feat: new Bytes and File types POWERPOINT and EXCEL

google/cloud/dlp_v2/types/dlp.py

@@ -189,9 +189,7 @@ class MatchingType(proto.Enum):
 
 
 class ContentOption(proto.Enum):
-    r"""Options describing which parts of the provided content should
-    be scanned.
-    """
+    r"""Deprecated and unused."""
     CONTENT_UNSPECIFIED = 0
     CONTENT_TEXT = 1
     CONTENT_IMAGE = 2
@@ -368,22 +366,22 @@ class InspectConfig(proto.Message):
             to learn more.
         limits (google.cloud.dlp_v2.types.InspectConfig.FindingLimits):
             Configuration to control the number of
-            findings returned.
+            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.
+            response; see Finding.quote. This is not used
+            for data profiling.
         exclude_info_types (bool):
             When true, excludes type information of the
-            findings.
+            findings. This is not used for data profiling.
         custom_info_types (Sequence[google.cloud.dlp_v2.types.CustomInfoType]):
             CustomInfoTypes provided by the user. See
             https://cloud.google.com/dlp/docs/creating-custom-infotypes
             to learn more.
         content_options (Sequence[google.cloud.dlp_v2.types.ContentOption]):
-            List of options defining data content to
-            scan. If empty, text, images, and other content
-            will be included.
+            Deprecated and unused.
         rule_set (Sequence[google.cloud.dlp_v2.types.InspectionRuleSet]):
             Set of rules to apply to the findings for
             this InspectConfig. Exclusion rules, contained
@@ -393,8 +391,9 @@ class InspectConfig(proto.Message):
     """
 
     class FindingLimits(proto.Message):
-        r"""Configuration to control the number of findings returned.
-        Cannot be set if de-identification is requested.
+        r"""Configuration to control the number of findings returned for
+        inspection. This is not used for de-identification or data
+        profiling.
 
         Attributes:
             max_findings_per_item (int):
@@ -476,6 +475,8 @@ class BytesType(proto.Enum):
         TEXT_UTF8 = 5
         WORD_DOCUMENT = 7
         PDF = 8
+        POWERPOINT_DOCUMENT = 9
+        EXCEL_DOCUMENT = 10
         AVRO = 11
         CSV = 12
         TSV = 13

google/cloud/dlp_v2/types/storage.py

@@ -75,6 +75,8 @@ class FileType(proto.Enum):
     AVRO = 7
     CSV = 8
     TSV = 9
+    POWERPOINT = 11
+    EXCEL = 12
 
 
 class InfoType(proto.Message):
@@ -188,23 +190,20 @@ class Dictionary(proto.Message):
         Plane <https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane>`__
         will be replaced with whitespace when scanning for matches, so the
         dictionary phrase "Sam Johnson" will match all three phrases "sam
-        johnson",
-        Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
-        surrounding any match must be of a different type than the adjacent
-        characters within the word, so letters must be next to non-letters
-        and digits next to non-digits. For example, the dictionary word
-        "jen" will match the first three letters of the text "jen123" but
-        will return no matches for "jennifer".
+        johnson", "Sam, Johnson", and "Sam (Johnson)". Additionally, the
+        characters surrounding any match must be of a different type than
+        the adjacent characters within the word, so letters must be next to
+        non-letters and digits next to non-digits. For example, the
+        dictionary word "jen" will match the first three letters of the text
+        "jen123" but will return no matches for "jennifer".
 
         Dictionary words containing a large number of characters that are
         not letters or digits may result in unexpected findings because such
         characters are treated as whitespace. The
         `limits <https://cloud.google.com/dlp/limits>`__ page contains
         details about the size limits of dictionaries. For dictionaries that
         do not fit within these constraints, consider using
-        ``LargeCustomDictionaryConfig`` in the
-        `limits <https://cloud.google.com/dlp/limits>`__ page contains
-        details about
+        ``LargeCustomDictionaryConfig`` in the ``StoredInfoType`` API.
 
         This message has `oneof`_ fields (mutually exclusive fields).
         For each oneof, at most one member field can be set at the same time.
@@ -260,11 +259,9 @@ class Regex(proto.Message):
                 be found under the google/re2 repository on
                 GitHub.
             group_indexes (Sequence[int]):
-                (https://github.com/google/re2/wiki/Syntax)
-                can be found under the The index of the submatch
-                to extract as findings. When not specified, the
-                entire match is returned. No more than 3 may be
-                included.
+                The index of the submatch to extract as
+                findings. When not specified, the entire match
+                is returned. No more than 3 may be included.
         """
 
         pattern = proto.Field(proto.STRING, number=1,)
@@ -275,10 +272,10 @@ class SurrogateType(proto.Message):
         such as
         ```CryptoReplaceFfxFpeConfig`` <https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig>`__.
         These types of transformations are those that perform
-        pseudonymization, thereby producing a "surrogate" as
-        ```CryptoReplaceFfxFpeConfig`` <https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig>`__.
-        transformation such as ``surrogate_info_type``. This CustomInfoType
-        does not support the use of ``detection_rules``.
+        pseudonymization, thereby producing a "surrogate" as output. This
+        should be used in conjunction with a field on the transformation
+        such as ``surrogate_info_type``. This CustomInfoType does not
+        support the use of ``detection_rules``.
 
         """
 
@@ -527,11 +524,9 @@ class CloudStorageRegexFileSet(proto.Message):
             guide can be found under the google/re2 repository on
             GitHub.
         exclude_regex (Sequence[str]):
-            `syntax <https://github.com/google/re2/wiki/Syntax>`__; a
-            guide can be found A list of regular expressions matching
-            file paths to exclude. All files in the bucket that match at
-            least one of these regular expressions will be excluded from
-            the scan.
+            A list of regular expressions matching file paths to
+            exclude. All files in the bucket that match at least one of
+            these regular expressions will be excluded from the scan.
 
             Regular expressions use RE2
             `syntax <https://github.com/google/re2/wiki/Syntax>`__; a