Class: Google::Privacy::Dlp::V2::CloudStorageOptions

Inherits:
Object
  • Object
show all
Defined in:
lib/google/cloud/dlp/v2/doc/google/privacy/dlp/v2/storage.rb

Overview

Options defining a file or a set of files within a Google Cloud Storage bucket.

Defined Under Namespace

Modules: SampleMethod Classes: FileSet

Instance Attribute Summary collapse

Instance Attribute Details

#bytes_limit_per_file ⇒ Integer

Returns Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

Returns:

  • (Integer) —

    Max number of bytes to scan from a file. If a scanned file's size is bigger than this value then the rest of the bytes are omitted. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.



331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
 
# File 'lib/google/cloud/dlp/v2/doc/google/privacy/dlp/v2/storage.rb', line 331

class CloudStorageOptions
  # Set of files to scan.
  # @!attribute [rw] url
  #   @return [String]
  #     The Cloud Storage url of the file(s) to scan, in the format
  #     `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.
  #
  #     If the url ends in a trailing slash, the bucket or directory represented
  #     by the url will be scanned non-recursively (content in sub-directories
  #     will not be scanned). This means that `gs://mybucket/` is equivalent to
  #     `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
  #     `gs://mybucket/directory/*`.
  #
  #     Exactly one of `url` or `regex_file_set` must be set.
  # @!attribute [rw] regex_file_set
  #   @return [Google::Privacy::Dlp::V2::CloudStorageRegexFileSet]
  #     The regex-filtered set of files to scan. Exactly one of `url` or
  #     `regex_file_set` must be set.
  class FileSet; end

  # How to sample bytes if not all bytes are scanned. Meaningful only when used
  # in conjunction with bytes_limit_per_file. If not specified, scanning would
  # start from the top.
  module SampleMethod
    SAMPLE_METHOD_UNSPECIFIED = 0

    # Scan from the top (default).
    TOP = 1

    # For each file larger than bytes_limit_per_file, randomly pick the offset
    # to start scanning. The scanned bytes are contiguous.
    RANDOM_START = 2
  end
end

#bytes_limit_per_file_percent ⇒ Integer

Returns Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

Returns:

  • (Integer) —

    Max percentage of bytes to scan from a file. The rest are omitted. The number of bytes scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.



331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
 
# File 'lib/google/cloud/dlp/v2/doc/google/privacy/dlp/v2/storage.rb', line 331

class CloudStorageOptions
  # Set of files to scan.
  # @!attribute [rw] url
  #   @return [String]
  #     The Cloud Storage url of the file(s) to scan, in the format
  #     `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.
  #
  #     If the url ends in a trailing slash, the bucket or directory represented
  #     by the url will be scanned non-recursively (content in sub-directories
  #     will not be scanned). This means that `gs://mybucket/` is equivalent to
  #     `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
  #     `gs://mybucket/directory/*`.
  #
  #     Exactly one of `url` or `regex_file_set` must be set.
  # @!attribute [rw] regex_file_set
  #   @return [Google::Privacy::Dlp::V2::CloudStorageRegexFileSet]
  #     The regex-filtered set of files to scan. Exactly one of `url` or
  #     `regex_file_set` must be set.
  class FileSet; end

  # How to sample bytes if not all bytes are scanned. Meaningful only when used
  # in conjunction with bytes_limit_per_file. If not specified, scanning would
  # start from the top.
  module SampleMethod
    SAMPLE_METHOD_UNSPECIFIED = 0

    # Scan from the top (default).
    TOP = 1

    # For each file larger than bytes_limit_per_file, randomly pick the offset
    # to start scanning. The scanned bytes are contiguous.
    RANDOM_START = 2
  end
end

#file_set ⇒ Google::Privacy::Dlp::V2::CloudStorageOptions::FileSet

Returns The set of one or more files to scan.

Returns:



331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
 
# File 'lib/google/cloud/dlp/v2/doc/google/privacy/dlp/v2/storage.rb', line 331

class CloudStorageOptions
  # Set of files to scan.
  # @!attribute [rw] url
  #   @return [String]
  #     The Cloud Storage url of the file(s) to scan, in the format
  #     `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.
  #
  #     If the url ends in a trailing slash, the bucket or directory represented
  #     by the url will be scanned non-recursively (content in sub-directories
  #     will not be scanned). This means that `gs://mybucket/` is equivalent to
  #     `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
  #     `gs://mybucket/directory/*`.
  #
  #     Exactly one of `url` or `regex_file_set` must be set.
  # @!attribute [rw] regex_file_set
  #   @return [Google::Privacy::Dlp::V2::CloudStorageRegexFileSet]
  #     The regex-filtered set of files to scan. Exactly one of `url` or
  #     `regex_file_set` must be set.
  class FileSet; end

  # How to sample bytes if not all bytes are scanned. Meaningful only when used
  # in conjunction with bytes_limit_per_file. If not specified, scanning would
  # start from the top.
  module SampleMethod
    SAMPLE_METHOD_UNSPECIFIED = 0

    # Scan from the top (default).
    TOP = 1

    # For each file larger than bytes_limit_per_file, randomly pick the offset
    # to start scanning. The scanned bytes are contiguous.
    RANDOM_START = 2
  end
end

#file_types ⇒ Array<Google::Privacy::Dlp::V2::FileType>

Returns List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well.

Returns:

  • (Array<Google::Privacy::Dlp::V2::FileType>) —

    List of file type groups to include in the scan. If empty, all files are scanned and available data format processors are applied. In addition, the binary content of the selected files is always scanned as well.



331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
 
# File 'lib/google/cloud/dlp/v2/doc/google/privacy/dlp/v2/storage.rb', line 331

class CloudStorageOptions
  # Set of files to scan.
  # @!attribute [rw] url
  #   @return [String]
  #     The Cloud Storage url of the file(s) to scan, in the format
  #     `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.
  #
  #     If the url ends in a trailing slash, the bucket or directory represented
  #     by the url will be scanned non-recursively (content in sub-directories
  #     will not be scanned). This means that `gs://mybucket/` is equivalent to
  #     `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
  #     `gs://mybucket/directory/*`.
  #
  #     Exactly one of `url` or `regex_file_set` must be set.
  # @!attribute [rw] regex_file_set
  #   @return [Google::Privacy::Dlp::V2::CloudStorageRegexFileSet]
  #     The regex-filtered set of files to scan. Exactly one of `url` or
  #     `regex_file_set` must be set.
  class FileSet; end

  # How to sample bytes if not all bytes are scanned. Meaningful only when used
  # in conjunction with bytes_limit_per_file. If not specified, scanning would
  # start from the top.
  module SampleMethod
    SAMPLE_METHOD_UNSPECIFIED = 0

    # Scan from the top (default).
    TOP = 1

    # For each file larger than bytes_limit_per_file, randomly pick the offset
    # to start scanning. The scanned bytes are contiguous.
    RANDOM_START = 2
  end
end

#files_limit_percent ⇒ Integer

Returns Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.

Returns:

  • (Integer) —

    Limits the number of files to scan to this percentage of the input FileSet. Number of files scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and 100 means no limit. Defaults to 0.



331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
 
# File 'lib/google/cloud/dlp/v2/doc/google/privacy/dlp/v2/storage.rb', line 331

class CloudStorageOptions
  # Set of files to scan.
  # @!attribute [rw] url
  #   @return [String]
  #     The Cloud Storage url of the file(s) to scan, in the format
  #     `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.
  #
  #     If the url ends in a trailing slash, the bucket or directory represented
  #     by the url will be scanned non-recursively (content in sub-directories
  #     will not be scanned). This means that `gs://mybucket/` is equivalent to
  #     `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
  #     `gs://mybucket/directory/*`.
  #
  #     Exactly one of `url` or `regex_file_set` must be set.
  # @!attribute [rw] regex_file_set
  #   @return [Google::Privacy::Dlp::V2::CloudStorageRegexFileSet]
  #     The regex-filtered set of files to scan. Exactly one of `url` or
  #     `regex_file_set` must be set.
  class FileSet; end

  # How to sample bytes if not all bytes are scanned. Meaningful only when used
  # in conjunction with bytes_limit_per_file. If not specified, scanning would
  # start from the top.
  module SampleMethod
    SAMPLE_METHOD_UNSPECIFIED = 0

    # Scan from the top (default).
    TOP = 1

    # For each file larger than bytes_limit_per_file, randomly pick the offset
    # to start scanning. The scanned bytes are contiguous.
    RANDOM_START = 2
  end
end

#sample_method ⇒ Google::Privacy::Dlp::V2::CloudStorageOptions::SampleMethod

Returns:



331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
 
# File 'lib/google/cloud/dlp/v2/doc/google/privacy/dlp/v2/storage.rb', line 331

class CloudStorageOptions
  # Set of files to scan.
  # @!attribute [rw] url
  #   @return [String]
  #     The Cloud Storage url of the file(s) to scan, in the format
  #     `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.
  #
  #     If the url ends in a trailing slash, the bucket or directory represented
  #     by the url will be scanned non-recursively (content in sub-directories
  #     will not be scanned). This means that `gs://mybucket/` is equivalent to
  #     `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
  #     `gs://mybucket/directory/*`.
  #
  #     Exactly one of `url` or `regex_file_set` must be set.
  # @!attribute [rw] regex_file_set
  #   @return [Google::Privacy::Dlp::V2::CloudStorageRegexFileSet]
  #     The regex-filtered set of files to scan. Exactly one of `url` or
  #     `regex_file_set` must be set.
  class FileSet; end

  # How to sample bytes if not all bytes are scanned. Meaningful only when used
  # in conjunction with bytes_limit_per_file. If not specified, scanning would
  # start from the top.
  module SampleMethod
    SAMPLE_METHOD_UNSPECIFIED = 0

    # Scan from the top (default).
    TOP = 1

    # For each file larger than bytes_limit_per_file, randomly pick the offset
    # to start scanning. The scanned bytes are contiguous.
    RANDOM_START = 2
  end
end