feat: InfoType categories were added to built-in infoTypes

google/cloud/dlp/__init__.py

@@ -81,6 +81,7 @@
     HybridInspectResponse,
     HybridInspectStatistics,
     ImageLocation,
+    InfoTypeCategory,
     InfoTypeDescription,
     InfoTypeStats,
     InfoTypeSummary,
@@ -255,6 +256,7 @@
     "HybridInspectResponse",
     "HybridInspectStatistics",
     "ImageLocation",
+    "InfoTypeCategory",
     "InfoTypeDescription",
     "InfoTypeStats",
     "InfoTypeSummary",

google/cloud/dlp_v2/__init__.py

@@ -80,6 +80,7 @@
     HybridInspectResponse,
     HybridInspectStatistics,
     ImageLocation,
+    InfoTypeCategory,
     InfoTypeDescription,
     InfoTypeStats,
     InfoTypeSummary,
@@ -273,6 +274,7 @@
     "HybridOptions",
     "ImageLocation",
     "InfoType",
+    "InfoTypeCategory",
     "InfoTypeDescription",
     "InfoTypeStats",
     "InfoTypeSummary",

google/cloud/dlp_v2/services/dlp_service/client.py

@@ -549,6 +549,7 @@ def __init__(
                 quota_project_id=client_options.quota_project_id,
                 client_info=client_info,
                 always_use_jwt_access=True,
+                api_audience=client_options.api_audience,
             )
 
     def inspect_content(

google/cloud/dlp_v2/services/dlp_service/transports/base.py

@@ -55,6 +55,7 @@ def __init__(
         quota_project_id: Optional[str] = None,
         client_info: gapic_v1.client_info.ClientInfo = DEFAULT_CLIENT_INFO,
         always_use_jwt_access: Optional[bool] = False,
+        api_audience: Optional[str] = None,
         **kwargs,
     ) -> None:
         """Instantiate the transport.
@@ -82,11 +83,6 @@ def __init__(
                 be used for service account credentials.
         """
 
-        # Save the hostname. Default to port 443 (HTTPS) if none is specified.
-        if ":" not in host:
-            host += ":443"
-        self._host = host
-
         scopes_kwargs = {"scopes": scopes, "default_scopes": self.AUTH_SCOPES}
 
         # Save the scopes.
@@ -107,6 +103,11 @@ def __init__(
             credentials, _ = google.auth.default(
                 **scopes_kwargs, quota_project_id=quota_project_id
             )
+            # Don't apply audience if the credentials file passed from user.
+            if hasattr(credentials, "with_gdch_audience"):
+                credentials = credentials.with_gdch_audience(
+                    api_audience if api_audience else host
+                )
 
         # If the credentials are service account credentials, then always try to use self signed JWT.
         if (
@@ -119,6 +120,11 @@ def __init__(
         # Save the credentials.
         self._credentials = credentials
 
+        # Save the hostname. Default to port 443 (HTTPS) if none is specified.
+        if ":" not in host:
+            host += ":443"
+        self._host = host
+
     def _prep_wrapped_messages(self, client_info):
         # Precompute the wrapped methods.
         self._wrapped_methods = {

google/cloud/dlp_v2/services/dlp_service/transports/grpc.py

@@ -67,6 +67,7 @@ def __init__(
         quota_project_id: Optional[str] = None,
         client_info: gapic_v1.client_info.ClientInfo = DEFAULT_CLIENT_INFO,
         always_use_jwt_access: Optional[bool] = False,
+        api_audience: Optional[str] = None,
     ) -> None:
         """Instantiate the transport.
 
@@ -162,6 +163,7 @@ def __init__(
             quota_project_id=quota_project_id,
             client_info=client_info,
             always_use_jwt_access=always_use_jwt_access,
+            api_audience=api_audience,
         )
 
         if not self._grpc_channel:

google/cloud/dlp_v2/services/dlp_service/transports/grpc_asyncio.py

@@ -112,6 +112,7 @@ def __init__(
         quota_project_id=None,
         client_info: gapic_v1.client_info.ClientInfo = DEFAULT_CLIENT_INFO,
         always_use_jwt_access: Optional[bool] = False,
+        api_audience: Optional[str] = None,
     ) -> None:
         """Instantiate the transport.
 
@@ -207,6 +208,7 @@ def __init__(
             quota_project_id=quota_project_id,
             client_info=client_info,
             always_use_jwt_access=always_use_jwt_access,
+            api_audience=api_audience,
         )
 
         if not self._grpc_channel:

google/cloud/dlp_v2/types/__init__.py

@@ -78,6 +78,7 @@
     HybridInspectResponse,
     HybridInspectStatistics,
     ImageLocation,
+    InfoTypeCategory,
     InfoTypeDescription,
     InfoTypeStats,
     InfoTypeSummary,
@@ -250,6 +251,7 @@
     "HybridInspectResponse",
     "HybridInspectStatistics",
     "ImageLocation",
+    "InfoTypeCategory",
     "InfoTypeDescription",
     "InfoTypeStats",
     "InfoTypeSummary",

google/cloud/dlp_v2/types/dlp.py

@@ -72,6 +72,7 @@
         "InspectDataSourceDetails",
         "HybridInspectStatistics",
         "InfoTypeDescription",
+        "InfoTypeCategory",
         "ListInfoTypesRequest",
         "ListInfoTypesResponse",
         "RiskAnalysisJobConfig",
@@ -423,10 +424,10 @@ class InspectConfig(proto.Message):
             findings returned. This is not used for data
             profiling.
         include_quote (bool):
-            When true, a contextual quote from the data
-            that triggered a finding is included in the
-            response; see Finding.quote. This is not used
-            for data profiling.
+            When true, a contextual quote from the data that triggered a
+            finding is included in the response; see
+            [Finding.quote][google.privacy.dlp.v2.Finding.quote]. This
+            is not used for data profiling.
         exclude_info_types (bool):
             When true, excludes type information of the
             findings. This is not used for data profiling.
@@ -1907,6 +1908,8 @@ class InfoTypeDescription(proto.Message):
         description (str):
             Description of the infotype. Translated when
             language is provided in the request.
+        categories (Sequence[google.cloud.dlp_v2.types.InfoTypeCategory]):
+            The category of the infoType.
     """
 
     name = proto.Field(
@@ -1926,6 +1929,128 @@ class InfoTypeDescription(proto.Message):
         proto.STRING,
         number=4,
     )
+    categories = proto.RepeatedField(
+        proto.MESSAGE,
+        number=10,
+        message="InfoTypeCategory",
+    )
+
+
+class InfoTypeCategory(proto.Message):
+    r"""Classification of infoTypes to organize them according to
+    geographic location, industry, and data type.
+
+    This message has `oneof`_ fields (mutually exclusive fields).
+    For each oneof, at most one member field can be set at the same time.
+    Setting any member of the oneof automatically clears all other
+    members.
+
+    .. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields
+
+    Attributes:
+        location_category (google.cloud.dlp_v2.types.InfoTypeCategory.LocationCategory):
+            The region or country that issued the ID or
+            document represented by the infoType.
+
+            This field is a member of `oneof`_ ``category``.
+        industry_category (google.cloud.dlp_v2.types.InfoTypeCategory.IndustryCategory):
+            The group of relevant businesses where this
+            infoType is commonly used
+
+            This field is a member of `oneof`_ ``category``.
+        type_category (google.cloud.dlp_v2.types.InfoTypeCategory.TypeCategory):
+            The class of identifiers where this infoType
+            belongs
+
+            This field is a member of `oneof`_ ``category``.
+    """
+
+    class LocationCategory(proto.Enum):
+        r"""Enum of the current locations.
+        We might add more locations in the future.
+        """
+        LOCATION_UNSPECIFIED = 0
+        GLOBAL = 1
+        ARGENTINA = 2
+        AUSTRALIA = 3
+        BELGIUM = 4
+        BRAZIL = 5
+        CANADA = 6
+        CHILE = 7
+        CHINA = 8
+        COLOMBIA = 9
+        DENMARK = 10
+        FRANCE = 11
+        FINLAND = 12
+        GERMANY = 13
+        HONG_KONG = 14
+        INDIA = 15
+        INDONESIA = 16
+        IRELAND = 17
+        ISRAEL = 18
+        ITALY = 19
+        JAPAN = 20
+        KOREA = 21
+        MEXICO = 22
+        THE_NETHERLANDS = 23
+        NORWAY = 24
+        PARAGUAY = 25
+        PERU = 26
+        POLAND = 27
+        PORTUGAL = 28
+        SINGAPORE = 29
+        SOUTH_AFRICA = 30
+        SPAIN = 31
+        SWEDEN = 32
+        TAIWAN = 33
+        THAILAND = 34
+        TURKEY = 35
+        UNITED_KINGDOM = 36
+        UNITED_STATES = 37
+        URUGUAY = 38
+        VENEZUELA = 39
+        INTERNAL = 40
+
+    class IndustryCategory(proto.Enum):
+        r"""Enum of the current industries in the category.
+        We might add more industries in the future.
+        """
+        INDUSTRY_UNSPECIFIED = 0
+        FINANCE = 1
+        HEALTH = 2
+        TELECOMMUNICATIONS = 3
+
+    class TypeCategory(proto.Enum):
+        r"""Enum of the current types in the category.
+        We might add more types in the future.
+        """
+        TYPE_UNSPECIFIED = 0
+        PII = 1
+        SPII = 2
+        DEMOGRAPHIC = 3
+        CREDENTIAL = 4
+        GOVERNMENT_ID = 5
+        DOCUMENT = 6
+        CONTEXTUAL_INFORMATION = 7
+
+    location_category = proto.Field(
+        proto.ENUM,
+        number=1,
+        oneof="category",
+        enum=LocationCategory,
+    )
+    industry_category = proto.Field(
+        proto.ENUM,
+        number=2,
+        oneof="category",
+        enum=IndustryCategory,
+    )
+    type_category = proto.Field(
+        proto.ENUM,
+        number=3,
+        oneof="category",
+        enum=TypeCategory,
+    )
 
 
 class ListInfoTypesRequest(proto.Message):

google/cloud/dlp_v2/types/storage.py

@@ -324,8 +324,12 @@ class Proximity(proto.Message):
 
             Attributes:
                 window_before (int):
-                    Number of characters before the finding to
-                    consider.
+                    Number of characters before the finding to consider. For
+                    tabular data, if you want to modify the likelihood of an
+                    entire column of findngs, set this to 1. For more
+                    information, see [Hotword example: Set the match likelihood
+                    of a table column]
+                    (https://cloud.google.com/dlp/docs/creating-custom-infotypes-likelihood#match-column-values).
                 window_after (int):
                     Number of characters after the finding to
                     consider.
@@ -392,18 +396,20 @@ class HotwordRule(proto.Message):
                     Regular expression pattern defining what
                     qualifies as a hotword.
                 proximity (google.cloud.dlp_v2.types.CustomInfoType.DetectionRule.Proximity):
-                    Proximity of the finding within which the
-                    entire hotword must reside. The total length of
-                    the window cannot exceed 1000 characters. Note
-                    that the finding itself will be included in the
-                    window, so that hotwords may be used to match
-                    substrings of the finding itself. For example,
-                    the certainty of a phone number regex "\(\d{3}\)
-                    \d{3}-\d{4}" could be adjusted upwards if the
-                    area code is known to be the local area code of
-                    a company office using the hotword regex
-                    "\(xxx\)", where "xxx" is the area code in
-                    question.
+                    Range of characters within which the entire hotword must
+                    reside. The total length of the window cannot exceed 1000
+                    characters. The finding itself will be included in the
+                    window, so that hotwords can be used to match substrings of
+                    the finding itself. Suppose you want Cloud DLP to promote
+                    the likelihood of the phone number regex "(\d{3})
+                    \\d{3}-\d{4}" if the area code is known to be the area code
+                    of a company's office. In this case, use the hotword regex
+                    "(xxx)", where "xxx" is the area code in question.
+
+                    For tabular data, if you want to modify the likelihood of an
+                    entire column of findngs, see [Hotword example: Set the
+                    match likelihood of a table column]
+                    (https://cloud.google.com/dlp/docs/creating-custom-infotypes-likelihood#match-column-values).
                 likelihood_adjustment (google.cloud.dlp_v2.types.CustomInfoType.DetectionRule.LikelihoodAdjustment):
                     Likelihood adjustment to apply to all
                     matching findings.

setup.py

@@ -24,10 +24,7 @@
 version = "3.7.1"
 release_status = "Development Status :: 5 - Production/Stable"
 dependencies = [
-    # NOTE: Maintainers, please do not require google-api-core>=2.x.x
-    # Until this issue is closed
-    # https://github.com/googleapis/google-cloud-python/issues/10566
-    "google-api-core[grpc] >= 1.31.5, <3.0.0dev,!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0",
+    "google-api-core[grpc] >= 1.32.0, <3.0.0dev,!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.*,!=2.4.*,!=2.5.*,!=2.6.*,!=2.7.*",
     "proto-plus >= 1.15.0, <2.0.0dev",
     "protobuf >= 3.19.0, <4.0.0dev",
 ]

testing/constraints-3.7.txt

@@ -5,7 +5,7 @@
 #
 # e.g., if setup.py has "foo >= 1.14.0, < 2.0.0dev",
 # Then this file should have foo==1.14.0
-google-api-core==1.31.5
+google-api-core==1.32.0
 proto-plus==1.15.0
 libcst==0.2.5
 protobuf==3.19.0