[text analytics] add domain_filter param (Azure#13451)

sdk/textanalytics/azure-ai-textanalytics/azure/ai/textanalytics/__init__.py

@@ -31,6 +31,7 @@
     OpinionSentiment,
     RecognizePiiEntitiesResult,
     PiiEntity,
+    PiiEntityDomainType,
 )
 
 __all__ = [
@@ -59,6 +60,7 @@
     'OpinionSentiment',
     'RecognizePiiEntitiesResult',
     'PiiEntity',
+    'PiiEntityDomainType',
 ]
 
 __version__ = VERSION

sdk/textanalytics/azure-ai-textanalytics/azure/ai/textanalytics/_models.py

@@ -4,6 +4,7 @@
 # Licensed under the MIT License.
 # ------------------------------------
 import re
+from enum import Enum
 from ._generated.models import (
     LanguageInput,
     MultiLanguageInput,
@@ -64,6 +65,10 @@ def get(self, key, default=None):
             return self.__dict__[key]
         return default
 
+class PiiEntityDomainType(str, Enum):
+    """The different domains of PII entities that users can filter by"""
+    PROTECTED_HEALTH_INFORMATION = "PHI"  # See https://aka.ms/tanerpii for more information.
+
 
 class DetectedLanguage(DictMixin):
     """DetectedLanguage contains the predicted language found in text,

sdk/textanalytics/azure-ai-textanalytics/azure/ai/textanalytics/_text_analytics_client.py

@@ -260,6 +260,10 @@ def recognize_pii_entities(  # type: ignore
             be used for scoring, e.g. "latest", "2019-10-01". If a model-version
             is not specified, the API will default to the latest, non-preview version.
         :keyword bool show_stats: If set to true, response will contain document level statistics.
+        :keyword domain_filter: Filters the response entities to ones only included in the specified domain.
+            I.e., if set to 'PHI', will only return entities in the Protected Healthcare Information domain.
+            See https://aka.ms/tanerpii for more information.
+        :paramtype domain_filter: str or ~azure.ai.textanalytics.PiiEntityDomainType
         :return: The combined list of :class:`~azure.ai.textanalytics.RecognizePiiEntitiesResult`
             and :class:`~azure.ai.textanalytics.DocumentError` in the order the original documents
             were passed in.
@@ -281,13 +285,15 @@ def recognize_pii_entities(  # type: ignore
         docs = _validate_input(documents, "language", language)
         model_version = kwargs.pop("model_version", None)
         show_stats = kwargs.pop("show_stats", False)
+        domain_filter = kwargs.pop("domain_filter", None)
         if self._string_code_unit:
             kwargs.update({"string_index_type": self._string_code_unit})
         try:
             return self._client.entities_recognition_pii(
                 documents=docs,
                 model_version=model_version,
                 show_stats=show_stats,
+                domain=domain_filter,
                 cls=kwargs.pop("cls", pii_entities_result),
                 **kwargs
             )

sdk/textanalytics/azure-ai-textanalytics/azure/ai/textanalytics/aio/_text_analytics_client_async.py

@@ -262,6 +262,10 @@ async def recognize_pii_entities(  # type: ignore
             be used for scoring, e.g. "latest", "2019-10-01". If a model-version
             is not specified, the API will default to the latest, non-preview version.
         :keyword bool show_stats: If set to true, response will contain document level statistics.
+        :keyword domain_filter: Filters the response entities to ones only included in the specified domain.
+            I.e., if set to 'PHI', will only return entities in the Protected Healthcare Information domain.
+            See https://aka.ms/tanerpii for more information.
+        :paramtype domain_filter: str or ~azure.ai.textanalytics.PiiEntityDomainType
         :return: The combined list of :class:`~azure.ai.textanalytics.RecognizePiiEntitiesResult`
             and :class:`~azure.ai.textanalytics.DocumentError` in the order the original documents
             were passed in.
@@ -283,13 +287,16 @@ async def recognize_pii_entities(  # type: ignore
         docs = _validate_input(documents, "language", language)
         model_version = kwargs.pop("model_version", None)
         show_stats = kwargs.pop("show_stats", False)
+        domain_filter = kwargs.pop("domain_filter", None)
+
         if self._string_code_unit:
             kwargs.update({"string_index_type": self._string_code_unit})
         try:
             return await self._client.entities_recognition_pii(
                 documents=docs,
                 model_version=model_version,
                 show_stats=show_stats,
+                domain=domain_filter,
                 cls=kwargs.pop("cls", pii_entities_result),
                 **kwargs
             )

sdk/textanalytics/azure-ai-textanalytics/tests/recordings/test_recognize_pii_entities.test_phi_domain_filter.yaml

@@ -0,0 +1,44 @@
+interactions:
+- request:
+    body: '{"documents": [{"id": "0", "text": "I work at Microsoft and my phone number
+      is 333-333-3333", "language": "en"}]}'
+    headers:
+      Accept:
+      - application/json, text/json
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '113'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - azsdk-python-ai-textanalytics/5.0.1 Python/3.8.5 (macOS-10.13.6-x86_64-i386-64bit)
+    method: POST
+    uri: https://westus2.api.cognitive.microsoft.com/text/analytics/v3.1-preview.1/entities/recognition/pii?showStats=false&domain=PHI&stringIndexType=UnicodeCodePoint
+  response:
+    body:
+      string: '{"documents":[{"id":"0","entities":[{"text":"333-333-3333","category":"Phone
+        Number","offset":43,"length":12,"confidenceScore":0.8}],"warnings":[]}],"errors":[],"modelVersion":"2020-07-01"}'
+    headers:
+      apim-request-id:
+      - c2319b95-6fd2-46c9-80e3-06c8f2701825
+      content-type:
+      - application/json; charset=utf-8
+      csp-billing-usage:
+      - CognitiveServices.TextAnalytics.BatchScoring=1
+      date:
+      - Mon, 31 Aug 2020 20:32:54 GMT
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      transfer-encoding:
+      - chunked
+      x-content-type-options:
+      - nosniff
+      x-envoy-upstream-service-time:
+      - '79'
+    status:
+      code: 200
+      message: OK
+version: 1

sdk/textanalytics/azure-ai-textanalytics/tests/recordings/test_recognize_pii_entities_async.test_phi_domain_filter.yaml

@@ -0,0 +1,33 @@
+interactions:
+- request:
+    body: '{"documents": [{"id": "0", "text": "I work at Microsoft and my phone number
+      is 333-333-3333", "language": "en"}]}'
+    headers:
+      Accept:
+      - application/json, text/json
+      Content-Length:
+      - '113'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - azsdk-python-ai-textanalytics/5.0.1 Python/3.8.5 (macOS-10.13.6-x86_64-i386-64bit)
+    method: POST
+    uri: https://westus2.api.cognitive.microsoft.com/text/analytics/v3.1-preview.1/entities/recognition/pii?showStats=false&domain=PHI&stringIndexType=UnicodeCodePoint
+  response:
+    body:
+      string: '{"documents":[{"id":"0","entities":[{"text":"333-333-3333","category":"Phone
+        Number","offset":43,"length":12,"confidenceScore":0.8}],"warnings":[]}],"errors":[],"modelVersion":"2020-07-01"}'
+    headers:
+      apim-request-id: 9265752d-3262-4dbb-94d6-be26889e3db9
+      content-type: application/json; charset=utf-8
+      csp-billing-usage: CognitiveServices.TextAnalytics.BatchScoring=1
+      date: Mon, 31 Aug 2020 20:32:55 GMT
+      strict-transport-security: max-age=31536000; includeSubDomains; preload
+      transfer-encoding: chunked
+      x-content-type-options: nosniff
+      x-envoy-upstream-service-time: '82'
+    status:
+      code: 200
+      message: OK
+    url: https://westus2.api.cognitive.microsoft.com//text/analytics/v3.1-preview.1/entities/recognition/pii?showStats=false&domain=PHI&stringIndexType=UnicodeCodePoint
+version: 1

sdk/textanalytics/azure-ai-textanalytics/tests/test_recognize_pii_entities.py

@@ -17,6 +17,7 @@
     TextDocumentInput,
     VERSION,
     TextAnalyticsApiVersion,
+    PiiEntityDomainType,
 )
 
 # pre-apply the client_cls positional argument so it needn't be explicitly passed below
@@ -573,4 +574,17 @@ def test_recognize_pii_entities_v3(self, client):
         with pytest.raises(NotImplementedError) as excinfo:
             client.recognize_pii_entities(["this should fail"])
 
-        assert "'recognize_pii_entities' endpoint is only available for API version v3.1-preview.1 and up" in str(excinfo.value)
+        assert "'recognize_pii_entities' endpoint is only available for API version v3.1-preview.1 and up" in str(excinfo.value)
+
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    def test_phi_domain_filter(self, client):
+        # without the domain filter, this should return two entities: Microsoft as an org,
+        # and the phone number. With the domain filter, it should only return one.
+        result = client.recognize_pii_entities(
+            ["I work at Microsoft and my phone number is 333-333-3333"],
+            domain_filter=PiiEntityDomainType.PROTECTED_HEALTH_INFORMATION
+        )
+        self.assertEqual(len(result[0].entities), 1)
+        self.assertEqual(result[0].entities[0].text, '333-333-3333')
+        self.assertEqual(result[0].entities[0].category, 'Phone Number')

sdk/textanalytics/azure-ai-textanalytics/tests/test_recognize_pii_entities_async.py

@@ -18,6 +18,7 @@
     TextDocumentInput,
     VERSION,
     TextAnalyticsApiVersion,
+    PiiEntityDomainType,
 )
 
 # pre-apply the client_cls positional argument so it needn't be explicitly passed below
@@ -572,3 +573,16 @@ async def test_recognize_pii_entities_v3(self, client):
             await client.recognize_pii_entities(["this should fail"])
 
         assert "'recognize_pii_entities' endpoint is only available for API version v3.1-preview.1 and up" in str(excinfo.value)
+
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    async def test_phi_domain_filter(self, client):
+        # without the domain filter, this should return two entities: Microsoft as an org,
+        # and the phone number. With the domain filter, it should only return one.
+        result = await client.recognize_pii_entities(
+            ["I work at Microsoft and my phone number is 333-333-3333"],
+            domain_filter=PiiEntityDomainType.PROTECTED_HEALTH_INFORMATION
+        )
+        self.assertEqual(len(result[0].entities), 1)
+        self.assertEqual(result[0].entities[0].text, '333-333-3333')
+        self.assertEqual(result[0].entities[0].category, 'Phone Number')