[CI] Test updates for central sanitizers (#35385)

This PR updates our Python testing framework to adopt the new TestProxy
which enables numerous common sanitizers.


Signed-off-by: Paul Van Eck <paulvaneck@microsoft.com>

eng/target_proxy_version.txt

@@ -1 +1 @@
-1.0.0-dev.20240410.1
+1.0.0-dev.20240506.5

sdk/ai/azure-ai-generative/tests/conftest.py

@@ -86,7 +86,7 @@ def fake_datastore_key() -> str:
     return str(b64_key, "ascii")
 
 
-@pytest.fixture(autouse=True)
+@pytest.fixture(scope="session", autouse=True)
 def add_sanitizers(test_proxy, fake_datastore_key):
     """Register recording sanitizers for the function under test"""
     add_remove_header_sanitizer(headers="x-azureml-token,Log-URL,Authorization")

sdk/ai/azure-ai-resources/tests/conftest.py

@@ -100,7 +100,7 @@ def fake_datastore_key() -> str:
     return str(b64_key, "ascii")
 
 
-@pytest.fixture(autouse=True)
+@pytest.fixture(scope="session", autouse=True)
 def add_sanitizers(test_proxy, fake_datastore_key):
     """Register recording sanitizers for the function under test"""
     add_remove_header_sanitizer(headers="x-azureml-token,Log-URL,Authorization")

sdk/appconfiguration/azure-appconfiguration-provider/tests/conftest.py

@@ -4,6 +4,7 @@
     add_general_string_sanitizer,
     add_oauth_response_sanitizer,
     set_custom_default_matcher,
+    remove_batch_sanitizers,
 )
 import pytest
 
@@ -37,3 +38,8 @@ def add_sanitizers(test_proxy):
     add_general_regex_sanitizer(value="api-version=1970-01-01", regex="api-version=.+")
     set_custom_default_matcher(ignored_headers="x-ms-content-sha256, Accept", excluded_headers="Content-Length")
     add_oauth_response_sanitizer()
+
+    # Remove the following sanitizers since certain fields are needed in tests and are non-sensitive:
+    #  - AZSDK3430: $..id
+    #  - AZSDK3447: $.key
+    remove_batch_sanitizers(["AZSDK3430", "AZSDK3447"])

sdk/appconfiguration/azure-appconfiguration/tests/conftest.py

@@ -25,7 +25,7 @@
 # --------------------------------------------------------------------------
 import pytest
 import os
-from devtools_testutils import add_general_regex_sanitizer, test_proxy, set_bodiless_matcher
+from devtools_testutils import add_general_regex_sanitizer, test_proxy, set_bodiless_matcher, remove_batch_sanitizers
 
 
 @pytest.fixture(scope="session", autouse=True)
@@ -38,3 +38,9 @@ def add_sanitizers(test_proxy):
     add_general_regex_sanitizer(regex=client_secret, value="client-secret")
     tenant_id = os.environ.get("APPCONFIGURATION_TENANT_ID", "00000000-0000-0000-0000-000000000000")
     add_general_regex_sanitizer(value="00000000-0000-0000-0000-000000000000", regex=tenant_id)
+
+    # Remove the following sanitizers since certain fields are needed in tests and are non-sensitive:
+    #  - AZSDK3447: $.key
+    #  - AZSDK3490: $..etag
+    #  - AZSDK3493: $..name
+    remove_batch_sanitizers(["AZSDK3447", "AZSDK3490", "AZSDK3493"])

sdk/cognitivelanguage/azure-ai-language-questionanswering/tests/conftest.py

@@ -6,7 +6,11 @@
 # --------------------------------------------------------------------------
 import pytest
 
-from devtools_testutils.sanitizers import add_header_regex_sanitizer, add_oauth_response_sanitizer
+from devtools_testutils.sanitizers import (
+    add_header_regex_sanitizer,
+    add_oauth_response_sanitizer,
+    remove_batch_sanitizers
+)
 
 
 # Environment variable keys
@@ -40,6 +44,10 @@ def add_sanitizers(test_proxy, environment_variables):
     add_oauth_response_sanitizer()
     add_header_regex_sanitizer(key="Set-Cookie", value="[set-cookie;]")
 
+    # Remove the following sanitizers since certain fields are needed in tests and are non-sensitive:
+    #  - AZSDK3430: $..id
+    remove_batch_sanitizers(["AZSDK3430"])
+
 
 @pytest.fixture(scope="session")
 def qna_creds(environment_variables):

sdk/communication/azure-communication-callautomation/assets.json

@@ -2,5 +2,5 @@
   "AssetsRepo": "Azure/azure-sdk-assets",
   "AssetsRepoPrefixPath": "python",
   "TagPrefix": "python/communication/azure-communication-callautomation",
-  "Tag": "python/communication/azure-communication-callautomation_707ce35a60"
+  "Tag": "python/communication/azure-communication-callautomation_ab7206cdd8"
 }

sdk/communication/azure-communication-callautomation/tests/conftest.py

@@ -11,6 +11,7 @@
     set_default_session_settings,
     add_body_key_sanitizer,
     add_general_string_sanitizer,
+    remove_batch_sanitizers,
 )
 
 # autouse=True will trigger this fixture on each pytest run, even if it's not explicitly used by a test method
@@ -24,7 +25,7 @@ def start_proxy(test_proxy):
     add_general_string_sanitizer(target=connection_str, value=fake_connection_str)
 
     add_general_regex_sanitizer(regex="https://[^/]+", value="https://sanitized")
-    add_body_key_sanitizer(json_path="callbackUri", value="https://sanitized")
+    add_body_key_sanitizer(json_path="callbackUri", value="https://sanitized/")
     add_body_key_sanitizer(json_path="$..file.uri", value="https://REDACTED/prompt.wav")
     add_header_regex_sanitizer(key="Set-Cookie", value="sanitized")
     add_header_regex_sanitizer(key="Date", value="sanitized")
@@ -40,4 +41,8 @@ def start_proxy(test_proxy):
     add_header_regex_sanitizer(key="Repeatability-First-Sent", value="sanitized")
     add_header_regex_sanitizer(key="Repeatability-Request-ID", value="sanitized")
 
-    return
+    # Remove the following sanitizers since certain fields are needed in tests and are non-sensitive:
+    #  - AZSDK3430: $..id
+    remove_batch_sanitizers(["AZSDK3430"])
+
+    return

sdk/communication/azure-communication-jobrouter/tests/conftest.py

@@ -35,6 +35,7 @@
     set_default_session_settings,
     add_uri_regex_sanitizer,
     add_body_key_sanitizer,
+    remove_batch_sanitizers,
 )
 from router_test_constants import SANITIZED, FAKE_FUNCTION_URI, FAKE_ENDPOINT, FAKE_CONNECTION_STRING
 from azure.communication.jobrouter._shared.utils import parse_connection_str
@@ -69,6 +70,11 @@ def start_proxy(test_proxy):
     add_body_key_sanitizer(json_path="$..functionKey", value=SANITIZED)
     add_body_key_sanitizer(json_path="$..appKey", value=SANITIZED)
     add_body_key_sanitizer(json_path="$..clientId", value=SANITIZED)
+
+    # Remove the following sanitizers since certain fields are needed in tests and are non-sensitive:
+    #  - AZSDK3430: $..id
+    #  - AZSDK3493: $..name
+    remove_batch_sanitizers(["AZSDK3430", "AZSDK3493"])
     return
 
 

sdk/communication/azure-communication-phonenumbers/test/conftest.py

@@ -6,7 +6,8 @@
     add_general_string_sanitizer,
     add_general_regex_sanitizer,
     add_header_regex_sanitizer,
-    test_proxy
+    test_proxy,
+    remove_batch_sanitizers,
 )
 
 
@@ -45,10 +46,10 @@ def add_sanitizers(test_proxy):
     add_body_key_sanitizer(json_path="phoneNumbers[*].id", value="sanitized")
     add_body_key_sanitizer(
         json_path="phoneNumbers[*].phoneNumber", value="sanitized")
-    
+
     add_general_regex_sanitizer(
         regex=r"-[0-9a-fA-F]{32}\.[0-9a-zA-Z\.]*(\.com|\.net|\.test)", value=".sanitized.com")
-    
+
     add_general_regex_sanitizer(regex=r"(?:(?:%2B)|\+)\d{10,15}", value="sanitized")
 
     add_general_regex_sanitizer(
@@ -68,3 +69,9 @@ def add_sanitizers(test_proxy):
     add_header_regex_sanitizer(key="x-ms-request-id", value="sanitized")
     add_header_regex_sanitizer(
         key="Content-Security-Policy-Report-Only", value="sanitized")
+
+    # Remove the following sanitizers since certain fields are needed in tests and are non-sensitive:
+    #  - AZSDK3493: $..name
+    #  - AZSDK2003: Location
+    remove_batch_sanitizers(["AZSDK3493", "AZSDK2003"])
+

sdk/communication/azure-communication-rooms/tests/conftest.py

@@ -25,7 +25,12 @@
 # --------------------------------------------------------------------------
 import pytest
 import os
-from devtools_testutils import add_general_string_sanitizer, add_header_regex_sanitizer, add_body_key_sanitizer, set_default_session_settings
+from devtools_testutils import (
+    add_general_string_sanitizer,
+    add_header_regex_sanitizer,
+    set_default_session_settings,
+    remove_batch_sanitizers,
+)
 from azure.communication.rooms._shared.utils import parse_connection_str
 
 @pytest.fixture(scope="session", autouse=True)
@@ -52,3 +57,7 @@ def add_sanitizers(test_proxy):
         key="Content-Security-Policy-Report-Only", value="sanitized")
     add_header_regex_sanitizer(key="Repeatability-First-Sent", value="sanitized")
     add_header_regex_sanitizer(key="Repeatability-Request-ID", value="sanitized")
+
+    # Remove the following sanitizers since certain fields are needed in tests and are non-sensitive:
+    #  - AZSDK3430: $..id
+    remove_batch_sanitizers(["AZSDK3430"])

sdk/containerregistry/azure-containerregistry/assets.json

@@ -2,5 +2,5 @@
   "AssetsRepo": "Azure/azure-sdk-assets",
   "AssetsRepoPrefixPath": "python",
   "TagPrefix": "python/containerregistry/azure-containerregistry",
-  "Tag": "python/containerregistry/azure-containerregistry_790d3fef6e"
+  "Tag": "python/containerregistry/azure-containerregistry_02a9c147da"
 }

sdk/containerregistry/azure-containerregistry/tests/conftest.py

@@ -13,6 +13,7 @@
     add_uri_regex_sanitizer,
     test_proxy,
     is_live,
+    remove_batch_sanitizers,
 )
 from testcase import import_image, is_public_endpoint
 from constants import HELLO_WORLD
@@ -54,3 +55,10 @@ def add_sanitizers(test_proxy):
     add_general_regex_sanitizer(regex=client_id, value="client-id")
     client_secret = os.environ.get("CONTAINERREGISTRY_CLIENT_SECRET", "client-secret")
     add_general_regex_sanitizer(regex=client_secret, value="client-secret")
+    tenant_id = os.environ.get("CONTAINERREGISTRY_TENANT_ID", "tenant-id")
+    add_general_regex_sanitizer(regex=tenant_id, value="00000000-0000-0000-0000-000000000000")
+
+    # Remove the following sanitizers since certain fields are needed in tests and are non-sensitive:
+    #  - AZSDK3493: $..name
+    #  - AZSDK2003: Location
+    remove_batch_sanitizers(["AZSDK3493", "AZSDK2003"])

sdk/core/azure-core/README.md

@@ -6,15 +6,11 @@ These libraries follow the [Azure SDK Design Guidelines for Python](https://azur
 
 If you are a client library developer, please reference [client library developer reference](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/core/azure-core/CLIENT_LIBRARY_DEVELOPER.md) for more information.
 
-[Source code](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/core/azure-core/) 
+[Source code](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/core/azure-core/)
 | [Package (Pypi)][package]
 | [Package (Conda)](https://anaconda.org/microsoft/azure-core/)
 | [API reference documentation](https://docs.microsoft.com/python/api/overview/azure/core-readme)
 
-## _Disclaimer_
-
-_Azure SDK Python packages support for Python 2.7 has ended 01 January 2022. For more information and questions, please refer to <https://github.com/Azure/azure-sdk-for-python/issues/20691>_
-
 ## Getting started
 
 Typically, you will not need to install azure core;

sdk/documentintelligence/azure-ai-documentintelligence/tests/conftest.py

@@ -15,6 +15,7 @@
     add_oauth_response_sanitizer,
     add_body_key_sanitizer,
     test_proxy,
+    remove_batch_sanitizers,
 )
 
 
@@ -38,6 +39,9 @@ def add_sanitizers(test_proxy):
         value="redacted",
         regex="([0-9a-f-]{36})",
     )
+    # Remove the following sanitizers since certain fields are needed in tests and are non-sensitive:
+    #  - AZSDK3496: "$..resourceLocation"
+    remove_batch_sanitizers(["AZSDK3496"])
 
 
 def skip_flaky_test(f):

sdk/documentintelligence/azure-ai-documentintelligence/tests/test_dmac_classifiers.py

@@ -74,7 +74,7 @@ def test_build_classifier(self, client, documentintelligence_training_data_class
         assert len(result.doc_types) == 5
         for doc_type, doc_details in result.doc_types.items():
             assert doc_type
-            assert doc_details.azure_blob_source.container_url.endswith("training-data-classifier")
+            assert doc_details.azure_blob_source.container_url
             assert doc_details.azure_blob_source.prefix.startswith(doc_type)
 
         classifier = client.get_classifier(result.classifier_id)
@@ -160,7 +160,7 @@ def test_build_classifier_file_list(self, client, documentintelligence_training_
         assert len(result.doc_types) == 5
         for doc_type, doc_details in result.doc_types.items():
             assert doc_type
-            assert doc_details.azure_blob_file_list_source.container_url.endswith("training-data-classifier")
+            assert doc_details.azure_blob_file_list_source.container_url
             assert doc_details.azure_blob_file_list_source.file_list.startswith(doc_type)
 
         classifier = client.get_classifier(result.classifier_id)

sdk/documentintelligence/azure-ai-documentintelligence/tests/test_dmac_classifiers_async.py

@@ -76,7 +76,7 @@ async def test_build_classifier(self, client, documentintelligence_training_data
             assert len(result.doc_types) == 5
             for doc_type, doc_details in result.doc_types.items():
                 assert doc_type
-                assert doc_details.azure_blob_source.container_url.endswith("training-data-classifier")
+                assert doc_details.azure_blob_source.container_url
                 assert doc_details.azure_blob_source.prefix.startswith(doc_type)
 
             classifier = await client.get_classifier(result.classifier_id)
@@ -165,7 +165,7 @@ async def test_build_classifier_file_list(
             assert len(result.doc_types) == 5
             for doc_type, doc_details in result.doc_types.items():
                 assert doc_type
-                assert doc_details.azure_blob_file_list_source.container_url.endswith("training-data-classifier")
+                assert doc_details.azure_blob_file_list_source.container_url
                 assert doc_details.azure_blob_file_list_source.file_list.startswith(doc_type)
 
             classifier = await client.get_classifier(result.classifier_id)

sdk/formrecognizer/azure-ai-formrecognizer/tests/conftest.py

@@ -17,6 +17,7 @@
     add_oauth_response_sanitizer,
     add_body_key_sanitizer,
     test_proxy,
+    remove_batch_sanitizers,
 )
 
 @pytest.fixture(scope="session", autouse=True)
@@ -42,6 +43,10 @@ def add_sanitizers(test_proxy):
         value="redacted",
         regex="([0-9a-f-]{36})",
     )
+    # Remove the following sanitizers since certain fields are needed in tests and are non-sensitive:
+    #  - AZSDK3447: $.key
+    #  - AZSDK2003: Location
+    remove_batch_sanitizers(["AZSDK3447", "AZSDK2003"])
 
 def skip_flaky_test(f):
     @wraps(f)

sdk/formrecognizer/azure-ai-formrecognizer/tests/test_dmac_classifiers.py

@@ -69,7 +69,7 @@ def test_build_classifier(self, client, formrecognizer_training_data_classifier,
         assert result.description == "IRS document classifier"
         for doc_type, source in result.doc_types.items():
             assert doc_type
-            assert source.source.container_url.endswith("training-data-classifier")
+            assert source.source.container_url
             assert source.source.prefix
 
     @FormRecognizerPreparer()
@@ -124,7 +124,7 @@ def test_build_classifier_file_list(self, client, formrecognizer_training_data_c
         assert result.description is None
         for doc_type, source in result.doc_types.items():
             assert doc_type
-            assert source.source.container_url.endswith("training-data-classifier")
+            assert source.source.container_url
             assert source.source.file_list
 
     @FormRecognizerPreparer()

sdk/formrecognizer/azure-ai-formrecognizer/tests/test_dmac_classifiers_async.py

@@ -71,7 +71,7 @@ async def test_build_classifier(self, client, formrecognizer_training_data_class
             assert result.description == "IRS document classifier"
             for doc_type, source in result.doc_types.items():
                 assert doc_type
-                assert source.source.container_url.endswith("training-data-classifier")
+                assert source.source.container_url
                 assert source.source.prefix
 
     @FormRecognizerPreparer()
@@ -127,7 +127,7 @@ async def test_build_classifier_file_list(self, client, formrecognizer_training_
             assert result.description is None
             for doc_type, source in result.doc_types.items():
                 assert doc_type
-                assert source.source.container_url.endswith("training-data-classifier")
+                assert source.source.container_url
                 assert source.source.file_list
 
     @FormRecognizerPreparer()

sdk/healthinsights/azure-healthinsights-radiologyinsights/assets.json

@@ -2,5 +2,5 @@
     "AssetsRepo":  "Azure/azure-sdk-assets",
     "AssetsRepoPrefixPath":  "python",
     "TagPrefix":  "python/healthinsights/azure-healthinsights-radiologyinsights",
-    "Tag": "python/healthinsights/azure-healthinsights-radiologyinsights_69d7fab8d7"
+    "Tag": "python/healthinsights/azure-healthinsights-radiologyinsights_d1fac89a24"
 }

sdk/healthinsights/azure-healthinsights-radiologyinsights/tests/conftest.py

@@ -39,6 +39,6 @@ def add_sanitizers(test_proxy):
     )
     healthinsights_key = os.environ.get("HEALTHINSIGHTS_KEY", "00000000000000000000000000000000")
     add_general_regex_sanitizer(
-        regex=healthinsights_endpoint, value="https://fake_ad_resource.cognitiveservices.azure.com"
+        regex=healthinsights_endpoint, value="https://fake_ad_resource.cognitiveservices.azure.com/"
     )
     add_general_regex_sanitizer(regex=healthinsights_key, value="00000000000000000000000000000000")

sdk/keyvault/azure-keyvault-administration/tests/conftest.py

@@ -13,6 +13,7 @@
     add_oauth_response_sanitizer,
     add_uri_regex_sanitizer,
     is_live,
+    remove_batch_sanitizers,
 )
 
 os.environ['PYTHONHASHSEED'] = '0'
@@ -48,6 +49,11 @@ def add_sanitizers(test_proxy):
     add_uri_regex_sanitizer(regex="keys/([^/]*)\\?api-version=(\\S*)", value="keys/$1?api-version=sanitized")
     add_oauth_response_sanitizer()
 
+    # Remove the following sanitizers since certain fields are needed in tests and are non-sensitive:
+    #  - AZSDK3430: $..id
+    #  - AZSDK3493: $..name
+    remove_batch_sanitizers(["AZSDK3430", "AZSDK3493"])
+
 
 @pytest.fixture(scope="session", autouse=True)
 def patch_async_sleep():