst(self, dt): + """No daylight saving for UTC.""" + return datetime.timedelta(hours=1) + + +try: + from datetime import timezone as _FixedOffset # type: ignore +except ImportError: # Python 2.7 + + class _FixedOffset(datetime.tzinfo): # type: ignore + """Fixed offset in minutes east from UTC. + Copy/pasted from Python doc + :param datetime.timedelta offset: offset in timedelta format + """ + + def __init__(self, offset): + self.__offset = offset + + def utcoffset(self, dt): + return self.__offset + + def tzname(self, dt): + return str(self.__offset.total_seconds() / 3600) + + def __repr__(self): + return "".format(self.tzname(None)) + + def dst(self, dt): + return datetime.timedelta(0) + + def __getinitargs__(self): + return (self.__offset,) + + +try: + from datetime import timezone + + TZ_UTC = timezone.utc +except ImportError: + TZ_UTC = UTC() # type: ignore + +_FLATTEN = re.compile(r"(? None: + self.additional_properties: Optional[Dict[str, Any]] = {} + for k in kwargs: + if k not in self._attribute_map: + _LOGGER.warning("%s is not a known attribute of class %s and will be ignored", k, self.__class__) + elif k in self._validation and self._validation[k].get("readonly", False): + _LOGGER.warning("Readonly attribute %s will be ignored in class %s", k, self.__class__) + else: + setattr(self, k, kwargs[k]) + + def __eq__(self, other: Any) -> bool: + """Compare objects by comparing all attributes.""" + if isinstance(other, self.__class__): + return self.__dict__ == other.__dict__ + return False + + def __ne__(self, other: Any) -> bool: + """Compare objects by comparing all attributes.""" + return not self.__eq__(other) + + def __str__(self) -> str: + return str(self.__dict__) + + @classmethod + def enable_additional_properties_sending(cls) -> None: + cls._attribute_map["additional_properties"] = {"key": "", "type": "{object}"} + + @classmethod + def is_xml_model(cls) -> bool: + try: + cls._xml_map # type: ignore + except AttributeError: + return False + return True + + @classmethod + def _create_xml_node(cls): + """Create XML node.""" + try: + xml_map = cls._xml_map # type: ignore + except AttributeError: + xml_map = {} + + return _create_xml_node(xml_map.get("name", cls.__name__), xml_map.get("prefix", None), xml_map.get("ns", None)) + + def serialize(self, keep_readonly: bool = False, **kwargs: Any) -> JSON: + """Return the JSON that would be sent to server from this model. + + This is an alias to `as_dict(full_restapi_key_transformer, keep_readonly=False)`. + + If you want XML serialization, you can pass the kwargs is_xml=True. + + :param bool keep_readonly: If you want to serialize the readonly attributes + :returns: A dict JSON compatible object + :rtype: dict + """ + serializer = Serializer(self._infer_class_models()) + return serializer._serialize(self, keep_readonly=keep_readonly, **kwargs) # type: ignore + + def as_dict( + self, + keep_readonly: bool = True, + key_transformer: Callable[[str, Dict[str, Any], Any], Any] = attribute_transformer, + **kwargs: Any + ) -> JSON: + """Return a dict that can be serialized using json.dump. + + Advanced usage might optionally use a callback as parameter: + + .. code::python + + def my_key_transformer(key, attr_desc, value): + return key + + Key is the attribute name used in Python. Attr_desc + is a dict of metadata. Currently contains 'type' with the + msrest type and 'key' with the RestAPI encoded key. + Value is the current value in this object. + + The string returned will be used to serialize the key. + If the return type is a list, this is considered hierarchical + result dict. + + See the three examples in this file: + + - attribute_transformer + - full_restapi_key_transformer + - last_restapi_key_transformer + + If you want XML serialization, you can pass the kwargs is_xml=True. + + :param function key_transformer: A key transformer function. + :returns: A dict JSON compatible object + :rtype: dict + """ + serializer = Serializer(self._infer_class_models()) + return serializer._serialize(self, key_transformer=key_transformer, keep_readonly=keep_readonly, **kwargs) # type: ignore + + @classmethod + def _infer_class_models(cls): + try: + str_models = cls.__module__.rsplit(".", 1)[0] + models = sys.modules[str_models] + client_models = {k: v for k, v in models.__dict__.items() if isinstance(v, type)} + if cls.__name__ not in client_models: + raise ValueError("Not Autorest generated code") + except Exception: + # Assume it's not Autorest generated (tests?). Add ourselves as dependencies. + client_models = {cls.__name__: cls} + return client_models + + @classmethod + def deserialize(cls: Type[ModelType], data: Any, content_type: Optional[str] = None) -> ModelType: + """Parse a str using the RestAPI syntax and return a model. + + :param str data: A str using RestAPI structure. JSON by default. + :param str content_type: JSON by default, set application/xml if XML. + :returns: An instance of this model + :raises: DeserializationError if something went wrong + """ + deserializer = Deserializer(cls._infer_class_models()) + return deserializer(cls.__name__, data, content_type=content_type) # type: ignore + + @classmethod + def from_dict( + cls: Type[ModelType], + data: Any, + key_extractors: Optional[Callable[[str, Dict[str, Any], Any], Any]] = None, + content_type: Optional[str] = None, + ) -> ModelType: + """Parse a dict using given key extractor return a model. + + By default consider key + extractors (rest_key_case_insensitive_extractor, attribute_key_case_insensitive_extractor + and last_rest_key_case_insensitive_extractor) + + :param dict data: A dict using RestAPI structure + :param str content_type: JSON by default, set application/xml if XML. + :returns: An instance of this model + :raises: DeserializationError if something went wrong + """ + deserializer = Deserializer(cls._infer_class_models()) + deserializer.key_extractors = ( # type: ignore + [ # type: ignore + attribute_key_case_insensitive_extractor, + rest_key_case_insensitive_extractor, + last_rest_key_case_insensitive_extractor, + ] + if key_extractors is None + else key_extractors + ) + return deserializer(cls.__name__, data, content_type=content_type) # type: ignore + + @classmethod + def _flatten_subtype(cls, key, objects): + if "_subtype_map" not in cls.__dict__: + return {} + result = dict(cls._subtype_map[key]) + for valuetype in cls._subtype_map[key].values(): + result.update(objects[valuetype]._flatten_subtype(key, objects)) + return result + + @classmethod + def _classify(cls, response, objects): + """Check the class _subtype_map for any child classes. + We want to ignore any inherited _subtype_maps. + Remove the polymorphic key from the initial data. + """ + for subtype_key in cls.__dict__.get("_subtype_map", {}).keys(): + subtype_value = None + + if not isinstance(response, ET.Element): + rest_api_response_key = cls._get_rest_key_parts(subtype_key)[-1] + subtype_value = response.pop(rest_api_response_key, None) or response.pop(subtype_key, None) + else: + subtype_value = xml_key_extractor(subtype_key, cls._attribute_map[subtype_key], response) + if subtype_value: + # Try to match base class. Can be class name only + # (bug to fix in Autorest to support x-ms-discriminator-name) + if cls.__name__ == subtype_value: + return cls + flatten_mapping_type = cls._flatten_subtype(subtype_key, objects) + try: + return objects[flatten_mapping_type[subtype_value]] # type: ignore + except KeyError: + _LOGGER.warning( + "Subtype value %s has no mapping, use base class %s.", + subtype_value, + cls.__name__, + ) + break + else: + _LOGGER.warning("Discriminator %s is absent or null, use base class %s.", subtype_key, cls.__name__) + break + return cls + + @classmethod + def _get_rest_key_parts(cls, attr_key): + """Get the RestAPI key of this attr, split it and decode part + :param str attr_key: Attribute key must be in attribute_map. + :returns: A list of RestAPI part + :rtype: list + """ + rest_split_key = _FLATTEN.split(cls._attribute_map[attr_key]["key"]) + return [_decode_attribute_map_key(key_part) for key_part in rest_split_key] + + +def _decode_attribute_map_key(key): + """This decode a key in an _attribute_map to the actual key we want to look at + inside the received data. + + :param str key: A key string from the generated code + """ + return key.replace("\\.", ".") + + +class Serializer(object): + """Request object model serializer.""" + + basic_types = {str: "str", int: "int", bool: "bool", float: "float"} + + _xml_basic_types_serializers = {"bool": lambda x: str(x).lower()} + days = {0: "Mon", 1: "Tue", 2: "Wed", 3: "Thu", 4: "Fri", 5: "Sat", 6: "Sun"} + months = { + 1: "Jan", + 2: "Feb", + 3: "Mar", + 4: "Apr", + 5: "May", + 6: "Jun", + 7: "Jul", + 8: "Aug", + 9: "Sep", + 10: "Oct", + 11: "Nov", + 12: "Dec", + } + validation = { + "min_length": lambda x, y: len(x) < y, + "max_length": lambda x, y: len(x) > y, + "minimum": lambda x, y: x < y, + "maximum": lambda x, y: x > y, + "minimum_ex": lambda x, y: x <= y, + "maximum_ex": lambda x, y: x >= y, + "min_items": lambda x, y: len(x) < y, + "max_items": lambda x, y: len(x) > y, + "pattern": lambda x, y: not re.match(y, x, re.UNICODE), + "unique": lambda x, y: len(x) != len(set(x)), + "multiple": lambda x, y: x % y != 0, + } + + def __init__(self, classes: Optional[Mapping[str, type]] = None): + self.serialize_type = { + "iso-8601": Serializer.serialize_iso, + "rfc-1123": Serializer.serialize_rfc, + "unix-time": Serializer.serialize_unix, + "duration": Serializer.serialize_duration, + "date": Serializer.serialize_date, + "time": Serializer.serialize_time, + "decimal": Serializer.serialize_decimal, + "long": Serializer.serialize_long, + "bytearray": Serializer.serialize_bytearray, + "base64": Serializer.serialize_base64, + "object": self.serialize_object, + "[]": self.serialize_iter, + "{}": self.serialize_dict, + } + self.dependencies: Dict[str, type] = dict(classes) if classes else {} + self.key_transformer = full_restapi_key_transformer + self.client_side_validation = True + + def _serialize(self, target_obj, data_type=None, **kwargs): + """Serialize data into a string according to type. + + :param target_obj: The data to be serialized. + :param str data_type: The type to be serialized from. + :rtype: str, dict + :raises: SerializationError if serialization fails. + """ + key_transformer = kwargs.get("key_transformer", self.key_transformer) + keep_readonly = kwargs.get("keep_readonly", False) + if target_obj is None: + return None + + attr_name = None + class_name = target_obj.__class__.__name__ + + if data_type: + return self.serialize_data(target_obj, data_type, **kwargs) + + if not hasattr(target_obj, "_attribute_map"): + data_type = type(target_obj).__name__ + if data_type in self.basic_types.values(): + return self.serialize_data(target_obj, data_type, **kwargs) + + # Force "is_xml" kwargs if we detect a XML model + try: + is_xml_model_serialization = kwargs["is_xml"] + except KeyError: + is_xml_model_serialization = kwargs.setdefault("is_xml", target_obj.is_xml_model()) + + serialized = {} + if is_xml_model_serialization: + serialized = target_obj._create_xml_node() + try: + attributes = target_obj._attribute_map + for attr, attr_desc in attributes.items(): + attr_name = attr + if not keep_readonly and target_obj._validation.get(attr_name, {}).get("readonly", False): + continue + + if attr_name == "additional_properties" and attr_desc["key"] == "": + if target_obj.additional_properties is not None: + serialized.update(target_obj.additional_properties) + continue + try: + + orig_attr = getattr(target_obj, attr) + if is_xml_model_serialization: + pass # Don't provide "transformer" for XML for now. Keep "orig_attr" + else: # JSON + keys, orig_attr = key_transformer(attr, attr_desc.copy(), orig_attr) + keys = keys if isinstance(keys, list) else [keys] + + kwargs["serialization_ctxt"] = attr_desc + new_attr = self.serialize_data(orig_attr, attr_desc["type"], **kwargs) + + if is_xml_model_serialization: + xml_desc = attr_desc.get("xml", {}) + xml_name = xml_desc.get("name", attr_desc["key"]) + xml_prefix = xml_desc.get("prefix", None) + xml_ns = xml_desc.get("ns", None) + if xml_desc.get("attr", False): + if xml_ns: + ET.register_namespace(xml_prefix, xml_ns) + xml_name = "{{{}}}{}".format(xml_ns, xml_name) + serialized.set(xml_name, new_attr) # type: ignore + continue + if xml_desc.get("text", False): + serialized.text = new_attr # type: ignore + continue + if isinstance(new_attr, list): + serialized.extend(new_attr) # type: ignore + elif isinstance(new_attr, ET.Element): + # If the down XML has no XML/Name, we MUST replace the tag with the local tag. But keeping the namespaces. + if "name" not in getattr(orig_attr, "_xml_map", {}): + splitted_tag = new_attr.tag.split("}") + if len(splitted_tag) == 2: # Namespace + new_attr.tag = "}".join([splitted_tag[0], xml_name]) + else: + new_attr.tag = xml_name + serialized.append(new_attr) # type: ignore + else: # That's a basic type + # Integrate namespace if necessary + local_node = _create_xml_node(xml_name, xml_prefix, xml_ns) + local_node.text = str(new_attr) + serialized.append(local_node) # type: ignore + else: # JSON + for k in reversed(keys): # type: ignore + new_attr = {k: new_attr} + + _new_attr = new_attr + _serialized = serialized + for k in keys: # type: ignore + if k not in _serialized: + _serialized.update(_new_attr) # type: ignore + _new_attr = _new_attr[k] # type: ignore + _serialized = _serialized[k] + except ValueError as err: + if isinstance(err, SerializationError): + raise + + except (AttributeError, KeyError, TypeError) as err: + msg = "Attribute {} in object {} cannot be serialized.\n{}".format(attr_name, class_name, str(target_obj)) + raise SerializationError(msg) from err + else: + return serialized + + def body(self, data, data_type, **kwargs): + """Serialize data intended for a request body. + + :param data: The data to be serialized. + :param str data_type: The type to be serialized from. + :rtype: dict + :raises: SerializationError if serialization fails. + :raises: ValueError if data is None + """ + + # Just in case this is a dict + internal_data_type_str = data_type.strip("[]{}") + internal_data_type = self.dependencies.get(internal_data_type_str, None) + try: + is_xml_model_serialization = kwargs["is_xml"] + except KeyError: + if internal_data_type and issubclass(internal_data_type, Model): + is_xml_model_serialization = kwargs.setdefault("is_xml", internal_data_type.is_xml_model()) + else: + is_xml_model_serialization = False + if internal_data_type and not isinstance(internal_data_type, Enum): + try: + deserializer = Deserializer(self.dependencies) + # Since it's on serialization, it's almost sure that format is not JSON REST + # We're not able to deal with additional properties for now. + deserializer.additional_properties_detection = False + if is_xml_model_serialization: + deserializer.key_extractors = [ # type: ignore + attribute_key_case_insensitive_extractor, + ] + else: + deserializer.key_extractors = [ + rest_key_case_insensitive_extractor, + attribute_key_case_insensitive_extractor, + last_rest_key_case_insensitive_extractor, + ] + data = deserializer._deserialize(data_type, data) + except DeserializationError as err: + raise SerializationError("Unable to build a model: " + str(err)) from err + + return self._serialize(data, data_type, **kwargs) + + def url(self, name, data, data_type, **kwargs): + """Serialize data intended for a URL path. + + :param data: The data to be serialized. + :param str data_type: The type to be serialized from. + :rtype: str + :raises: TypeError if serialization fails. + :raises: ValueError if data is None + """ + try: + output = self.serialize_data(data, data_type, **kwargs) + if data_type == "bool": + output = json.dumps(output) + + if kwargs.get("skip_quote") is True: + output = str(output) + output = output.replace("{", quote("{")).replace("}", quote("}")) + else: + output = quote(str(output), safe="") + except SerializationError: + raise TypeError("{} must be type {}.".format(name, data_type)) + else: + return output + + def query(self, name, data, data_type, **kwargs): + """Serialize data intended for a URL query. + + :param data: The data to be serialized. + :param str data_type: The type to be serialized from. + :keyword bool skip_quote: Whether to skip quote the serialized result. + Defaults to False. + :rtype: str, list + :raises: TypeError if serialization fails. + :raises: ValueError if data is None + """ + try: + # Treat the list aside, since we don't want to encode the div separator + if data_type.startswith("["): + internal_data_type = data_type[1:-1] + do_quote = not kwargs.get("skip_quote", False) + return self.serialize_iter(data, internal_data_type, do_quote=do_quote, **kwargs) + + # Not a list, regular serialization + output = self.serialize_data(data, data_type, **kwargs) + if data_type == "bool": + output = json.dumps(output) + if kwargs.get("skip_quote") is True: + output = str(output) + else: + output = quote(str(output), safe="") + except SerializationError: + raise TypeError("{} must be type {}.".format(name, data_type)) + else: + return str(output) + + def header(self, name, data, data_type, **kwargs): + """Serialize data intended for a request header. + + :param data: The data to be serialized. + :param str data_type: The type to be serialized from. + :rtype: str + :raises: TypeError if serialization fails. + :raises: ValueError if data is None + """ + try: + if data_type in ["[str]"]: + data = ["" if d is None else d for d in data] + + output = self.serialize_data(data, data_type, **kwargs) + if data_type == "bool": + output = json.dumps(output) + except SerializationError: + raise TypeError("{} must be type {}.".format(name, data_type)) + else: + return str(output) + + def serialize_data(self, data, data_type, **kwargs): + """Serialize generic data according to supplied data type. + + :param data: The data to be serialized. + :param str data_type: The type to be serialized from. + :param bool required: Whether it's essential that the data not be + empty or None + :raises: AttributeError if required data is None. + :raises: ValueError if data is None + :raises: SerializationError if serialization fails. + """ + if data is None: + raise ValueError("No value for given attribute") + + try: + if data is CoreNull: + return None + if data_type in self.basic_types.values(): + return self.serialize_basic(data, data_type, **kwargs) + + elif data_type in self.serialize_type: + return self.serialize_type[data_type](data, **kwargs) + + # If dependencies is empty, try with current data class + # It has to be a subclass of Enum anyway + enum_type = self.dependencies.get(data_type, data.__class__) + if issubclass(enum_type, Enum): + return Serializer.serialize_enum(data, enum_obj=enum_type) + + iter_type = data_type[0] + data_type[-1] + if iter_type in self.serialize_type: + return self.serialize_type[iter_type](data, data_type[1:-1], **kwargs) + + except (ValueError, TypeError) as err: + msg = "Unable to serialize value: {!r} as type: {!r}." + raise SerializationError(msg.format(data, data_type)) from err + else: + return self._serialize(data, **kwargs) + + @classmethod + def _get_custom_serializers(cls, data_type, **kwargs): + custom_serializer = kwargs.get("basic_types_serializers", {}).get(data_type) + if custom_serializer: + return custom_serializer + if kwargs.get("is_xml", False): + return cls._xml_basic_types_serializers.get(data_type) + + @classmethod + def serialize_basic(cls, data, data_type, **kwargs): + """Serialize basic builting data type. + Serializes objects to str, int, float or bool. + + Possible kwargs: + - basic_types_serializers dict[str, callable] : If set, use the callable as serializer + - is_xml bool : If set, use xml_basic_types_serializers + + :param data: Object to be serialized. + :param str data_type: Type of object in the iterable. + """ + custom_serializer = cls._get_custom_serializers(data_type, **kwargs) + if custom_serializer: + return custom_serializer(data) + if data_type == "str": + return cls.serialize_unicode(data) + return eval(data_type)(data) # nosec + + @classmethod + def serialize_unicode(cls, data): + """Special handling for serializing unicode strings in Py2. + Encode to UTF-8 if unicode, otherwise handle as a str. + + :param data: Object to be serialized. + :rtype: str + """ + try: # If I received an enum, return its value + return data.value + except AttributeError: + pass + + try: + if isinstance(data, unicode): # type: ignore + # Don't change it, JSON and XML ElementTree are totally able + # to serialize correctly u'' strings + return data + except NameError: + return str(data) + else: + return str(data) + + def serialize_iter(self, data, iter_type, div=None, **kwargs): + """Serialize iterable. + + Supported kwargs: + - serialization_ctxt dict : The current entry of _attribute_map, or same format. + serialization_ctxt['type'] should be same as data_type. + - is_xml bool : If set, serialize as XML + + :param list attr: Object to be serialized. + :param str iter_type: Type of object in the iterable. + :param bool required: Whether the objects in the iterable must + not be None or empty. + :param str div: If set, this str will be used to combine the elements + in the iterable into a combined string. Default is 'None'. + :keyword bool do_quote: Whether to quote the serialized result of each iterable element. + Defaults to False. + :rtype: list, str + """ + if isinstance(data, str): + raise SerializationError("Refuse str type as a valid iter type.") + + serialization_ctxt = kwargs.get("serialization_ctxt", {}) + is_xml = kwargs.get("is_xml", False) + + serialized = [] + for d in data: + try: + serialized.append(self.serialize_data(d, iter_type, **kwargs)) + except ValueError as err: + if isinstance(err, SerializationError): + raise + serialized.append(None) + + if kwargs.get("do_quote", False): + serialized = ["" if s is None else quote(str(s), safe="") for s in serialized] + + if div: + serialized = ["" if s is None else str(s) for s in serialized] + serialized = div.join(serialized) + + if "xml" in serialization_ctxt or is_xml: + # XML serialization is more complicated + xml_desc = serialization_ctxt.get("xml", {}) + xml_name = xml_desc.get("name") + if not xml_name: + xml_name = serialization_ctxt["key"] + + # Create a wrap node if necessary (use the fact that Element and list have "append") + is_wrapped = xml_desc.get("wrapped", False) + node_name = xml_desc.get("itemsName", xml_name) + if is_wrapped: + final_result = _create_xml_node(xml_name, xml_desc.get("prefix", None), xml_desc.get("ns", None)) + else: + final_result = [] + # All list elements to "local_node" + for el in serialized: + if isinstance(el, ET.Element): + el_node = el + else: + el_node = _create_xml_node(node_name, xml_desc.get("prefix", None), xml_desc.get("ns", None)) + if el is not None: # Otherwise it writes "None" :-p + el_node.text = str(el) + final_result.append(el_node) + return final_result + return serialized + + def serialize_dict(self, attr, dict_type, **kwargs): + """Serialize a dictionary of objects. + + :param dict attr: Object to be serialized. + :param str dict_type: Type of object in the dictionary. + :param bool required: Whether the objects in the dictionary must + not be None or empty. + :rtype: dict + """ + serialization_ctxt = kwargs.get("serialization_ctxt", {}) + serialized = {} + for key, value in attr.items(): + try: + serialized[self.serialize_unicode(key)] = self.serialize_data(value, dict_type, **kwargs) + except ValueError as err: + if isinstance(err, SerializationError): + raise + serialized[self.serialize_unicode(key)] = None + + if "xml" in serialization_ctxt: + # XML serialization is more complicated + xml_desc = serialization_ctxt["xml"] + xml_name = xml_desc["name"] + + final_result = _create_xml_node(xml_name, xml_desc.get("prefix", None), xml_desc.get("ns", None)) + for key, value in serialized.items(): + ET.SubElement(final_result, key).text = value + return final_result + + return serialized + + def serialize_object(self, attr, **kwargs): + """Serialize a generic object. + This will be handled as a dictionary. If object passed in is not + a basic type (str, int, float, dict, list) it will simply be + cast to str. + + :param dict attr: Object to be serialized. + :rtype: dict or str + """ + if attr is None: + return None + if isinstance(attr, ET.Element): + return attr + obj_type = type(attr) + if obj_type in self.basic_types: + return self.serialize_basic(attr, self.basic_types[obj_type], **kwargs) + if obj_type is _long_type: + return self.serialize_long(attr) + if obj_type is str: + return self.serialize_unicode(attr) + if obj_type is datetime.datetime: + return self.serialize_iso(attr) + if obj_type is datetime.date: + return self.serialize_date(attr) + if obj_type is datetime.time: + return self.serialize_time(attr) + if obj_type is datetime.timedelta: + return self.serialize_duration(attr) + if obj_type is decimal.Decimal: + return self.serialize_decimal(attr) + + # If it's a model or I know this dependency, serialize as a Model + elif obj_type in self.dependencies.values() or isinstance(attr, Model): + return self._serialize(attr) + + if obj_type == dict: + serialized = {} + for key, value in attr.items(): + try: + serialized[self.serialize_unicode(key)] = self.serialize_object(value, **kwargs) + except ValueError: + serialized[self.serialize_unicode(key)] = None + return serialized + + if obj_type == list: + serialized = [] + for obj in attr: + try: + serialized.append(self.serialize_object(obj, **kwargs)) + except ValueError: + pass + return serialized + return str(attr) + + @staticmethod + def serialize_enum(attr, enum_obj=None): + try: + result = attr.value + except AttributeError: + result = attr + try: + enum_obj(result) # type: ignore + return result + except ValueError: + for enum_value in enum_obj: # type: ignore + if enum_value.value.lower() == str(attr).lower(): + return enum_value.value + error = "{!r} is not valid value for enum {!r}" + raise SerializationError(error.format(attr, enum_obj)) + + @staticmethod + def serialize_bytearray(attr, **kwargs): + """Serialize bytearray into base-64 string. + + :param attr: Object to be serialized. + :rtype: str + """ + return b64encode(attr).decode() + + @staticmethod + def serialize_base64(attr, **kwargs): + """Serialize str into base-64 string. + + :param attr: Object to be serialized. + :rtype: str + """ + encoded = b64encode(attr).decode("ascii") + return encoded.strip("=").replace("+", "-").replace("/", "_") + + @staticmethod + def serialize_decimal(attr, **kwargs): + """Serialize Decimal object to float. + + :param attr: Object to be serialized. + :rtype: float + """ + return float(attr) + + @staticmethod + def serialize_long(attr, **kwargs): + """Serialize long (Py2) or int (Py3). + + :param attr: Object to be serialized. + :rtype: int/long + """ + return _long_type(attr) + + @staticmethod + def serialize_date(attr, **kwargs): + """Serialize Date object into ISO-8601 formatted string. + + :param Date attr: Object to be serialized. + :rtype: str + """ + if isinstance(attr, str): + attr = isodate.parse_date(attr) + t = "{:04}-{:02}-{:02}".format(attr.year, attr.month, attr.day) + return t + + @staticmethod + def serialize_time(attr, **kwargs): + """Serialize Time object into ISO-8601 formatted string. + + :param datetime.time attr: Object to be serialized. + :rtype: str + """ + if isinstance(attr, str): + attr = isodate.parse_time(attr) + t = "{:02}:{:02}:{:02}".format(attr.hour, attr.minute, attr.second) + if attr.microsecond: + t += ".{:02}".format(attr.microsecond) + return t + + @staticmethod + def serialize_duration(attr, **kwargs): + """Serialize TimeDelta object into ISO-8601 formatted string. + + :param TimeDelta attr: Object to be serialized. + :rtype: str + """ + if isinstance(attr, str): + attr = isodate.parse_duration(attr) + return isodate.duration_isoformat(attr) + + @staticmethod + def serialize_rfc(attr, **kwargs): + """Serialize Datetime object into RFC-1123 formatted string. + + :param Datetime attr: Object to be serialized. + :rtype: str + :raises: TypeError if format invalid. + """ + try: + if not attr.tzinfo: + _LOGGER.warning("Datetime with no tzinfo will be considered UTC.") + utc = attr.utctimetuple() + except AttributeError: + raise TypeError("RFC1123 object must be valid Datetime object.") + + return "{}, {:02} {} {:04} {:02}:{:02}:{:02} GMT".format( + Serializer.days[utc.tm_wday], + utc.tm_mday, + Serializer.months[utc.tm_mon], + utc.tm_year, + utc.tm_hour, + utc.tm_min, + utc.tm_sec, + ) + + @staticmethod + def serialize_iso(attr, **kwargs): + """Serialize Datetime object into ISO-8601 formatted string. + + :param Datetime attr: Object to be serialized. + :rtype: str + :raises: SerializationError if format invalid. + """ + if isinstance(attr, str): + attr = isodate.parse_datetime(attr) + try: + if not attr.tzinfo: + _LOGGER.warning("Datetime with no tzinfo will be considered UTC.") + utc = attr.utctimetuple() + if utc.tm_year > 9999 or utc.tm_year < 1: + raise OverflowError("Hit max or min date") + + microseconds = str(attr.microsecond).rjust(6, "0").rstrip("0").ljust(3, "0") + if microseconds: + microseconds = "." + microseconds + date = "{:04}-{:02}-{:02}T{:02}:{:02}:{:02}".format( + utc.tm_year, utc.tm_mon, utc.tm_mday, utc.tm_hour, utc.tm_min, utc.tm_sec + ) + return date + microseconds + "Z" + except (ValueError, OverflowError) as err: + msg = "Unable to serialize datetime object." + raise SerializationError(msg) from err + except AttributeError as err: + msg = "ISO-8601 object must be valid Datetime object." + raise TypeError(msg) from err + + @staticmethod + def serialize_unix(attr, **kwargs): + """Serialize Datetime object into IntTime format. + This is represented as seconds. + + :param Datetime attr: Object to be serialized. + :rtype: int + :raises: SerializationError if format invalid + """ + if isinstance(attr, int): + return attr + try: + if not attr.tzinfo: + _LOGGER.warning("Datetime with no tzinfo will be considered UTC.") + return int(calendar.timegm(attr.utctimetuple())) + except AttributeError: + raise TypeError("Unix time object must be valid Datetime object.") + + +def rest_key_extractor(attr, attr_desc, data): + key = attr_desc["key"] + working_data = data + + while "." in key: + # Need the cast, as for some reasons "split" is typed as list[str | Any] + dict_keys = cast(List[str], _FLATTEN.split(key)) + if len(dict_keys) == 1: + key = _decode_attribute_map_key(dict_keys[0]) + break + working_key = _decode_attribute_map_key(dict_keys[0]) + working_data = working_data.get(working_key, data) + if working_data is None: + # If at any point while following flatten JSON path see None, it means + # that all properties under are None as well + return None + key = ".".join(dict_keys[1:]) + + return working_data.get(key) + + +def rest_key_case_insensitive_extractor(attr, attr_desc, data): + key = attr_desc["key"] + working_data = data + + while "." in key: + dict_keys = _FLATTEN.split(key) + if len(dict_keys) == 1: + key = _decode_attribute_map_key(dict_keys[0]) + break + working_key = _decode_attribute_map_key(dict_keys[0]) + working_data = attribute_key_case_insensitive_extractor(working_key, None, working_data) + if working_data is None: + # If at any point while following flatten JSON path see None, it means + # that all properties under are None as well + return None + key = ".".join(dict_keys[1:]) + + if working_data: + return attribute_key_case_insensitive_extractor(key, None, working_data) + + +def last_rest_key_extractor(attr, attr_desc, data): + """Extract the attribute in "data" based on the last part of the JSON path key.""" + key = attr_desc["key"] + dict_keys = _FLATTEN.split(key) + return attribute_key_extractor(dict_keys[-1], None, data) + + +def last_rest_key_case_insensitive_extractor(attr, attr_desc, data): + """Extract the attribute in "data" based on the last part of the JSON path key. + + This is the case insensitive version of "last_rest_key_extractor" + """ + key = attr_desc["key"] + dict_keys = _FLATTEN.split(key) + return attribute_key_case_insensitive_extractor(dict_keys[-1], None, data) + + +def attribute_key_extractor(attr, _, data): + return data.get(attr) + + +def attribute_key_case_insensitive_extractor(attr, _, data): + found_key = None + lower_attr = attr.lower() + for key in data: + if lower_attr == key.lower(): + found_key = key + break + + return data.get(found_key) + + +def _extract_name_from_internal_type(internal_type): + """Given an internal type XML description, extract correct XML name with namespace. + + :param dict internal_type: An model type + :rtype: tuple + :returns: A tuple XML name + namespace dict + """ + internal_type_xml_map = getattr(internal_type, "_xml_map", {}) + xml_name = internal_type_xml_map.get("name", internal_type.__name__) + xml_ns = internal_type_xml_map.get("ns", None) + if xml_ns: + xml_name = "{{{}}}{}".format(xml_ns, xml_name) + return xml_name + + +def xml_key_extractor(attr, attr_desc, data): + if isinstance(data, dict): + return None + + # Test if this model is XML ready first + if not isinstance(data, ET.Element): + return None + + xml_desc = attr_desc.get("xml", {}) + xml_name = xml_desc.get("name", attr_desc["key"]) + + # Look for a children + is_iter_type = attr_desc["type"].startswith("[") + is_wrapped = xml_desc.get("wrapped", False) + internal_type = attr_desc.get("internalType", None) + internal_type_xml_map = getattr(internal_type, "_xml_map", {}) + + # Integrate namespace if necessary + xml_ns = xml_desc.get("ns", internal_type_xml_map.get("ns", None)) + if xml_ns: + xml_name = "{{{}}}{}".format(xml_ns, xml_name) + + # If it's an attribute, that's simple + if xml_desc.get("attr", False): + return data.get(xml_name) + + # If it's x-ms-text, that's simple too + if xml_desc.get("text", False): + return data.text + + # Scenario where I take the local name: + # - Wrapped node + # - Internal type is an enum (considered basic types) + # - Internal type has no XML/Name node + if is_wrapped or (internal_type and (issubclass(internal_type, Enum) or "name" not in internal_type_xml_map)): + children = data.findall(xml_name) + # If internal type has a local name and it's not a list, I use that name + elif not is_iter_type and internal_type and "name" in internal_type_xml_map: + xml_name = _extract_name_from_internal_type(internal_type) + children = data.findall(xml_name) + # That's an array + else: + if internal_type: # Complex type, ignore itemsName and use the complex type name + items_name = _extract_name_from_internal_type(internal_type) + else: + items_name = xml_desc.get("itemsName", xml_name) + children = data.findall(items_name) + + if len(children) == 0: + if is_iter_type: + if is_wrapped: + return None # is_wrapped no node, we want None + else: + return [] # not wrapped, assume empty list + return None # Assume it's not there, maybe an optional node. + + # If is_iter_type and not wrapped, return all found children + if is_iter_type: + if not is_wrapped: + return children + else: # Iter and wrapped, should have found one node only (the wrap one) + if len(children) != 1: + raise DeserializationError( + "Tried to deserialize an array not wrapped, and found several nodes '{}'. Maybe you should declare this array as wrapped?".format( + xml_name + ) + ) + return list(children[0]) # Might be empty list and that's ok. + + # Here it's not a itertype, we should have found one element only or empty + if len(children) > 1: + raise DeserializationError("Find several XML '{}' where it was not expected".format(xml_name)) + return children[0] + + +class Deserializer(object): + """Response object model deserializer. + + :param dict classes: Class type dictionary for deserializing complex types. + :ivar list key_extractors: Ordered list of extractors to be used by this deserializer. + """ + + basic_types = {str: "str", int: "int", bool: "bool", float: "float"} + + valid_date = re.compile(r"\d{4}[-]\d{2}[-]\d{2}T\d{2}:\d{2}:\d{2}" r"\.?\d*Z?[-+]?[\d{2}]?:?[\d{2}]?") + + def __init__(self, classes: Optional[Mapping[str, type]] = None): + self.deserialize_type = { + "iso-8601": Deserializer.deserialize_iso, + "rfc-1123": Deserializer.deserialize_rfc, + "unix-time": Deserializer.deserialize_unix, + "duration": Deserializer.deserialize_duration, + "date": Deserializer.deserialize_date, + "time": Deserializer.deserialize_time, + "decimal": Deserializer.deserialize_decimal, + "long": Deserializer.deserialize_long, + "bytearray": Deserializer.deserialize_bytearray, + "base64": Deserializer.deserialize_base64, + "object": self.deserialize_object, + "[]": self.deserialize_iter, + "{}": self.deserialize_dict, + } + self.deserialize_expected_types = { + "duration": (isodate.Duration, datetime.timedelta), + "iso-8601": (datetime.datetime), + } + self.dependencies: Dict[str, type] = dict(classes) if classes else {} + self.key_extractors = [rest_key_extractor, xml_key_extractor] + # Additional properties only works if the "rest_key_extractor" is used to + # extract the keys. Making it to work whatever the key extractor is too much + # complicated, with no real scenario for now. + # So adding a flag to disable additional properties detection. This flag should be + # used if your expect the deserialization to NOT come from a JSON REST syntax. + # Otherwise, result are unexpected + self.additional_properties_detection = True + + def __call__(self, target_obj, response_data, content_type=None): + """Call the deserializer to process a REST response. + + :param str target_obj: Target data type to deserialize to. + :param requests.Response response_data: REST response object. + :param str content_type: Swagger "produces" if available. + :raises: DeserializationError if deserialization fails. + :return: Deserialized object. + """ + data = self._unpack_content(response_data, content_type) + return self._deserialize(target_obj, data) + + def _deserialize(self, target_obj, data): + """Call the deserializer on a model. + + Data needs to be already deserialized as JSON or XML ElementTree + + :param str target_obj: Target data type to deserialize to. + :param object data: Object to deserialize. + :raises: DeserializationError if deserialization fails. + :return: Deserialized object. + """ + # This is already a model, go recursive just in case + if hasattr(data, "_attribute_map"): + constants = [name for name, config in getattr(data, "_validation", {}).items() if config.get("constant")] + try: + for attr, mapconfig in data._attribute_map.items(): + if attr in constants: + continue + value = getattr(data, attr) + if value is None: + continue + local_type = mapconfig["type"] + internal_data_type = local_type.strip("[]{}") + if internal_data_type not in self.dependencies or isinstance(internal_data_type, Enum): + continue + setattr(data, attr, self._deserialize(local_type, value)) + return data + except AttributeError: + return + + response, class_name = self._classify_target(target_obj, data) + + if isinstance(response, str): + return self.deserialize_data(data, response) + elif isinstance(response, type) and issubclass(response, Enum): + return self.deserialize_enum(data, response) + + if data is None or data is CoreNull: + return data + try: + attributes = response._attribute_map # type: ignore + d_attrs = {} + for attr, attr_desc in attributes.items(): + # Check empty string. If it's not empty, someone has a real "additionalProperties"... + if attr == "additional_properties" and attr_desc["key"] == "": + continue + raw_value = None + # Enhance attr_desc with some dynamic data + attr_desc = attr_desc.copy() # Do a copy, do not change the real one + internal_data_type = attr_desc["type"].strip("[]{}") + if internal_data_type in self.dependencies: + attr_desc["internalType"] = self.dependencies[internal_data_type] + + for key_extractor in self.key_extractors: + found_value = key_extractor(attr, attr_desc, data) + if found_value is not None: + if raw_value is not None and raw_value != found_value: + msg = ( + "Ignoring extracted value '%s' from %s for key '%s'" + " (duplicate extraction, follow extractors order)" + ) + _LOGGER.warning(msg, found_value, key_extractor, attr) + continue + raw_value = found_value + + value = self.deserialize_data(raw_value, attr_desc["type"]) + d_attrs[attr] = value + except (AttributeError, TypeError, KeyError) as err: + msg = "Unable to deserialize to object: " + class_name # type: ignore + raise DeserializationError(msg) from err + else: + additional_properties = self._build_additional_properties(attributes, data) + return self._instantiate_model(response, d_attrs, additional_properties) + + def _build_additional_properties(self, attribute_map, data): + if not self.additional_properties_detection: + return None + if "additional_properties" in attribute_map and attribute_map.get("additional_properties", {}).get("key") != "": + # Check empty string. If it's not empty, someone has a real "additionalProperties" + return None + if isinstance(data, ET.Element): + data = {el.tag: el.text for el in data} + + known_keys = { + _decode_attribute_map_key(_FLATTEN.split(desc["key"])[0]) + for desc in attribute_map.values() + if desc["key"] != "" + } + present_keys = set(data.keys()) + missing_keys = present_keys - known_keys + return {key: data[key] for key in missing_keys} + + def _classify_target(self, target, data): + """Check to see whether the deserialization target object can + be classified into a subclass. + Once classification has been determined, initialize object. + + :param str target: The target object type to deserialize to. + :param str/dict data: The response data to deserialize. + """ + if target is None: + return None, None + + if isinstance(target, str): + try: + target = self.dependencies[target] + except KeyError: + return target, target + + try: + target = target._classify(data, self.dependencies) # type: ignore + except AttributeError: + pass # Target is not a Model, no classify + return target, target.__class__.__name__ # type: ignore + + def failsafe_deserialize(self, target_obj, data, content_type=None): + """Ignores any errors encountered in deserialization, + and falls back to not deserializing the object. Recommended + for use in error deserialization, as we want to return the + HttpResponseError to users, and not have them deal with + a deserialization error. + + :param str target_obj: The target object type to deserialize to. + :param str/dict data: The response data to deserialize. + :param str content_type: Swagger "produces" if available. + """ + try: + return self(target_obj, data, content_type=content_type) + except: + _LOGGER.debug( + "Ran into a deserialization error. Ignoring since this is failsafe deserialization", exc_info=True + ) + return None + + @staticmethod + def _unpack_content(raw_data, content_type=None): + """Extract the correct structure for deserialization. + + If raw_data is a PipelineResponse, try to extract the result of RawDeserializer. + if we can't, raise. Your Pipeline should have a RawDeserializer. + + If not a pipeline response and raw_data is bytes or string, use content-type + to decode it. If no content-type, try JSON. + + If raw_data is something else, bypass all logic and return it directly. + + :param raw_data: Data to be processed. + :param content_type: How to parse if raw_data is a string/bytes. + :raises JSONDecodeError: If JSON is requested and parsing is impossible. + :raises UnicodeDecodeError: If bytes is not UTF8 + """ + # Assume this is enough to detect a Pipeline Response without importing it + context = getattr(raw_data, "context", {}) + if context: + if RawDeserializer.CONTEXT_NAME in context: + return context[RawDeserializer.CONTEXT_NAME] + raise ValueError("This pipeline didn't have the RawDeserializer policy; can't deserialize") + + # Assume this is enough to recognize universal_http.ClientResponse without importing it + if hasattr(raw_data, "body"): + return RawDeserializer.deserialize_from_http_generics(raw_data.text(), raw_data.headers) + + # Assume this enough to recognize requests.Response without importing it. + if hasattr(raw_data, "_content_consumed"): + return RawDeserializer.deserialize_from_http_generics(raw_data.text, raw_data.headers) + + if isinstance(raw_data, (str, bytes)) or hasattr(raw_data, "read"): + return RawDeserializer.deserialize_from_text(raw_data, content_type) # type: ignore + return raw_data + + def _instantiate_model(self, response, attrs, additional_properties=None): + """Instantiate a response model passing in deserialized args. + + :param response: The response model class. + :param d_attrs: The deserialized response attributes. + """ + if callable(response): + subtype = getattr(response, "_subtype_map", {}) + try: + readonly = [k for k, v in response._validation.items() if v.get("readonly")] + const = [k for k, v in response._validation.items() if v.get("constant")] + kwargs = {k: v for k, v in attrs.items() if k not in subtype and k not in readonly + const} + response_obj = response(**kwargs) + for attr in readonly: + setattr(response_obj, attr, attrs.get(attr)) + if additional_properties: + response_obj.additional_properties = additional_properties + return response_obj + except TypeError as err: + msg = "Unable to deserialize {} into model {}. ".format(kwargs, response) # type: ignore + raise DeserializationError(msg + str(err)) + else: + try: + for attr, value in attrs.items(): + setattr(response, attr, value) + return response + except Exception as exp: + msg = "Unable to populate response model. " + msg += "Type: {}, Error: {}".format(type(response), exp) + raise DeserializationError(msg) + + def deserialize_data(self, data, data_type): + """Process data for deserialization according to data type. + + :param str data: The response string to be deserialized. + :param str data_type: The type to deserialize to. + :raises: DeserializationError if deserialization fails. + :return: Deserialized object. + """ + if data is None: + return data + + try: + if not data_type: + return data + if data_type in self.basic_types.values(): + return self.deserialize_basic(data, data_type) + if data_type in self.deserialize_type: + if isinstance(data, self.deserialize_expected_types.get(data_type, tuple())): + return data + + is_a_text_parsing_type = lambda x: x not in ["object", "[]", r"{}"] + if isinstance(data, ET.Element) and is_a_text_parsing_type(data_type) and not data.text: + return None + data_val = self.deserialize_type[data_type](data) + return data_val + + iter_type = data_type[0] + data_type[-1] + if iter_type in self.deserialize_type: + return self.deserialize_type[iter_type](data, data_type[1:-1]) + + obj_type = self.dependencies[data_type] + if issubclass(obj_type, Enum): + if isinstance(data, ET.Element): + data = data.text + return self.deserialize_enum(data, obj_type) + + except (ValueError, TypeError, AttributeError) as err: + msg = "Unable to deserialize response data." + msg += " Data: {}, {}".format(data, data_type) + raise DeserializationError(msg) from err + else: + return self._deserialize(obj_type, data) + + def deserialize_iter(self, attr, iter_type): + """Deserialize an iterable. + + :param list attr: Iterable to be deserialized. + :param str iter_type: The type of object in the iterable. + :rtype: list + """ + if attr is None: + return None + if isinstance(attr, ET.Element): # If I receive an element here, get the children + attr = list(attr) + if not isinstance(attr, (list, set)): + raise DeserializationError("Cannot deserialize as [{}] an object of type {}".format(iter_type, type(attr))) + return [self.deserialize_data(a, iter_type) for a in attr] + + def deserialize_dict(self, attr, dict_type): + """Deserialize a dictionary. + + :param dict/list attr: Dictionary to be deserialized. Also accepts + a list of key, value pairs. + :param str dict_type: The object type of the items in the dictionary. + :rtype: dict + """ + if isinstance(attr, list): + return {x["key"]: self.deserialize_data(x["value"], dict_type) for x in attr} + + if isinstance(attr, ET.Element): + # Transform value into {"Key": "value"} + attr = {el.tag: el.text for el in attr} + return {k: self.deserialize_data(v, dict_type) for k, v in attr.items()} + + def deserialize_object(self, attr, **kwargs): + """Deserialize a generic object. + This will be handled as a dictionary. + + :param dict attr: Dictionary to be deserialized. + :rtype: dict + :raises: TypeError if non-builtin datatype encountered. + """ + if attr is None: + return None + if isinstance(attr, ET.Element): + # Do no recurse on XML, just return the tree as-is + return attr + if isinstance(attr, str): + return self.deserialize_basic(attr, "str") + obj_type = type(attr) + if obj_type in self.basic_types: + return self.deserialize_basic(attr, self.basic_types[obj_type]) + if obj_type is _long_type: + return self.deserialize_long(attr) + + if obj_type == dict: + deserialized = {} + for key, value in attr.items(): + try: + deserialized[key] = self.deserialize_object(value, **kwargs) + except ValueError: + deserialized[key] = None + return deserialized + + if obj_type == list: + deserialized = [] + for obj in attr: + try: + deserialized.append(self.deserialize_object(obj, **kwargs)) + except ValueError: + pass + return deserialized + + else: + error = "Cannot deserialize generic object with type: " + raise TypeError(error + str(obj_type)) + + def deserialize_basic(self, attr, data_type): + """Deserialize basic builtin data type from string. + Will attempt to convert to str, int, float and bool. + This function will also accept '1', '0', 'true' and 'false' as + valid bool values. + + :param str attr: response string to be deserialized. + :param str data_type: deserialization data type. + :rtype: str, int, float or bool + :raises: TypeError if string format is not valid. + """ + # If we're here, data is supposed to be a basic type. + # If it's still an XML node, take the text + if isinstance(attr, ET.Element): + attr = attr.text + if not attr: + if data_type == "str": + # None or '', node is empty string. + return "" + else: + # None or '', node with a strong type is None. + # Don't try to model "empty bool" or "empty int" + return None + + if data_type == "bool": + if attr in [True, False, 1, 0]: + return bool(attr) + elif isinstance(attr, str): + if attr.lower() in ["true", "1"]: + return True + elif attr.lower() in ["false", "0"]: + return False + raise TypeError("Invalid boolean value: {}".format(attr)) + + if data_type == "str": + return self.deserialize_unicode(attr) + return eval(data_type)(attr) # nosec + + @staticmethod + def deserialize_unicode(data): + """Preserve unicode objects in Python 2, otherwise return data + as a string. + + :param str data: response string to be deserialized. + :rtype: str or unicode + """ + # We might be here because we have an enum modeled as string, + # and we try to deserialize a partial dict with enum inside + if isinstance(data, Enum): + return data + + # Consider this is real string + try: + if isinstance(data, unicode): # type: ignore + return data + except NameError: + return str(data) + else: + return str(data) + + @staticmethod + def deserialize_enum(data, enum_obj): + """Deserialize string into enum object. + + If the string is not a valid enum value it will be returned as-is + and a warning will be logged. + + :param str data: Response string to be deserialized. If this value is + None or invalid it will be returned as-is. + :param Enum enum_obj: Enum object to deserialize to. + :rtype: Enum + """ + if isinstance(data, enum_obj) or data is None: + return data + if isinstance(data, Enum): + data = data.value + if isinstance(data, int): + # Workaround. We might consider remove it in the future. + try: + return list(enum_obj.__members__.values())[data] + except IndexError: + error = "{!r} is not a valid index for enum {!r}" + raise DeserializationError(error.format(data, enum_obj)) + try: + return enum_obj(str(data)) + except ValueError: + for enum_value in enum_obj: + if enum_value.value.lower() == str(data).lower(): + return enum_value + # We don't fail anymore for unknown value, we deserialize as a string + _LOGGER.warning("Deserializer is not able to find %s as valid enum in %s", data, enum_obj) + return Deserializer.deserialize_unicode(data) + + @staticmethod + def deserialize_bytearray(attr): + """Deserialize string into bytearray. + + :param str attr: response string to be deserialized. + :rtype: bytearray + :raises: TypeError if string format invalid. + """ + if isinstance(attr, ET.Element): + attr = attr.text + return bytearray(b64decode(attr)) # type: ignore + + @staticmethod + def deserialize_base64(attr): + """Deserialize base64 encoded string into string. + + :param str attr: response string to be deserialized. + :rtype: bytearray + :raises: TypeError if string format invalid. + """ + if isinstance(attr, ET.Element): + attr = attr.text + padding = "=" * (3 - (len(attr) + 3) % 4) # type: ignore + attr = attr + padding # type: ignore + encoded = attr.replace("-", "+").replace("_", "/") + return b64decode(encoded) + + @staticmethod + def deserialize_decimal(attr): + """Deserialize string into Decimal object. + + :param str attr: response string to be deserialized. + :rtype: Decimal + :raises: DeserializationError if string format invalid. + """ + if isinstance(attr, ET.Element): + attr = attr.text + try: + return decimal.Decimal(str(attr)) # type: ignore + except decimal.DecimalException as err: + msg = "Invalid decimal {}".format(attr) + raise DeserializationError(msg) from err + + @staticmethod + def deserialize_long(attr): + """Deserialize string into long (Py2) or int (Py3). + + :param str attr: response string to be deserialized. + :rtype: long or int + :raises: ValueError if string format invalid. + """ + if isinstance(attr, ET.Element): + attr = attr.text + return _long_type(attr) # type: ignore + + @staticmethod + def deserialize_duration(attr): + """Deserialize ISO-8601 formatted string into TimeDelta object. + + :param str attr: response string to be deserialized. + :rtype: TimeDelta + :raises: DeserializationError if string format invalid. + """ + if isinstance(attr, ET.Element): + attr = attr.text + try: + duration = isodate.parse_duration(attr) + except (ValueError, OverflowError, AttributeError) as err: + msg = "Cannot deserialize duration object." + raise DeserializationError(msg) from err + else: + return duration + + @staticmethod + def deserialize_date(attr): + """Deserialize ISO-8601 formatted string into Date object. + + :param str attr: response string to be deserialized. + :rtype: Date + :raises: DeserializationError if string format invalid. + """ + if isinstance(attr, ET.Element): + attr = attr.text + if re.search(r"[^\W\d_]", attr, re.I + re.U): # type: ignore + raise DeserializationError("Date must have only digits and -. Received: %s" % attr) + # This must NOT use defaultmonth/defaultday. Using None ensure this raises an exception. + return isodate.parse_date(attr, defaultmonth=0, defaultday=0) + + @staticmethod + def deserialize_time(attr): + """Deserialize ISO-8601 formatted string into time object. + + :param str attr: response string to be deserialized. + :rtype: datetime.time + :raises: DeserializationError if string format invalid. + """ + if isinstance(attr, ET.Element): + attr = attr.text + if re.search(r"[^\W\d_]", attr, re.I + re.U): # type: ignore + raise DeserializationError("Date must have only digits and -. Received: %s" % attr) + return isodate.parse_time(attr) + + @staticmethod + def deserialize_rfc(attr): + """Deserialize RFC-1123 formatted string into Datetime object. + + :param str attr: response string to be deserialized. + :rtype: Datetime + :raises: DeserializationError if string format invalid. + """ + if isinstance(attr, ET.Element): + attr = attr.text + try: + parsed_date = email.utils.parsedate_tz(attr) # type: ignore + date_obj = datetime.datetime( + *parsed_date[:6], tzinfo=_FixedOffset(datetime.timedelta(minutes=(parsed_date[9] or 0) / 60)) + ) + if not date_obj.tzinfo: + date_obj = date_obj.astimezone(tz=TZ_UTC) + except ValueError as err: + msg = "Cannot deserialize to rfc datetime object." + raise DeserializationError(msg) from err + else: + return date_obj + + @staticmethod + def deserialize_iso(attr): + """Deserialize ISO-8601 formatted string into Datetime object. + + :param str attr: response string to be deserialized. + :rtype: Datetime + :raises: DeserializationError if string format invalid. + """ + if isinstance(attr, ET.Element): + attr = attr.text + try: + attr = attr.upper() # type: ignore + match = Deserializer.valid_date.match(attr) + if not match: + raise ValueError("Invalid datetime string: " + attr) + + check_decimal = attr.split(".") + if len(check_decimal) > 1: + decimal_str = "" + for digit in check_decimal[1]: + if digit.isdigit(): + decimal_str += digit + else: + break + if len(decimal_str) > 6: + attr = attr.replace(decimal_str, decimal_str[0:6]) + + date_obj = isodate.parse_datetime(attr) + test_utc = date_obj.utctimetuple() + if test_utc.tm_year > 9999 or test_utc.tm_year < 1: + raise OverflowError("Hit max or min date") + except (ValueError, OverflowError, AttributeError) as err: + msg = "Cannot deserialize datetime object." + raise DeserializationError(msg) from err + else: + return date_obj + + @staticmethod + def deserialize_unix(attr): + """Serialize Datetime object into IntTime format. + This is represented as seconds. + + :param int attr: Object to be serialized. + :rtype: Datetime + :raises: DeserializationError if format invalid + """ + if isinstance(attr, ET.Element): + attr = int(attr.text) # type: ignore + try: + attr = int(attr) + date_obj = datetime.datetime.fromtimestamp(attr, TZ_UTC) + except ValueError as err: + msg = "Cannot deserialize to unix datetime object." + raise DeserializationError(msg) from err + else: + return date_obj diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_vendor.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_vendor.py new file mode 100644 index 000000000000..6dbcb5c20a91 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_vendor.py @@ -0,0 +1,26 @@ +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from abc import ABC +from typing import TYPE_CHECKING + +from ._configuration import DeidentificationClientConfiguration + +if TYPE_CHECKING: + # pylint: disable=unused-import,ungrouped-imports + from azure.core import PipelineClient + + from ._serialization import Deserializer, Serializer + + +class DeidentificationClientMixinABC(ABC): + """DO NOT use this class. It is for internal typing use only.""" + + _client: "PipelineClient" + _config: DeidentificationClientConfiguration + _serialize: "Serializer" + _deserialize: "Deserializer" diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_version.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_version.py new file mode 100644 index 000000000000..be71c81bd282 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/_version.py @@ -0,0 +1,9 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +VERSION = "1.0.0b1" diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/__init__.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/__init__.py new file mode 100644 index 000000000000..245e207d364a --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/__init__.py @@ -0,0 +1,23 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from ._client import DeidentificationClient + +try: + from ._patch import __all__ as _patch_all + from ._patch import * # pylint: disable=unused-wildcard-import +except ImportError: + _patch_all = [] +from ._patch import patch_sdk as _patch_sdk + +__all__ = [ + "DeidentificationClient", +] +__all__.extend([p for p in _patch_all if p not in __all__]) + +_patch_sdk() diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_client.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_client.py new file mode 100644 index 000000000000..b257b9201e01 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_client.py @@ -0,0 +1,105 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from copy import deepcopy +from typing import Any, Awaitable, TYPE_CHECKING +from typing_extensions import Self + +from azure.core import AsyncPipelineClient +from azure.core.pipeline import policies +from azure.core.rest import AsyncHttpResponse, HttpRequest + +from .._serialization import Deserializer, Serializer +from ._configuration import DeidentificationClientConfiguration +from ._operations import DeidentificationClientOperationsMixin + +if TYPE_CHECKING: + # pylint: disable=unused-import,ungrouped-imports + from azure.core.credentials_async import AsyncTokenCredential + + +class DeidentificationClient( + DeidentificationClientOperationsMixin +): # pylint: disable=client-accepts-api-version-keyword + """DeidentificationClient. + + :param endpoint: Url of your De-identification Service. Required. + :type endpoint: str + :param credential: Credential used to authenticate requests to the service. Required. + :type credential: ~azure.core.credentials_async.AsyncTokenCredential + :keyword api_version: The API version to use for this operation. Default value is + "2024-07-12-preview". Note that overriding this default value may result in unsupported + behavior. + :paramtype api_version: str + :keyword int polling_interval: Default waiting time between two polls for LRO operations if no + Retry-After header is present. + """ + + def __init__(self, endpoint: str, credential: "AsyncTokenCredential", **kwargs: Any) -> None: + _endpoint = "https://{endpoint}" + self._config = DeidentificationClientConfiguration(endpoint=endpoint, credential=credential, **kwargs) + _policies = kwargs.pop("policies", None) + if _policies is None: + _policies = [ + policies.RequestIdPolicy(**kwargs), + self._config.headers_policy, + self._config.user_agent_policy, + self._config.proxy_policy, + policies.ContentDecodePolicy(**kwargs), + self._config.redirect_policy, + self._config.retry_policy, + self._config.authentication_policy, + self._config.custom_hook_policy, + self._config.logging_policy, + policies.DistributedTracingPolicy(**kwargs), + policies.SensitiveHeaderCleanupPolicy(**kwargs) if self._config.redirect_policy else None, + self._config.http_logging_policy, + ] + self._client: AsyncPipelineClient = AsyncPipelineClient(base_url=_endpoint, policies=_policies, **kwargs) + + self._serialize = Serializer() + self._deserialize = Deserializer() + self._serialize.client_side_validation = False + + def send_request( + self, request: HttpRequest, *, stream: bool = False, **kwargs: Any + ) -> Awaitable[AsyncHttpResponse]: + """Runs the network request through the client's chained policies. + + >>> from azure.core.rest import HttpRequest + >>> request = HttpRequest("GET", "https://www.example.org/") + + >>> response = await client.send_request(request) + + + For more information on this code flow, see https://aka.ms/azsdk/dpcodegen/python/send_request + + :param request: The network request you want to make. Required. + :type request: ~azure.core.rest.HttpRequest + :keyword bool stream: Whether the response payload will be streamed. Defaults to False. + :return: The response of your network call. Does not do error handling on your response. + :rtype: ~azure.core.rest.AsyncHttpResponse + """ + + request_copy = deepcopy(request) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + + request_copy.url = self._client.format_url(request_copy.url, **path_format_arguments) + return self._client.send_request(request_copy, stream=stream, **kwargs) # type: ignore + + async def close(self) -> None: + await self._client.close() + + async def __aenter__(self) -> Self: + await self._client.__aenter__() + return self + + async def __aexit__(self, *exc_details: Any) -> None: + await self._client.__aexit__(*exc_details) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_configuration.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_configuration.py new file mode 100644 index 000000000000..3799c4c1d7b2 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_configuration.py @@ -0,0 +1,65 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from typing import Any, TYPE_CHECKING + +from azure.core.pipeline import policies + +from .._version import VERSION + +if TYPE_CHECKING: + # pylint: disable=unused-import,ungrouped-imports + from azure.core.credentials_async import AsyncTokenCredential + + +class DeidentificationClientConfiguration: # pylint: disable=too-many-instance-attributes,name-too-long + """Configuration for DeidentificationClient. + + Note that all parameters used to create this instance are saved as instance + attributes. + + :param endpoint: Url of your De-identification Service. Required. + :type endpoint: str + :param credential: Credential used to authenticate requests to the service. Required. + :type credential: ~azure.core.credentials_async.AsyncTokenCredential + :keyword api_version: The API version to use for this operation. Default value is + "2024-07-12-preview". Note that overriding this default value may result in unsupported + behavior. + :paramtype api_version: str + """ + + def __init__(self, endpoint: str, credential: "AsyncTokenCredential", **kwargs: Any) -> None: + api_version: str = kwargs.pop("api_version", "2024-07-12-preview") + + if endpoint is None: + raise ValueError("Parameter 'endpoint' must not be None.") + if credential is None: + raise ValueError("Parameter 'credential' must not be None.") + + self.endpoint = endpoint + self.credential = credential + self.api_version = api_version + self.credential_scopes = kwargs.pop("credential_scopes", ["https://deid.azure.com/.default"]) + kwargs.setdefault("sdk_moniker", "health-deidentification/{}".format(VERSION)) + self.polling_interval = kwargs.get("polling_interval", 30) + self._configure(**kwargs) + + def _configure(self, **kwargs: Any) -> None: + self.user_agent_policy = kwargs.get("user_agent_policy") or policies.UserAgentPolicy(**kwargs) + self.headers_policy = kwargs.get("headers_policy") or policies.HeadersPolicy(**kwargs) + self.proxy_policy = kwargs.get("proxy_policy") or policies.ProxyPolicy(**kwargs) + self.logging_policy = kwargs.get("logging_policy") or policies.NetworkTraceLoggingPolicy(**kwargs) + self.http_logging_policy = kwargs.get("http_logging_policy") or policies.HttpLoggingPolicy(**kwargs) + self.custom_hook_policy = kwargs.get("custom_hook_policy") or policies.CustomHookPolicy(**kwargs) + self.redirect_policy = kwargs.get("redirect_policy") or policies.AsyncRedirectPolicy(**kwargs) + self.retry_policy = kwargs.get("retry_policy") or policies.AsyncRetryPolicy(**kwargs) + self.authentication_policy = kwargs.get("authentication_policy") + if self.credential and not self.authentication_policy: + self.authentication_policy = policies.AsyncBearerTokenCredentialPolicy( + self.credential, *self.credential_scopes, **kwargs + ) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_operations/__init__.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_operations/__init__.py new file mode 100644 index 000000000000..f30b11092e89 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_operations/__init__.py @@ -0,0 +1,19 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from ._operations import DeidentificationClientOperationsMixin + +from ._patch import __all__ as _patch_all +from ._patch import * # pylint: disable=unused-wildcard-import +from ._patch import patch_sdk as _patch_sdk + +__all__ = [ + "DeidentificationClientOperationsMixin", +] +__all__.extend([p for p in _patch_all if p not in __all__]) +_patch_sdk() diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_operations/_operations.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_operations/_operations.py new file mode 100644 index 000000000000..dd3a7c4dbdcb --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_operations/_operations.py @@ -0,0 +1,1342 @@ +# pylint: disable=too-many-lines,too-many-statements +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- +from io import IOBase +import json +import sys +from typing import ( + Any, + AsyncIterable, + AsyncIterator, + Callable, + Dict, + IO, + List, + Optional, + Type, + TypeVar, + Union, + cast, + overload, +) +import urllib.parse + +from azure.core.async_paging import AsyncItemPaged, AsyncList +from azure.core.exceptions import ( + ClientAuthenticationError, + HttpResponseError, + ResourceExistsError, + ResourceNotFoundError, + ResourceNotModifiedError, + map_error, +) +from azure.core.pipeline import PipelineResponse +from azure.core.polling import AsyncLROPoller, AsyncNoPolling, AsyncPollingMethod +from azure.core.polling.async_base_polling import AsyncLROBasePolling +from azure.core.rest import AsyncHttpResponse, HttpRequest +from azure.core.tracing.decorator import distributed_trace +from azure.core.tracing.decorator_async import distributed_trace_async +from azure.core.utils import case_insensitive_dict + +from ... import models as _models +from ..._model_base import SdkJSONEncoder, _deserialize +from ..._operations._operations import ( + build_deidentification_cancel_job_request, + build_deidentification_create_job_request, + build_deidentification_deidentify_request, + build_deidentification_delete_job_request, + build_deidentification_get_job_request, + build_deidentification_list_job_documents_request, + build_deidentification_list_jobs_request, +) +from .._vendor import DeidentificationClientMixinABC + +if sys.version_info >= (3, 9): + from collections.abc import MutableMapping +else: + from typing import MutableMapping # type: ignore # pylint: disable=ungrouped-imports +JSON = MutableMapping[str, Any] # pylint: disable=unsubscriptable-object +T = TypeVar("T") +ClsType = Optional[Callable[[PipelineResponse[HttpRequest, AsyncHttpResponse], T, Dict[str, Any]], Any]] + + +class DeidentificationClientOperationsMixin(DeidentificationClientMixinABC): + + @distributed_trace_async + async def get_job(self, name: str, **kwargs: Any) -> _models.DeidentificationJob: + """Get a de-identification job. + + Resource read operation template. + + :param name: The name of a job. Required. + :type name: str + :return: DeidentificationJob. The DeidentificationJob is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationJob + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + _headers = kwargs.pop("headers", {}) or {} + _params = kwargs.pop("params", {}) or {} + + cls: ClsType[_models.DeidentificationJob] = kwargs.pop("cls", None) + + _request = build_deidentification_get_job_request( + name=name, + api_version=self._config.api_version, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + _stream = kwargs.pop("stream", False) + pipeline_response: PipelineResponse = await self._client._pipeline.run( # type: ignore # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + + response = pipeline_response.http_response + + if response.status_code not in [200]: + if _stream: + await response.read() # Load the body in memory and close the socket + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + response_headers = {} + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + + if _stream: + deserialized = response.iter_bytes() + else: + deserialized = _deserialize(_models.DeidentificationJob, response.json()) + + if cls: + return cls(pipeline_response, deserialized, response_headers) # type: ignore + + return deserialized # type: ignore + + async def _create_job_initial( + self, name: str, resource: Union[_models.DeidentificationJob, JSON, IO[bytes]], **kwargs: Any + ) -> AsyncIterator[bytes]: + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = kwargs.pop("params", {}) or {} + + content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("Content-Type", None)) + cls: ClsType[AsyncIterator[bytes]] = kwargs.pop("cls", None) + + content_type = content_type or "application/json" + _content = None + if isinstance(resource, (IOBase, bytes)): + _content = resource + else: + _content = json.dumps(resource, cls=SdkJSONEncoder, exclude_readonly=True) # type: ignore + + _request = build_deidentification_create_job_request( + name=name, + content_type=content_type, + api_version=self._config.api_version, + content=_content, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + _stream = True + pipeline_response: PipelineResponse = await self._client._pipeline.run( # type: ignore # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + + response = pipeline_response.http_response + + if response.status_code not in [200, 201]: + await response.read() # Load the body in memory and close the socket + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + response_headers = {} + if response.status_code == 200: + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + response_headers["Operation-Location"] = self._deserialize( + "str", response.headers.get("Operation-Location") + ) + + deserialized = response.iter_bytes() + + if response.status_code == 201: + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + response_headers["Operation-Location"] = self._deserialize( + "str", response.headers.get("Operation-Location") + ) + + deserialized = response.iter_bytes() + + if cls: + return cls(pipeline_response, deserialized, response_headers) # type: ignore + + return deserialized # type: ignore + + @overload + async def begin_create_job( + self, name: str, resource: _models.DeidentificationJob, *, content_type: str = "application/json", **kwargs: Any + ) -> AsyncLROPoller[_models.DeidentificationJob]: + """Create a de-identification job. + + Long-running resource create or replace operation template. + + :param name: The name of a job. Required. + :type name: str + :param resource: The resource instance. Required. + :type resource: ~azure.health.deidentification.models.DeidentificationJob + :keyword content_type: Body Parameter content-type. Content type parameter for JSON body. + Default value is "application/json". + :paramtype content_type: str + :return: An instance of AsyncLROPoller that returns DeidentificationJob. The + DeidentificationJob is compatible with MutableMapping + :rtype: + ~azure.core.polling.AsyncLROPoller[~azure.health.deidentification.models.DeidentificationJob] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # JSON input template you can fill out and use as your body input. + resource = { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + + # response body for status code(s): 201, 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + + @overload + async def begin_create_job( + self, name: str, resource: JSON, *, content_type: str = "application/json", **kwargs: Any + ) -> AsyncLROPoller[_models.DeidentificationJob]: + """Create a de-identification job. + + Long-running resource create or replace operation template. + + :param name: The name of a job. Required. + :type name: str + :param resource: The resource instance. Required. + :type resource: JSON + :keyword content_type: Body Parameter content-type. Content type parameter for JSON body. + Default value is "application/json". + :paramtype content_type: str + :return: An instance of AsyncLROPoller that returns DeidentificationJob. The + DeidentificationJob is compatible with MutableMapping + :rtype: + ~azure.core.polling.AsyncLROPoller[~azure.health.deidentification.models.DeidentificationJob] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 201, 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + + @overload + async def begin_create_job( + self, name: str, resource: IO[bytes], *, content_type: str = "application/json", **kwargs: Any + ) -> AsyncLROPoller[_models.DeidentificationJob]: + """Create a de-identification job. + + Long-running resource create or replace operation template. + + :param name: The name of a job. Required. + :type name: str + :param resource: The resource instance. Required. + :type resource: IO[bytes] + :keyword content_type: Body Parameter content-type. Content type parameter for binary body. + Default value is "application/json". + :paramtype content_type: str + :return: An instance of AsyncLROPoller that returns DeidentificationJob. The + DeidentificationJob is compatible with MutableMapping + :rtype: + ~azure.core.polling.AsyncLROPoller[~azure.health.deidentification.models.DeidentificationJob] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 201, 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + + @distributed_trace_async + async def begin_create_job( + self, name: str, resource: Union[_models.DeidentificationJob, JSON, IO[bytes]], **kwargs: Any + ) -> AsyncLROPoller[_models.DeidentificationJob]: + """Create a de-identification job. + + Long-running resource create or replace operation template. + + :param name: The name of a job. Required. + :type name: str + :param resource: The resource instance. Is one of the following types: DeidentificationJob, + JSON, IO[bytes] Required. + :type resource: ~azure.health.deidentification.models.DeidentificationJob or JSON or IO[bytes] + :return: An instance of AsyncLROPoller that returns DeidentificationJob. The + DeidentificationJob is compatible with MutableMapping + :rtype: + ~azure.core.polling.AsyncLROPoller[~azure.health.deidentification.models.DeidentificationJob] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # JSON input template you can fill out and use as your body input. + resource = { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + + # response body for status code(s): 201, 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = kwargs.pop("params", {}) or {} + + content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("Content-Type", None)) + cls: ClsType[_models.DeidentificationJob] = kwargs.pop("cls", None) + polling: Union[bool, AsyncPollingMethod] = kwargs.pop("polling", True) + lro_delay = kwargs.pop("polling_interval", self._config.polling_interval) + cont_token: Optional[str] = kwargs.pop("continuation_token", None) + if cont_token is None: + raw_result = await self._create_job_initial( + name=name, + resource=resource, + content_type=content_type, + cls=lambda x, y, z: x, + headers=_headers, + params=_params, + **kwargs + ) + await raw_result.http_response.read() # type: ignore + kwargs.pop("error_map", None) + + def get_long_running_output(pipeline_response): + response_headers = {} + response = pipeline_response.http_response + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + response_headers["Operation-Location"] = self._deserialize( + "str", response.headers.get("Operation-Location") + ) + + deserialized = _deserialize(_models.DeidentificationJob, response.json()) + if cls: + return cls(pipeline_response, deserialized, response_headers) # type: ignore + return deserialized + + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + + if polling is True: + polling_method: AsyncPollingMethod = cast( + AsyncPollingMethod, + AsyncLROBasePolling(lro_delay, path_format_arguments=path_format_arguments, **kwargs), + ) + elif polling is False: + polling_method = cast(AsyncPollingMethod, AsyncNoPolling()) + else: + polling_method = polling + if cont_token: + return AsyncLROPoller[_models.DeidentificationJob].from_continuation_token( + polling_method=polling_method, + continuation_token=cont_token, + client=self._client, + deserialization_callback=get_long_running_output, + ) + return AsyncLROPoller[_models.DeidentificationJob]( + self._client, raw_result, get_long_running_output, polling_method # type: ignore + ) + + @distributed_trace + def list_jobs( + self, *, continuation_token_parameter: Optional[str] = None, **kwargs: Any + ) -> AsyncIterable["_models.DeidentificationJob"]: + """List de-identification jobs. + + Resource list operation template. + + :keyword continuation_token_parameter: Token to continue a previous query. Default value is + None. + :paramtype continuation_token_parameter: str + :return: An iterator like instance of DeidentificationJob + :rtype: + ~azure.core.async_paging.AsyncItemPaged[~azure.health.deidentification.models.DeidentificationJob] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + _headers = kwargs.pop("headers", {}) or {} + _params = kwargs.pop("params", {}) or {} + + maxpagesize = kwargs.pop("maxpagesize", None) + cls: ClsType[List[_models.DeidentificationJob]] = kwargs.pop("cls", None) + + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + def prepare_request(next_link=None): + if not next_link: + + _request = build_deidentification_list_jobs_request( + maxpagesize=maxpagesize, + continuation_token_parameter=continuation_token_parameter, + api_version=self._config.api_version, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + else: + # make call to next link with the client's api-version + _parsed_next_link = urllib.parse.urlparse(next_link) + _next_request_params = case_insensitive_dict( + { + key: [urllib.parse.quote(v) for v in value] + for key, value in urllib.parse.parse_qs(_parsed_next_link.query).items() + } + ) + _next_request_params["api-version"] = self._config.api_version + _request = HttpRequest( + "GET", urllib.parse.urljoin(next_link, _parsed_next_link.path), params=_next_request_params + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + return _request + + async def extract_data(pipeline_response): + deserialized = pipeline_response.http_response.json() + list_of_elem = _deserialize(List[_models.DeidentificationJob], deserialized["value"]) + if cls: + list_of_elem = cls(list_of_elem) # type: ignore + return deserialized.get("nextLink") or None, AsyncList(list_of_elem) + + async def get_next(next_link=None): + _request = prepare_request(next_link) + + _stream = False + pipeline_response: PipelineResponse = await self._client._pipeline.run( # type: ignore # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + response = pipeline_response.http_response + + if response.status_code not in [200]: + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + return pipeline_response + + return AsyncItemPaged(get_next, extract_data) + + @distributed_trace + def list_job_documents( + self, name: str, *, continuation_token_parameter: Optional[str] = None, **kwargs: Any + ) -> AsyncIterable["_models.DocumentDetails"]: + """List processed documents within a job. + + Resource list operation template. + + :param name: The name of a job. Required. + :type name: str + :keyword continuation_token_parameter: Token to continue a previous query. Default value is + None. + :paramtype continuation_token_parameter: str + :return: An iterator like instance of DocumentDetails + :rtype: + ~azure.core.async_paging.AsyncItemPaged[~azure.health.deidentification.models.DocumentDetails] + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "id": "str", + "input": { + "etag": "str", + "path": "str" + }, + "status": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "output": { + "etag": "str", + "path": "str" + } + } + """ + _headers = kwargs.pop("headers", {}) or {} + _params = kwargs.pop("params", {}) or {} + + maxpagesize = kwargs.pop("maxpagesize", None) + cls: ClsType[List[_models.DocumentDetails]] = kwargs.pop("cls", None) + + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + def prepare_request(next_link=None): + if not next_link: + + _request = build_deidentification_list_job_documents_request( + name=name, + maxpagesize=maxpagesize, + continuation_token_parameter=continuation_token_parameter, + api_version=self._config.api_version, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + else: + # make call to next link with the client's api-version + _parsed_next_link = urllib.parse.urlparse(next_link) + _next_request_params = case_insensitive_dict( + { + key: [urllib.parse.quote(v) for v in value] + for key, value in urllib.parse.parse_qs(_parsed_next_link.query).items() + } + ) + _next_request_params["api-version"] = self._config.api_version + _request = HttpRequest( + "GET", urllib.parse.urljoin(next_link, _parsed_next_link.path), params=_next_request_params + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + return _request + + async def extract_data(pipeline_response): + deserialized = pipeline_response.http_response.json() + list_of_elem = _deserialize(List[_models.DocumentDetails], deserialized["value"]) + if cls: + list_of_elem = cls(list_of_elem) # type: ignore + return deserialized.get("nextLink") or None, AsyncList(list_of_elem) + + async def get_next(next_link=None): + _request = prepare_request(next_link) + + _stream = False + pipeline_response: PipelineResponse = await self._client._pipeline.run( # type: ignore # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + response = pipeline_response.http_response + + if response.status_code not in [200]: + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + return pipeline_response + + return AsyncItemPaged(get_next, extract_data) + + @distributed_trace_async + async def cancel_job(self, name: str, **kwargs: Any) -> _models.DeidentificationJob: + """Cancel a de-identification job. + + Cancels a job that is in progress. + + The job will be marked as canceled and the service will stop processing the job. The service + will not delete any documents that have already been processed. + + If the job is already complete, this will have no effect. + + :param name: The name of a job. Required. + :type name: str + :return: DeidentificationJob. The DeidentificationJob is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationJob + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "createdAt": "2020-02-20 00:00:00", + "lastUpdatedAt": "2020-02-20 00:00:00", + "name": "str", + "sourceLocation": { + "location": "str", + "prefix": "str", + "extensions": [ + "str" + ] + }, + "status": "str", + "targetLocation": { + "location": "str", + "prefix": "str" + }, + "dataType": "str", + "error": { + "code": "str", + "message": "str", + "details": [ + ... + ], + "innererror": { + "code": "str", + "innererror": ... + }, + "target": "str" + }, + "operation": "str", + "redactionFormat": "str", + "startedAt": "2020-02-20 00:00:00", + "summary": { + "bytesProcessed": 0, + "canceled": 0, + "failed": 0, + "successful": 0, + "total": 0 + } + } + """ + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + _headers = kwargs.pop("headers", {}) or {} + _params = kwargs.pop("params", {}) or {} + + cls: ClsType[_models.DeidentificationJob] = kwargs.pop("cls", None) + + _request = build_deidentification_cancel_job_request( + name=name, + api_version=self._config.api_version, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + _stream = kwargs.pop("stream", False) + pipeline_response: PipelineResponse = await self._client._pipeline.run( # type: ignore # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + + response = pipeline_response.http_response + + if response.status_code not in [200]: + if _stream: + await response.read() # Load the body in memory and close the socket + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + response_headers = {} + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + + if _stream: + deserialized = response.iter_bytes() + else: + deserialized = _deserialize(_models.DeidentificationJob, response.json()) + + if cls: + return cls(pipeline_response, deserialized, response_headers) # type: ignore + + return deserialized # type: ignore + + @distributed_trace_async + async def delete_job(self, name: str, **kwargs: Any) -> None: # pylint: disable=inconsistent-return-statements + """Delete a de-identification job. + + Removes the record of the job from the service. Does not delete any documents. + + :param name: The name of a job. Required. + :type name: str + :return: None + :rtype: None + :raises ~azure.core.exceptions.HttpResponseError: + """ + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + _headers = kwargs.pop("headers", {}) or {} + _params = kwargs.pop("params", {}) or {} + + cls: ClsType[None] = kwargs.pop("cls", None) + + _request = build_deidentification_delete_job_request( + name=name, + api_version=self._config.api_version, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + _stream = False + pipeline_response: PipelineResponse = await self._client._pipeline.run( # type: ignore # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + + response = pipeline_response.http_response + + if response.status_code not in [204]: + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + response_headers = {} + response_headers["x-ms-client-request-id"] = self._deserialize( + "str", response.headers.get("x-ms-client-request-id") + ) + + if cls: + return cls(pipeline_response, None, response_headers) # type: ignore + + @overload + async def deidentify( + self, body: _models.DeidentificationContent, *, content_type: str = "application/json", **kwargs: Any + ) -> _models.DeidentificationResult: + """De-identify text. + + A remote procedure call (RPC) operation. + + :param body: Request body for de-identification operation. Required. + :type body: ~azure.health.deidentification.models.DeidentificationContent + :keyword content_type: Body Parameter content-type. Content type parameter for JSON body. + Default value is "application/json". + :paramtype content_type: str + :return: DeidentificationResult. The DeidentificationResult is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationResult + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # JSON input template you can fill out and use as your body input. + body = { + "inputText": "str", + "dataType": "str", + "operation": "str", + "redactionFormat": "str" + } + + # response body for status code(s): 200 + response == { + "outputText": "str", + "taggerResult": { + "entities": [ + { + "category": "str", + "length": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "offset": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "confidenceScore": 0.0, + "text": "str" + } + ], + "etag": "str", + "path": "str" + } + } + """ + + @overload + async def deidentify( + self, body: JSON, *, content_type: str = "application/json", **kwargs: Any + ) -> _models.DeidentificationResult: + """De-identify text. + + A remote procedure call (RPC) operation. + + :param body: Request body for de-identification operation. Required. + :type body: JSON + :keyword content_type: Body Parameter content-type. Content type parameter for JSON body. + Default value is "application/json". + :paramtype content_type: str + :return: DeidentificationResult. The DeidentificationResult is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationResult + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "outputText": "str", + "taggerResult": { + "entities": [ + { + "category": "str", + "length": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "offset": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "confidenceScore": 0.0, + "text": "str" + } + ], + "etag": "str", + "path": "str" + } + } + """ + + @overload + async def deidentify( + self, body: IO[bytes], *, content_type: str = "application/json", **kwargs: Any + ) -> _models.DeidentificationResult: + """De-identify text. + + A remote procedure call (RPC) operation. + + :param body: Request body for de-identification operation. Required. + :type body: IO[bytes] + :keyword content_type: Body Parameter content-type. Content type parameter for binary body. + Default value is "application/json". + :paramtype content_type: str + :return: DeidentificationResult. The DeidentificationResult is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationResult + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # response body for status code(s): 200 + response == { + "outputText": "str", + "taggerResult": { + "entities": [ + { + "category": "str", + "length": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "offset": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "confidenceScore": 0.0, + "text": "str" + } + ], + "etag": "str", + "path": "str" + } + } + """ + + @distributed_trace_async + async def deidentify( + self, body: Union[_models.DeidentificationContent, JSON, IO[bytes]], **kwargs: Any + ) -> _models.DeidentificationResult: + """De-identify text. + + A remote procedure call (RPC) operation. + + :param body: Request body for de-identification operation. Is one of the following types: + DeidentificationContent, JSON, IO[bytes] Required. + :type body: ~azure.health.deidentification.models.DeidentificationContent or JSON or IO[bytes] + :return: DeidentificationResult. The DeidentificationResult is compatible with MutableMapping + :rtype: ~azure.health.deidentification.models.DeidentificationResult + :raises ~azure.core.exceptions.HttpResponseError: + + Example: + .. code-block:: python + + # JSON input template you can fill out and use as your body input. + body = { + "inputText": "str", + "dataType": "str", + "operation": "str", + "redactionFormat": "str" + } + + # response body for status code(s): 200 + response == { + "outputText": "str", + "taggerResult": { + "entities": [ + { + "category": "str", + "length": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "offset": { + "codePoint": 0, + "utf16": 0, + "utf8": 0 + }, + "confidenceScore": 0.0, + "text": "str" + } + ], + "etag": "str", + "path": "str" + } + } + """ + error_map: MutableMapping[int, Type[HttpResponseError]] = { + 401: ClientAuthenticationError, + 404: ResourceNotFoundError, + 409: ResourceExistsError, + 304: ResourceNotModifiedError, + } + error_map.update(kwargs.pop("error_map", {}) or {}) + + _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {}) + _params = kwargs.pop("params", {}) or {} + + content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("Content-Type", None)) + cls: ClsType[_models.DeidentificationResult] = kwargs.pop("cls", None) + + content_type = content_type or "application/json" + _content = None + if isinstance(body, (IOBase, bytes)): + _content = body + else: + _content = json.dumps(body, cls=SdkJSONEncoder, exclude_readonly=True) # type: ignore + + _request = build_deidentification_deidentify_request( + content_type=content_type, + api_version=self._config.api_version, + content=_content, + headers=_headers, + params=_params, + ) + path_format_arguments = { + "endpoint": self._serialize.url("self._config.endpoint", self._config.endpoint, "str"), + } + _request.url = self._client.format_url(_request.url, **path_format_arguments) + + _stream = kwargs.pop("stream", False) + pipeline_response: PipelineResponse = await self._client._pipeline.run( # type: ignore # pylint: disable=protected-access + _request, stream=_stream, **kwargs + ) + + response = pipeline_response.http_response + + if response.status_code not in [200]: + if _stream: + await response.read() # Load the body in memory and close the socket + map_error(status_code=response.status_code, response=response, error_map=error_map) + raise HttpResponseError(response=response) + + if _stream: + deserialized = response.iter_bytes() + else: + deserialized = _deserialize(_models.DeidentificationResult, response.json()) + + if cls: + return cls(pipeline_response, deserialized, {}) # type: ignore + + return deserialized # type: ignore diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_operations/_patch.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_operations/_patch.py new file mode 100644 index 000000000000..f7dd32510333 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_operations/_patch.py @@ -0,0 +1,20 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ +"""Customize generated code here. + +Follow our quickstart for examples: https://aka.ms/azsdk/python/dpcodegen/python/customize +""" +from typing import List + +__all__: List[str] = [] # Add all objects you want publicly available to users at this package level + + +def patch_sdk(): + """Do not remove from this file. + + `patch_sdk` is a last resort escape hatch that allows you to do customizations + you can't accomplish using the techniques described in + https://aka.ms/azsdk/python/dpcodegen/python/customize + """ diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_patch.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_patch.py new file mode 100644 index 000000000000..f7dd32510333 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_patch.py @@ -0,0 +1,20 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ +"""Customize generated code here. + +Follow our quickstart for examples: https://aka.ms/azsdk/python/dpcodegen/python/customize +""" +from typing import List + +__all__: List[str] = [] # Add all objects you want publicly available to users at this package level + + +def patch_sdk(): + """Do not remove from this file. + + `patch_sdk` is a last resort escape hatch that allows you to do customizations + you can't accomplish using the techniques described in + https://aka.ms/azsdk/python/dpcodegen/python/customize + """ diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_vendor.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_vendor.py new file mode 100644 index 000000000000..39bc7460b3a7 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/aio/_vendor.py @@ -0,0 +1,26 @@ +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from abc import ABC +from typing import TYPE_CHECKING + +from ._configuration import DeidentificationClientConfiguration + +if TYPE_CHECKING: + # pylint: disable=unused-import,ungrouped-imports + from azure.core import AsyncPipelineClient + + from .._serialization import Deserializer, Serializer + + +class DeidentificationClientMixinABC(ABC): + """DO NOT use this class. It is for internal typing use only.""" + + _client: "AsyncPipelineClient" + _config: DeidentificationClientConfiguration + _serialize: "Serializer" + _deserialize: "Deserializer" diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/__init__.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/__init__.py new file mode 100644 index 000000000000..2bbbe6e08cab --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/__init__.py @@ -0,0 +1,53 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from ._models import DeidentificationContent +from ._models import DeidentificationJob +from ._models import DeidentificationResult +from ._models import DocumentDetails +from ._models import DocumentLocation +from ._models import Error +from ._models import InnerError +from ._models import JobSummary +from ._models import PhiEntity +from ._models import PhiTaggerResult +from ._models import SourceStorageLocation +from ._models import StringIndex +from ._models import TargetStorageLocation + +from ._enums import DocumentDataType +from ._enums import JobStatus +from ._enums import OperationState +from ._enums import OperationType +from ._enums import PhiCategory +from ._patch import __all__ as _patch_all +from ._patch import * # pylint: disable=unused-wildcard-import +from ._patch import patch_sdk as _patch_sdk + +__all__ = [ + "DeidentificationContent", + "DeidentificationJob", + "DeidentificationResult", + "DocumentDetails", + "DocumentLocation", + "Error", + "InnerError", + "JobSummary", + "PhiEntity", + "PhiTaggerResult", + "SourceStorageLocation", + "StringIndex", + "TargetStorageLocation", + "DocumentDataType", + "JobStatus", + "OperationState", + "OperationType", + "PhiCategory", +] +__all__.extend([p for p in _patch_all if p not in __all__]) +_patch_sdk() diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/_enums.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/_enums.py new file mode 100644 index 000000000000..c05e0003b5b7 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/_enums.py @@ -0,0 +1,124 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +from enum import Enum +from azure.core import CaseInsensitiveEnumMeta + + +class DocumentDataType(str, Enum, metaclass=CaseInsensitiveEnumMeta): + """Enum of supported Data Types.""" + + PLAINTEXT = "Plaintext" + """Plain text data type.""" + + +class JobStatus(str, Enum, metaclass=CaseInsensitiveEnumMeta): + """List of statuses a job can have.""" + + NOT_STARTED = "NotStarted" + """Job has been submitted and is waiting to be processed.""" + RUNNING = "Running" + """Job has been started.""" + SUCCEEDED = "Succeeded" + """Job has completed successfully. All documents have succeeded.""" + PARTIAL_FAILED = "PartialFailed" + """Job has completed with at least a single document failing.""" + FAILED = "Failed" + """Job has completed with all documents failing, or a validation failure.""" + CANCELED = "Canceled" + """Job has been canceled after user request.""" + + +class OperationState(str, Enum, metaclass=CaseInsensitiveEnumMeta): + """Enum describing allowed operation states.""" + + NOT_STARTED = "NotStarted" + """The operation has not started.""" + RUNNING = "Running" + """The operation is in progress.""" + SUCCEEDED = "Succeeded" + """The operation has completed successfully.""" + FAILED = "Failed" + """The operation has failed.""" + CANCELED = "Canceled" + """The operation has been canceled by the user.""" + + +class OperationType(str, Enum, metaclass=CaseInsensitiveEnumMeta): + """Enum of supported Operation Types.""" + + REDACT = "Redact" + """Redact Operation will remove all entities of PHI and replace them with a placeholder value.""" + SURROGATE = "Surrogate" + """Surrogation Operation will replace all entities of PHI with a surrogate value.""" + TAG = "Tag" + """Tag Operation will detect all entities of PHI, their type, and return their locations in the + document.""" + + +class PhiCategory(str, Enum, metaclass=CaseInsensitiveEnumMeta): + """List of PHI Entities.""" + + UNKNOWN = "Unknown" + """Unknown PHI Type.""" + ACCOUNT = "Account" + """Account Number.""" + AGE = "Age" + """Age.""" + BIO_I_D = "BioID" + """Biological Identifier, such as a fingerprint or retinal scan.""" + CITY = "City" + """City.""" + COUNTRY_OR_REGION = "CountryOrRegion" + """Country or Region.""" + DATE = "Date" + """Date.""" + DEVICE = "Device" + """Device ID or serial numbers.""" + DOCTOR = "Doctor" + """Doctor's Name.""" + EMAIL = "Email" + """Email Addresses.""" + FAX = "Fax" + """Fax Number.""" + HEALTH_PLAN = "HealthPlan" + """Health Plan ID Numbers.""" + HOSPITAL = "Hospital" + """Hospital Name.""" + I_D_NUM = "IDNum" + """Id Number, eg. passport number.""" + I_P_ADDRESS = "IPAddress" + """IP Address.""" + LICENSE = "License" + """License, eg. Driver's license or medical license.""" + LOCATION_OTHER = "LocationOther" + """Location Other, eg. Golden Gate Park.""" + MEDICAL_RECORD = "MedicalRecord" + """Medical Record Number.""" + ORGANIZATION = "Organization" + """Organization, eg. Microsoft.""" + PATIENT = "Patient" + """Patient Name.""" + PHONE = "Phone" + """Phone Number.""" + PROFESSION = "Profession" + """Profession.""" + SOCIAL_SECURITY = "SocialSecurity" + """Social Security Number.""" + STATE = "State" + """State.""" + STREET = "Street" + """Street.""" + URL = "Url" + """Web URL.""" + USERNAME = "Username" + """Usernames, eg. a social media handle.""" + VEHICLE = "Vehicle" + """Vehicle IDs, eg. license plate or VIN number.""" + ZIP = "Zip" + """Zip Code.""" diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/_models.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/_models.py new file mode 100644 index 000000000000..2929c7e9b5d3 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/_models.py @@ -0,0 +1,630 @@ +# coding=utf-8 +# pylint: disable=too-many-lines +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- + +import datetime +from typing import Any, List, Mapping, Optional, TYPE_CHECKING, Union, overload + +from .. import _model_base +from .._model_base import rest_field + +if TYPE_CHECKING: + # pylint: disable=unused-import,ungrouped-imports + from .. import models as _models + + +class DeidentificationContent(_model_base.Model): + """Request body for de-identification operation. + + All required parameters must be populated in order to send to server. + + :ivar input_text: Input text to de-identify. Required. + :vartype input_text: str + :ivar operation: Operation to perform on the input. Known values are: "Redact", "Surrogate", + and "Tag". + :vartype operation: str or ~azure.health.deidentification.models.OperationType + :ivar data_type: Data type of the input. "Plaintext" + :vartype data_type: str or ~azure.health.deidentification.models.DocumentDataType + :ivar redaction_format: Format of the redacted output. Only valid when OperationType is + "Redact". + :vartype redaction_format: str + """ + + input_text: str = rest_field(name="inputText") + """Input text to de-identify. Required.""" + operation: Optional[Union[str, "_models.OperationType"]] = rest_field() + """Operation to perform on the input. Known values are: \"Redact\", \"Surrogate\", and \"Tag\".""" + data_type: Optional[Union[str, "_models.DocumentDataType"]] = rest_field(name="dataType") + """Data type of the input. \"Plaintext\"""" + redaction_format: Optional[str] = rest_field(name="redactionFormat") + """Format of the redacted output. Only valid when OperationType is \"Redact\".""" + + @overload + def __init__( + self, + *, + input_text: str, + operation: Optional[Union[str, "_models.OperationType"]] = None, + data_type: Optional[Union[str, "_models.DocumentDataType"]] = None, + redaction_format: Optional[str] = None, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class DeidentificationJob(_model_base.Model): # pylint: disable=too-many-instance-attributes + """A job containing a batch of documents to de-identify. + + Readonly variables are only populated by the server, and will be ignored when sending a request. + + All required parameters must be populated in order to send to server. + + :ivar name: The name of a job. Required. + :vartype name: str + :ivar source_location: Storage location to perform the operation on. Required. + :vartype source_location: ~azure.health.deidentification.models.SourceStorageLocation + :ivar target_location: Target location to store output of operation. Required. + :vartype target_location: ~azure.health.deidentification.models.TargetStorageLocation + :ivar operation: Operation to perform on the input documents. Known values are: "Redact", + "Surrogate", and "Tag". + :vartype operation: str or ~azure.health.deidentification.models.OperationType + :ivar data_type: Data type of the input documents. "Plaintext" + :vartype data_type: str or ~azure.health.deidentification.models.DocumentDataType + :ivar redaction_format: Format of the redacted output. Only valid when Operation is Redact. + :vartype redaction_format: str + :ivar status: Current status of a job. Required. Known values are: "NotStarted", "Running", + "Succeeded", "PartialFailed", "Failed", and "Canceled". + :vartype status: str or ~azure.health.deidentification.models.JobStatus + :ivar error: Error when job fails in it's entirety. + :vartype error: ~azure.health.deidentification.models.Error + :ivar last_updated_at: Date and time when the job was completed. + + If the job is canceled, this is the time when the job was canceled. + + If the job failed, this is the time when the job failed. Required. + :vartype last_updated_at: ~datetime.datetime + :ivar created_at: Date and time when the job was created. Required. + :vartype created_at: ~datetime.datetime + :ivar started_at: Date and time when the job was started. + :vartype started_at: ~datetime.datetime + :ivar summary: Summary of a job. Exists only when the job is completed. + :vartype summary: ~azure.health.deidentification.models.JobSummary + """ + + name: str = rest_field(visibility=["read"]) + """The name of a job. Required.""" + source_location: "_models.SourceStorageLocation" = rest_field(name="sourceLocation") + """Storage location to perform the operation on. Required.""" + target_location: "_models.TargetStorageLocation" = rest_field(name="targetLocation") + """Target location to store output of operation. Required.""" + operation: Optional[Union[str, "_models.OperationType"]] = rest_field() + """Operation to perform on the input documents. Known values are: \"Redact\", \"Surrogate\", and + \"Tag\".""" + data_type: Optional[Union[str, "_models.DocumentDataType"]] = rest_field(name="dataType") + """Data type of the input documents. \"Plaintext\"""" + redaction_format: Optional[str] = rest_field(name="redactionFormat") + """Format of the redacted output. Only valid when Operation is Redact.""" + status: Union[str, "_models.JobStatus"] = rest_field(visibility=["read"]) + """Current status of a job. Required. Known values are: \"NotStarted\", \"Running\", + \"Succeeded\", \"PartialFailed\", \"Failed\", and \"Canceled\".""" + error: Optional["_models.Error"] = rest_field(visibility=["read"]) + """Error when job fails in it's entirety.""" + last_updated_at: datetime.datetime = rest_field(name="lastUpdatedAt", visibility=["read"], format="rfc3339") + """Date and time when the job was completed. + + If the job is canceled, this is the time when the job was canceled. + + If the job failed, this is the time when the job failed. Required.""" + created_at: datetime.datetime = rest_field(name="createdAt", visibility=["read"], format="rfc3339") + """Date and time when the job was created. Required.""" + started_at: Optional[datetime.datetime] = rest_field(name="startedAt", visibility=["read"], format="rfc3339") + """Date and time when the job was started.""" + summary: Optional["_models.JobSummary"] = rest_field(visibility=["read"]) + """Summary of a job. Exists only when the job is completed.""" + + @overload + def __init__( + self, + *, + source_location: "_models.SourceStorageLocation", + target_location: "_models.TargetStorageLocation", + operation: Optional[Union[str, "_models.OperationType"]] = None, + data_type: Optional[Union[str, "_models.DocumentDataType"]] = None, + redaction_format: Optional[str] = None, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class DeidentificationResult(_model_base.Model): + """Response body for de-identification operation. + + :ivar output_text: Output text after de-identification. Not available for "Tag" operation. + :vartype output_text: str + :ivar tagger_result: Result of the "Tag" operation. Only available for "Tag" Operation. + :vartype tagger_result: ~azure.health.deidentification.models.PhiTaggerResult + """ + + output_text: Optional[str] = rest_field(name="outputText") + """Output text after de-identification. Not available for \"Tag\" operation.""" + tagger_result: Optional["_models.PhiTaggerResult"] = rest_field(name="taggerResult") + """Result of the \"Tag\" operation. Only available for \"Tag\" Operation.""" + + @overload + def __init__( + self, + *, + output_text: Optional[str] = None, + tagger_result: Optional["_models.PhiTaggerResult"] = None, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class DocumentDetails(_model_base.Model): + """Details of a single document in a job. + + Readonly variables are only populated by the server, and will be ignored when sending a request. + + + :ivar id: Id of the document details. Required. + :vartype id: str + :ivar input: Location for the input. Required. + :vartype input: ~azure.health.deidentification.models.DocumentLocation + :ivar output: Location for the output. + :vartype output: ~azure.health.deidentification.models.DocumentLocation + :ivar status: Status of the document. Required. Known values are: "NotStarted", "Running", + "Succeeded", "Failed", and "Canceled". + :vartype status: str or ~azure.health.deidentification.models.OperationState + :ivar error: Error when document fails. + :vartype error: ~azure.health.deidentification.models.Error + """ + + id: str = rest_field(visibility=["read"]) + """Id of the document details. Required.""" + input: "_models.DocumentLocation" = rest_field() + """Location for the input. Required.""" + output: Optional["_models.DocumentLocation"] = rest_field() + """Location for the output.""" + status: Union[str, "_models.OperationState"] = rest_field() + """Status of the document. Required. Known values are: \"NotStarted\", \"Running\", \"Succeeded\", + \"Failed\", and \"Canceled\".""" + error: Optional["_models.Error"] = rest_field() + """Error when document fails.""" + + @overload + def __init__( + self, + *, + input: "_models.DocumentLocation", + status: Union[str, "_models.OperationState"], + output: Optional["_models.DocumentLocation"] = None, + error: Optional["_models.Error"] = None, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class DocumentLocation(_model_base.Model): + """Location of a document. + + Readonly variables are only populated by the server, and will be ignored when sending a request. + + + :ivar path: Path of document in storage. Required. + :vartype path: str + :ivar etag: The entity tag for this resource. Required. + :vartype etag: str + """ + + path: str = rest_field() + """Path of document in storage. Required.""" + etag: str = rest_field(visibility=["read"]) + """The entity tag for this resource. Required.""" + + @overload + def __init__( + self, + *, + path: str, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class Error(_model_base.Model): + """The error object. + + All required parameters must be populated in order to send to server. + + :ivar code: One of a server-defined set of error codes. Required. + :vartype code: str + :ivar message: A human-readable representation of the error. Required. + :vartype message: str + :ivar target: The target of the error. + :vartype target: str + :ivar details: An array of details about specific errors that led to this reported error. + :vartype details: list[~azure.health.deidentification.models.Error] + :ivar innererror: An object containing more specific information than the current object about + the error. + :vartype innererror: ~azure.health.deidentification.models.InnerError + """ + + code: str = rest_field() + """One of a server-defined set of error codes. Required.""" + message: str = rest_field() + """A human-readable representation of the error. Required.""" + target: Optional[str] = rest_field() + """The target of the error.""" + details: Optional[List["_models.Error"]] = rest_field() + """An array of details about specific errors that led to this reported error.""" + innererror: Optional["_models.InnerError"] = rest_field() + """An object containing more specific information than the current object about the error.""" + + @overload + def __init__( + self, + *, + code: str, + message: str, + target: Optional[str] = None, + details: Optional[List["_models.Error"]] = None, + innererror: Optional["_models.InnerError"] = None, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class InnerError(_model_base.Model): + """An object containing more specific information about the error. As per Microsoft One API + guidelines - + https://github.com/Microsoft/api-guidelines/blob/vNext/Guidelines.md#7102-error-condition-responses. + + :ivar code: One of a server-defined set of error codes. + :vartype code: str + :ivar innererror: Inner error. + :vartype innererror: ~azure.health.deidentification.models.InnerError + """ + + code: Optional[str] = rest_field() + """One of a server-defined set of error codes.""" + innererror: Optional["_models.InnerError"] = rest_field() + """Inner error.""" + + @overload + def __init__( + self, + *, + code: Optional[str] = None, + innererror: Optional["_models.InnerError"] = None, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class JobSummary(_model_base.Model): + """Summary metrics of a job. + + + :ivar successful: Number of documents that have completed. Required. + :vartype successful: int + :ivar failed: Number of documents that have failed. Required. + :vartype failed: int + :ivar canceled: Number of documents that have been canceled. Required. + :vartype canceled: int + :ivar total: Number of documents total. Required. + :vartype total: int + :ivar bytes_processed: Number of bytes processed. Required. + :vartype bytes_processed: int + """ + + successful: int = rest_field() + """Number of documents that have completed. Required.""" + failed: int = rest_field() + """Number of documents that have failed. Required.""" + canceled: int = rest_field() + """Number of documents that have been canceled. Required.""" + total: int = rest_field() + """Number of documents total. Required.""" + bytes_processed: int = rest_field(name="bytesProcessed") + """Number of bytes processed. Required.""" + + @overload + def __init__( + self, + *, + successful: int, + failed: int, + canceled: int, + total: int, + bytes_processed: int, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class PhiEntity(_model_base.Model): + """PHI Entity tag in the input. + + + :ivar category: PHI Category of the entity. Required. Known values are: "Unknown", "Account", + "Age", "BioID", "City", "CountryOrRegion", "Date", "Device", "Doctor", "Email", "Fax", + "HealthPlan", "Hospital", "IDNum", "IPAddress", "License", "LocationOther", "MedicalRecord", + "Organization", "Patient", "Phone", "Profession", "SocialSecurity", "State", "Street", "Url", + "Username", "Vehicle", and "Zip". + :vartype category: str or ~azure.health.deidentification.models.PhiCategory + :ivar offset: Starting index of the location from within the input text. Required. + :vartype offset: ~azure.health.deidentification.models.StringIndex + :ivar length: Length of the input text. Required. + :vartype length: ~azure.health.deidentification.models.StringIndex + :ivar text: Text of the entity. + :vartype text: str + :ivar confidence_score: Confidence score of the category match. + :vartype confidence_score: float + """ + + category: Union[str, "_models.PhiCategory"] = rest_field() + """PHI Category of the entity. Required. Known values are: \"Unknown\", \"Account\", \"Age\", + \"BioID\", \"City\", \"CountryOrRegion\", \"Date\", \"Device\", \"Doctor\", \"Email\", \"Fax\", + \"HealthPlan\", \"Hospital\", \"IDNum\", \"IPAddress\", \"License\", \"LocationOther\", + \"MedicalRecord\", \"Organization\", \"Patient\", \"Phone\", \"Profession\", + \"SocialSecurity\", \"State\", \"Street\", \"Url\", \"Username\", \"Vehicle\", and \"Zip\".""" + offset: "_models.StringIndex" = rest_field() + """Starting index of the location from within the input text. Required.""" + length: "_models.StringIndex" = rest_field() + """Length of the input text. Required.""" + text: Optional[str] = rest_field() + """Text of the entity.""" + confidence_score: Optional[float] = rest_field(name="confidenceScore") + """Confidence score of the category match.""" + + @overload + def __init__( + self, + *, + category: Union[str, "_models.PhiCategory"], + offset: "_models.StringIndex", + length: "_models.StringIndex", + text: Optional[str] = None, + confidence_score: Optional[float] = None, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class PhiTaggerResult(_model_base.Model): + """Result of the "Tag" operation. + + + :ivar entities: List of entities detected in the input. Required. + :vartype entities: list[~azure.health.deidentification.models.PhiEntity] + :ivar path: Path to the document in storage. + :vartype path: str + :ivar etag: The entity tag for this resource. + :vartype etag: str + """ + + entities: List["_models.PhiEntity"] = rest_field() + """List of entities detected in the input. Required.""" + path: Optional[str] = rest_field() + """Path to the document in storage.""" + etag: Optional[str] = rest_field() + """The entity tag for this resource.""" + + @overload + def __init__( + self, + *, + entities: List["_models.PhiEntity"], + path: Optional[str] = None, + etag: Optional[str] = None, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class SourceStorageLocation(_model_base.Model): + """Storage location. + + All required parameters must be populated in order to send to server. + + :ivar location: URL to storage location. Required. + :vartype location: str + :ivar prefix: Prefix to filter path by. Required. + :vartype prefix: str + :ivar extensions: List of extensions to filter path by. + :vartype extensions: list[str] + """ + + location: str = rest_field() + """URL to storage location. Required.""" + prefix: str = rest_field() + """Prefix to filter path by. Required.""" + extensions: Optional[List[str]] = rest_field() + """List of extensions to filter path by.""" + + @overload + def __init__( + self, + *, + location: str, + prefix: str, + extensions: Optional[List[str]] = None, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class StringIndex(_model_base.Model): + """String index encoding model. + + + :ivar utf8: The offset or length of the substring in UTF-8 encoding. Required. + :vartype utf8: int + :ivar utf16: The offset or length of the substring in UTF-16 encoding. + + Primary encoding used by .NET, Java, and JavaScript. Required. + :vartype utf16: int + :ivar code_point: The offset or length of the substring in CodePoint encoding. + + Primary encoding used by Python. Required. + :vartype code_point: int + """ + + utf8: int = rest_field() + """The offset or length of the substring in UTF-8 encoding. Required.""" + utf16: int = rest_field() + """The offset or length of the substring in UTF-16 encoding. + + Primary encoding used by .NET, Java, and JavaScript. Required.""" + code_point: int = rest_field(name="codePoint") + """The offset or length of the substring in CodePoint encoding. + + Primary encoding used by Python. Required.""" + + @overload + def __init__( + self, + *, + utf8: int, + utf16: int, + code_point: int, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) + + +class TargetStorageLocation(_model_base.Model): + """Storage location. + + All required parameters must be populated in order to send to server. + + :ivar location: URL to storage location. Required. + :vartype location: str + :ivar prefix: Prefix to filter path by. Required. + :vartype prefix: str + """ + + location: str = rest_field() + """URL to storage location. Required.""" + prefix: str = rest_field() + """Prefix to filter path by. Required.""" + + @overload + def __init__( + self, + *, + location: str, + prefix: str, + ): ... + + @overload + def __init__(self, mapping: Mapping[str, Any]): + """ + :param mapping: raw JSON to initialize the model. + :type mapping: Mapping[str, Any] + """ + + def __init__(self, *args: Any, **kwargs: Any) -> None: # pylint: disable=useless-super-delegation + super().__init__(*args, **kwargs) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/_patch.py b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/_patch.py new file mode 100644 index 000000000000..807491528291 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/models/_patch.py @@ -0,0 +1,24 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ +"""Customize generated code here. + +Follow our quickstart for examples: https://aka.ms/azsdk/python/dpcodegen/python/customize +""" +from typing import TYPE_CHECKING, List + +if TYPE_CHECKING: + # pylint: disable=unused-import,ungrouped-imports + from .. import models as _models + +__all__: List[str] = [] # Add all objects you want publicly available to users at this package level + + +def patch_sdk(): + """Do not remove from this file. + + `patch_sdk` is a last resort escape hatch that allows you to do customizations + you can't accomplish using the techniques described in + https://aka.ms/azsdk/python/dpcodegen/python/customize + """ diff --git a/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/py.typed b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/py.typed new file mode 100644 index 000000000000..e5aff4f83af8 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification/py.typed @@ -0,0 +1 @@ +# Marker file for PEP 561. \ No newline at end of file diff --git a/sdk/healthdataaiservices/azure-health-deidentification/dev_requirements.txt b/sdk/healthdataaiservices/azure-health-deidentification/dev_requirements.txt new file mode 100644 index 000000000000..c82827bb56f4 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/dev_requirements.txt @@ -0,0 +1,4 @@ +-e ../../../tools/azure-sdk-tools +../../core/azure-core +../../identity/azure-identity +aiohttp \ No newline at end of file diff --git a/sdk/healthdataaiservices/azure-health-deidentification/samples/README.md b/sdk/healthdataaiservices/azure-health-deidentification/samples/README.md new file mode 100644 index 000000000000..58aa93367e7c --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/samples/README.md @@ -0,0 +1,66 @@ +# Azure Health Deidentification client library for Python +Azure Health Deidentification is Microsoft's solution to anonymize unstructured health text. + +[Source code](https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/healthdataaiservices/azure-health-deidentification/azure/health/deidentification) + + +| [Samples](https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/healthdataaiservices/azure-health-deidentification/samples) + + +## Getting started + +### Prerequisites +* Python 3.8 or later is required to use this package. For more details, please read our page on [Azure SDK for Python version support policy](https://github.com/Azure/azure-sdk-for-python/wiki/Azure-SDKs-Python-version-support-policy). +* You must have an [Azure subscription](https://azure.microsoft.com/free/) and an +**Azure Deidentification Service** to use this package. + +### Install the package +Install the Azure Health Deidentification client library for Python with [pip](https://pypi.org/project/pip/): + +```bash +pip install azure-health-deidentification +``` + +### Create a Deidentification Service +If you wish to create a new storage account, you can use the +[Azure Portal](https://docs.microsoft.com/azure/storage/common/storage-quickstart-create-account?tabs=azure-portal). + +### Create the client +In order to create a Deidentification client you must obtain the **Service URL** from your Azure Deidentification Service + +```python + endpoint = os.environ["AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT"] + endpoint = endpoint.replace("https://", "") + print(endpoint) + # example: fuf4h4bxg5b0d0dr.api.cac001.deid.azure.com + + credential = DefaultAzureCredential() + + client = DeidentificationClient(endpoint, DefaultAzureCredential()) +``` + +### Deidentify a string + +```python + body = DeidentificationContent(input_text="Hello, my name is John Smith.") + + result: DeidentificationResult = client.deidentify(body) + + print(f'Original Text: "{body.input_text}"') + print(f'Deidentified Text: "{result.output_text}"') +``` + +## Key concepts +Operation Modes: +- Tag: Will return a structure of offset and length with the PHI category of the related text spans. +- Redact: Will return output text with placeholder stubbed text. ex. `[name]` +- Surrogate: Will return output text with synthetic replacements. + - `My name is John Smith` + - `My name is Tom Jones` + +## 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 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. \ No newline at end of file diff --git a/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_create_and_wait_job_async.py b/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_create_and_wait_job_async.py new file mode 100644 index 000000000000..e1816415c037 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_create_and_wait_job_async.py @@ -0,0 +1,81 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ + +""" +FILE: sample_create_and_wait_job_async.py + +DESCRIPTION: + This sample demonstrates the most simple job-based deidentification scenario. + It takes a blob uri as input and an input prefix. It will create a job and wait for the job to complete. + +USAGE: + python sample_create_and_wait_job_async.py + + Set the environment variables with your own values before running the sample: + 1) AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT - the endpoint to your Deidentification Service resource. + 2) AZURE_STORAGE_ACCOUNT_LOCATION - the location of the storage account where the input and output files are stored. + This is an Azure Storage url to a container which must be configured with Managed Identity.. + 3) INPUT_PREFIX - the prefix of the input files in the storage account. +""" +import asyncio + +import uuid + + +async def sample_create_and_wait_job_async(): + # [START sample_create_and_wait_job_async] + import os + from azure.identity.aio import DefaultAzureCredential + from azure.health.deidentification.aio import DeidentificationClient + from azure.health.deidentification.models import ( + DeidentificationJob, + SourceStorageLocation, + TargetStorageLocation, + ) + from azure.core.polling import AsyncLROPoller + + endpoint = os.environ["AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT"] + endpoint = endpoint.replace("https://", "") + + storage_location = os.environ["AZURE_STORAGE_ACCOUNT_LOCATION"] + inputPrefix = os.environ["INPUT_PREFIX"] + outputPrefix = "_output" + + credential = DefaultAzureCredential() + + client = DeidentificationClient(endpoint, credential) + + jobname = f"sample-job-{uuid.uuid4().hex[:8]}" + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix=inputPrefix, + ), + target_location=TargetStorageLocation( + location=storage_location, prefix=outputPrefix + ), + ) + + async with client: + lro: AsyncLROPoller = await client.begin_create_job(jobname, job) + finished_job: DeidentificationJob = await lro.result() + + await credential.close() + + print(f"Job Name: {finished_job.name}") + print(f"Job Status: {finished_job.status}") # Succeeded + print( + f"File Count: {finished_job.summary.total if finished_job.summary is not None else 0}" + ) + # [END sample_create_and_wait_job_async] + + +async def main(): + await sample_create_and_wait_job_async() + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_list_job_files_async.py b/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_list_job_files_async.py new file mode 100644 index 000000000000..198153982a6c --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_list_job_files_async.py @@ -0,0 +1,87 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ + +""" +FILE: sample_list_job_documents_async.py + +DESCRIPTION: + This sample demonstrates how to create a job, wait for it to finish, and then list the files associated with the job. + +USAGE: + python sample_list_job_documents_async.py + + Set the environment variables with your own values before running the sample: + 1) AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT - the endpoint to your Deidentification Service resource. + 2) AZURE_STORAGE_ACCOUNT_LOCATION - the location of the storage account where the input and output files are stored. + This is an Azure Storage url to a container which must be configured with Managed Identity.. + 3) INPUT_PREFIX - the prefix of the input files in the storage account. +""" + +import asyncio +import uuid + + +async def sample_list_job_documents_async(): + # [START sample_list_job_documents_async] + import os + from azure.identity.aio import DefaultAzureCredential + from azure.health.deidentification.aio import DeidentificationClient + from azure.health.deidentification.models import ( + DeidentificationJob, + SourceStorageLocation, + TargetStorageLocation, + ) + from azure.core.polling import AsyncLROPoller + + endpoint = os.environ["AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT"] + endpoint = endpoint.replace("https://", "") + + storage_location = os.environ["AZURE_STORAGE_ACCOUNT_LOCATION"] + inputPrefix = os.environ["INPUT_PREFIX"] + outputPrefix = "_output" + + credential = DefaultAzureCredential() + + client = DeidentificationClient(endpoint, credential) + + jobname = f"sample-job-{uuid.uuid4().hex[:8]}" + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix=inputPrefix, + ), + target_location=TargetStorageLocation( + location=storage_location, prefix=outputPrefix + ), + ) + + print(f"Creating job with name: {jobname}") + async with client: + poller: AsyncLROPoller = await client.begin_create_job(jobname, job) + job = await poller.result() + print(f"Job Status: {job.status}") + + files = client.list_job_documents(job.name) + + print("Completed files (Max 10):") + filesToLookThrough = 10 + async for f in files: + print(f"\t - {f.input.path}") + + filesToLookThrough -= 1 + if filesToLookThrough <= 0: + break + + await credential.close() + # [END sample_list_job_documents_async] + + +async def main(): + await sample_list_job_documents_async() + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_list_jobs_async.py b/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_list_jobs_async.py new file mode 100644 index 000000000000..546cff83b471 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_list_jobs_async.py @@ -0,0 +1,60 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ + +""" +FILE: sample_list_jobs_async.py + +DESCRIPTION: + This sample demonstrates how to list the latest 5 jobs in the Deidentification Service resource. + It will create a job and then list it using the list_jobs method. + +USAGE: + python sample_list_jobs_async.py + + Set the environment variables with your own values before running the sample: + 1) AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT - the endpoint to your Deidentification Service resource. + 2) AZURE_STORAGE_ACCOUNT_LOCATION - the location of the storage account where the input and output files are stored. + This is an Azure Storage url to a container which must be configured with Managed Identity.. + 3) INPUT_PREFIX - the prefix of the input files in the storage account. +""" +import asyncio +import uuid + + +async def sample_list_jobs_async(): + # [START sample_list_jobs_async] + import os + from azure.identity.aio import DefaultAzureCredential + from azure.health.deidentification.aio import DeidentificationClient + + endpoint = os.environ["AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT"] + endpoint = endpoint.replace("https://", "") + + credential = DefaultAzureCredential() + + client = DeidentificationClient(endpoint, credential) + + async with client: + jobs = client.list_jobs() + + print("Listing latest 5 jobs:") + jobsToLookThrough = 5 + async for j in jobs: + print(f"Job Name: {j.name}") + + jobsToLookThrough -= 1 + if jobsToLookThrough <= 0: + break + + await credential.close() + # [END sample_list_jobs_async] + + +async def main(): + await sample_list_jobs_async() + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_realtime_deidentification_async.py b/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_realtime_deidentification_async.py new file mode 100644 index 000000000000..02e6813c9199 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/samples/async_samples/sample_realtime_deidentification_async.py @@ -0,0 +1,55 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ + +""" +FILE: sample_realtime_deidentification_async.py + +DESCRIPTION: + This sample demonstrates the most simple deidentification scenario. It takes in a string of text and will return + the deidentified text. + +USAGE: + python sample_realtime_deidentification_async.py + + Set the environment variables with your own values before running the sample: + 1) AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT - the endpoint to your Deidentification Service resource. +""" +import asyncio + + +async def sample_realtime_deidentification_async(): + # [START realtime_deidentification_async] + import os + from azure.identity.aio import DefaultAzureCredential + from azure.health.deidentification.aio import DeidentificationClient + from azure.health.deidentification.models import ( + DeidentificationResult, + DeidentificationContent, + ) + + endpoint = os.environ["AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT"] + endpoint = endpoint.replace("https://", "") + + credential = DefaultAzureCredential() + + client = DeidentificationClient(endpoint, credential) + + body = DeidentificationContent(input_text="Hello, my name is John Smith.") + + async with client: + result: DeidentificationResult = await client.deidentify(body) + + await credential.close() + print(f'Original Text: "{body.input_text}"') + print(f'Deidentified Text: "{result.output_text}"') + # [END realtime_deidentification] + + +async def main(): + await sample_realtime_deidentification_async() + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_create_and_wait_job.py b/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_create_and_wait_job.py new file mode 100644 index 000000000000..1c63c38cd86d --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_create_and_wait_job.py @@ -0,0 +1,75 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ + +""" +FILE: sample_create_and_wait_job.py + +DESCRIPTION: + This sample demonstrates the most simple job-based deidentification scenario. + It takes a blob uri as input and an input prefix. It will create a job and wait for the job to complete. + +USAGE: + python sample_create_and_wait_job.py + + Set the environment variables with your own values before running the sample: + 1) AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT - the endpoint to your Deidentification Service resource. + 2) AZURE_STORAGE_ACCOUNT_LOCATION - the location of the storage account where the input and output files are stored. + This is an Azure Storage url to a container which must be configured with Managed Identity.. + 3) INPUT_PREFIX - the prefix of the input files in the storage account. +""" + + +import uuid + + +def sample_create_and_wait_job(): + # [START sample_create_and_wait_job] + import os + from azure.identity import DefaultAzureCredential + from azure.health.deidentification import DeidentificationClient + from azure.health.deidentification.models import ( + DeidentificationJob, + SourceStorageLocation, + TargetStorageLocation, + ) + from azure.core.polling import LROPoller + + endpoint = os.environ["AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT"] + endpoint = endpoint.replace("https://", "") + + storage_location = os.environ["AZURE_STORAGE_ACCOUNT_LOCATION"] + inputPrefix = os.environ["INPUT_PREFIX"] + outputPrefix = "_output" + + credential = DefaultAzureCredential() + + client = DeidentificationClient(endpoint, credential) + + jobname = f"sample-job-{uuid.uuid4().hex[:8]}" + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix=inputPrefix, + ), + target_location=TargetStorageLocation( + location=storage_location, prefix=outputPrefix + ), + ) + + lro: LROPoller = client.begin_create_job(jobname, job) + lro.wait(timeout=60) + + finished_job: DeidentificationJob = lro.result() + print(f"Job Name: {finished_job.name}") + print(f"Job Status: {finished_job.status}") + print( + f"File Count: {finished_job.summary.total if finished_job.summary is not None else 0}" + ) + # [END sample_create_and_wait_job] + + +if __name__ == "__main__": + sample_create_and_wait_job() diff --git a/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_list_job_files.py b/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_list_job_files.py new file mode 100644 index 000000000000..438ebfaa267a --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_list_job_files.py @@ -0,0 +1,83 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ + +""" +FILE: sample_list_job_documents.py + +DESCRIPTION: + This sample demonstrates how to create a job, wait for it to finish, and then list the files associated with the job. + +USAGE: + python sample_list_job_documents.py + + Set the environment variables with your own values before running the sample: + 1) AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT - the endpoint to your Deidentification Service resource. + 2) AZURE_STORAGE_ACCOUNT_LOCATION - the location of the storage account where the input and output files are stored. + This is an Azure Storage url to a container which must be configured with Managed Identity.. + 3) INPUT_PREFIX - the prefix of the input files in the storage account. +""" + + +import uuid + + +def sample_list_job_documents(): + # [START sample_list_job_documents] + import os + from azure.identity import DefaultAzureCredential + from azure.health.deidentification import DeidentificationClient + from azure.health.deidentification.models import ( + DeidentificationJob, + SourceStorageLocation, + TargetStorageLocation, + ) + from azure.core.polling import LROPoller + + endpoint = os.environ["AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT"] + endpoint = endpoint.replace("https://", "") + + storage_location = os.environ["AZURE_STORAGE_ACCOUNT_LOCATION"] + inputPrefix = os.environ["INPUT_PREFIX"] + outputPrefix = "_output" + + credential = DefaultAzureCredential() + + client = DeidentificationClient(endpoint, credential) + + jobname = f"sample-job-{uuid.uuid4().hex[:8]}" + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix=inputPrefix, + ), + target_location=TargetStorageLocation( + location=storage_location, prefix=outputPrefix + ), + ) + + print(f"Creating job with name: {jobname}") + poller: LROPoller = client.begin_create_job(jobname, job) + poller.wait(timeout=60) + + job = poller.result() + print(f"Job Status: {job.status}") + + files = client.list_job_documents(job.name) + + print("Completed files (Max 10):") + filesToLookThrough = 10 + for f in files: + print(f"\t - {f.input.path}") + + filesToLookThrough -= 1 + if filesToLookThrough <= 0: + break + + # [END sample_list_job_documents] + + +if __name__ == "__main__": + sample_list_job_documents() diff --git a/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_list_jobs.py b/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_list_jobs.py new file mode 100644 index 000000000000..4eb70c5c7af0 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_list_jobs.py @@ -0,0 +1,55 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ + +""" +FILE: sample_list_jobs.py + +DESCRIPTION: + This sample demonstrates how to list the latest 5 jobs in the Deidentification Service resource. + It will create a job and then list it using the list_jobs method. + +USAGE: + python sample_list_jobs.py + + Set the environment variables with your own values before running the sample: + 1) AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT - the endpoint to your Deidentification Service resource. + 2) AZURE_STORAGE_ACCOUNT_LOCATION - the location of the storage account where the input and output files are stored. + This is an Azure Storage url to a container which must be configured with Managed Identity.. + 3) INPUT_PREFIX - the prefix of the input files in the storage account. +""" + + +import uuid + + +def sample_list_jobs(): + # [START sample_list_jobs] + import os + from azure.identity import DefaultAzureCredential + from azure.health.deidentification import DeidentificationClient + + endpoint = os.environ["AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT"] + endpoint = endpoint.replace("https://", "") + + credential = DefaultAzureCredential() + + client = DeidentificationClient(endpoint, credential) + + jobs = client.list_jobs() + + print("Listing latest 5 jobs:") + jobsToLookThrough = 5 + for j in jobs: + print(f"Job Name: {j.name}") + + jobsToLookThrough -= 1 + if jobsToLookThrough <= 0: + break + + # [END sample_list_jobs] + + +if __name__ == "__main__": + sample_list_jobs() diff --git a/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_realtime_deidentification.py b/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_realtime_deidentification.py new file mode 100644 index 000000000000..8ebef8c1af61 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/samples/sample_realtime_deidentification.py @@ -0,0 +1,49 @@ +# ------------------------------------ +# Copyright (c) Microsoft Corporation. +# Licensed under the MIT License. +# ------------------------------------ + +""" +FILE: sample_realtime_deidentification.py + +DESCRIPTION: + This sample demonstrates the most simple deidentification scenario. It takes in a string of text and will return + the deidentified text. + +USAGE: + python sample_realtime_deidentification.py + + Set the environment variables with your own values before running the sample: + 1) AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT - the endpoint to your Deidentification Service resource. +""" + + +def sample_realtime_deidentification(): + # [START realtime_deidentification] + import os + from azure.identity import DefaultAzureCredential + from azure.health.deidentification import DeidentificationClient + from azure.health.deidentification.models import ( + DeidentificationResult, + DeidentificationContent, + OperationType, + DocumentDataType, + ) + + endpoint = os.environ["AZURE_HEALTH_DEIDENTIFICATION_ENDPOINT"] + endpoint = endpoint.replace("https://", "") + + credential = DefaultAzureCredential() + + client = DeidentificationClient(endpoint, credential) + + body = DeidentificationContent(input_text="Hello, my name is John Smith.") + + result: DeidentificationResult = client.deidentify(body) + print(f'Original Text: "{body.input_text}"') + print(f'Deidentified Text: "{result.output_text}"') + # [END realtime_deidentification] + + +if __name__ == "__main__": + sample_realtime_deidentification() diff --git a/sdk/healthdataaiservices/azure-health-deidentification/setup.py b/sdk/healthdataaiservices/azure-health-deidentification/setup.py new file mode 100644 index 000000000000..9ca62adf44ad --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/setup.py @@ -0,0 +1,71 @@ +# coding=utf-8 +# -------------------------------------------------------------------------- +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. See License.txt in the project root for license information. +# Code generated by Microsoft (R) Python Code Generator. +# Changes may cause incorrect behavior and will be lost if the code is regenerated. +# -------------------------------------------------------------------------- +# coding: utf-8 + +import os +import re +from setuptools import setup, find_packages + + +PACKAGE_NAME = "azure-health-deidentification" +PACKAGE_PPRINT_NAME = "Azure Health Deidentification" + +# a-b-c => a/b/c +package_folder_path = PACKAGE_NAME.replace("-", "/") + +# Version extraction inspired from 'requests' +with open(os.path.join(package_folder_path, "_version.py"), "r") as fd: + version = re.search(r'^VERSION\s*=\s*[\'"]([^\'"]*)[\'"]', fd.read(), re.MULTILINE).group(1) + +if not version: + raise RuntimeError("Cannot find version information") + + +setup( + name=PACKAGE_NAME, + version=version, + description="Microsoft {} Client Library for Python".format(PACKAGE_PPRINT_NAME), + long_description=open("README.md", "r").read(), + long_description_content_type="text/markdown", + license="MIT License", + author="Microsoft Corporation", + author_email="azpysdkhelp@microsoft.com", + url="https://github.com/Azure/azure-sdk-for-python/tree/main/sdk", + keywords="azure, azure sdk", + classifiers=[ + "Development Status :: 4 - Beta", + "Programming Language :: Python", + "Programming Language :: Python :: 3 :: Only", + "Programming Language :: Python :: 3", + "Programming Language :: Python :: 3.8", + "Programming Language :: Python :: 3.9", + "Programming Language :: Python :: 3.10", + "Programming Language :: Python :: 3.11", + "Programming Language :: Python :: 3.12", + "License :: OSI Approved :: MIT License", + ], + zip_safe=False, + packages=find_packages( + exclude=[ + "tests", + # Exclude packages that will be covered by PEP420 or nspkg + "azure", + "azure.health", + ] + ), + include_package_data=True, + package_data={ + "azure.health.deidentification": ["py.typed"], + }, + install_requires=[ + "isodate>=0.6.1", + "azure-core>=1.30.0", + "typing-extensions>=4.6.0", + ], + python_requires=">=3.8", +) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/test-resources-post.ps1 b/sdk/healthdataaiservices/azure-health-deidentification/test-resources-post.ps1 new file mode 100644 index 000000000000..e0bf9d743ccb --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/test-resources-post.ps1 @@ -0,0 +1,62 @@ +# Copyright (c) Microsoft Corporation. All rights reserved. +# Licensed under the MIT License. + +# This script is used to set up SIP Configuration domains for Azure Communication Services SIP Routing SDK GA tests + +# It is invoked by the https://github.com/Azure/azure-sdk-for-net/blob/main/eng/New-TestResources.ps1 +# script after the ARM template, defined in https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/storage/test-resources.json, +# is finished being deployed. The ARM template is responsible for creating the Storage accounts needed for live tests. + +param ( + [hashtable] $DeploymentOutputs, + [string] $TenantId, + [string] $TestApplicationId, + [string] $TestApplicationSecret +) + +# Retrieve the connection string from environment variables +$resourceGroup = $DeploymentOutputs['HEALTHDATAAISERVICES_RESOURCE_GROUP'] +$storageAccountName = $DeploymentOutputs['HEALTHDATAAISERVICES_STORAGE_ACCOUNT_NAME'] +$containerName = $DeploymentOutputs['HEALTHDATAAISERVICES_STORAGE_CONTAINER_NAME'] + +# Set the local folder path to upload +$localFolderPath = "tests\data\example_patient_1" + +# Check if the connection string is present +if ([string]::IsNullOrWhiteSpace($storageAccountName)) { + Write-Host "Error: Azure Storage Name string not found in environment variables." + exit 1 +} + +# Load the Azure Storage module +Import-Module Az.Storage + +# Connect to the storage account +$storageContext = New-AzStorageContext -StorageAccountName $storageAccountName -UseConnectedAccount + +# FIXME Remove once vpn team fixes the network acl issue +$networkRuleSet = New-Object -TypeName Microsoft.Azure.Commands.Management.Storage.Models.PSNetworkRuleSet +$networkRuleSet.DefaultAction = "Allow" +Set-AzStorageAccount -ResourceGroupName $resourceGroup -Name $storageAccountName -NetworkRuleSet $networkRuleSet + +# Sleep for 30 seconds to allow the network rule to take effect +Write-Host "[Fix] Temporary sleep to allow network rule to take effect." +Start-Sleep -Seconds 30 + +Get-AzStorageContainer -Name $containerName -Context $storageContext + +# Upload the folder and its contents to the container +# Gets last folder name + filename. example_patient_1\doctor_dictation.txt +Get-ChildItem -Path $localFolderPath -Recurse | ForEach-Object { + $relativePath = $_.FullName + $relativePath = $relativePath.Replace("\\", "\") + $folderName = ($relativePath -split "\\")[-2] # Get only the folder name. + $blobName = ($relativePath -split "\\")[-1] # Get only the file name. + $destinationBlob = $blobName -replace ":", "" + + $destinationBlob = "$folderName\$destinationBlob" + Write-Host "Uploading file '$destinationBlob'" + Set-AzStorageBlobContent -File $_.FullName -Container $containerName -Blob $destinationBlob -Context $storageContext -Force +} + +Write-Host "Folder '$localFolderPath' uploaded to container '$containerName' successfully." \ No newline at end of file diff --git a/sdk/healthdataaiservices/azure-health-deidentification/test-resources.bicep b/sdk/healthdataaiservices/azure-health-deidentification/test-resources.bicep new file mode 100644 index 000000000000..a4cccabd07c3 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/test-resources.bicep @@ -0,0 +1,205 @@ +// "id": "/subscriptions/d12535ed-5958-4ce6-8350-b17b3af1d6b1/resourceGroups/oro-billing-exhaust-test/providers/Microsoft.HealthDataAIServices/DeidServices/deid-billing-test", +// "name": "deid-billing-test", +// "type": "microsoft.healthdataaiservices/deidservices", +// "location": "East US 2 EUAP", +// "tags": {}, + +@minLength(10) +param testApplicationOid string + +@minLength(6) +@maxLength(50) +@description('The base resource name.') +param baseName string + +param location string = resourceGroup().location + +@description('The location of the resource. By default, this is the same as the resource group.') +param deidLocation string = 'eastus2euap' +param deidLocationShort string = 'eup' + +param deploymentTime string = utcNow('u') + +var realtimeDataUserRoleId = 'bb6577c4-ea0a-40b2-8962-ea18cb8ecd4e' +var batchDataOwnerRoleId = '8a90fa6b-6997-4a07-8a95-30633a7c97b9' +var storageBlobDataContributor = 'ba92f5b4-2d11-453d-a403-e96b0029c9fe' + +var blobStorageName = take(toLower(replace('blob-${baseName}', '-', '')), 24) +var blobContainerName = 'container-${baseName}' +var deidServiceName = 'deid-${baseName}-${deidLocationShort}' + +resource storageAccount 'Microsoft.Storage/storageAccounts@2022-05-01' = { + name: blobStorageName + location: location + sku: { + name: 'Standard_LRS' + } + kind: 'StorageV2' + properties: { + minimumTlsVersion: 'TLS1_2' + networkAcls: { + bypass: 'AzureServices' + defaultAction: 'Deny' + ipRules: [ + { + action: 'Allow' + value: '4.0.0.0/8' + } + { + action: 'Allow' + value: '13.0.0.0/8' + } + { + action: 'Allow' + value: '20.0.0.0/8' + } + { + action: 'Allow' + value: '40.0.0.0/8' + } + { + action: 'Allow' + value: '51.0.0.0/8' + } + { + action: 'Allow' + value: '52.0.0.0/8' + } + { + action: 'Allow' + value: '65.0.0.0/8' + } + { + action: 'Allow' + value: '70.0.0.0/8' + } + { + action: 'Allow' + value: '74.234.0.0/16' + } + { + action: 'Allow' + value: '74.235.60.120/30' + } + { + action: 'Allow' + value: '94.245.0.0/16' + } + { + action: 'Allow' + value: '98.71.0.0/16' + } + { + action: 'Allow' + value: '102.133.0.0/16' + } + { + action: 'Allow' + value: '104.41.214.32/29' + } + { + action: 'Allow' + value: '104.44.0.0/16' + } + { + action: 'Allow' + value: '104.45.71.156/30' + } + { + action: 'Allow' + value: '104.208.0.0/12' + } + { + action: 'Allow' + value: '108.142.0.0/16' + } + { + action: 'Allow' + value: '131.107.0.0/16' + } + { + action: 'Allow' + value: '157.58.0.0/16' + } + { + action: 'Allow' + value: '167.220.0.0/16' + } + { + action: 'Allow' + value: '172.128.0.0/13' + } + { + action: 'Allow' + value: '191.234.97.0/26' + } + { + action: 'Allow' + value: '194.69.0.0/16' + } + { + action: 'Allow' + value: '207.46.0.0/16' + } + ] + } + } +} + +resource blobService 'Microsoft.Storage/storageAccounts/blobServices@2022-05-01' = { + parent: storageAccount + name: 'default' +} + +resource container 'Microsoft.Storage/storageAccounts/blobServices/containers@2022-05-01' = { + parent: blobService + name: blobContainerName +} + +resource storageRoleAssignment 'Microsoft.Authorization/roleAssignments@2020-04-01-preview' = { + name: guid(resourceGroup().id, storageAccount.id, testApplicationOid, storageBlobDataContributor) + properties: { + roleDefinitionId: resourceId('Microsoft.Authorization/roleDefinitions', storageBlobDataContributor) + principalId: testApplicationOid + } + scope: storageAccount +} + +resource testDeidService 'microsoft.healthdataaiservices/deidservices@2024-02-28-preview' = { + name: deidServiceName + location: deidLocation + identity: { + type: 'SystemAssigned' + } +} + +resource storageMIRoleAssignment 'Microsoft.Authorization/roleAssignments@2020-04-01-preview' = { + name: guid(resourceGroup().id, storageAccount.id, testDeidService.id, storageBlobDataContributor) + properties: { + roleDefinitionId: resourceId('Microsoft.Authorization/roleDefinitions', storageBlobDataContributor) + principalId: testDeidService.identity.principalId + } + scope: storageAccount +} + +resource realtimeRole 'Microsoft.Authorization/roleAssignments@2020-10-01-preview' = { + name: guid(resourceGroup().id, testDeidService.id, testApplicationOid, realtimeDataUserRoleId) + scope: testDeidService + properties: { + roleDefinitionId: resourceId('Microsoft.Authorization/roleDefinitions', realtimeDataUserRoleId) + principalId: testApplicationOid + } +} + +resource batchRole 'Microsoft.Authorization/roleAssignments@2020-10-01-preview' = { + name: guid(resourceGroup().id, testDeidService.id, testApplicationOid, batchDataOwnerRoleId) + scope: testDeidService + properties: { + roleDefinitionId: resourceId('Microsoft.Authorization/roleDefinitions', batchDataOwnerRoleId) + principalId: testApplicationOid + } +} + +output HEALTHDATAAISERVICES_DEID_SERVICE_ENDPOINT string = testDeidService.properties.serviceUrl +output HEALTHDATAAISERVICES_STORAGE_ACCOUNT_NAME string = storageAccount.name +output HEALTHDATAAISERVICES_STORAGE_CONTAINER_NAME string = container.name diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/conftest.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/conftest.py new file mode 100644 index 000000000000..e7f366daf096 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/conftest.py @@ -0,0 +1,55 @@ +import uuid +import pytest +import os +from devtools_testutils import ( + add_body_key_sanitizer, + add_general_string_sanitizer, + remove_batch_sanitizers, + test_proxy, +) + + +# autouse=True will trigger this fixture on each pytest run, even if it's not explicitly used by a test method +# test_proxy auto-starts the test proxy +# patch_sleep and patch_async_sleep streamline tests by disabling wait times during LRO polling +@pytest.fixture(scope="session", autouse=True) +def start_proxy(test_proxy, patch_sleep, patch_async_sleep): + return + + +uniquifier_file = os.path.join(os.path.dirname(__file__), "uniquifier.conf") + + +@pytest.fixture(scope="session", autouse=True) +def create_session_uniquifier(): + if ( + os.environ.get("AZURE_TEST_RUN_LIVE", "false").lower() + == "true" # Don't override uniquifier by default + and os.environ.get("AZURE_SKIP_LIVE_RECORDING", "false").lower() != "true" + ): + uniquifier = uuid.uuid4().hex[:6] + os.environ["HEALTHDATAAISERVICES_UNIQUIFIER"] = uniquifier + with open(uniquifier_file, "w") as file: + file.write(uniquifier) + else: + with open(uniquifier_file, "r") as file: + uniquifier = file.read() + os.environ["HEALTHDATAAISERVICES_UNIQUIFIER"] = uniquifier + + +@pytest.fixture(scope="session", autouse=True) +def add_sanitizers(test_proxy): + # $..name + # $..id + # uri sanitization in favor of substitution + remove_batch_sanitizers(["AZSDK3493", "AZSDK3430", "AZSDK4001"]) + account_name = os.environ.get( + "HEALTHDATAAISERVICES_STORAGE_ACCOUNT_NAME", "Not Found." + ) + container_name = os.environ.get( + "HEALTHDATAAISERVICES_STORAGE_CONTAINER_NAME", "Not Found." + ) + add_body_key_sanitizer( + json_path="..location", + value=f"https://{account_name}.blob.core.windows.net:443/{container_name}", + ) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/data/example_patient_1/doctor_dictation.txt b/sdk/healthdataaiservices/azure-health-deidentification/tests/data/example_patient_1/doctor_dictation.txt new file mode 100644 index 000000000000..dfb10187f123 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/data/example_patient_1/doctor_dictation.txt @@ -0,0 +1 @@ +Mr. Doe is a 97-year-old gentleman who presented to the clinic today complaining of persistent lower back pain. He reports the pain as dull and achy, primarily localized to the lumbar region. Onset was approximately three weeks ago, following a period of heavy lifting during a recent move. The pain is exacerbated by prolonged sitting and relieved with rest. No associated symptoms of radiculopathy, such as numbness or weakness, were reported. diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/data/example_patient_1/visit_summary.txt b/sdk/healthdataaiservices/azure-health-deidentification/tests/data/example_patient_1/visit_summary.txt new file mode 100644 index 000000000000..427472ff8d1d --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/data/example_patient_1/visit_summary.txt @@ -0,0 +1,8 @@ +Patient Name: John Doe +Date of Visit: May 8, 2024 +Physician: Dr. Emily Carter + +Summary: + +Chief Complaint: +John Doe presented today with complaints of persistent lower back pain that has been bothering him for the past three weeks. He reports the pain as dull and achy, localized primarily to the lumbar region, exacerbated by prolonged sitting and relieved with rest. diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/deid_base_test_case.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/deid_base_test_case.py new file mode 100644 index 000000000000..383e72676898 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/deid_base_test_case.py @@ -0,0 +1,72 @@ +import functools +import inspect +import os +import random +import datetime +import uuid +from azure.health.deidentification import DeidentificationClient +from azure.health.deidentification.aio import ( + DeidentificationClient as DeidentificationClientAsync, +) + + +from devtools_testutils import ( + AzureRecordedTestCase, + EnvironmentVariableLoader, +) + +RealtimeEnv = functools.partial( + EnvironmentVariableLoader, + "healthdataaiservices", + healthdataaiservices_deid_service_endpoint="https://example-deid.api.deid.azure.com", +) + +BatchEnv = functools.partial( + EnvironmentVariableLoader, + "healthdataaiservices", + healthdataaiservices_deid_service_endpoint="https://example-deid.api.deid.azure.com", + healthdataaiservices_storage_account_name="blobstorageaccount", + healthdataaiservices_storage_container_name="containername", +) + + +class DeidBaseTestCase(AzureRecordedTestCase): + OUTPUT_PATH = "_output" + + def make_client(self, endpoint) -> DeidentificationClient: + credential = self.get_credential(DeidentificationClient) + client = self.create_client_from_credential( + DeidentificationClient, + credential=credential, + # Client library expects just hostname + endpoint=endpoint.replace("https://", ""), + # TODO: test-proxy not playing well with SSL verification + # connection_verify=False, + ) + return client + + def make_client_async(self, endpoint) -> DeidentificationClientAsync: + credential = self.get_credential(DeidentificationClientAsync) + client = self.create_client_from_credential( + DeidentificationClientAsync, + credential=credential, + # Client library expects just hostname + endpoint=endpoint.replace("https://", ""), + # TODO: test-proxy not playing well with SSL verification + connection_verify=False, + ) + return client + + def generate_job_name(self) -> str: + caller_function_name = inspect.stack()[1].function + uniquifier = os.environ.get("HEALTHDATAAISERVICES_UNIQUIFIER", "") + job_name = f"{caller_function_name[:28]}-{uniquifier}" + return job_name + + def get_storage_location(self, kwargs): + storage_name: str = kwargs.pop("healthdataaiservices_storage_account_name") + container_name: str = kwargs.pop("healthdataaiservices_storage_container_name") + storage_location = ( + f"https://{storage_name}.blob.core.windows.net/{container_name}" + ) + return storage_location diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_delete.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_delete.py new file mode 100644 index 000000000000..cf2516fb7a8c --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_delete.py @@ -0,0 +1,54 @@ +from datetime import time +from azure.core.exceptions import ResourceNotFoundError + +import pytest +from deid_base_test_case import DeidBaseTestCase, BatchEnv +from devtools_testutils import ( + recorded_by_proxy, +) + +from azure.health.deidentification.models import * + + +class TestHealthDeidentificationCreateCancelDelete(DeidBaseTestCase): + @BatchEnv() + @recorded_by_proxy + def test_create_cancel_delete(self, **kwargs): + endpoint: str = kwargs.pop("healthdataaiservices_deid_service_endpoint") + storage_location: str = self.get_storage_location(kwargs) + client = self.make_client(endpoint) + assert client is not None + + jobname = self.generate_job_name() + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix="example_patient_1", + ), + target_location=TargetStorageLocation( + location=storage_location, prefix=self.OUTPUT_PATH + ), + operation=OperationType.SURROGATE, + data_type=DocumentDataType.PLAINTEXT, + ) + + client.begin_create_job(jobname, job) + + job = client.get_job(jobname) + while job.status == JobStatus.NOT_STARTED: + self.sleep(2) + job = client.get_job(jobname) + + assert job.error is None, "Job should not have an error" + assert job.status == JobStatus.RUNNING, "Job should be running" + + job = client.cancel_job(jobname) + + assert job.error is None, "Job should not have an error after cancelling" + assert job.status == JobStatus.CANCELED, "Job should be cancelled" + + client.delete_job(jobname) + + with pytest.raises(ResourceNotFoundError): + job = client.get_job(jobname) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_delete_async.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_delete_async.py new file mode 100644 index 000000000000..ccf32214ba37 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_delete_async.py @@ -0,0 +1,53 @@ +from datetime import time +from azure.core.exceptions import ResourceNotFoundError + +import pytest +from deid_base_test_case import DeidBaseTestCase, BatchEnv +from devtools_testutils.aio import ( + recorded_by_proxy_async, +) + +from azure.health.deidentification.models import * + + +class TestHealthDeidentificationCreateCancelDelete(DeidBaseTestCase): + @BatchEnv() + @pytest.mark.asyncio + @recorded_by_proxy_async + async def test_create_cancel_delete_async(self, **kwargs): + endpoint: str = kwargs.pop("healthdataaiservices_deid_service_endpoint") + storage_location: str = self.get_storage_location(kwargs) + client = self.make_client_async(endpoint) + assert client is not None + + jobname = self.generate_job_name() + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix="example_patient_1", + ), + target_location=TargetStorageLocation( + location=storage_location, prefix=self.OUTPUT_PATH + ), + ) + + await client.begin_create_job(jobname, job) + + job = await client.get_job(jobname) + while job.status == JobStatus.NOT_STARTED: + self.sleep(2) + job = await client.get_job(jobname) + + assert job.error is None, "Job should not have an error" + assert job.status == JobStatus.RUNNING, "Job should be running" + + job = await client.cancel_job(jobname) + + assert job.error is None, "Job should not have an error after cancelling" + assert job.status == JobStatus.CANCELED, "Job should be cancelled" + + await client.delete_job(jobname) + + with pytest.raises(ResourceNotFoundError): + job = await client.get_job(jobname) diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_list.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_list.py new file mode 100644 index 000000000000..9cb3fedf0d5c --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_list.py @@ -0,0 +1,52 @@ +from deid_base_test_case import * +from devtools_testutils import ( + recorded_by_proxy, +) + +from azure.health.deidentification.models import * +from azure.core.polling import LROPoller + + +class TestHealthDeidentificationCreateAndListJob(DeidBaseTestCase): + @BatchEnv() + @recorded_by_proxy + def test_create_list(self, **kwargs): + endpoint: str = kwargs.pop("healthdataaiservices_deid_service_endpoint") + inputPrefix = "example_patient_1" + storage_location: str = self.get_storage_location(kwargs) + client = self.make_client(endpoint) + assert client is not None + + jobname = self.generate_job_name() + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix=inputPrefix, + ), + target_location=TargetStorageLocation(location=storage_location, prefix=self.OUTPUT_PATH), + operation=OperationType.TAG, + data_type=DocumentDataType.PLAINTEXT, + ) + + client.begin_create_job(jobname, job) + jobs = client.list_jobs() + + job = None + jobsToLookThrough = 10 + for j in jobs: + jobsToLookThrough -= 1 + if j.name == jobname: + job = j + break + elif jobsToLookThrough <= 0: + raise Exception("Job not found in list_jobs") + + assert job.name == jobname + assert job.status == JobStatus.NOT_STARTED or job.status == JobStatus.RUNNING + assert job.operation == OperationType.TAG + assert job.error is None + assert job.summary is None + assert job.created_at is not None + assert job.last_updated_at is not None + assert job.redaction_format is None diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_list_async.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_list_async.py new file mode 100644 index 000000000000..51383e5313a7 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_list_async.py @@ -0,0 +1,55 @@ +from deid_base_test_case import * +from devtools_testutils.aio import ( + recorded_by_proxy_async, +) + +from azure.health.deidentification.models import * +import pytest + + +class TestHealthDeidentificationCreateAndListJob(DeidBaseTestCase): + @BatchEnv() + @pytest.mark.asyncio + @recorded_by_proxy_async + async def test_create_list_async(self, **kwargs): + endpoint: str = kwargs.pop("healthdataaiservices_deid_service_endpoint") + inputPrefix = "example_patient_1" + storage_location: str = self.get_storage_location(kwargs) + client = self.make_client_async(endpoint) + assert client is not None + + jobname = self.generate_job_name() + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix=inputPrefix, + ), + target_location=TargetStorageLocation( + location=storage_location, prefix=self.OUTPUT_PATH + ), + operation=OperationType.TAG, + data_type=DocumentDataType.PLAINTEXT, + ) + + await client.begin_create_job(jobname, job) + jobs = client.list_jobs() + + job = None + jobsToLookThrough = 10 + async for j in jobs: + jobsToLookThrough -= 1 + if j.name == jobname: + job = j + break + elif jobsToLookThrough <= 0: + raise Exception("Job not found in list_jobs") + + assert job.name == jobname + assert job.status == JobStatus.NOT_STARTED or job.status == JobStatus.RUNNING + assert job.operation == OperationType.TAG + assert job.error is None + assert job.summary is None + assert job.created_at is not None + assert job.last_updated_at is not None + assert job.redaction_format is None diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_wait_finish.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_wait_finish.py new file mode 100644 index 000000000000..79954337cf3b --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_wait_finish.py @@ -0,0 +1,60 @@ +from deid_base_test_case import * +from devtools_testutils import ( + recorded_by_proxy, +) + +from azure.health.deidentification.models import * +from azure.core.polling import LROPoller + + +class TestHealthDeidentificationCreateJobWaitUntil(DeidBaseTestCase): + @BatchEnv() + @recorded_by_proxy + def test_create_wait_finish(self, **kwargs): + endpoint: str = kwargs.pop("healthdataaiservices_deid_service_endpoint") + inputPrefix = "example_patient_1" + storage_location: str = self.get_storage_location(kwargs) + client = self.make_client(endpoint) + assert client is not None + + jobname = self.generate_job_name() + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix=inputPrefix, + ), + target_location=TargetStorageLocation( + location=storage_location, prefix=self.OUTPUT_PATH + ), + operation=OperationType.SURROGATE, + data_type=DocumentDataType.PLAINTEXT, + ) + + lro: LROPoller = client.begin_create_job(jobname, job) + lro.wait(timeout=60) + + finished_job: DeidentificationJob = lro.result() + + assert finished_job.status == JobStatus.SUCCEEDED + assert finished_job.name == jobname + assert finished_job.operation == OperationType.SURROGATE + assert finished_job.data_type == DocumentDataType.PLAINTEXT + assert finished_job.summary.total == 2 + assert finished_job.summary.successful == 2 + assert finished_job.summary.failed == 0 + assert finished_job.started_at > finished_job.created_at + assert finished_job.last_updated_at > finished_job.started_at + assert finished_job.redaction_format is None + assert finished_job.error is None + assert finished_job.source_location.prefix == inputPrefix + + files = client.list_job_documents(jobname) + count = 0 + for my_file in files: + assert len(my_file.id) == 36 # GUID + assert my_file.input.path.startswith(inputPrefix) + assert my_file.status == OperationState.SUCCEEDED + assert my_file.output.path.startswith(self.OUTPUT_PATH) + count += 1 + assert count == 2, f"Expected 2 files, found {count}" diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_wait_finish_async.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_wait_finish_async.py new file mode 100644 index 000000000000..97af65c1d224 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_create_wait_finish_async.py @@ -0,0 +1,62 @@ +from deid_base_test_case import * +from devtools_testutils.aio import ( + recorded_by_proxy_async, +) + +from azure.health.deidentification.models import * +from azure.core.polling import AsyncLROPoller +import pytest + + +class TestHealthDeidentificationCreateJobWaitUntil(DeidBaseTestCase): + @BatchEnv() + @pytest.mark.asyncio + @recorded_by_proxy_async + async def test_create_wait_finish_async(self, **kwargs): + endpoint: str = kwargs.pop("healthdataaiservices_deid_service_endpoint") + inputPrefix = "example_patient_1" + storage_location: str = self.get_storage_location(kwargs) + client = self.make_client_async(endpoint) + assert client is not None + + jobname = self.generate_job_name() + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix=inputPrefix, + ), + target_location=TargetStorageLocation( + location=storage_location, prefix=self.OUTPUT_PATH + ), + operation=OperationType.SURROGATE, + data_type=DocumentDataType.PLAINTEXT, + ) + + lro: AsyncLROPoller = await client.begin_create_job(jobname, job) + lro.wait() + + finished_job: DeidentificationJob = await lro.result() + + assert finished_job.status == JobStatus.SUCCEEDED + assert finished_job.name == jobname + assert finished_job.operation == OperationType.SURROGATE + assert finished_job.data_type == DocumentDataType.PLAINTEXT + assert finished_job.summary.total == 2 + assert finished_job.summary.successful == 2 + assert finished_job.summary.failed == 0 + assert finished_job.started_at > finished_job.created_at + assert finished_job.last_updated_at > finished_job.started_at + assert finished_job.redaction_format is None + assert finished_job.error is None + assert finished_job.source_location.prefix == inputPrefix + + files = client.list_job_documents(jobname) + count = 0 + async for my_file in files: + assert len(my_file.id) == 36 # GUID + assert my_file.input.path.startswith(inputPrefix) + assert my_file.status == OperationState.SUCCEEDED + assert my_file.output.path.startswith(self.OUTPUT_PATH) + count += 1 + assert count == 2, f"Expected 2 files, found {count}" diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/test_exception_throws.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_exception_throws.py new file mode 100644 index 000000000000..ff0daaad26d6 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_exception_throws.py @@ -0,0 +1,45 @@ +from datetime import time +from time import sleep +from azure.core.exceptions import HttpResponseError + +import pytest +from deid_base_test_case import DeidBaseTestCase, BatchEnv +from devtools_testutils import ( + recorded_by_proxy, +) + +from azure.health.deidentification.models import * +from azure.core.polling import LROPoller + + +class TestHealthDeidentificationExceptionThrows(DeidBaseTestCase): + @BatchEnv() + @recorded_by_proxy + def test_exception_throws(self, **kwargs): + endpoint: str = kwargs.pop("healthdataaiservices_deid_service_endpoint") + storage_location: str = self.get_storage_location(kwargs) + client = self.make_client(endpoint) + assert client is not None + + jobname = self.generate_job_name() + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix="no_files_in_this_folder", + ), + target_location=TargetStorageLocation(location=storage_location, prefix=self.OUTPUT_PATH), + operation=OperationType.SURROGATE, + data_type=DocumentDataType.PLAINTEXT, + ) + + lro: LROPoller = client.begin_create_job(jobname, job) + with pytest.raises(HttpResponseError): + lro.wait(timeout=60) + + job = client.get_job(jobname) + + assert job.status == JobStatus.FAILED + assert job.error is not None + assert job.error.code == "JobValidationError" + assert len(job.error.message) > 10 diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/test_exception_throws_async.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_exception_throws_async.py new file mode 100644 index 000000000000..2f1858a2ce9e --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_exception_throws_async.py @@ -0,0 +1,48 @@ +from datetime import time +from time import sleep +from azure.core.exceptions import HttpResponseError + +import pytest +from deid_base_test_case import DeidBaseTestCase, BatchEnv +from devtools_testutils.aio import ( + recorded_by_proxy_async, +) + +from azure.health.deidentification.models import * +from azure.core.polling import AsyncLROPoller + + +class TestHealthDeidentificationExceptionThrows(DeidBaseTestCase): + @BatchEnv() + @pytest.mark.asyncio + @recorded_by_proxy_async + async def test_exception_throws_async(self, **kwargs): + endpoint: str = kwargs.pop("healthdataaiservices_deid_service_endpoint") + storage_location: str = self.get_storage_location(kwargs) + client = self.make_client_async(endpoint) + assert client is not None + + jobname = self.generate_job_name() + + job = DeidentificationJob( + source_location=SourceStorageLocation( + location=storage_location, + prefix="no_files_in_this_folder", + ), + target_location=TargetStorageLocation( + location=storage_location, prefix=self.OUTPUT_PATH + ), + operation=OperationType.SURROGATE, + data_type=DocumentDataType.PLAINTEXT, + ) + + lro: AsyncLROPoller = await client.begin_create_job(jobname, job) + with pytest.raises(HttpResponseError): + await lro.wait() + + job = await client.get_job(jobname) + + assert job.status == JobStatus.FAILED + assert job.error is not None + assert job.error.code == "JobValidationError" + assert len(job.error.message) > 10 diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/test_hello_world.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_hello_world.py new file mode 100644 index 000000000000..32e700227510 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_hello_world.py @@ -0,0 +1,31 @@ +from deid_base_test_case import DeidBaseTestCase, RealtimeEnv +from devtools_testutils import ( + recorded_by_proxy, +) +import pytest + +from azure.health.deidentification.models import * + + +class TestHealthDeidentificationHelloWorld(DeidBaseTestCase): + @RealtimeEnv() + @recorded_by_proxy + def test_hello_world(self, healthdataaiservices_deid_service_endpoint): + client = self.make_client(healthdataaiservices_deid_service_endpoint) + assert client is not None + + content = DeidentificationContent( + input_text="Hello, my name is John Smith.", + operation=OperationType.SURROGATE, + data_type=DocumentDataType.PLAINTEXT, + ) + + result: DeidentificationResult = client.deidentify(content) + + assert result is not None + assert result.output_text is not None + assert result.tagger_result is None + + assert result.output_text.startswith("Hello, my name is ") + assert "John Smith" not in result.output_text + assert "[" not in result.output_text diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/test_hello_world_async.py b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_hello_world_async.py new file mode 100644 index 000000000000..6506850de0f8 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/test_hello_world_async.py @@ -0,0 +1,32 @@ +from deid_base_test_case import DeidBaseTestCase, RealtimeEnv +from devtools_testutils.aio import ( + recorded_by_proxy_async, +) +import pytest + +from azure.health.deidentification.models import * + + +class TestHealthDeidentificationHelloWorld(DeidBaseTestCase): + @RealtimeEnv() + @pytest.mark.asyncio + @recorded_by_proxy_async + async def test_hello_world_async(self, healthdataaiservices_deid_service_endpoint): + client = self.make_client_async(healthdataaiservices_deid_service_endpoint) + assert client is not None + + content = DeidentificationContent( + input_text="Hello, my name is John Smith.", + operation=OperationType.SURROGATE, + data_type=DocumentDataType.PLAINTEXT, + ) + + result: DeidentificationResult = await client.deidentify(content) + + assert result is not None + assert result.output_text is not None + assert result.tagger_result is None + + assert result.output_text.startswith("Hello, my name is ") + assert "John Smith" not in result.output_text + assert "[" not in result.output_text diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tests/uniquifier.conf b/sdk/healthdataaiservices/azure-health-deidentification/tests/uniquifier.conf new file mode 100644 index 000000000000..5ceb18d86ac6 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tests/uniquifier.conf @@ -0,0 +1 @@ +10ea88 \ No newline at end of file diff --git a/sdk/healthdataaiservices/azure-health-deidentification/tsp-location.yaml b/sdk/healthdataaiservices/azure-health-deidentification/tsp-location.yaml new file mode 100644 index 000000000000..090caaf79c28 --- /dev/null +++ b/sdk/healthdataaiservices/azure-health-deidentification/tsp-location.yaml @@ -0,0 +1,5 @@ +directory: specification/healthdataaiservices/HealthDataAIServices.DeidServices +commit: 2771da5baeee73dfd70b2a5f2813a55549c2aa73 +additionalDirectories: [] +repo: Azure/azure-rest-api-specs + diff --git a/sdk/healthdataaiservices/ci.yml b/sdk/healthdataaiservices/ci.yml new file mode 100644 index 000000000000..7e269fbb1473 --- /dev/null +++ b/sdk/healthdataaiservices/ci.yml @@ -0,0 +1,41 @@ +# NOTE: Please refer to https://aka.ms/azsdk/engsys/ci-yaml before editing this file. + +trigger: + branches: + include: + - main + - hotfix/* + - release/* + - restapi* + paths: + include: + - sdk/healthdataaiservices + - sdk/healthdataaiservices/test-resources.bicep + - sdk/healthdataaiservices/test-resources-post.ps1 + - sdk/healthdataaiservices/ci.yml + - sdk/healthdataaiservices/azure-health-deidentification + +pr: + branches: + include: + - main + - feature/* + - hotfix/* + - release/* + - restapi* + paths: + include: + - sdk/healthdataaiservices + - sdk/healthdataaiservices/test-resources.bicep + - sdk/healthdataaiservices/test-resources-post.ps1 + - sdk/healthdataaiservices/ci.yml + - sdk/healthdataaiservices/azure-health-deidentification + +extends: + template: /eng/pipelines/templates/stages/archetype-sdk-client.yml + parameters: + ServiceDirectory: healthdataaiservices + TestProxy: true + Artifacts: + - name: azure-health-deidentification + safeName: azurehealthdeidentification diff --git a/sdk/healthdataaiservices/tests.yml b/sdk/healthdataaiservices/tests.yml new file mode 100644 index 000000000000..64b083802a0d --- /dev/null +++ b/sdk/healthdataaiservices/tests.yml @@ -0,0 +1,9 @@ +trigger: none + +extends: + template: ../../eng/pipelines/templates/stages/archetype-sdk-tests.yml + parameters: + ServiceDirectory: healthdataaiservices + EnvVars: + AZURE_SKIP_LIVE_RECORDING: 'True' + AZURE_TEST_RUN_LIVE: 'true'