| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1 | <html><body> |
| 2 | <style> |
| 3 | |
| 4 | body, h1, h2, h3, div, span, p, pre, a { |
| 5 | margin: 0; |
| 6 | padding: 0; |
| 7 | border: 0; |
| 8 | font-weight: inherit; |
| 9 | font-style: inherit; |
| 10 | font-size: 100%; |
| 11 | font-family: inherit; |
| 12 | vertical-align: baseline; |
| 13 | } |
| 14 | |
| 15 | body { |
| 16 | font-size: 13px; |
| 17 | padding: 1em; |
| 18 | } |
| 19 | |
| 20 | h1 { |
| 21 | font-size: 26px; |
| 22 | margin-bottom: 1em; |
| 23 | } |
| 24 | |
| 25 | h2 { |
| 26 | font-size: 24px; |
| 27 | margin-bottom: 1em; |
| 28 | } |
| 29 | |
| 30 | h3 { |
| 31 | font-size: 20px; |
| 32 | margin-bottom: 1em; |
| 33 | margin-top: 1em; |
| 34 | } |
| 35 | |
| 36 | pre, code { |
| 37 | line-height: 1.5; |
| 38 | font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace; |
| 39 | } |
| 40 | |
| 41 | pre { |
| 42 | margin-top: 0.5em; |
| 43 | } |
| 44 | |
| 45 | h1, h2, h3, p { |
| 46 | font-family: Arial, sans serif; |
| 47 | } |
| 48 | |
| 49 | h1, h2, h3 { |
| 50 | border-bottom: solid #CCC 1px; |
| 51 | } |
| 52 | |
| 53 | .toc_element { |
| 54 | margin-top: 0.5em; |
| 55 | } |
| 56 | |
| 57 | .firstline { |
| 58 | margin-left: 2 em; |
| 59 | } |
| 60 | |
| 61 | .method { |
| 62 | margin-top: 1em; |
| 63 | border: solid 1px #CCC; |
| 64 | padding: 1em; |
| 65 | background: #EEE; |
| 66 | } |
| 67 | |
| 68 | .details { |
| 69 | font-weight: bold; |
| 70 | font-size: 14px; |
| 71 | } |
| 72 | |
| 73 | </style> |
| 74 | |
| 75 | <h1><a href="dlp_v2.html">Cloud Data Loss Prevention (DLP) API</a> . <a href="dlp_v2.projects.html">projects</a> . <a href="dlp_v2.projects.dlpJobs.html">dlpJobs</a></h1> |
| 76 | <h2>Instance Methods</h2> |
| 77 | <p class="toc_element"> |
| 78 | <code><a href="#cancel">cancel(name, body=None, x__xgafv=None)</a></code></p> |
| 79 | <p class="firstline">Starts asynchronous cancellation on a long-running DlpJob. The server</p> |
| 80 | <p class="toc_element"> |
| Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 81 | <code><a href="#create">create(parent, body=None, x__xgafv=None)</a></code></p> |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 82 | <p class="firstline">Creates a new job to inspect storage or calculate risk metrics.</p> |
| 83 | <p class="toc_element"> |
| 84 | <code><a href="#delete">delete(name, x__xgafv=None)</a></code></p> |
| 85 | <p class="firstline">Deletes a long-running DlpJob. This method indicates that the client is</p> |
| 86 | <p class="toc_element"> |
| 87 | <code><a href="#get">get(name, x__xgafv=None)</a></code></p> |
| 88 | <p class="firstline">Gets the latest state of a long-running DlpJob.</p> |
| 89 | <p class="toc_element"> |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 90 | <code><a href="#list">list(parent, orderBy=None, type=None, filter=None, pageToken=None, locationId=None, pageSize=None, x__xgafv=None)</a></code></p> |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 91 | <p class="firstline">Lists DlpJobs that match the specified filter in the request.</p> |
| 92 | <p class="toc_element"> |
| 93 | <code><a href="#list_next">list_next(previous_request, previous_response)</a></code></p> |
| 94 | <p class="firstline">Retrieves the next page of results.</p> |
| 95 | <h3>Method Details</h3> |
| 96 | <div class="method"> |
| 97 | <code class="details" id="cancel">cancel(name, body=None, x__xgafv=None)</code> |
| 98 | <pre>Starts asynchronous cancellation on a long-running DlpJob. The server |
| 99 | makes a best effort to cancel the DlpJob, but success is not |
| 100 | guaranteed. |
| 101 | See https://cloud.google.com/dlp/docs/inspecting-storage and |
| 102 | https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more. |
| 103 | |
| 104 | Args: |
| Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 105 | name: string, Required. The name of the DlpJob resource to be cancelled. (required) |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 106 | body: object, The request body. |
| 107 | The object takes the form of: |
| 108 | |
| 109 | { # The request message for canceling a DLP job. |
| 110 | } |
| 111 | |
| 112 | x__xgafv: string, V1 error format. |
| 113 | Allowed values |
| 114 | 1 - v1 error format |
| 115 | 2 - v2 error format |
| 116 | |
| 117 | Returns: |
| 118 | An object of the form: |
| 119 | |
| 120 | { # A generic empty message that you can re-use to avoid defining duplicated |
| 121 | # empty messages in your APIs. A typical example is to use it as the request |
| 122 | # or the response type of an API method. For instance: |
| 123 | # |
| 124 | # service Foo { |
| 125 | # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); |
| 126 | # } |
| 127 | # |
| 128 | # The JSON representation for `Empty` is empty JSON object `{}`. |
| 129 | }</pre> |
| 130 | </div> |
| 131 | |
| 132 | <div class="method"> |
| Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 133 | <code class="details" id="create">create(parent, body=None, x__xgafv=None)</code> |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 134 | <pre>Creates a new job to inspect storage or calculate risk metrics. |
| 135 | See https://cloud.google.com/dlp/docs/inspecting-storage and |
| 136 | https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more. |
| 137 | |
| 138 | When no InfoTypes or CustomInfoTypes are specified in inspect jobs, the |
| 139 | system will automatically choose what detectors to run. By default this may |
| 140 | be all types, but may change over time as detectors are updated. |
| 141 | |
| 142 | Args: |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 143 | parent: string, Required. Parent resource name. |
| 144 | - Format:projects/[PROJECT-ID] |
| 145 | - Format:projects/[PROJECT-ID]/locations/[LOCATION-ID] (required) |
| Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 146 | body: object, The request body. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 147 | The object takes the form of: |
| 148 | |
| 149 | { # Request message for CreateDlpJobRequest. Used to initiate long running |
| 150 | # jobs such as calculating risk metrics or inspecting Google Cloud |
| 151 | # Storage. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 152 | "jobId": "A String", # The job id can contain uppercase and lowercase letters, |
| 153 | # numbers, and hyphens; that is, it must match the regular |
| 154 | # expression: `[a-zA-Z\\d-_]+`. The maximum length is 100 |
| 155 | # characters. Can be empty to allow the system to generate one. |
| 156 | "locationId": "A String", # Deprecated. This field has no effect. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 157 | "riskJob": { # Configuration for a risk analysis job. See # Set to choose what metric to calculate. |
| 158 | # https://cloud.google.com/dlp/docs/concepts-risk-analysis to learn more. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 159 | "privacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 160 | "categoricalStatsConfig": { # Compute numerical stats over an individual column, including # Categorical stats |
| 161 | # number of distinct values and value count distribution. |
| 162 | "field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are |
| 163 | # supported except for arrays and structs. However, it may be more |
| 164 | # informative to use NumericalStats when the field type is supported, |
| 165 | # depending on the data. |
| 166 | "name": "A String", # Name describing the field. |
| 167 | }, |
| 168 | }, |
| 169 | "lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity |
| 170 | "sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value. |
| 171 | "name": "A String", # Name describing the field. |
| 172 | }, |
| 173 | "quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are |
| 174 | # defined for the l-diversity computation. When multiple fields are |
| 175 | # specified, they are considered a single composite key. |
| 176 | { # General identifier of a data field in a storage service. |
| 177 | "name": "A String", # Name describing the field. |
| 178 | }, |
| 179 | ], |
| 180 | }, |
| 181 | "kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what # k-map |
| 182 | # is called "journalist risk" in the literature, except the attack dataset is |
| 183 | # statistically modeled instead of being perfectly known. This can be done |
| 184 | # using publicly available data (like the US Census), or using a custom |
| 185 | # statistical model (indicated as one or several BigQuery tables), or by |
| 186 | # extrapolating from the distribution of values in the input dataset. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 187 | "regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. |
| 188 | # Set if no column is tagged with a region-specific InfoType (like |
| 189 | # US_ZIP_5) or a region code. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 190 | "quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the |
| 191 | # same tag. |
| 192 | { # A column with a semantic tag attached. |
| 193 | "field": { # General identifier of a data field in a storage service. # Required. Identifies the column. |
| 194 | "name": "A String", # Name describing the field. |
| 195 | }, |
| 196 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 197 | # indicate an auxiliary table that contains statistical information on |
| 198 | # the possible values of this column (below). |
| 199 | "infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public |
| 200 | # dataset as a statistical model of population, if available. We |
| 201 | # currently support US ZIP codes, region codes, ages and genders. |
| 202 | # To programmatically obtain the list of supported InfoTypes, use |
| 203 | # ListInfoTypes with the supported_by=RISK_ANALYSIS filter. |
| 204 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 205 | # creating a CustomInfoType, or one of the names listed |
| 206 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 207 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 208 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 209 | }, |
| 210 | "inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from |
| 211 | # the distribution of values in the input data |
| 212 | # empty messages in your APIs. A typical example is to use it as the request |
| 213 | # or the response type of an API method. For instance: |
| 214 | # |
| 215 | # service Foo { |
| 216 | # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); |
| 217 | # } |
| 218 | # |
| 219 | # The JSON representation for `Empty` is empty JSON object `{}`. |
| 220 | }, |
| 221 | }, |
| 222 | ], |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 223 | "auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 224 | # used to tag a quasi-identifiers column must appear in exactly one column |
| 225 | # of one auxiliary table. |
| 226 | { # An auxiliary table contains statistical information on the relative |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 227 | # frequency of different quasi-identifiers values. It has one or several |
| 228 | # quasi-identifiers columns, and one column that indicates the relative |
| 229 | # frequency of each quasi-identifier tuple. |
| 230 | # If a tuple is present in the data but not in the auxiliary table, the |
| 231 | # corresponding relative frequency is assumed to be zero (and thus, the |
| 232 | # tuple is highly reidentifiable). |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 233 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location. |
| 234 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 235 | # a table is often referenced with a string in the format of: |
| 236 | # `<project_id>:<dataset_id>.<table_id>` or |
| 237 | # `<project_id>.<dataset_id>.<table_id>`. |
| 238 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 239 | # If omitted, project ID is inferred from the API call. |
| 240 | "datasetId": "A String", # Dataset ID of the table. |
| 241 | "tableId": "A String", # Name of the table. |
| 242 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 243 | "quasiIds": [ # Required. Quasi-identifier columns. |
| 244 | { # A quasi-identifier column has a custom_tag, used to know which column |
| 245 | # in the data corresponds to which column in the statistical model. |
| 246 | "customTag": "A String", # A auxiliary field. |
| 247 | "field": { # General identifier of a data field in a storage service. # Identifies the column. |
| 248 | "name": "A String", # Name describing the field. |
| 249 | }, |
| 250 | }, |
| 251 | ], |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 252 | "relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number |
| 253 | # between 0 and 1 (inclusive). Null values are assumed to be zero. |
| 254 | "name": "A String", # Name describing the field. |
| 255 | }, |
| 256 | }, |
| 257 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 258 | }, |
| 259 | "deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to # delta-presence |
| 260 | # figure out that one given individual appears in a de-identified dataset. |
| 261 | # Similarly to the k-map metric, we cannot compute δ-presence exactly without |
| 262 | # knowing the attack dataset, so we use a statistical model instead. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 263 | "quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the |
| 264 | # same tag. |
| 265 | { # A column with a semantic tag attached. |
| 266 | "field": { # General identifier of a data field in a storage service. # Required. Identifies the column. |
| 267 | "name": "A String", # Name describing the field. |
| 268 | }, |
| 269 | "infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public |
| 270 | # dataset as a statistical model of population, if available. We |
| 271 | # currently support US ZIP codes, region codes, ages and genders. |
| 272 | # To programmatically obtain the list of supported InfoTypes, use |
| 273 | # ListInfoTypes with the supported_by=RISK_ANALYSIS filter. |
| 274 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 275 | # creating a CustomInfoType, or one of the names listed |
| 276 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 277 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 278 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 279 | }, |
| 280 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 281 | # indicate an auxiliary table that contains statistical information on |
| 282 | # the possible values of this column (below). |
| 283 | "inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from |
| 284 | # the distribution of values in the input data |
| 285 | # empty messages in your APIs. A typical example is to use it as the request |
| 286 | # or the response type of an API method. For instance: |
| 287 | # |
| 288 | # service Foo { |
| 289 | # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); |
| 290 | # } |
| 291 | # |
| 292 | # The JSON representation for `Empty` is empty JSON object `{}`. |
| 293 | }, |
| 294 | }, |
| 295 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 296 | "auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag |
| 297 | # used to tag a quasi-identifiers field must appear in exactly one |
| 298 | # field of one auxiliary table. |
| 299 | { # An auxiliary table containing statistical information on the relative |
| 300 | # frequency of different quasi-identifiers values. It has one or several |
| 301 | # quasi-identifiers columns, and one column that indicates the relative |
| 302 | # frequency of each quasi-identifier tuple. |
| 303 | # If a tuple is present in the data but not in the auxiliary table, the |
| 304 | # corresponding relative frequency is assumed to be zero (and thus, the |
| 305 | # tuple is highly reidentifiable). |
| 306 | "relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number |
| 307 | # between 0 and 1 (inclusive). Null values are assumed to be zero. |
| 308 | "name": "A String", # Name describing the field. |
| 309 | }, |
| 310 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location. |
| 311 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 312 | # a table is often referenced with a string in the format of: |
| 313 | # `<project_id>:<dataset_id>.<table_id>` or |
| 314 | # `<project_id>.<dataset_id>.<table_id>`. |
| 315 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 316 | # If omitted, project ID is inferred from the API call. |
| 317 | "datasetId": "A String", # Dataset ID of the table. |
| 318 | "tableId": "A String", # Name of the table. |
| 319 | }, |
| 320 | "quasiIds": [ # Required. Quasi-identifier columns. |
| 321 | { # A quasi-identifier column has a custom_tag, used to know which column |
| 322 | # in the data corresponds to which column in the statistical model. |
| 323 | "field": { # General identifier of a data field in a storage service. # Identifies the column. |
| 324 | "name": "A String", # Name describing the field. |
| 325 | }, |
| 326 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 327 | # indicate an auxiliary table that contains statistical information on |
| 328 | # the possible values of this column (below). |
| 329 | }, |
| 330 | ], |
| 331 | }, |
| 332 | ], |
| 333 | "regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. |
| 334 | # Set if no column is tagged with a region-specific InfoType (like |
| 335 | # US_ZIP_5) or a region code. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 336 | }, |
| 337 | "kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity |
| 338 | "entityId": { # An entity in a dataset is a field or set of fields that correspond to a # Message indicating that multiple rows might be associated to a |
| 339 | # single individual. If the same entity_id is associated to multiple |
| 340 | # quasi-identifier tuples over distinct rows, we consider the entire |
| 341 | # collection of tuples as the composite quasi-identifier. This collection |
| 342 | # is a multiset: the order in which the different tuples appear in the |
| 343 | # dataset is ignored, but their frequency is taken into account. |
| 344 | # |
| 345 | # Important note: a maximum of 1000 rows can be associated to a single |
| 346 | # entity ID. If more rows are associated with the same entity ID, some |
| 347 | # might be ignored. |
| 348 | # single person. For example, in medical records the `EntityId` might be a |
| 349 | # patient identifier, or for financial records it might be an account |
| 350 | # identifier. This message is used when generalizations or analysis must take |
| 351 | # into account that multiple rows correspond to the same entity. |
| 352 | "field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier. |
| 353 | "name": "A String", # Name describing the field. |
| 354 | }, |
| 355 | }, |
| 356 | "quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are |
| 357 | # specified, they are considered a single composite key. Structs and |
| 358 | # repeated data types are not supported; however, nested fields are |
| 359 | # supported so long as they are not structs themselves or nested within |
| 360 | # a repeated field. |
| 361 | { # General identifier of a data field in a storage service. |
| 362 | "name": "A String", # Name describing the field. |
| 363 | }, |
| 364 | ], |
| 365 | }, |
| 366 | "numericalStatsConfig": { # Compute numerical stats over an individual column, including # Numerical stats |
| 367 | # min, max, and quantiles. |
| 368 | "field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are |
| 369 | # integer, float, date, datetime, timestamp, time. |
| 370 | "name": "A String", # Name describing the field. |
| 371 | }, |
| 372 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 373 | }, |
| 374 | "actions": [ # Actions to execute at the completion of the job. Are executed in the order |
| 375 | # provided. |
| 376 | { # A task to execute on the completion of a job. |
| 377 | # See https://cloud.google.com/dlp/docs/concepts-actions to learn more. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 378 | "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count. |
| 379 | # will publish a metric to stack driver on each infotype requested and |
| 380 | # how many findings were found for it. CustomDetectors will be bucketed |
| 381 | # as 'Custom' under the Stackdriver label 'info_type'. |
| 382 | }, |
| 383 | "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub. |
| 384 | # results of the DlpJob will be applied to the entry for the resource scanned |
| 385 | # in Cloud Data Catalog. Any labels previously written by another DlpJob will |
| 386 | # be deleted. InfoType naming patterns are strictly enforced when using this |
| 387 | # feature. Note that the findings will be persisted in Cloud Data Catalog |
| 388 | # storage and are governed by Data Catalog service-specific policy, see |
| 389 | # https://cloud.google.com/terms/service-terms |
| 390 | # Only a single instance of this action can be specified and only allowed if |
| 391 | # all resources being scanned are BigQuery tables. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 392 | # Compatible with: Inspect |
| 393 | }, |
| 394 | "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's |
| 395 | # completion/failure. |
| 396 | # completion/failure. |
| 397 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 398 | "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic. |
| 399 | # message contains a single field, `DlpJobName`, which is equal to the |
| 400 | # finished job's |
| 401 | # [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob). |
| 402 | # Compatible with: Inspect, Risk |
| 403 | "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given |
| 404 | # publishing access rights to the DLP API service account executing |
| 405 | # the long running DlpJob sending the notifications. |
| 406 | # Format is projects/{project}/topics/{topic}. |
| 407 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 408 | "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location. |
| 409 | # OutputStorageConfig. Only a single instance of this action can be |
| 410 | # specified. |
| 411 | # Compatible with: Inspect, Risk |
| 412 | "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 413 | "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only |
| 414 | # used for Inspect and must be unspecified for Risk jobs. Columns are derived |
| 415 | # from the `Finding` object. If appending to an existing table, any columns |
| 416 | # from the predefined schema that are missing will be added. No columns in |
| 417 | # the existing table will be deleted. |
| 418 | # |
| 419 | # If unspecified, then all available columns will be used for a new table or |
| 420 | # an (existing) table with no schema, and no changes will be made to an |
| 421 | # existing table that has a schema. |
| 422 | # Only for use with external storage. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 423 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Store findings in an existing table or a new table in an existing |
| 424 | # dataset. If table_id is not set a new one will be generated |
| 425 | # for you with the following format: |
| 426 | # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for |
| 427 | # generating the date details. |
| 428 | # |
| 429 | # For Inspect, each column in an existing output table must have the same |
| 430 | # name, type, and mode of a field in the `Finding` object. |
| 431 | # |
| 432 | # For Risk, an existing output table should be the output of a previous |
| 433 | # Risk analysis job run on the same source table, with the same privacy |
| 434 | # metric and quasi-identifiers. Risk jobs that analyze the same table but |
| 435 | # compute a different privacy metric, or use different sets of |
| 436 | # quasi-identifiers, cannot store their results in the same table. |
| 437 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 438 | # a table is often referenced with a string in the format of: |
| 439 | # `<project_id>:<dataset_id>.<table_id>` or |
| 440 | # `<project_id>.<dataset_id>.<table_id>`. |
| 441 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 442 | # If omitted, project ID is inferred from the API call. |
| 443 | "datasetId": "A String", # Dataset ID of the table. |
| 444 | "tableId": "A String", # Name of the table. |
| 445 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 446 | }, |
| 447 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 448 | "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha). |
| 449 | # Command Center (CSCC Alpha). |
| 450 | # This action is only available for projects which are parts of |
| 451 | # an organization and whitelisted for the alpha Cloud Security Command |
| 452 | # Center. |
| 453 | # The action will publish count of finding instances and their info types. |
| 454 | # The summary of findings will be persisted in CSCC and are governed by CSCC |
| 455 | # service-specific policy, see https://cloud.google.com/terms/service-terms |
| 456 | # Only a single instance of this action can be specified. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 457 | # Compatible with: Inspect |
| 458 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 459 | }, |
| 460 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 461 | "sourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over. |
| 462 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 463 | # a table is often referenced with a string in the format of: |
| 464 | # `<project_id>:<dataset_id>.<table_id>` or |
| 465 | # `<project_id>.<dataset_id>.<table_id>`. |
| 466 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 467 | # If omitted, project ID is inferred from the API call. |
| 468 | "datasetId": "A String", # Dataset ID of the table. |
| 469 | "tableId": "A String", # Name of the table. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 470 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 471 | }, |
| 472 | "inspectJob": { # Controls what and how to inspect for findings. # Set to control what and how to inspect. |
| 473 | "inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. |
| 474 | # `inspect_config` will be merged into the values persisted as part of the |
| 475 | # template. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 476 | "actions": [ # Actions to execute at the completion of the job. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 477 | { # A task to execute on the completion of a job. |
| 478 | # See https://cloud.google.com/dlp/docs/concepts-actions to learn more. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 479 | "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count. |
| 480 | # will publish a metric to stack driver on each infotype requested and |
| 481 | # how many findings were found for it. CustomDetectors will be bucketed |
| 482 | # as 'Custom' under the Stackdriver label 'info_type'. |
| 483 | }, |
| 484 | "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub. |
| 485 | # results of the DlpJob will be applied to the entry for the resource scanned |
| 486 | # in Cloud Data Catalog. Any labels previously written by another DlpJob will |
| 487 | # be deleted. InfoType naming patterns are strictly enforced when using this |
| 488 | # feature. Note that the findings will be persisted in Cloud Data Catalog |
| 489 | # storage and are governed by Data Catalog service-specific policy, see |
| 490 | # https://cloud.google.com/terms/service-terms |
| 491 | # Only a single instance of this action can be specified and only allowed if |
| 492 | # all resources being scanned are BigQuery tables. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 493 | # Compatible with: Inspect |
| 494 | }, |
| 495 | "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's |
| 496 | # completion/failure. |
| 497 | # completion/failure. |
| 498 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 499 | "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic. |
| 500 | # message contains a single field, `DlpJobName`, which is equal to the |
| 501 | # finished job's |
| 502 | # [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob). |
| 503 | # Compatible with: Inspect, Risk |
| 504 | "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given |
| 505 | # publishing access rights to the DLP API service account executing |
| 506 | # the long running DlpJob sending the notifications. |
| 507 | # Format is projects/{project}/topics/{topic}. |
| 508 | }, |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 509 | "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 510 | # OutputStorageConfig. Only a single instance of this action can be |
| 511 | # specified. |
| 512 | # Compatible with: Inspect, Risk |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 513 | "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 514 | "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only |
| 515 | # used for Inspect and must be unspecified for Risk jobs. Columns are derived |
| 516 | # from the `Finding` object. If appending to an existing table, any columns |
| 517 | # from the predefined schema that are missing will be added. No columns in |
| 518 | # the existing table will be deleted. |
| 519 | # |
| 520 | # If unspecified, then all available columns will be used for a new table or |
| 521 | # an (existing) table with no schema, and no changes will be made to an |
| 522 | # existing table that has a schema. |
| 523 | # Only for use with external storage. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 524 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Store findings in an existing table or a new table in an existing |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 525 | # dataset. If table_id is not set a new one will be generated |
| 526 | # for you with the following format: |
| 527 | # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for |
| 528 | # generating the date details. |
| 529 | # |
| 530 | # For Inspect, each column in an existing output table must have the same |
| 531 | # name, type, and mode of a field in the `Finding` object. |
| 532 | # |
| 533 | # For Risk, an existing output table should be the output of a previous |
| 534 | # Risk analysis job run on the same source table, with the same privacy |
| 535 | # metric and quasi-identifiers. Risk jobs that analyze the same table but |
| 536 | # compute a different privacy metric, or use different sets of |
| 537 | # quasi-identifiers, cannot store their results in the same table. |
| 538 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 539 | # a table is often referenced with a string in the format of: |
| Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 540 | # `<project_id>:<dataset_id>.<table_id>` or |
| 541 | # `<project_id>.<dataset_id>.<table_id>`. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 542 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 543 | # If omitted, project ID is inferred from the API call. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 544 | "datasetId": "A String", # Dataset ID of the table. |
| 545 | "tableId": "A String", # Name of the table. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 546 | }, |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 547 | }, |
| 548 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 549 | "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha). |
| 550 | # Command Center (CSCC Alpha). |
| 551 | # This action is only available for projects which are parts of |
| 552 | # an organization and whitelisted for the alpha Cloud Security Command |
| 553 | # Center. |
| 554 | # The action will publish count of finding instances and their info types. |
| 555 | # The summary of findings will be persisted in CSCC and are governed by CSCC |
| 556 | # service-specific policy, see https://cloud.google.com/terms/service-terms |
| 557 | # Only a single instance of this action can be specified. |
| Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 558 | # Compatible with: Inspect |
| 559 | }, |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 560 | }, |
| 561 | ], |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 562 | "storageConfig": { # Shared message indicating Cloud storage type. # The data to scan. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 563 | "cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options. |
| 564 | # bucket. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 565 | "bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The |
| 566 | # number of bytes scanned is rounded down. Must be between 0 and 100, |
| 567 | # inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one |
| 568 | # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. |
| 569 | "fileTypes": [ # List of file type groups to include in the scan. |
| 570 | # If empty, all files are scanned and available data format processors |
| 571 | # are applied. In addition, the binary content of the selected files |
| 572 | # is always scanned as well. |
| 573 | # Images are scanned only as binary if the specified region |
| 574 | # does not support image inspection and no file_types were specified. |
| 575 | # Image inspection is restricted to 'global', 'us', 'asia', and 'europe'. |
| 576 | "A String", |
| 577 | ], |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 578 | "bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger |
| 579 | # than this value then the rest of the bytes are omitted. Only one |
| 580 | # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 581 | "filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. |
| 582 | # Number of files scanned is rounded down. Must be between 0 and 100, |
| 583 | # inclusively. Both 0 and 100 means no limit. Defaults to 0. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 584 | "fileSet": { # Set of files to scan. # The set of one or more files to scan. |
| 585 | "regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular # The regex-filtered set of files to scan. Exactly one of `url` or |
| 586 | # `regex_file_set` must be set. |
| 587 | # expressions are used to allow fine-grained control over which files in the |
| 588 | # bucket to include. |
| 589 | # |
| 590 | # Included files are those that match at least one item in `include_regex` and |
| 591 | # do not match any items in `exclude_regex`. Note that a file that matches |
| 592 | # items from both lists will _not_ be included. For a match to occur, the |
| 593 | # entire file path (i.e., everything in the url after the bucket name) must |
| 594 | # match the regular expression. |
| 595 | # |
| 596 | # For example, given the input `{bucket_name: "mybucket", include_regex: |
| 597 | # ["directory1/.*"], exclude_regex: |
| 598 | # ["directory1/excluded.*"]}`: |
| 599 | # |
| 600 | # * `gs://mybucket/directory1/myfile` will be included |
| 601 | # * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches |
| 602 | # across `/`) |
| 603 | # * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the |
| 604 | # full path doesn't match any items in `include_regex`) |
| 605 | # * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path |
| 606 | # matches an item in `exclude_regex`) |
| 607 | # |
| 608 | # If `include_regex` is left empty, it will match all files by default |
| 609 | # (this is equivalent to setting `include_regex: [".*"]`). |
| 610 | # |
| 611 | # Some other common use cases: |
| 612 | # |
| 613 | # * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all |
| 614 | # files in `mybucket` except for .pdf files |
| 615 | # * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will |
| 616 | # include all files directly under `gs://mybucket/directory/`, without matching |
| 617 | # across `/` |
| 618 | "bucketName": "A String", # The name of a Cloud Storage bucket. Required. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 619 | "excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 620 | # the bucket that match at least one of these regular expressions will be |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 621 | # excluded from the scan. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 622 | # |
| 623 | # Regular expressions use RE2 |
| 624 | # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found |
| 625 | # under the google/re2 repository on GitHub. |
| 626 | "A String", |
| 627 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 628 | "includeRegex": [ # A list of regular expressions matching file paths to include. All files in |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 629 | # the bucket that match at least one of these regular expressions will be |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 630 | # included in the set of files, except for those that also match an item in |
| 631 | # `exclude_regex`. Leaving this field empty will match all files by default |
| 632 | # (this is equivalent to including `.*` in the list). |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 633 | # |
| 634 | # Regular expressions use RE2 |
| 635 | # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found |
| 636 | # under the google/re2 repository on GitHub. |
| 637 | "A String", |
| 638 | ], |
| 639 | }, |
| 640 | "url": "A String", # The Cloud Storage url of the file(s) to scan, in the format |
| 641 | # `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed. |
| 642 | # |
| 643 | # If the url ends in a trailing slash, the bucket or directory represented |
| 644 | # by the url will be scanned non-recursively (content in sub-directories |
| 645 | # will not be scanned). This means that `gs://mybucket/` is equivalent to |
| 646 | # `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to |
| 647 | # `gs://mybucket/directory/*`. |
| 648 | # |
| 649 | # Exactly one of `url` or `regex_file_set` must be set. |
| 650 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 651 | "sampleMethod": "A String", |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 652 | }, |
| 653 | "bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 654 | "sampleMethod": "A String", |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 655 | "tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference. |
| 656 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 657 | # a table is often referenced with a string in the format of: |
| 658 | # `<project_id>:<dataset_id>.<table_id>` or |
| 659 | # `<project_id>.<dataset_id>.<table_id>`. |
| 660 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 661 | # If omitted, project ID is inferred from the API call. |
| 662 | "datasetId": "A String", # Dataset ID of the table. |
| 663 | "tableId": "A String", # Name of the table. |
| 664 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 665 | "rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows |
| 666 | # scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and |
| 667 | # 100 means no limit. Defaults to 0. Only one of rows_limit and |
| 668 | # rows_limit_percent can be specified. Cannot be used in conjunction with |
| 669 | # TimespanConfig. |
| 670 | "rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the |
| 671 | # rest of the rows are omitted. If not set, or if set to 0, all rows will be |
| 672 | # scanned. Only one of rows_limit and rows_limit_percent can be specified. |
| 673 | # Cannot be used in conjunction with TimespanConfig. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 674 | "identifyingFields": [ # Table fields that may uniquely identify a row within the table. When |
| 675 | # `actions.saveFindings.outputConfig.table` is specified, the values of |
| 676 | # columns specified here are available in the output table under |
| 677 | # `location.content_locations.record_location.record_key.id_values`. Nested |
| 678 | # fields such as `person.birthdate.year` are allowed. |
| 679 | { # General identifier of a data field in a storage service. |
| 680 | "name": "A String", # Name describing the field. |
| 681 | }, |
| 682 | ], |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 683 | "excludedFields": [ # References to fields excluded from scanning. This allows you to skip |
| 684 | # inspection of entire columns which you know have no findings. |
| 685 | { # General identifier of a data field in a storage service. |
| 686 | "name": "A String", # Name describing the field. |
| 687 | }, |
| 688 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 689 | }, |
| 690 | "timespanConfig": { # Configuration of the timespan of the items to include in scanning. |
| 691 | # Currently only supported when inspecting Google Cloud Storage and BigQuery. |
| 692 | "timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. |
| 693 | # Used for data sources like Datastore and BigQuery. |
| 694 | # |
| 695 | # For BigQuery: |
| 696 | # Required to filter out rows based on the given start and |
| 697 | # end times. If not specified and the table was modified between the given |
| 698 | # start and end times, the entire table will be scanned. |
| 699 | # The valid data types of the timestamp field are: `INTEGER`, `DATE`, |
| 700 | # `TIMESTAMP`, or `DATETIME` BigQuery column. |
| 701 | # |
| 702 | # For Datastore. |
| 703 | # Valid data types of the timestamp field are: `TIMESTAMP`. |
| 704 | # Datastore entity will be scanned if the timestamp property does not |
| 705 | # exist or its value is empty or invalid. |
| 706 | "name": "A String", # Name describing the field. |
| 707 | }, |
| 708 | "enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out |
| 709 | # a valid start_time to avoid scanning files that have not been modified |
| 710 | # since the last time the JobTrigger executed. This will be based on the |
| 711 | # time of the execution of the last run of the JobTrigger. |
| 712 | "startTime": "A String", # Exclude files or rows older than this value. |
| 713 | "endTime": "A String", # Exclude files or rows newer than this value. |
| 714 | # If set to zero, no upper time limit is applied. |
| 715 | }, |
| 716 | "datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options. |
| 717 | "kind": { # A representation of a Datastore kind. # The kind to process. |
| 718 | "name": "A String", # The name of the kind. |
| 719 | }, |
| 720 | "partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always |
| 721 | # by project and namespace, however the namespace ID may be empty. |
| 722 | # A partition ID identifies a grouping of entities. The grouping is always |
| 723 | # by project and namespace, however the namespace ID may be empty. |
| 724 | # |
| 725 | # A partition ID contains several dimensions: |
| 726 | # project ID and namespace ID. |
| 727 | "namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong. |
| 728 | "projectId": "A String", # The ID of the project to which the entities belong. |
| 729 | }, |
| 730 | }, |
| 731 | "hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options. |
| 732 | # Early access feature is in a pre-release state and might change or have |
| 733 | # limited support. For more information, see |
| 734 | # https://cloud.google.com/products#product-launch-stages. |
| 735 | # of Google Cloud Platform. |
| 736 | "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings |
| 737 | # meaningful such as the columns that are primary keys. |
| 738 | "identifyingFields": [ # The columns that are the primary keys for table objects included in |
| 739 | # ContentItem. A copy of this cell's value will stored alongside alongside |
| 740 | # each finding so that the finding can be traced to the specific row it came |
| 741 | # from. No more than 3 may be provided. |
| 742 | { # General identifier of a data field in a storage service. |
| 743 | "name": "A String", # Name describing the field. |
| 744 | }, |
| 745 | ], |
| 746 | }, |
| 747 | "requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their |
| 748 | # 'finding_labels' map. Request may contain others, but any missing one of |
| 749 | # these will be rejected. |
| 750 | # |
| 751 | # Label keys must be between 1 and 63 characters long and must conform |
| 752 | # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. |
| 753 | # |
| 754 | # No more than 10 keys can be required. |
| 755 | "A String", |
| 756 | ], |
| 757 | "labels": { # To organize findings, these labels will be added to each finding. |
| 758 | # |
| 759 | # Label keys must be between 1 and 63 characters long and must conform |
| 760 | # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. |
| 761 | # |
| 762 | # Label values must be between 0 and 63 characters long and must conform |
| 763 | # to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. |
| 764 | # |
| 765 | # No more than 10 labels can be associated with a given finding. |
| 766 | # |
| 767 | # Examples: |
| 768 | # * `"environment" : "production"` |
| 769 | # * `"pipeline" : "etl"` |
| 770 | "a_key": "A String", |
| 771 | }, |
| 772 | "description": "A String", # A short description of where the data is coming from. Will be stored once |
| 773 | # in the job. 256 max length. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 774 | }, |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 775 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 776 | "inspectConfig": { # Configuration description of the scanning process. # How and what to scan for. |
| 777 | # When used with redactContent only info_types and min_likelihood are currently |
| 778 | # used. |
| 779 | "customInfoTypes": [ # CustomInfoTypes provided by the user. See |
| 780 | # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more. |
| 781 | { # Custom information type provided by the user. Used to find domain-specific |
| 782 | # sensitive information configurable to the data in question. |
| 783 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType. |
| 784 | # be used to match sensitive information specific to the data, such as a list |
| 785 | # of employee IDs or job titles. |
| 786 | # |
| 787 | # Dictionary words are case-insensitive and all characters other than letters |
| 788 | # and digits in the unicode [Basic Multilingual |
| 789 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 790 | # will be replaced with whitespace when scanning for matches, so the |
| 791 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 792 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 793 | # surrounding any match must be of a different type than the adjacent |
| 794 | # characters within the word, so letters must be next to non-letters and |
| 795 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 796 | # match the first three letters of the text "jen123" but will return no |
| 797 | # matches for "jennifer". |
| 798 | # |
| 799 | # Dictionary words containing a large number of characters that are not |
| 800 | # letters or digits may result in unexpected findings because such characters |
| 801 | # are treated as whitespace. The |
| 802 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 803 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 804 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 805 | # `StoredInfoType` API. |
| 806 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 807 | # is accepted. |
| 808 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 809 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 810 | }, |
| 811 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 812 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 813 | # at least one phrase and every phrase must contain at least 2 characters |
| 814 | # that are letters or digits. [required] |
| 815 | "A String", |
| 816 | ], |
| 817 | }, |
| 818 | }, |
| 819 | "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in |
| 820 | # infoType, when the name matches one of existing infoTypes and that infoType |
| 821 | # is specified in `InspectContent.info_types` field. Specifying the latter |
| 822 | # adds findings to the one detected by the system. If built-in info type is |
| 823 | # not specified in `InspectContent.info_types` list then the name is treated |
| 824 | # as a custom info type. |
| 825 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 826 | # creating a CustomInfoType, or one of the names listed |
| 827 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 828 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 829 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 830 | }, |
| 831 | "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be |
| 832 | # altered by a detection rule if the finding meets the criteria specified by |
| 833 | # the rule. Defaults to `VERY_LIKELY` if not specified. |
| 834 | "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. |
| 835 | # Rules are applied in order that they are specified. Not supported for the |
| 836 | # `surrogate_type` CustomInfoType. |
| 837 | { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a |
| 838 | # `CustomInfoType` to alter behavior under certain circumstances, depending |
| 839 | # on the specific details of the rule. Not supported for the `surrogate_type` |
| 840 | # custom infoType. |
| 841 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 842 | # proximity of hotwords. |
| 843 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 844 | # The total length of the window cannot exceed 1000 characters. Note that |
| 845 | # the finding itself will be included in the window, so that hotwords may |
| 846 | # be used to match substrings of the finding itself. For example, the |
| 847 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 848 | # adjusted upwards if the area code is known to be the local area code of |
| 849 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 850 | # is the area code in question. |
| 851 | # rule. |
| 852 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 853 | "windowBefore": 42, # Number of characters before the finding to consider. |
| 854 | }, |
| 855 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 856 | # part of a detection rule. |
| 857 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 858 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 859 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 860 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 861 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 862 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 863 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 864 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 865 | # a final likelihood of `LIKELY`. |
| 866 | }, |
| 867 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 868 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 869 | # specified, the entire match is returned. No more than 3 may be included. |
| 870 | 42, |
| 871 | ], |
| 872 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 873 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 874 | # google/re2 repository on GitHub. |
| 875 | }, |
| 876 | }, |
| 877 | }, |
| 878 | ], |
| 879 | "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that |
| 880 | # support reversing. |
| 881 | # such as |
| 882 | # [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). |
| 883 | # These types of transformations are |
| 884 | # those that perform pseudonymization, thereby producing a "surrogate" as |
| 885 | # output. This should be used in conjunction with a field on the |
| 886 | # transformation such as `surrogate_info_type`. This CustomInfoType does |
| 887 | # not support the use of `detection_rules`. |
| 888 | }, |
| 889 | "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType. |
| 890 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 891 | # specified, the entire match is returned. No more than 3 may be included. |
| 892 | 42, |
| 893 | ], |
| 894 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 895 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 896 | # google/re2 repository on GitHub. |
| 897 | }, |
| 898 | "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in |
| 899 | # `InspectDataSource`. Not currently supported in `InspectContent`. |
| 900 | "name": "A String", # Resource name of the requested `StoredInfoType`, for example |
| 901 | # `organizations/433245324/storedInfoTypes/432452342` or |
| 902 | # `projects/project-id/storedInfoTypes/432452342`. |
| 903 | "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for |
| 904 | # inspection was created. Output-only field, populated by the system. |
| 905 | }, |
| 906 | "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding |
| 907 | # to be returned. It still can be used for rules matching. |
| 908 | }, |
| 909 | ], |
| 910 | "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is |
| 911 | # POSSIBLE. |
| 912 | # See https://cloud.google.com/dlp/docs/likelihood to learn more. |
| 913 | "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned. |
| 914 | "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job. |
| 915 | # When set within `InspectContentRequest`, the maximum returned is 2000 |
| 916 | # regardless if this is set higher. |
| 917 | "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes. |
| 918 | { # Max findings configuration per infoType, per content item or long |
| 919 | # running DlpJob. |
| 920 | "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per |
| 921 | # info_type should be provided. If InfoTypeLimit does not have an |
| 922 | # info_type, the DLP API applies the limit against all info_types that |
| 923 | # are found but not specified in another InfoTypeLimit. |
| 924 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 925 | # creating a CustomInfoType, or one of the names listed |
| 926 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 927 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 928 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 929 | }, |
| 930 | "maxFindings": 42, # Max findings limit for the given infoType. |
| 931 | }, |
| 932 | ], |
| 933 | "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned. |
| 934 | # When set within `InspectJobConfig`, |
| 935 | # the maximum returned is 2000 regardless if this is set higher. |
| 936 | # When set within `InspectContentRequest`, this field is ignored. |
| 937 | }, |
| 938 | "excludeInfoTypes": True or False, # When true, excludes type information of the findings. |
| 939 | "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is |
| 940 | # included in the response; see Finding.quote. |
| 941 | "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. |
| 942 | # Exclusion rules, contained in the set are executed in the end, other |
| 943 | # rules are executed in the order they are specified for each info type. |
| 944 | { # Rule set for modifying a set of infoTypes to alter behavior under certain |
| 945 | # circumstances, depending on the specific details of the rules within the set. |
| 946 | "infoTypes": [ # List of infoTypes this rule set is applied to. |
| 947 | { # Type of information detected by the API. |
| 948 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 949 | # creating a CustomInfoType, or one of the names listed |
| 950 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 951 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 952 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 953 | }, |
| 954 | ], |
| 955 | "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order. |
| 956 | { # A single inspection rule to be applied to infoTypes, specified in |
| 957 | # `InspectionRuleSet`. |
| 958 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 959 | # proximity of hotwords. |
| 960 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 961 | # The total length of the window cannot exceed 1000 characters. Note that |
| 962 | # the finding itself will be included in the window, so that hotwords may |
| 963 | # be used to match substrings of the finding itself. For example, the |
| 964 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 965 | # adjusted upwards if the area code is known to be the local area code of |
| 966 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 967 | # is the area code in question. |
| 968 | # rule. |
| 969 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 970 | "windowBefore": 42, # Number of characters before the finding to consider. |
| 971 | }, |
| 972 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 973 | # part of a detection rule. |
| 974 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 975 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 976 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 977 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 978 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 979 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 980 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 981 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 982 | # a final likelihood of `LIKELY`. |
| 983 | }, |
| 984 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 985 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 986 | # specified, the entire match is returned. No more than 3 may be included. |
| 987 | 42, |
| 988 | ], |
| 989 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 990 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 991 | # google/re2 repository on GitHub. |
| 992 | }, |
| 993 | }, |
| 994 | "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule. |
| 995 | # `InspectionRuleSet` are removed from results. |
| 996 | "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details. |
| 997 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule. |
| 998 | # be used to match sensitive information specific to the data, such as a list |
| 999 | # of employee IDs or job titles. |
| 1000 | # |
| 1001 | # Dictionary words are case-insensitive and all characters other than letters |
| 1002 | # and digits in the unicode [Basic Multilingual |
| 1003 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 1004 | # will be replaced with whitespace when scanning for matches, so the |
| 1005 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 1006 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 1007 | # surrounding any match must be of a different type than the adjacent |
| 1008 | # characters within the word, so letters must be next to non-letters and |
| 1009 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 1010 | # match the first three letters of the text "jen123" but will return no |
| 1011 | # matches for "jennifer". |
| 1012 | # |
| 1013 | # Dictionary words containing a large number of characters that are not |
| 1014 | # letters or digits may result in unexpected findings because such characters |
| 1015 | # are treated as whitespace. The |
| 1016 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 1017 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 1018 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 1019 | # `StoredInfoType` API. |
| 1020 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 1021 | # is accepted. |
| 1022 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 1023 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 1024 | }, |
| 1025 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 1026 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 1027 | # at least one phrase and every phrase must contain at least 2 characters |
| 1028 | # that are letters or digits. [required] |
| 1029 | "A String", |
| 1030 | ], |
| 1031 | }, |
| 1032 | }, |
| 1033 | "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule. |
| 1034 | "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or |
| 1035 | # contained within with a finding of an infoType from this list. For |
| 1036 | # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and |
| 1037 | # `exclusion_rule` containing `exclude_info_types.info_types` with |
| 1038 | # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap |
| 1039 | # with EMAIL_ADDRESS finding. |
| 1040 | # That leads to "555-222-2222@example.org" to generate only a single |
| 1041 | # finding, namely email address. |
| 1042 | { # Type of information detected by the API. |
| 1043 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 1044 | # creating a CustomInfoType, or one of the names listed |
| 1045 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 1046 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 1047 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 1048 | }, |
| 1049 | ], |
| 1050 | }, |
| 1051 | "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule. |
| 1052 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 1053 | # specified, the entire match is returned. No more than 3 may be included. |
| 1054 | 42, |
| 1055 | ], |
| 1056 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 1057 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 1058 | # google/re2 repository on GitHub. |
| 1059 | }, |
| 1060 | }, |
| 1061 | }, |
| 1062 | ], |
| 1063 | }, |
| 1064 | ], |
| 1065 | "contentOptions": [ # List of options defining data content to scan. |
| 1066 | # If empty, text, images, and other content will be included. |
| 1067 | "A String", |
| 1068 | ], |
| 1069 | "infoTypes": [ # Restricts what info_types to look for. The values must correspond to |
| 1070 | # InfoType values returned by ListInfoTypes or listed at |
| 1071 | # https://cloud.google.com/dlp/docs/infotypes-reference. |
| 1072 | # |
| 1073 | # When no InfoTypes or CustomInfoTypes are specified in a request, the |
| 1074 | # system may automatically choose what detectors to run. By default this may |
| 1075 | # be all types, but may change over time as detectors are updated. |
| 1076 | # |
| 1077 | # If you need precise control and predictability as to what detectors are |
| 1078 | # run you should specify specific InfoTypes listed in the reference, |
| 1079 | # otherwise a default list will be used, which may change over time. |
| 1080 | { # Type of information detected by the API. |
| 1081 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 1082 | # creating a CustomInfoType, or one of the names listed |
| 1083 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 1084 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 1085 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 1086 | }, |
| 1087 | ], |
| 1088 | }, |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 1089 | }, |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1090 | } |
| 1091 | |
| 1092 | x__xgafv: string, V1 error format. |
| 1093 | Allowed values |
| 1094 | 1 - v1 error format |
| 1095 | 2 - v2 error format |
| 1096 | |
| 1097 | Returns: |
| 1098 | An object of the form: |
| 1099 | |
| 1100 | { # Combines all of the information about a DLP job. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1101 | "errors": [ # A stream of errors encountered running the job. |
| 1102 | { # Details information about an error encountered during job execution or |
| 1103 | # the results of an unsuccessful activation of the JobTrigger. |
| 1104 | "timestamps": [ # The times the error occurred. |
| 1105 | "A String", |
| 1106 | ], |
| 1107 | "details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages. |
| 1108 | # different programming environments, including REST APIs and RPC APIs. It is |
| 1109 | # used by [gRPC](https://github.com/grpc). Each `Status` message contains |
| 1110 | # three pieces of data: error code, error message, and error details. |
| 1111 | # |
| 1112 | # You can find out more about this error model and how to work with it in the |
| 1113 | # [API Design Guide](https://cloud.google.com/apis/design/errors). |
| 1114 | "code": 42, # The status code, which should be an enum value of google.rpc.Code. |
| 1115 | "details": [ # A list of messages that carry the error details. There is a common set of |
| 1116 | # message types for APIs to use. |
| 1117 | { |
| 1118 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1119 | }, |
| 1120 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1121 | "message": "A String", # A developer-facing error message, which should be in English. Any |
| 1122 | # user-facing error message should be localized and sent in the |
| 1123 | # google.rpc.Status.details field, or localized by the client. |
| 1124 | }, |
| 1125 | }, |
| 1126 | ], |
| 1127 | "createTime": "A String", # Time when the job was created. |
| 1128 | "state": "A String", # State of a job. |
| 1129 | "riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source. |
| 1130 | "kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an # K-map result |
| 1131 | # estimation, not exact values. |
| 1132 | "kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value |
| 1133 | # doesn't correspond to any such interval, the associated frequency is |
| 1134 | # zero. For example, the following records: |
| 1135 | # {min_anonymity: 1, max_anonymity: 1, frequency: 17} |
| 1136 | # {min_anonymity: 2, max_anonymity: 3, frequency: 42} |
| 1137 | # {min_anonymity: 5, max_anonymity: 10, frequency: 99} |
| 1138 | # mean that there are no record with an estimated anonymity of 4, 5, or |
| 1139 | # larger than 10. |
| 1140 | { # A KMapEstimationHistogramBucket message with the following values: |
| 1141 | # min_anonymity: 3 |
| 1142 | # max_anonymity: 5 |
| 1143 | # frequency: 42 |
| 1144 | # means that there are 42 records whose quasi-identifier values correspond |
| 1145 | # to 3, 4 or 5 people in the overlying population. An important particular |
| 1146 | # case is when min_anonymity = max_anonymity = 1: the frequency field then |
| 1147 | # corresponds to the number of uniquely identifiable records. |
| 1148 | "maxAnonymity": "A String", # Always greater than or equal to min_anonymity. |
| 1149 | "bucketSize": "A String", # Number of records within these anonymity bounds. |
| 1150 | "bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket. |
| 1151 | "bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total |
| 1152 | # number of classes returned per bucket is capped at 20. |
| 1153 | { # A tuple of values for the quasi-identifier columns. |
| 1154 | "estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values. |
| 1155 | "quasiIdsValues": [ # The quasi-identifier values. |
| 1156 | { # Set of primitive values supported by the system. |
| 1157 | # Note that for the purposes of inspection or transformation, the number |
| 1158 | # of bytes considered to comprise a 'Value' is based on its representation |
| 1159 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 1160 | # 123456789, the number of bytes would be counted as 9, even though an |
| 1161 | # int64 only holds up to 8 bytes of data. |
| 1162 | "integerValue": "A String", # integer |
| 1163 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 1164 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 1165 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 1166 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 1167 | # allow the value 60 if it allows leap-seconds. |
| 1168 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 1169 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 1170 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 1171 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 1172 | }, |
| 1173 | "dayOfWeekValue": "A String", # day of week |
| 1174 | "floatValue": 3.14, # float |
| 1175 | "stringValue": "A String", # string |
| 1176 | "timestampValue": "A String", # timestamp |
| 1177 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 1178 | # and time zone are either specified elsewhere or are not significant. The date |
| 1179 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 1180 | # |
| 1181 | # * A full date, with non-zero year, month and day values |
| 1182 | # * A month and day value, with a zero year, e.g. an anniversary |
| 1183 | # * A year on its own, with zero month and day values |
| 1184 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 1185 | # |
| 1186 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 1187 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 1188 | # month and day. |
| 1189 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 1190 | # a year. |
| 1191 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 1192 | # if specifying a year by itself or a year and month where the day is not |
| 1193 | # significant. |
| 1194 | }, |
| 1195 | "booleanValue": True or False, # boolean |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 1196 | }, |
| 1197 | ], |
| 1198 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1199 | ], |
| 1200 | "minAnonymity": "A String", # Always positive. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1201 | }, |
| 1202 | ], |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1203 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1204 | "deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an # Delta-presence result |
| 1205 | # estimation, not exact values. |
| 1206 | "deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a |
| 1207 | # value doesn't correspond to any such interval, the associated frequency |
| 1208 | # is zero. For example, the following records: |
| 1209 | # {min_probability: 0, max_probability: 0.1, frequency: 17} |
| 1210 | # {min_probability: 0.2, max_probability: 0.3, frequency: 42} |
| 1211 | # {min_probability: 0.3, max_probability: 0.4, frequency: 99} |
| 1212 | # mean that there are no record with an estimated probability in [0.1, 0.2) |
| 1213 | # nor larger or equal to 0.4. |
| 1214 | { # A DeltaPresenceEstimationHistogramBucket message with the following |
| 1215 | # values: |
| 1216 | # min_probability: 0.1 |
| 1217 | # max_probability: 0.2 |
| 1218 | # frequency: 42 |
| 1219 | # means that there are 42 records for which δ is in [0.1, 0.2). An |
| 1220 | # important particular case is when min_probability = max_probability = 1: |
| 1221 | # then, every individual who shares this quasi-identifier combination is in |
| 1222 | # the dataset. |
| 1223 | "maxProbability": 3.14, # Always greater than or equal to min_probability. |
| 1224 | "bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket. |
| 1225 | "bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total |
| 1226 | # number of classes returned per bucket is capped at 20. |
| 1227 | { # A tuple of values for the quasi-identifier columns. |
| 1228 | "estimatedProbability": 3.14, # The estimated probability that a given individual sharing these |
| 1229 | # quasi-identifier values is in the dataset. This value, typically called |
| 1230 | # δ, is the ratio between the number of records in the dataset with these |
| 1231 | # quasi-identifier values, and the total number of individuals (inside |
| 1232 | # *and* outside the dataset) with these quasi-identifier values. |
| 1233 | # For example, if there are 15 individuals in the dataset who share the |
| 1234 | # same quasi-identifier values, and an estimated 100 people in the entire |
| 1235 | # population with these values, then δ is 0.15. |
| 1236 | "quasiIdsValues": [ # The quasi-identifier values. |
| 1237 | { # Set of primitive values supported by the system. |
| 1238 | # Note that for the purposes of inspection or transformation, the number |
| 1239 | # of bytes considered to comprise a 'Value' is based on its representation |
| 1240 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 1241 | # 123456789, the number of bytes would be counted as 9, even though an |
| 1242 | # int64 only holds up to 8 bytes of data. |
| 1243 | "integerValue": "A String", # integer |
| 1244 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 1245 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 1246 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 1247 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 1248 | # allow the value 60 if it allows leap-seconds. |
| 1249 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 1250 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 1251 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 1252 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 1253 | }, |
| 1254 | "dayOfWeekValue": "A String", # day of week |
| 1255 | "floatValue": 3.14, # float |
| 1256 | "stringValue": "A String", # string |
| 1257 | "timestampValue": "A String", # timestamp |
| 1258 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 1259 | # and time zone are either specified elsewhere or are not significant. The date |
| 1260 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 1261 | # |
| 1262 | # * A full date, with non-zero year, month and day values |
| 1263 | # * A month and day value, with a zero year, e.g. an anniversary |
| 1264 | # * A year on its own, with zero month and day values |
| 1265 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 1266 | # |
| 1267 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 1268 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 1269 | # month and day. |
| 1270 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 1271 | # a year. |
| 1272 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 1273 | # if specifying a year by itself or a year and month where the day is not |
| 1274 | # significant. |
| 1275 | }, |
| 1276 | "booleanValue": True or False, # boolean |
| 1277 | }, |
| 1278 | ], |
| 1279 | }, |
| 1280 | ], |
| 1281 | "minProbability": 3.14, # Between 0 and 1. |
| 1282 | "bucketSize": "A String", # Number of records within these probability bounds. |
| 1283 | }, |
| 1284 | ], |
| 1285 | }, |
| 1286 | "categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result |
| 1287 | "valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column. |
| 1288 | { # Histogram of value frequencies in the column. |
| 1289 | "valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket. |
| 1290 | "bucketValueCount": "A String", # Total number of distinct values in this bucket. |
| 1291 | "bucketSize": "A String", # Total number of values in this bucket. |
| 1292 | "valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket. |
| 1293 | "bucketValues": [ # Sample of value frequencies in this bucket. The total number of |
| 1294 | # values returned per bucket is capped at 20. |
| 1295 | { # A value of a field, including its frequency. |
| 1296 | "count": "A String", # How many times the value is contained in the field. |
| 1297 | "value": { # Set of primitive values supported by the system. # A value contained in the field in question. |
| 1298 | # Note that for the purposes of inspection or transformation, the number |
| 1299 | # of bytes considered to comprise a 'Value' is based on its representation |
| 1300 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 1301 | # 123456789, the number of bytes would be counted as 9, even though an |
| 1302 | # int64 only holds up to 8 bytes of data. |
| 1303 | "integerValue": "A String", # integer |
| 1304 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 1305 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 1306 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 1307 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 1308 | # allow the value 60 if it allows leap-seconds. |
| 1309 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 1310 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 1311 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 1312 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 1313 | }, |
| 1314 | "dayOfWeekValue": "A String", # day of week |
| 1315 | "floatValue": 3.14, # float |
| 1316 | "stringValue": "A String", # string |
| 1317 | "timestampValue": "A String", # timestamp |
| 1318 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 1319 | # and time zone are either specified elsewhere or are not significant. The date |
| 1320 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 1321 | # |
| 1322 | # * A full date, with non-zero year, month and day values |
| 1323 | # * A month and day value, with a zero year, e.g. an anniversary |
| 1324 | # * A year on its own, with zero month and day values |
| 1325 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 1326 | # |
| 1327 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 1328 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 1329 | # month and day. |
| 1330 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 1331 | # a year. |
| 1332 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 1333 | # if specifying a year by itself or a year and month where the day is not |
| 1334 | # significant. |
| 1335 | }, |
| 1336 | "booleanValue": True or False, # boolean |
| 1337 | }, |
| 1338 | }, |
| 1339 | ], |
| 1340 | }, |
| 1341 | ], |
| 1342 | }, |
| 1343 | "numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result |
| 1344 | "quantileValues": [ # List of 99 values that partition the set of field values into 100 equal |
| 1345 | # sized buckets. |
| 1346 | { # Set of primitive values supported by the system. |
| 1347 | # Note that for the purposes of inspection or transformation, the number |
| 1348 | # of bytes considered to comprise a 'Value' is based on its representation |
| 1349 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 1350 | # 123456789, the number of bytes would be counted as 9, even though an |
| 1351 | # int64 only holds up to 8 bytes of data. |
| 1352 | "integerValue": "A String", # integer |
| 1353 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 1354 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 1355 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 1356 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 1357 | # allow the value 60 if it allows leap-seconds. |
| 1358 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 1359 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 1360 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 1361 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 1362 | }, |
| 1363 | "dayOfWeekValue": "A String", # day of week |
| 1364 | "floatValue": 3.14, # float |
| 1365 | "stringValue": "A String", # string |
| 1366 | "timestampValue": "A String", # timestamp |
| 1367 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 1368 | # and time zone are either specified elsewhere or are not significant. The date |
| 1369 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 1370 | # |
| 1371 | # * A full date, with non-zero year, month and day values |
| 1372 | # * A month and day value, with a zero year, e.g. an anniversary |
| 1373 | # * A year on its own, with zero month and day values |
| 1374 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 1375 | # |
| 1376 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 1377 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 1378 | # month and day. |
| 1379 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 1380 | # a year. |
| 1381 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 1382 | # if specifying a year by itself or a year and month where the day is not |
| 1383 | # significant. |
| 1384 | }, |
| 1385 | "booleanValue": True or False, # boolean |
| 1386 | }, |
| 1387 | ], |
| 1388 | "minValue": { # Set of primitive values supported by the system. # Minimum value appearing in the column. |
| 1389 | # Note that for the purposes of inspection or transformation, the number |
| 1390 | # of bytes considered to comprise a 'Value' is based on its representation |
| 1391 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 1392 | # 123456789, the number of bytes would be counted as 9, even though an |
| 1393 | # int64 only holds up to 8 bytes of data. |
| 1394 | "integerValue": "A String", # integer |
| 1395 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 1396 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 1397 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 1398 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 1399 | # allow the value 60 if it allows leap-seconds. |
| 1400 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 1401 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 1402 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 1403 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 1404 | }, |
| 1405 | "dayOfWeekValue": "A String", # day of week |
| 1406 | "floatValue": 3.14, # float |
| 1407 | "stringValue": "A String", # string |
| 1408 | "timestampValue": "A String", # timestamp |
| 1409 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 1410 | # and time zone are either specified elsewhere or are not significant. The date |
| 1411 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 1412 | # |
| 1413 | # * A full date, with non-zero year, month and day values |
| 1414 | # * A month and day value, with a zero year, e.g. an anniversary |
| 1415 | # * A year on its own, with zero month and day values |
| 1416 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 1417 | # |
| 1418 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 1419 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 1420 | # month and day. |
| 1421 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 1422 | # a year. |
| 1423 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 1424 | # if specifying a year by itself or a year and month where the day is not |
| 1425 | # significant. |
| 1426 | }, |
| 1427 | "booleanValue": True or False, # boolean |
| 1428 | }, |
| 1429 | "maxValue": { # Set of primitive values supported by the system. # Maximum value appearing in the column. |
| 1430 | # Note that for the purposes of inspection or transformation, the number |
| 1431 | # of bytes considered to comprise a 'Value' is based on its representation |
| 1432 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 1433 | # 123456789, the number of bytes would be counted as 9, even though an |
| 1434 | # int64 only holds up to 8 bytes of data. |
| 1435 | "integerValue": "A String", # integer |
| 1436 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 1437 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 1438 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 1439 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 1440 | # allow the value 60 if it allows leap-seconds. |
| 1441 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 1442 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 1443 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 1444 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 1445 | }, |
| 1446 | "dayOfWeekValue": "A String", # day of week |
| 1447 | "floatValue": 3.14, # float |
| 1448 | "stringValue": "A String", # string |
| 1449 | "timestampValue": "A String", # timestamp |
| 1450 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 1451 | # and time zone are either specified elsewhere or are not significant. The date |
| 1452 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 1453 | # |
| 1454 | # * A full date, with non-zero year, month and day values |
| 1455 | # * A month and day value, with a zero year, e.g. an anniversary |
| 1456 | # * A year on its own, with zero month and day values |
| 1457 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 1458 | # |
| 1459 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 1460 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 1461 | # month and day. |
| 1462 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 1463 | # a year. |
| 1464 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 1465 | # if specifying a year by itself or a year and month where the day is not |
| 1466 | # significant. |
| 1467 | }, |
| 1468 | "booleanValue": True or False, # boolean |
| 1469 | }, |
| 1470 | }, |
| 1471 | "kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result |
| 1472 | "equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes. |
| 1473 | { # Histogram of k-anonymity equivalence classes. |
| 1474 | "bucketValues": [ # Sample of equivalence classes in this bucket. The total number of |
| 1475 | # classes returned per bucket is capped at 20. |
| 1476 | { # The set of columns' values that share the same ldiversity value |
| 1477 | "quasiIdsValues": [ # Set of values defining the equivalence class. One value per |
| 1478 | # quasi-identifier column in the original KAnonymity metric message. |
| 1479 | # The order is always the same as the original request. |
| 1480 | { # Set of primitive values supported by the system. |
| 1481 | # Note that for the purposes of inspection or transformation, the number |
| 1482 | # of bytes considered to comprise a 'Value' is based on its representation |
| 1483 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 1484 | # 123456789, the number of bytes would be counted as 9, even though an |
| 1485 | # int64 only holds up to 8 bytes of data. |
| 1486 | "integerValue": "A String", # integer |
| 1487 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 1488 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 1489 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 1490 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 1491 | # allow the value 60 if it allows leap-seconds. |
| 1492 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 1493 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 1494 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 1495 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 1496 | }, |
| 1497 | "dayOfWeekValue": "A String", # day of week |
| 1498 | "floatValue": 3.14, # float |
| 1499 | "stringValue": "A String", # string |
| 1500 | "timestampValue": "A String", # timestamp |
| 1501 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 1502 | # and time zone are either specified elsewhere or are not significant. The date |
| 1503 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 1504 | # |
| 1505 | # * A full date, with non-zero year, month and day values |
| 1506 | # * A month and day value, with a zero year, e.g. an anniversary |
| 1507 | # * A year on its own, with zero month and day values |
| 1508 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 1509 | # |
| 1510 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 1511 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 1512 | # month and day. |
| 1513 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 1514 | # a year. |
| 1515 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 1516 | # if specifying a year by itself or a year and month where the day is not |
| 1517 | # significant. |
| 1518 | }, |
| 1519 | "booleanValue": True or False, # boolean |
| 1520 | }, |
| 1521 | ], |
| 1522 | "equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the |
| 1523 | # above set of values. |
| 1524 | }, |
| 1525 | ], |
| 1526 | "equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket. |
| 1527 | "equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket. |
| 1528 | "bucketSize": "A String", # Total number of equivalence classes in this bucket. |
| 1529 | "bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket. |
| 1530 | }, |
| 1531 | ], |
| 1532 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1533 | "requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1534 | "categoricalStatsConfig": { # Compute numerical stats over an individual column, including # Categorical stats |
| 1535 | # number of distinct values and value count distribution. |
| 1536 | "field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are |
| 1537 | # supported except for arrays and structs. However, it may be more |
| 1538 | # informative to use NumericalStats when the field type is supported, |
| 1539 | # depending on the data. |
| 1540 | "name": "A String", # Name describing the field. |
| 1541 | }, |
| 1542 | }, |
| 1543 | "lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity |
| 1544 | "sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value. |
| 1545 | "name": "A String", # Name describing the field. |
| 1546 | }, |
| 1547 | "quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are |
| 1548 | # defined for the l-diversity computation. When multiple fields are |
| 1549 | # specified, they are considered a single composite key. |
| 1550 | { # General identifier of a data field in a storage service. |
| 1551 | "name": "A String", # Name describing the field. |
| 1552 | }, |
| 1553 | ], |
| 1554 | }, |
| 1555 | "kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what # k-map |
| 1556 | # is called "journalist risk" in the literature, except the attack dataset is |
| 1557 | # statistically modeled instead of being perfectly known. This can be done |
| 1558 | # using publicly available data (like the US Census), or using a custom |
| 1559 | # statistical model (indicated as one or several BigQuery tables), or by |
| 1560 | # extrapolating from the distribution of values in the input dataset. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1561 | "regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. |
| 1562 | # Set if no column is tagged with a region-specific InfoType (like |
| 1563 | # US_ZIP_5) or a region code. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1564 | "quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the |
| 1565 | # same tag. |
| 1566 | { # A column with a semantic tag attached. |
| 1567 | "field": { # General identifier of a data field in a storage service. # Required. Identifies the column. |
| 1568 | "name": "A String", # Name describing the field. |
| 1569 | }, |
| 1570 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 1571 | # indicate an auxiliary table that contains statistical information on |
| 1572 | # the possible values of this column (below). |
| 1573 | "infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public |
| 1574 | # dataset as a statistical model of population, if available. We |
| 1575 | # currently support US ZIP codes, region codes, ages and genders. |
| 1576 | # To programmatically obtain the list of supported InfoTypes, use |
| 1577 | # ListInfoTypes with the supported_by=RISK_ANALYSIS filter. |
| 1578 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 1579 | # creating a CustomInfoType, or one of the names listed |
| 1580 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 1581 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 1582 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 1583 | }, |
| 1584 | "inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from |
| 1585 | # the distribution of values in the input data |
| 1586 | # empty messages in your APIs. A typical example is to use it as the request |
| 1587 | # or the response type of an API method. For instance: |
| 1588 | # |
| 1589 | # service Foo { |
| 1590 | # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); |
| 1591 | # } |
| 1592 | # |
| 1593 | # The JSON representation for `Empty` is empty JSON object `{}`. |
| 1594 | }, |
| 1595 | }, |
| 1596 | ], |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1597 | "auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1598 | # used to tag a quasi-identifiers column must appear in exactly one column |
| 1599 | # of one auxiliary table. |
| 1600 | { # An auxiliary table contains statistical information on the relative |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1601 | # frequency of different quasi-identifiers values. It has one or several |
| 1602 | # quasi-identifiers columns, and one column that indicates the relative |
| 1603 | # frequency of each quasi-identifier tuple. |
| 1604 | # If a tuple is present in the data but not in the auxiliary table, the |
| 1605 | # corresponding relative frequency is assumed to be zero (and thus, the |
| 1606 | # tuple is highly reidentifiable). |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1607 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location. |
| 1608 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 1609 | # a table is often referenced with a string in the format of: |
| 1610 | # `<project_id>:<dataset_id>.<table_id>` or |
| 1611 | # `<project_id>.<dataset_id>.<table_id>`. |
| 1612 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 1613 | # If omitted, project ID is inferred from the API call. |
| 1614 | "datasetId": "A String", # Dataset ID of the table. |
| 1615 | "tableId": "A String", # Name of the table. |
| 1616 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1617 | "quasiIds": [ # Required. Quasi-identifier columns. |
| 1618 | { # A quasi-identifier column has a custom_tag, used to know which column |
| 1619 | # in the data corresponds to which column in the statistical model. |
| 1620 | "customTag": "A String", # A auxiliary field. |
| 1621 | "field": { # General identifier of a data field in a storage service. # Identifies the column. |
| 1622 | "name": "A String", # Name describing the field. |
| 1623 | }, |
| 1624 | }, |
| 1625 | ], |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1626 | "relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number |
| 1627 | # between 0 and 1 (inclusive). Null values are assumed to be zero. |
| 1628 | "name": "A String", # Name describing the field. |
| 1629 | }, |
| 1630 | }, |
| 1631 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1632 | }, |
| 1633 | "deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to # delta-presence |
| 1634 | # figure out that one given individual appears in a de-identified dataset. |
| 1635 | # Similarly to the k-map metric, we cannot compute δ-presence exactly without |
| 1636 | # knowing the attack dataset, so we use a statistical model instead. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1637 | "quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the |
| 1638 | # same tag. |
| 1639 | { # A column with a semantic tag attached. |
| 1640 | "field": { # General identifier of a data field in a storage service. # Required. Identifies the column. |
| 1641 | "name": "A String", # Name describing the field. |
| 1642 | }, |
| 1643 | "infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public |
| 1644 | # dataset as a statistical model of population, if available. We |
| 1645 | # currently support US ZIP codes, region codes, ages and genders. |
| 1646 | # To programmatically obtain the list of supported InfoTypes, use |
| 1647 | # ListInfoTypes with the supported_by=RISK_ANALYSIS filter. |
| 1648 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 1649 | # creating a CustomInfoType, or one of the names listed |
| 1650 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1651 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 1652 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1653 | }, |
| 1654 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 1655 | # indicate an auxiliary table that contains statistical information on |
| 1656 | # the possible values of this column (below). |
| 1657 | "inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from |
| 1658 | # the distribution of values in the input data |
| 1659 | # empty messages in your APIs. A typical example is to use it as the request |
| 1660 | # or the response type of an API method. For instance: |
| 1661 | # |
| 1662 | # service Foo { |
| 1663 | # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); |
| 1664 | # } |
| 1665 | # |
| 1666 | # The JSON representation for `Empty` is empty JSON object `{}`. |
| 1667 | }, |
| 1668 | }, |
| 1669 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1670 | "auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag |
| 1671 | # used to tag a quasi-identifiers field must appear in exactly one |
| 1672 | # field of one auxiliary table. |
| 1673 | { # An auxiliary table containing statistical information on the relative |
| 1674 | # frequency of different quasi-identifiers values. It has one or several |
| 1675 | # quasi-identifiers columns, and one column that indicates the relative |
| 1676 | # frequency of each quasi-identifier tuple. |
| 1677 | # If a tuple is present in the data but not in the auxiliary table, the |
| 1678 | # corresponding relative frequency is assumed to be zero (and thus, the |
| 1679 | # tuple is highly reidentifiable). |
| 1680 | "relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number |
| 1681 | # between 0 and 1 (inclusive). Null values are assumed to be zero. |
| 1682 | "name": "A String", # Name describing the field. |
| 1683 | }, |
| 1684 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location. |
| 1685 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 1686 | # a table is often referenced with a string in the format of: |
| 1687 | # `<project_id>:<dataset_id>.<table_id>` or |
| 1688 | # `<project_id>.<dataset_id>.<table_id>`. |
| 1689 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 1690 | # If omitted, project ID is inferred from the API call. |
| 1691 | "datasetId": "A String", # Dataset ID of the table. |
| 1692 | "tableId": "A String", # Name of the table. |
| 1693 | }, |
| 1694 | "quasiIds": [ # Required. Quasi-identifier columns. |
| 1695 | { # A quasi-identifier column has a custom_tag, used to know which column |
| 1696 | # in the data corresponds to which column in the statistical model. |
| 1697 | "field": { # General identifier of a data field in a storage service. # Identifies the column. |
| 1698 | "name": "A String", # Name describing the field. |
| 1699 | }, |
| 1700 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 1701 | # indicate an auxiliary table that contains statistical information on |
| 1702 | # the possible values of this column (below). |
| 1703 | }, |
| 1704 | ], |
| 1705 | }, |
| 1706 | ], |
| 1707 | "regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. |
| 1708 | # Set if no column is tagged with a region-specific InfoType (like |
| 1709 | # US_ZIP_5) or a region code. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1710 | }, |
| 1711 | "kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity |
| 1712 | "entityId": { # An entity in a dataset is a field or set of fields that correspond to a # Message indicating that multiple rows might be associated to a |
| 1713 | # single individual. If the same entity_id is associated to multiple |
| 1714 | # quasi-identifier tuples over distinct rows, we consider the entire |
| 1715 | # collection of tuples as the composite quasi-identifier. This collection |
| 1716 | # is a multiset: the order in which the different tuples appear in the |
| 1717 | # dataset is ignored, but their frequency is taken into account. |
| 1718 | # |
| 1719 | # Important note: a maximum of 1000 rows can be associated to a single |
| 1720 | # entity ID. If more rows are associated with the same entity ID, some |
| 1721 | # might be ignored. |
| 1722 | # single person. For example, in medical records the `EntityId` might be a |
| 1723 | # patient identifier, or for financial records it might be an account |
| 1724 | # identifier. This message is used when generalizations or analysis must take |
| 1725 | # into account that multiple rows correspond to the same entity. |
| 1726 | "field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier. |
| 1727 | "name": "A String", # Name describing the field. |
| 1728 | }, |
| 1729 | }, |
| 1730 | "quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are |
| 1731 | # specified, they are considered a single composite key. Structs and |
| 1732 | # repeated data types are not supported; however, nested fields are |
| 1733 | # supported so long as they are not structs themselves or nested within |
| 1734 | # a repeated field. |
| 1735 | { # General identifier of a data field in a storage service. |
| 1736 | "name": "A String", # Name describing the field. |
| 1737 | }, |
| 1738 | ], |
| 1739 | }, |
| 1740 | "numericalStatsConfig": { # Compute numerical stats over an individual column, including # Numerical stats |
| 1741 | # min, max, and quantiles. |
| 1742 | "field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are |
| 1743 | # integer, float, date, datetime, timestamp, time. |
| 1744 | "name": "A String", # Name describing the field. |
| 1745 | }, |
| 1746 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1747 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1748 | "lDiversityResult": { # Result of the l-diversity computation. # L-divesity result |
| 1749 | "sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies. |
| 1750 | { # Histogram of l-diversity equivalence class sensitive value frequencies. |
| 1751 | "bucketSize": "A String", # Total number of equivalence classes in this bucket. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1752 | "bucketValues": [ # Sample of equivalence classes in this bucket. The total number of |
| 1753 | # classes returned per bucket is capped at 20. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1754 | { # The set of columns' values that share the same ldiversity value. |
| 1755 | "quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence |
| 1756 | # class. The order is always the same as the original request. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1757 | { # Set of primitive values supported by the system. |
| 1758 | # Note that for the purposes of inspection or transformation, the number |
| 1759 | # of bytes considered to comprise a 'Value' is based on its representation |
| 1760 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 1761 | # 123456789, the number of bytes would be counted as 9, even though an |
| 1762 | # int64 only holds up to 8 bytes of data. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1763 | "integerValue": "A String", # integer |
| 1764 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 1765 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 1766 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 1767 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 1768 | # allow the value 60 if it allows leap-seconds. |
| 1769 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 1770 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 1771 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 1772 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 1773 | }, |
| 1774 | "dayOfWeekValue": "A String", # day of week |
| 1775 | "floatValue": 3.14, # float |
| 1776 | "stringValue": "A String", # string |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1777 | "timestampValue": "A String", # timestamp |
| 1778 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 1779 | # and time zone are either specified elsewhere or are not significant. The date |
| 1780 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 1781 | # |
| 1782 | # * A full date, with non-zero year, month and day values |
| 1783 | # * A month and day value, with a zero year, e.g. an anniversary |
| 1784 | # * A year on its own, with zero month and day values |
| 1785 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 1786 | # |
| 1787 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1788 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 1789 | # month and day. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1790 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 1791 | # a year. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1792 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 1793 | # if specifying a year by itself or a year and month where the day is not |
| 1794 | # significant. |
| 1795 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1796 | "booleanValue": True or False, # boolean |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1797 | }, |
| 1798 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1799 | "topSensitiveValues": [ # Estimated frequencies of top sensitive values. |
| 1800 | { # A value of a field, including its frequency. |
| 1801 | "count": "A String", # How many times the value is contained in the field. |
| 1802 | "value": { # Set of primitive values supported by the system. # A value contained in the field in question. |
| 1803 | # Note that for the purposes of inspection or transformation, the number |
| 1804 | # of bytes considered to comprise a 'Value' is based on its representation |
| 1805 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 1806 | # 123456789, the number of bytes would be counted as 9, even though an |
| 1807 | # int64 only holds up to 8 bytes of data. |
| 1808 | "integerValue": "A String", # integer |
| 1809 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 1810 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 1811 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 1812 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 1813 | # allow the value 60 if it allows leap-seconds. |
| 1814 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 1815 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 1816 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 1817 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 1818 | }, |
| 1819 | "dayOfWeekValue": "A String", # day of week |
| 1820 | "floatValue": 3.14, # float |
| 1821 | "stringValue": "A String", # string |
| 1822 | "timestampValue": "A String", # timestamp |
| 1823 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 1824 | # and time zone are either specified elsewhere or are not significant. The date |
| 1825 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 1826 | # |
| 1827 | # * A full date, with non-zero year, month and day values |
| 1828 | # * A month and day value, with a zero year, e.g. an anniversary |
| 1829 | # * A year on its own, with zero month and day values |
| 1830 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 1831 | # |
| 1832 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 1833 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 1834 | # month and day. |
| 1835 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 1836 | # a year. |
| 1837 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 1838 | # if specifying a year by itself or a year and month where the day is not |
| 1839 | # significant. |
| 1840 | }, |
| 1841 | "booleanValue": True or False, # boolean |
| 1842 | }, |
| 1843 | }, |
| 1844 | ], |
| 1845 | "equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class. |
| 1846 | "numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1847 | }, |
| 1848 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1849 | "sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence |
| 1850 | # classes in this bucket. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1851 | "bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1852 | "sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence |
| 1853 | # classes in this bucket. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1854 | }, |
| 1855 | ], |
| 1856 | }, |
| 1857 | "requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over. |
| 1858 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 1859 | # a table is often referenced with a string in the format of: |
| 1860 | # `<project_id>:<dataset_id>.<table_id>` or |
| 1861 | # `<project_id>.<dataset_id>.<table_id>`. |
| 1862 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 1863 | # If omitted, project ID is inferred from the API call. |
| 1864 | "datasetId": "A String", # Dataset ID of the table. |
| 1865 | "tableId": "A String", # Name of the table. |
| 1866 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1867 | }, |
| 1868 | "type": "A String", # The type of job. |
| 1869 | "endTime": "A String", # Time when the job finished. |
| 1870 | "startTime": "A String", # Time when the job started. |
| 1871 | "jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that |
| 1872 | # instantiated the job. |
| 1873 | "inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source. |
| 1874 | "requestedOptions": { # Snapshot of the inspection configuration. # The configuration used for this job. |
| 1875 | "jobConfig": { # Controls what and how to inspect for findings. # Inspect config. |
| 1876 | "inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. |
| 1877 | # `inspect_config` will be merged into the values persisted as part of the |
| 1878 | # template. |
| 1879 | "actions": [ # Actions to execute at the completion of the job. |
| 1880 | { # A task to execute on the completion of a job. |
| 1881 | # See https://cloud.google.com/dlp/docs/concepts-actions to learn more. |
| 1882 | "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count. |
| 1883 | # will publish a metric to stack driver on each infotype requested and |
| 1884 | # how many findings were found for it. CustomDetectors will be bucketed |
| 1885 | # as 'Custom' under the Stackdriver label 'info_type'. |
| 1886 | }, |
| 1887 | "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub. |
| 1888 | # results of the DlpJob will be applied to the entry for the resource scanned |
| 1889 | # in Cloud Data Catalog. Any labels previously written by another DlpJob will |
| 1890 | # be deleted. InfoType naming patterns are strictly enforced when using this |
| 1891 | # feature. Note that the findings will be persisted in Cloud Data Catalog |
| 1892 | # storage and are governed by Data Catalog service-specific policy, see |
| 1893 | # https://cloud.google.com/terms/service-terms |
| 1894 | # Only a single instance of this action can be specified and only allowed if |
| 1895 | # all resources being scanned are BigQuery tables. |
| 1896 | # Compatible with: Inspect |
| 1897 | }, |
| 1898 | "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's |
| 1899 | # completion/failure. |
| 1900 | # completion/failure. |
| 1901 | }, |
| 1902 | "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic. |
| 1903 | # message contains a single field, `DlpJobName`, which is equal to the |
| 1904 | # finished job's |
| 1905 | # [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob). |
| 1906 | # Compatible with: Inspect, Risk |
| 1907 | "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given |
| 1908 | # publishing access rights to the DLP API service account executing |
| 1909 | # the long running DlpJob sending the notifications. |
| 1910 | # Format is projects/{project}/topics/{topic}. |
| 1911 | }, |
| 1912 | "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location. |
| 1913 | # OutputStorageConfig. Only a single instance of this action can be |
| 1914 | # specified. |
| 1915 | # Compatible with: Inspect, Risk |
| 1916 | "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP. |
| 1917 | "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only |
| 1918 | # used for Inspect and must be unspecified for Risk jobs. Columns are derived |
| 1919 | # from the `Finding` object. If appending to an existing table, any columns |
| 1920 | # from the predefined schema that are missing will be added. No columns in |
| 1921 | # the existing table will be deleted. |
| 1922 | # |
| 1923 | # If unspecified, then all available columns will be used for a new table or |
| 1924 | # an (existing) table with no schema, and no changes will be made to an |
| 1925 | # existing table that has a schema. |
| 1926 | # Only for use with external storage. |
| 1927 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Store findings in an existing table or a new table in an existing |
| 1928 | # dataset. If table_id is not set a new one will be generated |
| 1929 | # for you with the following format: |
| 1930 | # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for |
| 1931 | # generating the date details. |
| 1932 | # |
| 1933 | # For Inspect, each column in an existing output table must have the same |
| 1934 | # name, type, and mode of a field in the `Finding` object. |
| 1935 | # |
| 1936 | # For Risk, an existing output table should be the output of a previous |
| 1937 | # Risk analysis job run on the same source table, with the same privacy |
| 1938 | # metric and quasi-identifiers. Risk jobs that analyze the same table but |
| 1939 | # compute a different privacy metric, or use different sets of |
| 1940 | # quasi-identifiers, cannot store their results in the same table. |
| 1941 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 1942 | # a table is often referenced with a string in the format of: |
| 1943 | # `<project_id>:<dataset_id>.<table_id>` or |
| 1944 | # `<project_id>.<dataset_id>.<table_id>`. |
| 1945 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 1946 | # If omitted, project ID is inferred from the API call. |
| 1947 | "datasetId": "A String", # Dataset ID of the table. |
| 1948 | "tableId": "A String", # Name of the table. |
| 1949 | }, |
| 1950 | }, |
| 1951 | }, |
| 1952 | "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha). |
| 1953 | # Command Center (CSCC Alpha). |
| 1954 | # This action is only available for projects which are parts of |
| 1955 | # an organization and whitelisted for the alpha Cloud Security Command |
| 1956 | # Center. |
| 1957 | # The action will publish count of finding instances and their info types. |
| 1958 | # The summary of findings will be persisted in CSCC and are governed by CSCC |
| 1959 | # service-specific policy, see https://cloud.google.com/terms/service-terms |
| 1960 | # Only a single instance of this action can be specified. |
| 1961 | # Compatible with: Inspect |
| 1962 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 1963 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 1964 | ], |
| 1965 | "storageConfig": { # Shared message indicating Cloud storage type. # The data to scan. |
| 1966 | "cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options. |
| 1967 | # bucket. |
| 1968 | "bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The |
| 1969 | # number of bytes scanned is rounded down. Must be between 0 and 100, |
| 1970 | # inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one |
| 1971 | # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. |
| 1972 | "fileTypes": [ # List of file type groups to include in the scan. |
| 1973 | # If empty, all files are scanned and available data format processors |
| 1974 | # are applied. In addition, the binary content of the selected files |
| 1975 | # is always scanned as well. |
| 1976 | # Images are scanned only as binary if the specified region |
| 1977 | # does not support image inspection and no file_types were specified. |
| 1978 | # Image inspection is restricted to 'global', 'us', 'asia', and 'europe'. |
| 1979 | "A String", |
| 1980 | ], |
| 1981 | "bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger |
| 1982 | # than this value then the rest of the bytes are omitted. Only one |
| 1983 | # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. |
| 1984 | "filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. |
| 1985 | # Number of files scanned is rounded down. Must be between 0 and 100, |
| 1986 | # inclusively. Both 0 and 100 means no limit. Defaults to 0. |
| 1987 | "fileSet": { # Set of files to scan. # The set of one or more files to scan. |
| 1988 | "regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular # The regex-filtered set of files to scan. Exactly one of `url` or |
| 1989 | # `regex_file_set` must be set. |
| 1990 | # expressions are used to allow fine-grained control over which files in the |
| 1991 | # bucket to include. |
| 1992 | # |
| 1993 | # Included files are those that match at least one item in `include_regex` and |
| 1994 | # do not match any items in `exclude_regex`. Note that a file that matches |
| 1995 | # items from both lists will _not_ be included. For a match to occur, the |
| 1996 | # entire file path (i.e., everything in the url after the bucket name) must |
| 1997 | # match the regular expression. |
| 1998 | # |
| 1999 | # For example, given the input `{bucket_name: "mybucket", include_regex: |
| 2000 | # ["directory1/.*"], exclude_regex: |
| 2001 | # ["directory1/excluded.*"]}`: |
| 2002 | # |
| 2003 | # * `gs://mybucket/directory1/myfile` will be included |
| 2004 | # * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches |
| 2005 | # across `/`) |
| 2006 | # * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the |
| 2007 | # full path doesn't match any items in `include_regex`) |
| 2008 | # * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path |
| 2009 | # matches an item in `exclude_regex`) |
| 2010 | # |
| 2011 | # If `include_regex` is left empty, it will match all files by default |
| 2012 | # (this is equivalent to setting `include_regex: [".*"]`). |
| 2013 | # |
| 2014 | # Some other common use cases: |
| 2015 | # |
| 2016 | # * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all |
| 2017 | # files in `mybucket` except for .pdf files |
| 2018 | # * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will |
| 2019 | # include all files directly under `gs://mybucket/directory/`, without matching |
| 2020 | # across `/` |
| 2021 | "bucketName": "A String", # The name of a Cloud Storage bucket. Required. |
| 2022 | "excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in |
| 2023 | # the bucket that match at least one of these regular expressions will be |
| 2024 | # excluded from the scan. |
| 2025 | # |
| 2026 | # Regular expressions use RE2 |
| 2027 | # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found |
| 2028 | # under the google/re2 repository on GitHub. |
| 2029 | "A String", |
| 2030 | ], |
| 2031 | "includeRegex": [ # A list of regular expressions matching file paths to include. All files in |
| 2032 | # the bucket that match at least one of these regular expressions will be |
| 2033 | # included in the set of files, except for those that also match an item in |
| 2034 | # `exclude_regex`. Leaving this field empty will match all files by default |
| 2035 | # (this is equivalent to including `.*` in the list). |
| 2036 | # |
| 2037 | # Regular expressions use RE2 |
| 2038 | # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found |
| 2039 | # under the google/re2 repository on GitHub. |
| 2040 | "A String", |
| 2041 | ], |
| 2042 | }, |
| 2043 | "url": "A String", # The Cloud Storage url of the file(s) to scan, in the format |
| 2044 | # `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed. |
| 2045 | # |
| 2046 | # If the url ends in a trailing slash, the bucket or directory represented |
| 2047 | # by the url will be scanned non-recursively (content in sub-directories |
| 2048 | # will not be scanned). This means that `gs://mybucket/` is equivalent to |
| 2049 | # `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to |
| 2050 | # `gs://mybucket/directory/*`. |
| 2051 | # |
| 2052 | # Exactly one of `url` or `regex_file_set` must be set. |
| 2053 | }, |
| 2054 | "sampleMethod": "A String", |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 2055 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 2056 | "bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options. |
| 2057 | "sampleMethod": "A String", |
| 2058 | "tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference. |
| 2059 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 2060 | # a table is often referenced with a string in the format of: |
| 2061 | # `<project_id>:<dataset_id>.<table_id>` or |
| 2062 | # `<project_id>.<dataset_id>.<table_id>`. |
| 2063 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 2064 | # If omitted, project ID is inferred from the API call. |
| 2065 | "datasetId": "A String", # Dataset ID of the table. |
| 2066 | "tableId": "A String", # Name of the table. |
| 2067 | }, |
| 2068 | "rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows |
| 2069 | # scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and |
| 2070 | # 100 means no limit. Defaults to 0. Only one of rows_limit and |
| 2071 | # rows_limit_percent can be specified. Cannot be used in conjunction with |
| 2072 | # TimespanConfig. |
| 2073 | "rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the |
| 2074 | # rest of the rows are omitted. If not set, or if set to 0, all rows will be |
| 2075 | # scanned. Only one of rows_limit and rows_limit_percent can be specified. |
| 2076 | # Cannot be used in conjunction with TimespanConfig. |
| 2077 | "identifyingFields": [ # Table fields that may uniquely identify a row within the table. When |
| 2078 | # `actions.saveFindings.outputConfig.table` is specified, the values of |
| 2079 | # columns specified here are available in the output table under |
| 2080 | # `location.content_locations.record_location.record_key.id_values`. Nested |
| 2081 | # fields such as `person.birthdate.year` are allowed. |
| 2082 | { # General identifier of a data field in a storage service. |
| 2083 | "name": "A String", # Name describing the field. |
| 2084 | }, |
| 2085 | ], |
| 2086 | "excludedFields": [ # References to fields excluded from scanning. This allows you to skip |
| 2087 | # inspection of entire columns which you know have no findings. |
| 2088 | { # General identifier of a data field in a storage service. |
| 2089 | "name": "A String", # Name describing the field. |
| 2090 | }, |
| 2091 | ], |
| 2092 | }, |
| 2093 | "timespanConfig": { # Configuration of the timespan of the items to include in scanning. |
| 2094 | # Currently only supported when inspecting Google Cloud Storage and BigQuery. |
| 2095 | "timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. |
| 2096 | # Used for data sources like Datastore and BigQuery. |
| 2097 | # |
| 2098 | # For BigQuery: |
| 2099 | # Required to filter out rows based on the given start and |
| 2100 | # end times. If not specified and the table was modified between the given |
| 2101 | # start and end times, the entire table will be scanned. |
| 2102 | # The valid data types of the timestamp field are: `INTEGER`, `DATE`, |
| 2103 | # `TIMESTAMP`, or `DATETIME` BigQuery column. |
| 2104 | # |
| 2105 | # For Datastore. |
| 2106 | # Valid data types of the timestamp field are: `TIMESTAMP`. |
| 2107 | # Datastore entity will be scanned if the timestamp property does not |
| 2108 | # exist or its value is empty or invalid. |
| 2109 | "name": "A String", # Name describing the field. |
| 2110 | }, |
| 2111 | "enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out |
| 2112 | # a valid start_time to avoid scanning files that have not been modified |
| 2113 | # since the last time the JobTrigger executed. This will be based on the |
| 2114 | # time of the execution of the last run of the JobTrigger. |
| 2115 | "startTime": "A String", # Exclude files or rows older than this value. |
| 2116 | "endTime": "A String", # Exclude files or rows newer than this value. |
| 2117 | # If set to zero, no upper time limit is applied. |
| 2118 | }, |
| 2119 | "datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options. |
| 2120 | "kind": { # A representation of a Datastore kind. # The kind to process. |
| 2121 | "name": "A String", # The name of the kind. |
| 2122 | }, |
| 2123 | "partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always |
| 2124 | # by project and namespace, however the namespace ID may be empty. |
| 2125 | # A partition ID identifies a grouping of entities. The grouping is always |
| 2126 | # by project and namespace, however the namespace ID may be empty. |
| 2127 | # |
| 2128 | # A partition ID contains several dimensions: |
| 2129 | # project ID and namespace ID. |
| 2130 | "namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong. |
| 2131 | "projectId": "A String", # The ID of the project to which the entities belong. |
| 2132 | }, |
| 2133 | }, |
| 2134 | "hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options. |
| 2135 | # Early access feature is in a pre-release state and might change or have |
| 2136 | # limited support. For more information, see |
| 2137 | # https://cloud.google.com/products#product-launch-stages. |
| 2138 | # of Google Cloud Platform. |
| 2139 | "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings |
| 2140 | # meaningful such as the columns that are primary keys. |
| 2141 | "identifyingFields": [ # The columns that are the primary keys for table objects included in |
| 2142 | # ContentItem. A copy of this cell's value will stored alongside alongside |
| 2143 | # each finding so that the finding can be traced to the specific row it came |
| 2144 | # from. No more than 3 may be provided. |
| 2145 | { # General identifier of a data field in a storage service. |
| 2146 | "name": "A String", # Name describing the field. |
| 2147 | }, |
| 2148 | ], |
| 2149 | }, |
| 2150 | "requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their |
| 2151 | # 'finding_labels' map. Request may contain others, but any missing one of |
| 2152 | # these will be rejected. |
| 2153 | # |
| 2154 | # Label keys must be between 1 and 63 characters long and must conform |
| 2155 | # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. |
| 2156 | # |
| 2157 | # No more than 10 keys can be required. |
| 2158 | "A String", |
| 2159 | ], |
| 2160 | "labels": { # To organize findings, these labels will be added to each finding. |
| 2161 | # |
| 2162 | # Label keys must be between 1 and 63 characters long and must conform |
| 2163 | # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. |
| 2164 | # |
| 2165 | # Label values must be between 0 and 63 characters long and must conform |
| 2166 | # to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. |
| 2167 | # |
| 2168 | # No more than 10 labels can be associated with a given finding. |
| 2169 | # |
| 2170 | # Examples: |
| 2171 | # * `"environment" : "production"` |
| 2172 | # * `"pipeline" : "etl"` |
| 2173 | "a_key": "A String", |
| 2174 | }, |
| 2175 | "description": "A String", # A short description of where the data is coming from. Will be stored once |
| 2176 | # in the job. 256 max length. |
| 2177 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 2178 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 2179 | "inspectConfig": { # Configuration description of the scanning process. # How and what to scan for. |
| 2180 | # When used with redactContent only info_types and min_likelihood are currently |
| 2181 | # used. |
| 2182 | "customInfoTypes": [ # CustomInfoTypes provided by the user. See |
| 2183 | # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more. |
| 2184 | { # Custom information type provided by the user. Used to find domain-specific |
| 2185 | # sensitive information configurable to the data in question. |
| 2186 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType. |
| 2187 | # be used to match sensitive information specific to the data, such as a list |
| 2188 | # of employee IDs or job titles. |
| 2189 | # |
| 2190 | # Dictionary words are case-insensitive and all characters other than letters |
| 2191 | # and digits in the unicode [Basic Multilingual |
| 2192 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 2193 | # will be replaced with whitespace when scanning for matches, so the |
| 2194 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 2195 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 2196 | # surrounding any match must be of a different type than the adjacent |
| 2197 | # characters within the word, so letters must be next to non-letters and |
| 2198 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 2199 | # match the first three letters of the text "jen123" but will return no |
| 2200 | # matches for "jennifer". |
| 2201 | # |
| 2202 | # Dictionary words containing a large number of characters that are not |
| 2203 | # letters or digits may result in unexpected findings because such characters |
| 2204 | # are treated as whitespace. The |
| 2205 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 2206 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 2207 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 2208 | # `StoredInfoType` API. |
| 2209 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 2210 | # is accepted. |
| 2211 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 2212 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 2213 | }, |
| 2214 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 2215 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 2216 | # at least one phrase and every phrase must contain at least 2 characters |
| 2217 | # that are letters or digits. [required] |
| 2218 | "A String", |
| 2219 | ], |
| 2220 | }, |
| 2221 | }, |
| 2222 | "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in |
| 2223 | # infoType, when the name matches one of existing infoTypes and that infoType |
| 2224 | # is specified in `InspectContent.info_types` field. Specifying the latter |
| 2225 | # adds findings to the one detected by the system. If built-in info type is |
| 2226 | # not specified in `InspectContent.info_types` list then the name is treated |
| 2227 | # as a custom info type. |
| 2228 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 2229 | # creating a CustomInfoType, or one of the names listed |
| 2230 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 2231 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 2232 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 2233 | }, |
| 2234 | "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be |
| 2235 | # altered by a detection rule if the finding meets the criteria specified by |
| 2236 | # the rule. Defaults to `VERY_LIKELY` if not specified. |
| 2237 | "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. |
| 2238 | # Rules are applied in order that they are specified. Not supported for the |
| 2239 | # `surrogate_type` CustomInfoType. |
| 2240 | { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a |
| 2241 | # `CustomInfoType` to alter behavior under certain circumstances, depending |
| 2242 | # on the specific details of the rule. Not supported for the `surrogate_type` |
| 2243 | # custom infoType. |
| 2244 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 2245 | # proximity of hotwords. |
| 2246 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 2247 | # The total length of the window cannot exceed 1000 characters. Note that |
| 2248 | # the finding itself will be included in the window, so that hotwords may |
| 2249 | # be used to match substrings of the finding itself. For example, the |
| 2250 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 2251 | # adjusted upwards if the area code is known to be the local area code of |
| 2252 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 2253 | # is the area code in question. |
| 2254 | # rule. |
| 2255 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 2256 | "windowBefore": 42, # Number of characters before the finding to consider. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 2257 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 2258 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 2259 | # part of a detection rule. |
| 2260 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 2261 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 2262 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 2263 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 2264 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 2265 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 2266 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 2267 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 2268 | # a final likelihood of `LIKELY`. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 2269 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 2270 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 2271 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 2272 | # specified, the entire match is returned. No more than 3 may be included. |
| 2273 | 42, |
| 2274 | ], |
| 2275 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 2276 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 2277 | # google/re2 repository on GitHub. |
| 2278 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 2279 | }, |
| 2280 | }, |
| 2281 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 2282 | "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that |
| 2283 | # support reversing. |
| 2284 | # such as |
| 2285 | # [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). |
| 2286 | # These types of transformations are |
| 2287 | # those that perform pseudonymization, thereby producing a "surrogate" as |
| 2288 | # output. This should be used in conjunction with a field on the |
| 2289 | # transformation such as `surrogate_info_type`. This CustomInfoType does |
| 2290 | # not support the use of `detection_rules`. |
| 2291 | }, |
| 2292 | "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType. |
| 2293 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 2294 | # specified, the entire match is returned. No more than 3 may be included. |
| 2295 | 42, |
| 2296 | ], |
| 2297 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 2298 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 2299 | # google/re2 repository on GitHub. |
| 2300 | }, |
| 2301 | "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in |
| 2302 | # `InspectDataSource`. Not currently supported in `InspectContent`. |
| 2303 | "name": "A String", # Resource name of the requested `StoredInfoType`, for example |
| 2304 | # `organizations/433245324/storedInfoTypes/432452342` or |
| 2305 | # `projects/project-id/storedInfoTypes/432452342`. |
| 2306 | "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for |
| 2307 | # inspection was created. Output-only field, populated by the system. |
| 2308 | }, |
| 2309 | "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding |
| 2310 | # to be returned. It still can be used for rules matching. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 2311 | }, |
| 2312 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 2313 | "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is |
| 2314 | # POSSIBLE. |
| 2315 | # See https://cloud.google.com/dlp/docs/likelihood to learn more. |
| 2316 | "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned. |
| 2317 | "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job. |
| 2318 | # When set within `InspectContentRequest`, the maximum returned is 2000 |
| 2319 | # regardless if this is set higher. |
| 2320 | "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes. |
| 2321 | { # Max findings configuration per infoType, per content item or long |
| 2322 | # running DlpJob. |
| 2323 | "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per |
| 2324 | # info_type should be provided. If InfoTypeLimit does not have an |
| 2325 | # info_type, the DLP API applies the limit against all info_types that |
| 2326 | # are found but not specified in another InfoTypeLimit. |
| 2327 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 2328 | # creating a CustomInfoType, or one of the names listed |
| 2329 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 2330 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 2331 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 2332 | }, |
| 2333 | "maxFindings": 42, # Max findings limit for the given infoType. |
| 2334 | }, |
| 2335 | ], |
| 2336 | "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned. |
| 2337 | # When set within `InspectJobConfig`, |
| 2338 | # the maximum returned is 2000 regardless if this is set higher. |
| 2339 | # When set within `InspectContentRequest`, this field is ignored. |
| 2340 | }, |
| 2341 | "excludeInfoTypes": True or False, # When true, excludes type information of the findings. |
| 2342 | "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is |
| 2343 | # included in the response; see Finding.quote. |
| 2344 | "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. |
| 2345 | # Exclusion rules, contained in the set are executed in the end, other |
| 2346 | # rules are executed in the order they are specified for each info type. |
| 2347 | { # Rule set for modifying a set of infoTypes to alter behavior under certain |
| 2348 | # circumstances, depending on the specific details of the rules within the set. |
| 2349 | "infoTypes": [ # List of infoTypes this rule set is applied to. |
| 2350 | { # Type of information detected by the API. |
| 2351 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 2352 | # creating a CustomInfoType, or one of the names listed |
| 2353 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 2354 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 2355 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 2356 | }, |
| 2357 | ], |
| 2358 | "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order. |
| 2359 | { # A single inspection rule to be applied to infoTypes, specified in |
| 2360 | # `InspectionRuleSet`. |
| 2361 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 2362 | # proximity of hotwords. |
| 2363 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 2364 | # The total length of the window cannot exceed 1000 characters. Note that |
| 2365 | # the finding itself will be included in the window, so that hotwords may |
| 2366 | # be used to match substrings of the finding itself. For example, the |
| 2367 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 2368 | # adjusted upwards if the area code is known to be the local area code of |
| 2369 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 2370 | # is the area code in question. |
| 2371 | # rule. |
| 2372 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 2373 | "windowBefore": 42, # Number of characters before the finding to consider. |
| 2374 | }, |
| 2375 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 2376 | # part of a detection rule. |
| 2377 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 2378 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 2379 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 2380 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 2381 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 2382 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 2383 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 2384 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 2385 | # a final likelihood of `LIKELY`. |
| 2386 | }, |
| 2387 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 2388 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 2389 | # specified, the entire match is returned. No more than 3 may be included. |
| 2390 | 42, |
| 2391 | ], |
| 2392 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 2393 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 2394 | # google/re2 repository on GitHub. |
| 2395 | }, |
| 2396 | }, |
| 2397 | "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule. |
| 2398 | # `InspectionRuleSet` are removed from results. |
| 2399 | "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details. |
| 2400 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule. |
| 2401 | # be used to match sensitive information specific to the data, such as a list |
| 2402 | # of employee IDs or job titles. |
| 2403 | # |
| 2404 | # Dictionary words are case-insensitive and all characters other than letters |
| 2405 | # and digits in the unicode [Basic Multilingual |
| 2406 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 2407 | # will be replaced with whitespace when scanning for matches, so the |
| 2408 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 2409 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 2410 | # surrounding any match must be of a different type than the adjacent |
| 2411 | # characters within the word, so letters must be next to non-letters and |
| 2412 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 2413 | # match the first three letters of the text "jen123" but will return no |
| 2414 | # matches for "jennifer". |
| 2415 | # |
| 2416 | # Dictionary words containing a large number of characters that are not |
| 2417 | # letters or digits may result in unexpected findings because such characters |
| 2418 | # are treated as whitespace. The |
| 2419 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 2420 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 2421 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 2422 | # `StoredInfoType` API. |
| 2423 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 2424 | # is accepted. |
| 2425 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 2426 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 2427 | }, |
| 2428 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 2429 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 2430 | # at least one phrase and every phrase must contain at least 2 characters |
| 2431 | # that are letters or digits. [required] |
| 2432 | "A String", |
| 2433 | ], |
| 2434 | }, |
| 2435 | }, |
| 2436 | "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule. |
| 2437 | "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or |
| 2438 | # contained within with a finding of an infoType from this list. For |
| 2439 | # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and |
| 2440 | # `exclusion_rule` containing `exclude_info_types.info_types` with |
| 2441 | # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap |
| 2442 | # with EMAIL_ADDRESS finding. |
| 2443 | # That leads to "555-222-2222@example.org" to generate only a single |
| 2444 | # finding, namely email address. |
| 2445 | { # Type of information detected by the API. |
| 2446 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 2447 | # creating a CustomInfoType, or one of the names listed |
| 2448 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 2449 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 2450 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 2451 | }, |
| 2452 | ], |
| 2453 | }, |
| 2454 | "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule. |
| 2455 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 2456 | # specified, the entire match is returned. No more than 3 may be included. |
| 2457 | 42, |
| 2458 | ], |
| 2459 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 2460 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 2461 | # google/re2 repository on GitHub. |
| 2462 | }, |
| 2463 | }, |
| 2464 | }, |
| 2465 | ], |
| 2466 | }, |
| 2467 | ], |
| 2468 | "contentOptions": [ # List of options defining data content to scan. |
| 2469 | # If empty, text, images, and other content will be included. |
| 2470 | "A String", |
| 2471 | ], |
| 2472 | "infoTypes": [ # Restricts what info_types to look for. The values must correspond to |
| 2473 | # InfoType values returned by ListInfoTypes or listed at |
| 2474 | # https://cloud.google.com/dlp/docs/infotypes-reference. |
| 2475 | # |
| 2476 | # When no InfoTypes or CustomInfoTypes are specified in a request, the |
| 2477 | # system may automatically choose what detectors to run. By default this may |
| 2478 | # be all types, but may change over time as detectors are updated. |
| 2479 | # |
| 2480 | # If you need precise control and predictability as to what detectors are |
| 2481 | # run you should specify specific InfoTypes listed in the reference, |
| 2482 | # otherwise a default list will be used, which may change over time. |
| 2483 | { # Type of information detected by the API. |
| 2484 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 2485 | # creating a CustomInfoType, or one of the names listed |
| 2486 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 2487 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 2488 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 2489 | }, |
| 2490 | ], |
| 2491 | }, |
| 2492 | }, |
| 2493 | "snapshotInspectTemplate": { # The inspectTemplate contains a configuration (set of types of sensitive data # If run with an InspectTemplate, a snapshot of its state at the time of |
| 2494 | # this run. |
| 2495 | # to be detected) to be used anywhere you otherwise would normally specify |
| 2496 | # InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates |
| 2497 | # to learn more. |
| 2498 | "description": "A String", # Short description (max 256 chars). |
| 2499 | "displayName": "A String", # Display name (max 256 chars). |
| 2500 | "createTime": "A String", # Output only. The creation timestamp of an inspectTemplate. |
| 2501 | "updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate. |
| 2502 | "name": "A String", # Output only. The template name. |
| 2503 | # |
| 2504 | # The template will have one of the following formats: |
| 2505 | # `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR |
| 2506 | # `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`; |
| 2507 | "inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process. |
| 2508 | # When used with redactContent only info_types and min_likelihood are currently |
| 2509 | # used. |
| 2510 | "customInfoTypes": [ # CustomInfoTypes provided by the user. See |
| 2511 | # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more. |
| 2512 | { # Custom information type provided by the user. Used to find domain-specific |
| 2513 | # sensitive information configurable to the data in question. |
| 2514 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType. |
| 2515 | # be used to match sensitive information specific to the data, such as a list |
| 2516 | # of employee IDs or job titles. |
| 2517 | # |
| 2518 | # Dictionary words are case-insensitive and all characters other than letters |
| 2519 | # and digits in the unicode [Basic Multilingual |
| 2520 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 2521 | # will be replaced with whitespace when scanning for matches, so the |
| 2522 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 2523 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 2524 | # surrounding any match must be of a different type than the adjacent |
| 2525 | # characters within the word, so letters must be next to non-letters and |
| 2526 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 2527 | # match the first three letters of the text "jen123" but will return no |
| 2528 | # matches for "jennifer". |
| 2529 | # |
| 2530 | # Dictionary words containing a large number of characters that are not |
| 2531 | # letters or digits may result in unexpected findings because such characters |
| 2532 | # are treated as whitespace. The |
| 2533 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 2534 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 2535 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 2536 | # `StoredInfoType` API. |
| 2537 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 2538 | # is accepted. |
| 2539 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 2540 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 2541 | }, |
| 2542 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 2543 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 2544 | # at least one phrase and every phrase must contain at least 2 characters |
| 2545 | # that are letters or digits. [required] |
| 2546 | "A String", |
| 2547 | ], |
| 2548 | }, |
| 2549 | }, |
| 2550 | "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in |
| 2551 | # infoType, when the name matches one of existing infoTypes and that infoType |
| 2552 | # is specified in `InspectContent.info_types` field. Specifying the latter |
| 2553 | # adds findings to the one detected by the system. If built-in info type is |
| 2554 | # not specified in `InspectContent.info_types` list then the name is treated |
| 2555 | # as a custom info type. |
| 2556 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 2557 | # creating a CustomInfoType, or one of the names listed |
| 2558 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 2559 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 2560 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 2561 | }, |
| 2562 | "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be |
| 2563 | # altered by a detection rule if the finding meets the criteria specified by |
| 2564 | # the rule. Defaults to `VERY_LIKELY` if not specified. |
| 2565 | "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. |
| 2566 | # Rules are applied in order that they are specified. Not supported for the |
| 2567 | # `surrogate_type` CustomInfoType. |
| 2568 | { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a |
| 2569 | # `CustomInfoType` to alter behavior under certain circumstances, depending |
| 2570 | # on the specific details of the rule. Not supported for the `surrogate_type` |
| 2571 | # custom infoType. |
| 2572 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 2573 | # proximity of hotwords. |
| 2574 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 2575 | # The total length of the window cannot exceed 1000 characters. Note that |
| 2576 | # the finding itself will be included in the window, so that hotwords may |
| 2577 | # be used to match substrings of the finding itself. For example, the |
| 2578 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 2579 | # adjusted upwards if the area code is known to be the local area code of |
| 2580 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 2581 | # is the area code in question. |
| 2582 | # rule. |
| 2583 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 2584 | "windowBefore": 42, # Number of characters before the finding to consider. |
| 2585 | }, |
| 2586 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 2587 | # part of a detection rule. |
| 2588 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 2589 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 2590 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 2591 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 2592 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 2593 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 2594 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 2595 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 2596 | # a final likelihood of `LIKELY`. |
| 2597 | }, |
| 2598 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 2599 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 2600 | # specified, the entire match is returned. No more than 3 may be included. |
| 2601 | 42, |
| 2602 | ], |
| 2603 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 2604 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 2605 | # google/re2 repository on GitHub. |
| 2606 | }, |
| 2607 | }, |
| 2608 | }, |
| 2609 | ], |
| 2610 | "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that |
| 2611 | # support reversing. |
| 2612 | # such as |
| 2613 | # [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). |
| 2614 | # These types of transformations are |
| 2615 | # those that perform pseudonymization, thereby producing a "surrogate" as |
| 2616 | # output. This should be used in conjunction with a field on the |
| 2617 | # transformation such as `surrogate_info_type`. This CustomInfoType does |
| 2618 | # not support the use of `detection_rules`. |
| 2619 | }, |
| 2620 | "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType. |
| 2621 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 2622 | # specified, the entire match is returned. No more than 3 may be included. |
| 2623 | 42, |
| 2624 | ], |
| 2625 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 2626 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 2627 | # google/re2 repository on GitHub. |
| 2628 | }, |
| 2629 | "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in |
| 2630 | # `InspectDataSource`. Not currently supported in `InspectContent`. |
| 2631 | "name": "A String", # Resource name of the requested `StoredInfoType`, for example |
| 2632 | # `organizations/433245324/storedInfoTypes/432452342` or |
| 2633 | # `projects/project-id/storedInfoTypes/432452342`. |
| 2634 | "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for |
| 2635 | # inspection was created. Output-only field, populated by the system. |
| 2636 | }, |
| 2637 | "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding |
| 2638 | # to be returned. It still can be used for rules matching. |
| 2639 | }, |
| 2640 | ], |
| 2641 | "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is |
| 2642 | # POSSIBLE. |
| 2643 | # See https://cloud.google.com/dlp/docs/likelihood to learn more. |
| 2644 | "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned. |
| 2645 | "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job. |
| 2646 | # When set within `InspectContentRequest`, the maximum returned is 2000 |
| 2647 | # regardless if this is set higher. |
| 2648 | "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes. |
| 2649 | { # Max findings configuration per infoType, per content item or long |
| 2650 | # running DlpJob. |
| 2651 | "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per |
| 2652 | # info_type should be provided. If InfoTypeLimit does not have an |
| 2653 | # info_type, the DLP API applies the limit against all info_types that |
| 2654 | # are found but not specified in another InfoTypeLimit. |
| 2655 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 2656 | # creating a CustomInfoType, or one of the names listed |
| 2657 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 2658 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 2659 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 2660 | }, |
| 2661 | "maxFindings": 42, # Max findings limit for the given infoType. |
| 2662 | }, |
| 2663 | ], |
| 2664 | "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned. |
| 2665 | # When set within `InspectJobConfig`, |
| 2666 | # the maximum returned is 2000 regardless if this is set higher. |
| 2667 | # When set within `InspectContentRequest`, this field is ignored. |
| 2668 | }, |
| 2669 | "excludeInfoTypes": True or False, # When true, excludes type information of the findings. |
| 2670 | "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is |
| 2671 | # included in the response; see Finding.quote. |
| 2672 | "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. |
| 2673 | # Exclusion rules, contained in the set are executed in the end, other |
| 2674 | # rules are executed in the order they are specified for each info type. |
| 2675 | { # Rule set for modifying a set of infoTypes to alter behavior under certain |
| 2676 | # circumstances, depending on the specific details of the rules within the set. |
| 2677 | "infoTypes": [ # List of infoTypes this rule set is applied to. |
| 2678 | { # Type of information detected by the API. |
| 2679 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 2680 | # creating a CustomInfoType, or one of the names listed |
| 2681 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 2682 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 2683 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 2684 | }, |
| 2685 | ], |
| 2686 | "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order. |
| 2687 | { # A single inspection rule to be applied to infoTypes, specified in |
| 2688 | # `InspectionRuleSet`. |
| 2689 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 2690 | # proximity of hotwords. |
| 2691 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 2692 | # The total length of the window cannot exceed 1000 characters. Note that |
| 2693 | # the finding itself will be included in the window, so that hotwords may |
| 2694 | # be used to match substrings of the finding itself. For example, the |
| 2695 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 2696 | # adjusted upwards if the area code is known to be the local area code of |
| 2697 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 2698 | # is the area code in question. |
| 2699 | # rule. |
| 2700 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 2701 | "windowBefore": 42, # Number of characters before the finding to consider. |
| 2702 | }, |
| 2703 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 2704 | # part of a detection rule. |
| 2705 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 2706 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 2707 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 2708 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 2709 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 2710 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 2711 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 2712 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 2713 | # a final likelihood of `LIKELY`. |
| 2714 | }, |
| 2715 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 2716 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 2717 | # specified, the entire match is returned. No more than 3 may be included. |
| 2718 | 42, |
| 2719 | ], |
| 2720 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 2721 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 2722 | # google/re2 repository on GitHub. |
| 2723 | }, |
| 2724 | }, |
| 2725 | "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule. |
| 2726 | # `InspectionRuleSet` are removed from results. |
| 2727 | "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details. |
| 2728 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule. |
| 2729 | # be used to match sensitive information specific to the data, such as a list |
| 2730 | # of employee IDs or job titles. |
| 2731 | # |
| 2732 | # Dictionary words are case-insensitive and all characters other than letters |
| 2733 | # and digits in the unicode [Basic Multilingual |
| 2734 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 2735 | # will be replaced with whitespace when scanning for matches, so the |
| 2736 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 2737 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 2738 | # surrounding any match must be of a different type than the adjacent |
| 2739 | # characters within the word, so letters must be next to non-letters and |
| 2740 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 2741 | # match the first three letters of the text "jen123" but will return no |
| 2742 | # matches for "jennifer". |
| 2743 | # |
| 2744 | # Dictionary words containing a large number of characters that are not |
| 2745 | # letters or digits may result in unexpected findings because such characters |
| 2746 | # are treated as whitespace. The |
| 2747 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 2748 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 2749 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 2750 | # `StoredInfoType` API. |
| 2751 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 2752 | # is accepted. |
| 2753 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 2754 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 2755 | }, |
| 2756 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 2757 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 2758 | # at least one phrase and every phrase must contain at least 2 characters |
| 2759 | # that are letters or digits. [required] |
| 2760 | "A String", |
| 2761 | ], |
| 2762 | }, |
| 2763 | }, |
| 2764 | "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule. |
| 2765 | "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or |
| 2766 | # contained within with a finding of an infoType from this list. For |
| 2767 | # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and |
| 2768 | # `exclusion_rule` containing `exclude_info_types.info_types` with |
| 2769 | # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap |
| 2770 | # with EMAIL_ADDRESS finding. |
| 2771 | # That leads to "555-222-2222@example.org" to generate only a single |
| 2772 | # finding, namely email address. |
| 2773 | { # Type of information detected by the API. |
| 2774 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 2775 | # creating a CustomInfoType, or one of the names listed |
| 2776 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 2777 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 2778 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 2779 | }, |
| 2780 | ], |
| 2781 | }, |
| 2782 | "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule. |
| 2783 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 2784 | # specified, the entire match is returned. No more than 3 may be included. |
| 2785 | 42, |
| 2786 | ], |
| 2787 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 2788 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 2789 | # google/re2 repository on GitHub. |
| 2790 | }, |
| 2791 | }, |
| 2792 | }, |
| 2793 | ], |
| 2794 | }, |
| 2795 | ], |
| 2796 | "contentOptions": [ # List of options defining data content to scan. |
| 2797 | # If empty, text, images, and other content will be included. |
| 2798 | "A String", |
| 2799 | ], |
| 2800 | "infoTypes": [ # Restricts what info_types to look for. The values must correspond to |
| 2801 | # InfoType values returned by ListInfoTypes or listed at |
| 2802 | # https://cloud.google.com/dlp/docs/infotypes-reference. |
| 2803 | # |
| 2804 | # When no InfoTypes or CustomInfoTypes are specified in a request, the |
| 2805 | # system may automatically choose what detectors to run. By default this may |
| 2806 | # be all types, but may change over time as detectors are updated. |
| 2807 | # |
| 2808 | # If you need precise control and predictability as to what detectors are |
| 2809 | # run you should specify specific InfoTypes listed in the reference, |
| 2810 | # otherwise a default list will be used, which may change over time. |
| 2811 | { # Type of information detected by the API. |
| 2812 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 2813 | # creating a CustomInfoType, or one of the names listed |
| 2814 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 2815 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 2816 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 2817 | }, |
| 2818 | ], |
| 2819 | }, |
| 2820 | }, |
| 2821 | }, |
| 2822 | "result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspect job. |
| 2823 | "hybridStats": { # Statistics related to processing hybrid inspect requests. # Statistics related to the processing of hybrid inspect. |
| 2824 | # Early access feature is in a pre-release state and might change or have |
| 2825 | # limited support. For more information, see |
| 2826 | # https://cloud.google.com/products#product-launch-stages. |
| 2827 | "processedCount": "A String", # The number of hybrid inspection requests processed within this job. |
| 2828 | "abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran |
| 2829 | # out of quota or was ended before they could be processed. |
| 2830 | "pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated |
| 2831 | # when called via method `getDlpJob`. |
| 2832 | # A burst of traffic may cause hybrid inspect requests to be enqueued. |
| 2833 | # Processing will take place as quickly as possible, but resource limitations |
| 2834 | # may impact how long a request is enqueued for. |
| 2835 | }, |
| 2836 | "totalEstimatedBytes": "A String", # Estimate of the number of bytes to process. |
| 2837 | "infoTypeStats": [ # Statistics of how many instances of each info type were found during |
| 2838 | # inspect job. |
| 2839 | { # Statistics regarding a specific InfoType. |
| 2840 | "infoType": { # Type of information detected by the API. # The type of finding this stat is for. |
| 2841 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 2842 | # creating a CustomInfoType, or one of the names listed |
| 2843 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 2844 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 2845 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 2846 | }, |
| 2847 | "count": "A String", # Number of findings for this infoType. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 2848 | }, |
| 2849 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 2850 | "processedBytes": "A String", # Total size in bytes that were processed. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 2851 | }, |
| 2852 | }, |
| 2853 | "name": "A String", # The server-assigned name. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2854 | }</pre> |
| 2855 | </div> |
| 2856 | |
| 2857 | <div class="method"> |
| 2858 | <code class="details" id="delete">delete(name, x__xgafv=None)</code> |
| 2859 | <pre>Deletes a long-running DlpJob. This method indicates that the client is |
| 2860 | no longer interested in the DlpJob result. The job will be cancelled if |
| 2861 | possible. |
| 2862 | See https://cloud.google.com/dlp/docs/inspecting-storage and |
| 2863 | https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more. |
| 2864 | |
| 2865 | Args: |
| Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2866 | name: string, Required. The name of the DlpJob resource to be deleted. (required) |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2867 | x__xgafv: string, V1 error format. |
| 2868 | Allowed values |
| 2869 | 1 - v1 error format |
| 2870 | 2 - v2 error format |
| 2871 | |
| 2872 | Returns: |
| 2873 | An object of the form: |
| 2874 | |
| 2875 | { # A generic empty message that you can re-use to avoid defining duplicated |
| 2876 | # empty messages in your APIs. A typical example is to use it as the request |
| 2877 | # or the response type of an API method. For instance: |
| 2878 | # |
| 2879 | # service Foo { |
| 2880 | # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); |
| 2881 | # } |
| 2882 | # |
| 2883 | # The JSON representation for `Empty` is empty JSON object `{}`. |
| 2884 | }</pre> |
| 2885 | </div> |
| 2886 | |
| 2887 | <div class="method"> |
| 2888 | <code class="details" id="get">get(name, x__xgafv=None)</code> |
| 2889 | <pre>Gets the latest state of a long-running DlpJob. |
| 2890 | See https://cloud.google.com/dlp/docs/inspecting-storage and |
| 2891 | https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more. |
| 2892 | |
| 2893 | Args: |
| Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2894 | name: string, Required. The name of the DlpJob resource. (required) |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2895 | x__xgafv: string, V1 error format. |
| 2896 | Allowed values |
| 2897 | 1 - v1 error format |
| 2898 | 2 - v2 error format |
| 2899 | |
| 2900 | Returns: |
| 2901 | An object of the form: |
| 2902 | |
| 2903 | { # Combines all of the information about a DLP job. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 2904 | "errors": [ # A stream of errors encountered running the job. |
| 2905 | { # Details information about an error encountered during job execution or |
| 2906 | # the results of an unsuccessful activation of the JobTrigger. |
| 2907 | "timestamps": [ # The times the error occurred. |
| 2908 | "A String", |
| 2909 | ], |
| 2910 | "details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages. |
| 2911 | # different programming environments, including REST APIs and RPC APIs. It is |
| 2912 | # used by [gRPC](https://github.com/grpc). Each `Status` message contains |
| 2913 | # three pieces of data: error code, error message, and error details. |
| 2914 | # |
| 2915 | # You can find out more about this error model and how to work with it in the |
| 2916 | # [API Design Guide](https://cloud.google.com/apis/design/errors). |
| 2917 | "code": 42, # The status code, which should be an enum value of google.rpc.Code. |
| 2918 | "details": [ # A list of messages that carry the error details. There is a common set of |
| 2919 | # message types for APIs to use. |
| 2920 | { |
| 2921 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 2922 | }, |
| 2923 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 2924 | "message": "A String", # A developer-facing error message, which should be in English. Any |
| 2925 | # user-facing error message should be localized and sent in the |
| 2926 | # google.rpc.Status.details field, or localized by the client. |
| 2927 | }, |
| 2928 | }, |
| 2929 | ], |
| 2930 | "createTime": "A String", # Time when the job was created. |
| 2931 | "state": "A String", # State of a job. |
| 2932 | "riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source. |
| 2933 | "kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an # K-map result |
| 2934 | # estimation, not exact values. |
| 2935 | "kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value |
| 2936 | # doesn't correspond to any such interval, the associated frequency is |
| 2937 | # zero. For example, the following records: |
| 2938 | # {min_anonymity: 1, max_anonymity: 1, frequency: 17} |
| 2939 | # {min_anonymity: 2, max_anonymity: 3, frequency: 42} |
| 2940 | # {min_anonymity: 5, max_anonymity: 10, frequency: 99} |
| 2941 | # mean that there are no record with an estimated anonymity of 4, 5, or |
| 2942 | # larger than 10. |
| 2943 | { # A KMapEstimationHistogramBucket message with the following values: |
| 2944 | # min_anonymity: 3 |
| 2945 | # max_anonymity: 5 |
| 2946 | # frequency: 42 |
| 2947 | # means that there are 42 records whose quasi-identifier values correspond |
| 2948 | # to 3, 4 or 5 people in the overlying population. An important particular |
| 2949 | # case is when min_anonymity = max_anonymity = 1: the frequency field then |
| 2950 | # corresponds to the number of uniquely identifiable records. |
| 2951 | "maxAnonymity": "A String", # Always greater than or equal to min_anonymity. |
| 2952 | "bucketSize": "A String", # Number of records within these anonymity bounds. |
| 2953 | "bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket. |
| 2954 | "bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total |
| 2955 | # number of classes returned per bucket is capped at 20. |
| 2956 | { # A tuple of values for the quasi-identifier columns. |
| 2957 | "estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values. |
| 2958 | "quasiIdsValues": [ # The quasi-identifier values. |
| 2959 | { # Set of primitive values supported by the system. |
| 2960 | # Note that for the purposes of inspection or transformation, the number |
| 2961 | # of bytes considered to comprise a 'Value' is based on its representation |
| 2962 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 2963 | # 123456789, the number of bytes would be counted as 9, even though an |
| 2964 | # int64 only holds up to 8 bytes of data. |
| 2965 | "integerValue": "A String", # integer |
| 2966 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 2967 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 2968 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 2969 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 2970 | # allow the value 60 if it allows leap-seconds. |
| 2971 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 2972 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 2973 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 2974 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 2975 | }, |
| 2976 | "dayOfWeekValue": "A String", # day of week |
| 2977 | "floatValue": 3.14, # float |
| 2978 | "stringValue": "A String", # string |
| 2979 | "timestampValue": "A String", # timestamp |
| 2980 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 2981 | # and time zone are either specified elsewhere or are not significant. The date |
| 2982 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 2983 | # |
| 2984 | # * A full date, with non-zero year, month and day values |
| 2985 | # * A month and day value, with a zero year, e.g. an anniversary |
| 2986 | # * A year on its own, with zero month and day values |
| 2987 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 2988 | # |
| 2989 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 2990 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 2991 | # month and day. |
| 2992 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 2993 | # a year. |
| 2994 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 2995 | # if specifying a year by itself or a year and month where the day is not |
| 2996 | # significant. |
| 2997 | }, |
| 2998 | "booleanValue": True or False, # boolean |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 2999 | }, |
| 3000 | ], |
| 3001 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3002 | ], |
| 3003 | "minAnonymity": "A String", # Always positive. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3004 | }, |
| 3005 | ], |
| 3006 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3007 | "deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an # Delta-presence result |
| 3008 | # estimation, not exact values. |
| 3009 | "deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a |
| 3010 | # value doesn't correspond to any such interval, the associated frequency |
| 3011 | # is zero. For example, the following records: |
| 3012 | # {min_probability: 0, max_probability: 0.1, frequency: 17} |
| 3013 | # {min_probability: 0.2, max_probability: 0.3, frequency: 42} |
| 3014 | # {min_probability: 0.3, max_probability: 0.4, frequency: 99} |
| 3015 | # mean that there are no record with an estimated probability in [0.1, 0.2) |
| 3016 | # nor larger or equal to 0.4. |
| 3017 | { # A DeltaPresenceEstimationHistogramBucket message with the following |
| 3018 | # values: |
| 3019 | # min_probability: 0.1 |
| 3020 | # max_probability: 0.2 |
| 3021 | # frequency: 42 |
| 3022 | # means that there are 42 records for which δ is in [0.1, 0.2). An |
| 3023 | # important particular case is when min_probability = max_probability = 1: |
| 3024 | # then, every individual who shares this quasi-identifier combination is in |
| 3025 | # the dataset. |
| 3026 | "maxProbability": 3.14, # Always greater than or equal to min_probability. |
| 3027 | "bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket. |
| 3028 | "bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total |
| 3029 | # number of classes returned per bucket is capped at 20. |
| 3030 | { # A tuple of values for the quasi-identifier columns. |
| 3031 | "estimatedProbability": 3.14, # The estimated probability that a given individual sharing these |
| 3032 | # quasi-identifier values is in the dataset. This value, typically called |
| 3033 | # δ, is the ratio between the number of records in the dataset with these |
| 3034 | # quasi-identifier values, and the total number of individuals (inside |
| 3035 | # *and* outside the dataset) with these quasi-identifier values. |
| 3036 | # For example, if there are 15 individuals in the dataset who share the |
| 3037 | # same quasi-identifier values, and an estimated 100 people in the entire |
| 3038 | # population with these values, then δ is 0.15. |
| 3039 | "quasiIdsValues": [ # The quasi-identifier values. |
| 3040 | { # Set of primitive values supported by the system. |
| 3041 | # Note that for the purposes of inspection or transformation, the number |
| 3042 | # of bytes considered to comprise a 'Value' is based on its representation |
| 3043 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 3044 | # 123456789, the number of bytes would be counted as 9, even though an |
| 3045 | # int64 only holds up to 8 bytes of data. |
| 3046 | "integerValue": "A String", # integer |
| 3047 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 3048 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 3049 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 3050 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 3051 | # allow the value 60 if it allows leap-seconds. |
| 3052 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 3053 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 3054 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 3055 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 3056 | }, |
| 3057 | "dayOfWeekValue": "A String", # day of week |
| 3058 | "floatValue": 3.14, # float |
| 3059 | "stringValue": "A String", # string |
| 3060 | "timestampValue": "A String", # timestamp |
| 3061 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 3062 | # and time zone are either specified elsewhere or are not significant. The date |
| 3063 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 3064 | # |
| 3065 | # * A full date, with non-zero year, month and day values |
| 3066 | # * A month and day value, with a zero year, e.g. an anniversary |
| 3067 | # * A year on its own, with zero month and day values |
| 3068 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 3069 | # |
| 3070 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 3071 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 3072 | # month and day. |
| 3073 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 3074 | # a year. |
| 3075 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 3076 | # if specifying a year by itself or a year and month where the day is not |
| 3077 | # significant. |
| 3078 | }, |
| 3079 | "booleanValue": True or False, # boolean |
| 3080 | }, |
| 3081 | ], |
| 3082 | }, |
| 3083 | ], |
| 3084 | "minProbability": 3.14, # Between 0 and 1. |
| 3085 | "bucketSize": "A String", # Number of records within these probability bounds. |
| 3086 | }, |
| 3087 | ], |
| 3088 | }, |
| 3089 | "categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result |
| 3090 | "valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column. |
| 3091 | { # Histogram of value frequencies in the column. |
| 3092 | "valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket. |
| 3093 | "bucketValueCount": "A String", # Total number of distinct values in this bucket. |
| 3094 | "bucketSize": "A String", # Total number of values in this bucket. |
| 3095 | "valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket. |
| 3096 | "bucketValues": [ # Sample of value frequencies in this bucket. The total number of |
| 3097 | # values returned per bucket is capped at 20. |
| 3098 | { # A value of a field, including its frequency. |
| 3099 | "count": "A String", # How many times the value is contained in the field. |
| 3100 | "value": { # Set of primitive values supported by the system. # A value contained in the field in question. |
| 3101 | # Note that for the purposes of inspection or transformation, the number |
| 3102 | # of bytes considered to comprise a 'Value' is based on its representation |
| 3103 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 3104 | # 123456789, the number of bytes would be counted as 9, even though an |
| 3105 | # int64 only holds up to 8 bytes of data. |
| 3106 | "integerValue": "A String", # integer |
| 3107 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 3108 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 3109 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 3110 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 3111 | # allow the value 60 if it allows leap-seconds. |
| 3112 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 3113 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 3114 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 3115 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 3116 | }, |
| 3117 | "dayOfWeekValue": "A String", # day of week |
| 3118 | "floatValue": 3.14, # float |
| 3119 | "stringValue": "A String", # string |
| 3120 | "timestampValue": "A String", # timestamp |
| 3121 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 3122 | # and time zone are either specified elsewhere or are not significant. The date |
| 3123 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 3124 | # |
| 3125 | # * A full date, with non-zero year, month and day values |
| 3126 | # * A month and day value, with a zero year, e.g. an anniversary |
| 3127 | # * A year on its own, with zero month and day values |
| 3128 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 3129 | # |
| 3130 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 3131 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 3132 | # month and day. |
| 3133 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 3134 | # a year. |
| 3135 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 3136 | # if specifying a year by itself or a year and month where the day is not |
| 3137 | # significant. |
| 3138 | }, |
| 3139 | "booleanValue": True or False, # boolean |
| 3140 | }, |
| 3141 | }, |
| 3142 | ], |
| 3143 | }, |
| 3144 | ], |
| 3145 | }, |
| 3146 | "numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result |
| 3147 | "quantileValues": [ # List of 99 values that partition the set of field values into 100 equal |
| 3148 | # sized buckets. |
| 3149 | { # Set of primitive values supported by the system. |
| 3150 | # Note that for the purposes of inspection or transformation, the number |
| 3151 | # of bytes considered to comprise a 'Value' is based on its representation |
| 3152 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 3153 | # 123456789, the number of bytes would be counted as 9, even though an |
| 3154 | # int64 only holds up to 8 bytes of data. |
| 3155 | "integerValue": "A String", # integer |
| 3156 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 3157 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 3158 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 3159 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 3160 | # allow the value 60 if it allows leap-seconds. |
| 3161 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 3162 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 3163 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 3164 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 3165 | }, |
| 3166 | "dayOfWeekValue": "A String", # day of week |
| 3167 | "floatValue": 3.14, # float |
| 3168 | "stringValue": "A String", # string |
| 3169 | "timestampValue": "A String", # timestamp |
| 3170 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 3171 | # and time zone are either specified elsewhere or are not significant. The date |
| 3172 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 3173 | # |
| 3174 | # * A full date, with non-zero year, month and day values |
| 3175 | # * A month and day value, with a zero year, e.g. an anniversary |
| 3176 | # * A year on its own, with zero month and day values |
| 3177 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 3178 | # |
| 3179 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 3180 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 3181 | # month and day. |
| 3182 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 3183 | # a year. |
| 3184 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 3185 | # if specifying a year by itself or a year and month where the day is not |
| 3186 | # significant. |
| 3187 | }, |
| 3188 | "booleanValue": True or False, # boolean |
| 3189 | }, |
| 3190 | ], |
| 3191 | "minValue": { # Set of primitive values supported by the system. # Minimum value appearing in the column. |
| 3192 | # Note that for the purposes of inspection or transformation, the number |
| 3193 | # of bytes considered to comprise a 'Value' is based on its representation |
| 3194 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 3195 | # 123456789, the number of bytes would be counted as 9, even though an |
| 3196 | # int64 only holds up to 8 bytes of data. |
| 3197 | "integerValue": "A String", # integer |
| 3198 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 3199 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 3200 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 3201 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 3202 | # allow the value 60 if it allows leap-seconds. |
| 3203 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 3204 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 3205 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 3206 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 3207 | }, |
| 3208 | "dayOfWeekValue": "A String", # day of week |
| 3209 | "floatValue": 3.14, # float |
| 3210 | "stringValue": "A String", # string |
| 3211 | "timestampValue": "A String", # timestamp |
| 3212 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 3213 | # and time zone are either specified elsewhere or are not significant. The date |
| 3214 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 3215 | # |
| 3216 | # * A full date, with non-zero year, month and day values |
| 3217 | # * A month and day value, with a zero year, e.g. an anniversary |
| 3218 | # * A year on its own, with zero month and day values |
| 3219 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 3220 | # |
| 3221 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 3222 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 3223 | # month and day. |
| 3224 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 3225 | # a year. |
| 3226 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 3227 | # if specifying a year by itself or a year and month where the day is not |
| 3228 | # significant. |
| 3229 | }, |
| 3230 | "booleanValue": True or False, # boolean |
| 3231 | }, |
| 3232 | "maxValue": { # Set of primitive values supported by the system. # Maximum value appearing in the column. |
| 3233 | # Note that for the purposes of inspection or transformation, the number |
| 3234 | # of bytes considered to comprise a 'Value' is based on its representation |
| 3235 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 3236 | # 123456789, the number of bytes would be counted as 9, even though an |
| 3237 | # int64 only holds up to 8 bytes of data. |
| 3238 | "integerValue": "A String", # integer |
| 3239 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 3240 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 3241 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 3242 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 3243 | # allow the value 60 if it allows leap-seconds. |
| 3244 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 3245 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 3246 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 3247 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 3248 | }, |
| 3249 | "dayOfWeekValue": "A String", # day of week |
| 3250 | "floatValue": 3.14, # float |
| 3251 | "stringValue": "A String", # string |
| 3252 | "timestampValue": "A String", # timestamp |
| 3253 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 3254 | # and time zone are either specified elsewhere or are not significant. The date |
| 3255 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 3256 | # |
| 3257 | # * A full date, with non-zero year, month and day values |
| 3258 | # * A month and day value, with a zero year, e.g. an anniversary |
| 3259 | # * A year on its own, with zero month and day values |
| 3260 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 3261 | # |
| 3262 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 3263 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 3264 | # month and day. |
| 3265 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 3266 | # a year. |
| 3267 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 3268 | # if specifying a year by itself or a year and month where the day is not |
| 3269 | # significant. |
| 3270 | }, |
| 3271 | "booleanValue": True or False, # boolean |
| 3272 | }, |
| 3273 | }, |
| 3274 | "kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result |
| 3275 | "equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes. |
| 3276 | { # Histogram of k-anonymity equivalence classes. |
| 3277 | "bucketValues": [ # Sample of equivalence classes in this bucket. The total number of |
| 3278 | # classes returned per bucket is capped at 20. |
| 3279 | { # The set of columns' values that share the same ldiversity value |
| 3280 | "quasiIdsValues": [ # Set of values defining the equivalence class. One value per |
| 3281 | # quasi-identifier column in the original KAnonymity metric message. |
| 3282 | # The order is always the same as the original request. |
| 3283 | { # Set of primitive values supported by the system. |
| 3284 | # Note that for the purposes of inspection or transformation, the number |
| 3285 | # of bytes considered to comprise a 'Value' is based on its representation |
| 3286 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 3287 | # 123456789, the number of bytes would be counted as 9, even though an |
| 3288 | # int64 only holds up to 8 bytes of data. |
| 3289 | "integerValue": "A String", # integer |
| 3290 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 3291 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 3292 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 3293 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 3294 | # allow the value 60 if it allows leap-seconds. |
| 3295 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 3296 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 3297 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 3298 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 3299 | }, |
| 3300 | "dayOfWeekValue": "A String", # day of week |
| 3301 | "floatValue": 3.14, # float |
| 3302 | "stringValue": "A String", # string |
| 3303 | "timestampValue": "A String", # timestamp |
| 3304 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 3305 | # and time zone are either specified elsewhere or are not significant. The date |
| 3306 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 3307 | # |
| 3308 | # * A full date, with non-zero year, month and day values |
| 3309 | # * A month and day value, with a zero year, e.g. an anniversary |
| 3310 | # * A year on its own, with zero month and day values |
| 3311 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 3312 | # |
| 3313 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 3314 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 3315 | # month and day. |
| 3316 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 3317 | # a year. |
| 3318 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 3319 | # if specifying a year by itself or a year and month where the day is not |
| 3320 | # significant. |
| 3321 | }, |
| 3322 | "booleanValue": True or False, # boolean |
| 3323 | }, |
| 3324 | ], |
| 3325 | "equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the |
| 3326 | # above set of values. |
| 3327 | }, |
| 3328 | ], |
| 3329 | "equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket. |
| 3330 | "equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket. |
| 3331 | "bucketSize": "A String", # Total number of equivalence classes in this bucket. |
| 3332 | "bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket. |
| 3333 | }, |
| 3334 | ], |
| 3335 | }, |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3336 | "requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3337 | "categoricalStatsConfig": { # Compute numerical stats over an individual column, including # Categorical stats |
| 3338 | # number of distinct values and value count distribution. |
| 3339 | "field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are |
| 3340 | # supported except for arrays and structs. However, it may be more |
| 3341 | # informative to use NumericalStats when the field type is supported, |
| 3342 | # depending on the data. |
| 3343 | "name": "A String", # Name describing the field. |
| 3344 | }, |
| 3345 | }, |
| 3346 | "lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity |
| 3347 | "sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value. |
| 3348 | "name": "A String", # Name describing the field. |
| 3349 | }, |
| 3350 | "quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are |
| 3351 | # defined for the l-diversity computation. When multiple fields are |
| 3352 | # specified, they are considered a single composite key. |
| 3353 | { # General identifier of a data field in a storage service. |
| 3354 | "name": "A String", # Name describing the field. |
| 3355 | }, |
| 3356 | ], |
| 3357 | }, |
| 3358 | "kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what # k-map |
| 3359 | # is called "journalist risk" in the literature, except the attack dataset is |
| 3360 | # statistically modeled instead of being perfectly known. This can be done |
| 3361 | # using publicly available data (like the US Census), or using a custom |
| 3362 | # statistical model (indicated as one or several BigQuery tables), or by |
| 3363 | # extrapolating from the distribution of values in the input dataset. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3364 | "regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. |
| 3365 | # Set if no column is tagged with a region-specific InfoType (like |
| 3366 | # US_ZIP_5) or a region code. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3367 | "quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the |
| 3368 | # same tag. |
| 3369 | { # A column with a semantic tag attached. |
| 3370 | "field": { # General identifier of a data field in a storage service. # Required. Identifies the column. |
| 3371 | "name": "A String", # Name describing the field. |
| 3372 | }, |
| 3373 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 3374 | # indicate an auxiliary table that contains statistical information on |
| 3375 | # the possible values of this column (below). |
| 3376 | "infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public |
| 3377 | # dataset as a statistical model of population, if available. We |
| 3378 | # currently support US ZIP codes, region codes, ages and genders. |
| 3379 | # To programmatically obtain the list of supported InfoTypes, use |
| 3380 | # ListInfoTypes with the supported_by=RISK_ANALYSIS filter. |
| 3381 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 3382 | # creating a CustomInfoType, or one of the names listed |
| 3383 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 3384 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 3385 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 3386 | }, |
| 3387 | "inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from |
| 3388 | # the distribution of values in the input data |
| 3389 | # empty messages in your APIs. A typical example is to use it as the request |
| 3390 | # or the response type of an API method. For instance: |
| 3391 | # |
| 3392 | # service Foo { |
| 3393 | # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); |
| 3394 | # } |
| 3395 | # |
| 3396 | # The JSON representation for `Empty` is empty JSON object `{}`. |
| 3397 | }, |
| 3398 | }, |
| 3399 | ], |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3400 | "auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3401 | # used to tag a quasi-identifiers column must appear in exactly one column |
| 3402 | # of one auxiliary table. |
| 3403 | { # An auxiliary table contains statistical information on the relative |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3404 | # frequency of different quasi-identifiers values. It has one or several |
| 3405 | # quasi-identifiers columns, and one column that indicates the relative |
| 3406 | # frequency of each quasi-identifier tuple. |
| 3407 | # If a tuple is present in the data but not in the auxiliary table, the |
| 3408 | # corresponding relative frequency is assumed to be zero (and thus, the |
| 3409 | # tuple is highly reidentifiable). |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3410 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location. |
| 3411 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 3412 | # a table is often referenced with a string in the format of: |
| 3413 | # `<project_id>:<dataset_id>.<table_id>` or |
| 3414 | # `<project_id>.<dataset_id>.<table_id>`. |
| 3415 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 3416 | # If omitted, project ID is inferred from the API call. |
| 3417 | "datasetId": "A String", # Dataset ID of the table. |
| 3418 | "tableId": "A String", # Name of the table. |
| 3419 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3420 | "quasiIds": [ # Required. Quasi-identifier columns. |
| 3421 | { # A quasi-identifier column has a custom_tag, used to know which column |
| 3422 | # in the data corresponds to which column in the statistical model. |
| 3423 | "customTag": "A String", # A auxiliary field. |
| 3424 | "field": { # General identifier of a data field in a storage service. # Identifies the column. |
| 3425 | "name": "A String", # Name describing the field. |
| 3426 | }, |
| 3427 | }, |
| 3428 | ], |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3429 | "relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number |
| 3430 | # between 0 and 1 (inclusive). Null values are assumed to be zero. |
| 3431 | "name": "A String", # Name describing the field. |
| 3432 | }, |
| 3433 | }, |
| 3434 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3435 | }, |
| 3436 | "deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to # delta-presence |
| 3437 | # figure out that one given individual appears in a de-identified dataset. |
| 3438 | # Similarly to the k-map metric, we cannot compute δ-presence exactly without |
| 3439 | # knowing the attack dataset, so we use a statistical model instead. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3440 | "quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the |
| 3441 | # same tag. |
| 3442 | { # A column with a semantic tag attached. |
| 3443 | "field": { # General identifier of a data field in a storage service. # Required. Identifies the column. |
| 3444 | "name": "A String", # Name describing the field. |
| 3445 | }, |
| 3446 | "infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public |
| 3447 | # dataset as a statistical model of population, if available. We |
| 3448 | # currently support US ZIP codes, region codes, ages and genders. |
| 3449 | # To programmatically obtain the list of supported InfoTypes, use |
| 3450 | # ListInfoTypes with the supported_by=RISK_ANALYSIS filter. |
| 3451 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 3452 | # creating a CustomInfoType, or one of the names listed |
| 3453 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3454 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 3455 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3456 | }, |
| 3457 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 3458 | # indicate an auxiliary table that contains statistical information on |
| 3459 | # the possible values of this column (below). |
| 3460 | "inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from |
| 3461 | # the distribution of values in the input data |
| 3462 | # empty messages in your APIs. A typical example is to use it as the request |
| 3463 | # or the response type of an API method. For instance: |
| 3464 | # |
| 3465 | # service Foo { |
| 3466 | # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); |
| 3467 | # } |
| 3468 | # |
| 3469 | # The JSON representation for `Empty` is empty JSON object `{}`. |
| 3470 | }, |
| 3471 | }, |
| 3472 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3473 | "auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag |
| 3474 | # used to tag a quasi-identifiers field must appear in exactly one |
| 3475 | # field of one auxiliary table. |
| 3476 | { # An auxiliary table containing statistical information on the relative |
| 3477 | # frequency of different quasi-identifiers values. It has one or several |
| 3478 | # quasi-identifiers columns, and one column that indicates the relative |
| 3479 | # frequency of each quasi-identifier tuple. |
| 3480 | # If a tuple is present in the data but not in the auxiliary table, the |
| 3481 | # corresponding relative frequency is assumed to be zero (and thus, the |
| 3482 | # tuple is highly reidentifiable). |
| 3483 | "relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number |
| 3484 | # between 0 and 1 (inclusive). Null values are assumed to be zero. |
| 3485 | "name": "A String", # Name describing the field. |
| 3486 | }, |
| 3487 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location. |
| 3488 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 3489 | # a table is often referenced with a string in the format of: |
| 3490 | # `<project_id>:<dataset_id>.<table_id>` or |
| 3491 | # `<project_id>.<dataset_id>.<table_id>`. |
| 3492 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 3493 | # If omitted, project ID is inferred from the API call. |
| 3494 | "datasetId": "A String", # Dataset ID of the table. |
| 3495 | "tableId": "A String", # Name of the table. |
| 3496 | }, |
| 3497 | "quasiIds": [ # Required. Quasi-identifier columns. |
| 3498 | { # A quasi-identifier column has a custom_tag, used to know which column |
| 3499 | # in the data corresponds to which column in the statistical model. |
| 3500 | "field": { # General identifier of a data field in a storage service. # Identifies the column. |
| 3501 | "name": "A String", # Name describing the field. |
| 3502 | }, |
| 3503 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 3504 | # indicate an auxiliary table that contains statistical information on |
| 3505 | # the possible values of this column (below). |
| 3506 | }, |
| 3507 | ], |
| 3508 | }, |
| 3509 | ], |
| 3510 | "regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. |
| 3511 | # Set if no column is tagged with a region-specific InfoType (like |
| 3512 | # US_ZIP_5) or a region code. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3513 | }, |
| 3514 | "kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3515 | "entityId": { # An entity in a dataset is a field or set of fields that correspond to a # Message indicating that multiple rows might be associated to a |
| 3516 | # single individual. If the same entity_id is associated to multiple |
| 3517 | # quasi-identifier tuples over distinct rows, we consider the entire |
| 3518 | # collection of tuples as the composite quasi-identifier. This collection |
| 3519 | # is a multiset: the order in which the different tuples appear in the |
| 3520 | # dataset is ignored, but their frequency is taken into account. |
| 3521 | # |
| 3522 | # Important note: a maximum of 1000 rows can be associated to a single |
| 3523 | # entity ID. If more rows are associated with the same entity ID, some |
| 3524 | # might be ignored. |
| 3525 | # single person. For example, in medical records the `EntityId` might be a |
| 3526 | # patient identifier, or for financial records it might be an account |
| 3527 | # identifier. This message is used when generalizations or analysis must take |
| 3528 | # into account that multiple rows correspond to the same entity. |
| 3529 | "field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier. |
| 3530 | "name": "A String", # Name describing the field. |
| 3531 | }, |
| 3532 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3533 | "quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are |
| 3534 | # specified, they are considered a single composite key. Structs and |
| 3535 | # repeated data types are not supported; however, nested fields are |
| 3536 | # supported so long as they are not structs themselves or nested within |
| 3537 | # a repeated field. |
| 3538 | { # General identifier of a data field in a storage service. |
| 3539 | "name": "A String", # Name describing the field. |
| 3540 | }, |
| 3541 | ], |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3542 | }, |
| 3543 | "numericalStatsConfig": { # Compute numerical stats over an individual column, including # Numerical stats |
| 3544 | # min, max, and quantiles. |
| 3545 | "field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are |
| 3546 | # integer, float, date, datetime, timestamp, time. |
| 3547 | "name": "A String", # Name describing the field. |
| 3548 | }, |
| 3549 | }, |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3550 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3551 | "lDiversityResult": { # Result of the l-diversity computation. # L-divesity result |
| 3552 | "sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies. |
| 3553 | { # Histogram of l-diversity equivalence class sensitive value frequencies. |
| 3554 | "bucketSize": "A String", # Total number of equivalence classes in this bucket. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3555 | "bucketValues": [ # Sample of equivalence classes in this bucket. The total number of |
| 3556 | # classes returned per bucket is capped at 20. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3557 | { # The set of columns' values that share the same ldiversity value. |
| 3558 | "quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence |
| 3559 | # class. The order is always the same as the original request. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3560 | { # Set of primitive values supported by the system. |
| 3561 | # Note that for the purposes of inspection or transformation, the number |
| 3562 | # of bytes considered to comprise a 'Value' is based on its representation |
| 3563 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 3564 | # 123456789, the number of bytes would be counted as 9, even though an |
| 3565 | # int64 only holds up to 8 bytes of data. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3566 | "integerValue": "A String", # integer |
| 3567 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 3568 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 3569 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 3570 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 3571 | # allow the value 60 if it allows leap-seconds. |
| 3572 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 3573 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 3574 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 3575 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 3576 | }, |
| 3577 | "dayOfWeekValue": "A String", # day of week |
| 3578 | "floatValue": 3.14, # float |
| 3579 | "stringValue": "A String", # string |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3580 | "timestampValue": "A String", # timestamp |
| 3581 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 3582 | # and time zone are either specified elsewhere or are not significant. The date |
| 3583 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 3584 | # |
| 3585 | # * A full date, with non-zero year, month and day values |
| 3586 | # * A month and day value, with a zero year, e.g. an anniversary |
| 3587 | # * A year on its own, with zero month and day values |
| 3588 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 3589 | # |
| 3590 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3591 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 3592 | # month and day. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3593 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 3594 | # a year. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3595 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 3596 | # if specifying a year by itself or a year and month where the day is not |
| 3597 | # significant. |
| 3598 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3599 | "booleanValue": True or False, # boolean |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3600 | }, |
| 3601 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3602 | "topSensitiveValues": [ # Estimated frequencies of top sensitive values. |
| 3603 | { # A value of a field, including its frequency. |
| 3604 | "count": "A String", # How many times the value is contained in the field. |
| 3605 | "value": { # Set of primitive values supported by the system. # A value contained in the field in question. |
| 3606 | # Note that for the purposes of inspection or transformation, the number |
| 3607 | # of bytes considered to comprise a 'Value' is based on its representation |
| 3608 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 3609 | # 123456789, the number of bytes would be counted as 9, even though an |
| 3610 | # int64 only holds up to 8 bytes of data. |
| 3611 | "integerValue": "A String", # integer |
| 3612 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 3613 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 3614 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 3615 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 3616 | # allow the value 60 if it allows leap-seconds. |
| 3617 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 3618 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 3619 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 3620 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 3621 | }, |
| 3622 | "dayOfWeekValue": "A String", # day of week |
| 3623 | "floatValue": 3.14, # float |
| 3624 | "stringValue": "A String", # string |
| 3625 | "timestampValue": "A String", # timestamp |
| 3626 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 3627 | # and time zone are either specified elsewhere or are not significant. The date |
| 3628 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 3629 | # |
| 3630 | # * A full date, with non-zero year, month and day values |
| 3631 | # * A month and day value, with a zero year, e.g. an anniversary |
| 3632 | # * A year on its own, with zero month and day values |
| 3633 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 3634 | # |
| 3635 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 3636 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 3637 | # month and day. |
| 3638 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 3639 | # a year. |
| 3640 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 3641 | # if specifying a year by itself or a year and month where the day is not |
| 3642 | # significant. |
| 3643 | }, |
| 3644 | "booleanValue": True or False, # boolean |
| 3645 | }, |
| 3646 | }, |
| 3647 | ], |
| 3648 | "equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class. |
| 3649 | "numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3650 | }, |
| 3651 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3652 | "sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence |
| 3653 | # classes in this bucket. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3654 | "bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3655 | "sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence |
| 3656 | # classes in this bucket. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 3657 | }, |
| 3658 | ], |
| 3659 | }, |
| 3660 | "requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over. |
| 3661 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 3662 | # a table is often referenced with a string in the format of: |
| 3663 | # `<project_id>:<dataset_id>.<table_id>` or |
| 3664 | # `<project_id>.<dataset_id>.<table_id>`. |
| 3665 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 3666 | # If omitted, project ID is inferred from the API call. |
| 3667 | "datasetId": "A String", # Dataset ID of the table. |
| 3668 | "tableId": "A String", # Name of the table. |
| 3669 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3670 | }, |
| 3671 | "type": "A String", # The type of job. |
| 3672 | "endTime": "A String", # Time when the job finished. |
| 3673 | "startTime": "A String", # Time when the job started. |
| 3674 | "jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that |
| 3675 | # instantiated the job. |
| 3676 | "inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source. |
| 3677 | "requestedOptions": { # Snapshot of the inspection configuration. # The configuration used for this job. |
| 3678 | "jobConfig": { # Controls what and how to inspect for findings. # Inspect config. |
| 3679 | "inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. |
| 3680 | # `inspect_config` will be merged into the values persisted as part of the |
| 3681 | # template. |
| 3682 | "actions": [ # Actions to execute at the completion of the job. |
| 3683 | { # A task to execute on the completion of a job. |
| 3684 | # See https://cloud.google.com/dlp/docs/concepts-actions to learn more. |
| 3685 | "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count. |
| 3686 | # will publish a metric to stack driver on each infotype requested and |
| 3687 | # how many findings were found for it. CustomDetectors will be bucketed |
| 3688 | # as 'Custom' under the Stackdriver label 'info_type'. |
| 3689 | }, |
| 3690 | "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub. |
| 3691 | # results of the DlpJob will be applied to the entry for the resource scanned |
| 3692 | # in Cloud Data Catalog. Any labels previously written by another DlpJob will |
| 3693 | # be deleted. InfoType naming patterns are strictly enforced when using this |
| 3694 | # feature. Note that the findings will be persisted in Cloud Data Catalog |
| 3695 | # storage and are governed by Data Catalog service-specific policy, see |
| 3696 | # https://cloud.google.com/terms/service-terms |
| 3697 | # Only a single instance of this action can be specified and only allowed if |
| 3698 | # all resources being scanned are BigQuery tables. |
| 3699 | # Compatible with: Inspect |
| 3700 | }, |
| 3701 | "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's |
| 3702 | # completion/failure. |
| 3703 | # completion/failure. |
| 3704 | }, |
| 3705 | "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic. |
| 3706 | # message contains a single field, `DlpJobName`, which is equal to the |
| 3707 | # finished job's |
| 3708 | # [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob). |
| 3709 | # Compatible with: Inspect, Risk |
| 3710 | "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given |
| 3711 | # publishing access rights to the DLP API service account executing |
| 3712 | # the long running DlpJob sending the notifications. |
| 3713 | # Format is projects/{project}/topics/{topic}. |
| 3714 | }, |
| 3715 | "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location. |
| 3716 | # OutputStorageConfig. Only a single instance of this action can be |
| 3717 | # specified. |
| 3718 | # Compatible with: Inspect, Risk |
| 3719 | "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP. |
| 3720 | "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only |
| 3721 | # used for Inspect and must be unspecified for Risk jobs. Columns are derived |
| 3722 | # from the `Finding` object. If appending to an existing table, any columns |
| 3723 | # from the predefined schema that are missing will be added. No columns in |
| 3724 | # the existing table will be deleted. |
| 3725 | # |
| 3726 | # If unspecified, then all available columns will be used for a new table or |
| 3727 | # an (existing) table with no schema, and no changes will be made to an |
| 3728 | # existing table that has a schema. |
| 3729 | # Only for use with external storage. |
| 3730 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Store findings in an existing table or a new table in an existing |
| 3731 | # dataset. If table_id is not set a new one will be generated |
| 3732 | # for you with the following format: |
| 3733 | # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for |
| 3734 | # generating the date details. |
| 3735 | # |
| 3736 | # For Inspect, each column in an existing output table must have the same |
| 3737 | # name, type, and mode of a field in the `Finding` object. |
| 3738 | # |
| 3739 | # For Risk, an existing output table should be the output of a previous |
| 3740 | # Risk analysis job run on the same source table, with the same privacy |
| 3741 | # metric and quasi-identifiers. Risk jobs that analyze the same table but |
| 3742 | # compute a different privacy metric, or use different sets of |
| 3743 | # quasi-identifiers, cannot store their results in the same table. |
| 3744 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 3745 | # a table is often referenced with a string in the format of: |
| 3746 | # `<project_id>:<dataset_id>.<table_id>` or |
| 3747 | # `<project_id>.<dataset_id>.<table_id>`. |
| 3748 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 3749 | # If omitted, project ID is inferred from the API call. |
| 3750 | "datasetId": "A String", # Dataset ID of the table. |
| 3751 | "tableId": "A String", # Name of the table. |
| 3752 | }, |
| 3753 | }, |
| 3754 | }, |
| 3755 | "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha). |
| 3756 | # Command Center (CSCC Alpha). |
| 3757 | # This action is only available for projects which are parts of |
| 3758 | # an organization and whitelisted for the alpha Cloud Security Command |
| 3759 | # Center. |
| 3760 | # The action will publish count of finding instances and their info types. |
| 3761 | # The summary of findings will be persisted in CSCC and are governed by CSCC |
| 3762 | # service-specific policy, see https://cloud.google.com/terms/service-terms |
| 3763 | # Only a single instance of this action can be specified. |
| 3764 | # Compatible with: Inspect |
| 3765 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3766 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3767 | ], |
| 3768 | "storageConfig": { # Shared message indicating Cloud storage type. # The data to scan. |
| 3769 | "cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options. |
| 3770 | # bucket. |
| 3771 | "bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The |
| 3772 | # number of bytes scanned is rounded down. Must be between 0 and 100, |
| 3773 | # inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one |
| 3774 | # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. |
| 3775 | "fileTypes": [ # List of file type groups to include in the scan. |
| 3776 | # If empty, all files are scanned and available data format processors |
| 3777 | # are applied. In addition, the binary content of the selected files |
| 3778 | # is always scanned as well. |
| 3779 | # Images are scanned only as binary if the specified region |
| 3780 | # does not support image inspection and no file_types were specified. |
| 3781 | # Image inspection is restricted to 'global', 'us', 'asia', and 'europe'. |
| 3782 | "A String", |
| 3783 | ], |
| 3784 | "bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger |
| 3785 | # than this value then the rest of the bytes are omitted. Only one |
| 3786 | # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. |
| 3787 | "filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. |
| 3788 | # Number of files scanned is rounded down. Must be between 0 and 100, |
| 3789 | # inclusively. Both 0 and 100 means no limit. Defaults to 0. |
| 3790 | "fileSet": { # Set of files to scan. # The set of one or more files to scan. |
| 3791 | "regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular # The regex-filtered set of files to scan. Exactly one of `url` or |
| 3792 | # `regex_file_set` must be set. |
| 3793 | # expressions are used to allow fine-grained control over which files in the |
| 3794 | # bucket to include. |
| 3795 | # |
| 3796 | # Included files are those that match at least one item in `include_regex` and |
| 3797 | # do not match any items in `exclude_regex`. Note that a file that matches |
| 3798 | # items from both lists will _not_ be included. For a match to occur, the |
| 3799 | # entire file path (i.e., everything in the url after the bucket name) must |
| 3800 | # match the regular expression. |
| 3801 | # |
| 3802 | # For example, given the input `{bucket_name: "mybucket", include_regex: |
| 3803 | # ["directory1/.*"], exclude_regex: |
| 3804 | # ["directory1/excluded.*"]}`: |
| 3805 | # |
| 3806 | # * `gs://mybucket/directory1/myfile` will be included |
| 3807 | # * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches |
| 3808 | # across `/`) |
| 3809 | # * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the |
| 3810 | # full path doesn't match any items in `include_regex`) |
| 3811 | # * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path |
| 3812 | # matches an item in `exclude_regex`) |
| 3813 | # |
| 3814 | # If `include_regex` is left empty, it will match all files by default |
| 3815 | # (this is equivalent to setting `include_regex: [".*"]`). |
| 3816 | # |
| 3817 | # Some other common use cases: |
| 3818 | # |
| 3819 | # * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all |
| 3820 | # files in `mybucket` except for .pdf files |
| 3821 | # * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will |
| 3822 | # include all files directly under `gs://mybucket/directory/`, without matching |
| 3823 | # across `/` |
| 3824 | "bucketName": "A String", # The name of a Cloud Storage bucket. Required. |
| 3825 | "excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in |
| 3826 | # the bucket that match at least one of these regular expressions will be |
| 3827 | # excluded from the scan. |
| 3828 | # |
| 3829 | # Regular expressions use RE2 |
| 3830 | # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found |
| 3831 | # under the google/re2 repository on GitHub. |
| 3832 | "A String", |
| 3833 | ], |
| 3834 | "includeRegex": [ # A list of regular expressions matching file paths to include. All files in |
| 3835 | # the bucket that match at least one of these regular expressions will be |
| 3836 | # included in the set of files, except for those that also match an item in |
| 3837 | # `exclude_regex`. Leaving this field empty will match all files by default |
| 3838 | # (this is equivalent to including `.*` in the list). |
| 3839 | # |
| 3840 | # Regular expressions use RE2 |
| 3841 | # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found |
| 3842 | # under the google/re2 repository on GitHub. |
| 3843 | "A String", |
| 3844 | ], |
| 3845 | }, |
| 3846 | "url": "A String", # The Cloud Storage url of the file(s) to scan, in the format |
| 3847 | # `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed. |
| 3848 | # |
| 3849 | # If the url ends in a trailing slash, the bucket or directory represented |
| 3850 | # by the url will be scanned non-recursively (content in sub-directories |
| 3851 | # will not be scanned). This means that `gs://mybucket/` is equivalent to |
| 3852 | # `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to |
| 3853 | # `gs://mybucket/directory/*`. |
| 3854 | # |
| 3855 | # Exactly one of `url` or `regex_file_set` must be set. |
| 3856 | }, |
| 3857 | "sampleMethod": "A String", |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3858 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3859 | "bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options. |
| 3860 | "sampleMethod": "A String", |
| 3861 | "tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference. |
| 3862 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 3863 | # a table is often referenced with a string in the format of: |
| 3864 | # `<project_id>:<dataset_id>.<table_id>` or |
| 3865 | # `<project_id>.<dataset_id>.<table_id>`. |
| 3866 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 3867 | # If omitted, project ID is inferred from the API call. |
| 3868 | "datasetId": "A String", # Dataset ID of the table. |
| 3869 | "tableId": "A String", # Name of the table. |
| 3870 | }, |
| 3871 | "rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows |
| 3872 | # scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and |
| 3873 | # 100 means no limit. Defaults to 0. Only one of rows_limit and |
| 3874 | # rows_limit_percent can be specified. Cannot be used in conjunction with |
| 3875 | # TimespanConfig. |
| 3876 | "rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the |
| 3877 | # rest of the rows are omitted. If not set, or if set to 0, all rows will be |
| 3878 | # scanned. Only one of rows_limit and rows_limit_percent can be specified. |
| 3879 | # Cannot be used in conjunction with TimespanConfig. |
| 3880 | "identifyingFields": [ # Table fields that may uniquely identify a row within the table. When |
| 3881 | # `actions.saveFindings.outputConfig.table` is specified, the values of |
| 3882 | # columns specified here are available in the output table under |
| 3883 | # `location.content_locations.record_location.record_key.id_values`. Nested |
| 3884 | # fields such as `person.birthdate.year` are allowed. |
| 3885 | { # General identifier of a data field in a storage service. |
| 3886 | "name": "A String", # Name describing the field. |
| 3887 | }, |
| 3888 | ], |
| 3889 | "excludedFields": [ # References to fields excluded from scanning. This allows you to skip |
| 3890 | # inspection of entire columns which you know have no findings. |
| 3891 | { # General identifier of a data field in a storage service. |
| 3892 | "name": "A String", # Name describing the field. |
| 3893 | }, |
| 3894 | ], |
| 3895 | }, |
| 3896 | "timespanConfig": { # Configuration of the timespan of the items to include in scanning. |
| 3897 | # Currently only supported when inspecting Google Cloud Storage and BigQuery. |
| 3898 | "timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. |
| 3899 | # Used for data sources like Datastore and BigQuery. |
| 3900 | # |
| 3901 | # For BigQuery: |
| 3902 | # Required to filter out rows based on the given start and |
| 3903 | # end times. If not specified and the table was modified between the given |
| 3904 | # start and end times, the entire table will be scanned. |
| 3905 | # The valid data types of the timestamp field are: `INTEGER`, `DATE`, |
| 3906 | # `TIMESTAMP`, or `DATETIME` BigQuery column. |
| 3907 | # |
| 3908 | # For Datastore. |
| 3909 | # Valid data types of the timestamp field are: `TIMESTAMP`. |
| 3910 | # Datastore entity will be scanned if the timestamp property does not |
| 3911 | # exist or its value is empty or invalid. |
| 3912 | "name": "A String", # Name describing the field. |
| 3913 | }, |
| 3914 | "enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out |
| 3915 | # a valid start_time to avoid scanning files that have not been modified |
| 3916 | # since the last time the JobTrigger executed. This will be based on the |
| 3917 | # time of the execution of the last run of the JobTrigger. |
| 3918 | "startTime": "A String", # Exclude files or rows older than this value. |
| 3919 | "endTime": "A String", # Exclude files or rows newer than this value. |
| 3920 | # If set to zero, no upper time limit is applied. |
| 3921 | }, |
| 3922 | "datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options. |
| 3923 | "kind": { # A representation of a Datastore kind. # The kind to process. |
| 3924 | "name": "A String", # The name of the kind. |
| 3925 | }, |
| 3926 | "partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always |
| 3927 | # by project and namespace, however the namespace ID may be empty. |
| 3928 | # A partition ID identifies a grouping of entities. The grouping is always |
| 3929 | # by project and namespace, however the namespace ID may be empty. |
| 3930 | # |
| 3931 | # A partition ID contains several dimensions: |
| 3932 | # project ID and namespace ID. |
| 3933 | "namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong. |
| 3934 | "projectId": "A String", # The ID of the project to which the entities belong. |
| 3935 | }, |
| 3936 | }, |
| 3937 | "hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options. |
| 3938 | # Early access feature is in a pre-release state and might change or have |
| 3939 | # limited support. For more information, see |
| 3940 | # https://cloud.google.com/products#product-launch-stages. |
| 3941 | # of Google Cloud Platform. |
| 3942 | "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings |
| 3943 | # meaningful such as the columns that are primary keys. |
| 3944 | "identifyingFields": [ # The columns that are the primary keys for table objects included in |
| 3945 | # ContentItem. A copy of this cell's value will stored alongside alongside |
| 3946 | # each finding so that the finding can be traced to the specific row it came |
| 3947 | # from. No more than 3 may be provided. |
| 3948 | { # General identifier of a data field in a storage service. |
| 3949 | "name": "A String", # Name describing the field. |
| 3950 | }, |
| 3951 | ], |
| 3952 | }, |
| 3953 | "requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their |
| 3954 | # 'finding_labels' map. Request may contain others, but any missing one of |
| 3955 | # these will be rejected. |
| 3956 | # |
| 3957 | # Label keys must be between 1 and 63 characters long and must conform |
| 3958 | # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. |
| 3959 | # |
| 3960 | # No more than 10 keys can be required. |
| 3961 | "A String", |
| 3962 | ], |
| 3963 | "labels": { # To organize findings, these labels will be added to each finding. |
| 3964 | # |
| 3965 | # Label keys must be between 1 and 63 characters long and must conform |
| 3966 | # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. |
| 3967 | # |
| 3968 | # Label values must be between 0 and 63 characters long and must conform |
| 3969 | # to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. |
| 3970 | # |
| 3971 | # No more than 10 labels can be associated with a given finding. |
| 3972 | # |
| 3973 | # Examples: |
| 3974 | # * `"environment" : "production"` |
| 3975 | # * `"pipeline" : "etl"` |
| 3976 | "a_key": "A String", |
| 3977 | }, |
| 3978 | "description": "A String", # A short description of where the data is coming from. Will be stored once |
| 3979 | # in the job. 256 max length. |
| 3980 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 3981 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 3982 | "inspectConfig": { # Configuration description of the scanning process. # How and what to scan for. |
| 3983 | # When used with redactContent only info_types and min_likelihood are currently |
| 3984 | # used. |
| 3985 | "customInfoTypes": [ # CustomInfoTypes provided by the user. See |
| 3986 | # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more. |
| 3987 | { # Custom information type provided by the user. Used to find domain-specific |
| 3988 | # sensitive information configurable to the data in question. |
| 3989 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType. |
| 3990 | # be used to match sensitive information specific to the data, such as a list |
| 3991 | # of employee IDs or job titles. |
| 3992 | # |
| 3993 | # Dictionary words are case-insensitive and all characters other than letters |
| 3994 | # and digits in the unicode [Basic Multilingual |
| 3995 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 3996 | # will be replaced with whitespace when scanning for matches, so the |
| 3997 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 3998 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 3999 | # surrounding any match must be of a different type than the adjacent |
| 4000 | # characters within the word, so letters must be next to non-letters and |
| 4001 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 4002 | # match the first three letters of the text "jen123" but will return no |
| 4003 | # matches for "jennifer". |
| 4004 | # |
| 4005 | # Dictionary words containing a large number of characters that are not |
| 4006 | # letters or digits may result in unexpected findings because such characters |
| 4007 | # are treated as whitespace. The |
| 4008 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 4009 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 4010 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 4011 | # `StoredInfoType` API. |
| 4012 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 4013 | # is accepted. |
| 4014 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 4015 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 4016 | }, |
| 4017 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 4018 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 4019 | # at least one phrase and every phrase must contain at least 2 characters |
| 4020 | # that are letters or digits. [required] |
| 4021 | "A String", |
| 4022 | ], |
| 4023 | }, |
| 4024 | }, |
| 4025 | "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in |
| 4026 | # infoType, when the name matches one of existing infoTypes and that infoType |
| 4027 | # is specified in `InspectContent.info_types` field. Specifying the latter |
| 4028 | # adds findings to the one detected by the system. If built-in info type is |
| 4029 | # not specified in `InspectContent.info_types` list then the name is treated |
| 4030 | # as a custom info type. |
| 4031 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 4032 | # creating a CustomInfoType, or one of the names listed |
| 4033 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 4034 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 4035 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 4036 | }, |
| 4037 | "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be |
| 4038 | # altered by a detection rule if the finding meets the criteria specified by |
| 4039 | # the rule. Defaults to `VERY_LIKELY` if not specified. |
| 4040 | "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. |
| 4041 | # Rules are applied in order that they are specified. Not supported for the |
| 4042 | # `surrogate_type` CustomInfoType. |
| 4043 | { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a |
| 4044 | # `CustomInfoType` to alter behavior under certain circumstances, depending |
| 4045 | # on the specific details of the rule. Not supported for the `surrogate_type` |
| 4046 | # custom infoType. |
| 4047 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 4048 | # proximity of hotwords. |
| 4049 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 4050 | # The total length of the window cannot exceed 1000 characters. Note that |
| 4051 | # the finding itself will be included in the window, so that hotwords may |
| 4052 | # be used to match substrings of the finding itself. For example, the |
| 4053 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 4054 | # adjusted upwards if the area code is known to be the local area code of |
| 4055 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 4056 | # is the area code in question. |
| 4057 | # rule. |
| 4058 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 4059 | "windowBefore": 42, # Number of characters before the finding to consider. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 4060 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4061 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 4062 | # part of a detection rule. |
| 4063 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 4064 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 4065 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 4066 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 4067 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 4068 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 4069 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 4070 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 4071 | # a final likelihood of `LIKELY`. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 4072 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4073 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 4074 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 4075 | # specified, the entire match is returned. No more than 3 may be included. |
| 4076 | 42, |
| 4077 | ], |
| 4078 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 4079 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 4080 | # google/re2 repository on GitHub. |
| 4081 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 4082 | }, |
| 4083 | }, |
| 4084 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4085 | "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that |
| 4086 | # support reversing. |
| 4087 | # such as |
| 4088 | # [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). |
| 4089 | # These types of transformations are |
| 4090 | # those that perform pseudonymization, thereby producing a "surrogate" as |
| 4091 | # output. This should be used in conjunction with a field on the |
| 4092 | # transformation such as `surrogate_info_type`. This CustomInfoType does |
| 4093 | # not support the use of `detection_rules`. |
| 4094 | }, |
| 4095 | "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType. |
| 4096 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 4097 | # specified, the entire match is returned. No more than 3 may be included. |
| 4098 | 42, |
| 4099 | ], |
| 4100 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 4101 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 4102 | # google/re2 repository on GitHub. |
| 4103 | }, |
| 4104 | "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in |
| 4105 | # `InspectDataSource`. Not currently supported in `InspectContent`. |
| 4106 | "name": "A String", # Resource name of the requested `StoredInfoType`, for example |
| 4107 | # `organizations/433245324/storedInfoTypes/432452342` or |
| 4108 | # `projects/project-id/storedInfoTypes/432452342`. |
| 4109 | "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for |
| 4110 | # inspection was created. Output-only field, populated by the system. |
| 4111 | }, |
| 4112 | "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding |
| 4113 | # to be returned. It still can be used for rules matching. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 4114 | }, |
| 4115 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4116 | "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is |
| 4117 | # POSSIBLE. |
| 4118 | # See https://cloud.google.com/dlp/docs/likelihood to learn more. |
| 4119 | "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned. |
| 4120 | "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job. |
| 4121 | # When set within `InspectContentRequest`, the maximum returned is 2000 |
| 4122 | # regardless if this is set higher. |
| 4123 | "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes. |
| 4124 | { # Max findings configuration per infoType, per content item or long |
| 4125 | # running DlpJob. |
| 4126 | "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per |
| 4127 | # info_type should be provided. If InfoTypeLimit does not have an |
| 4128 | # info_type, the DLP API applies the limit against all info_types that |
| 4129 | # are found but not specified in another InfoTypeLimit. |
| 4130 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 4131 | # creating a CustomInfoType, or one of the names listed |
| 4132 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 4133 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 4134 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 4135 | }, |
| 4136 | "maxFindings": 42, # Max findings limit for the given infoType. |
| 4137 | }, |
| 4138 | ], |
| 4139 | "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned. |
| 4140 | # When set within `InspectJobConfig`, |
| 4141 | # the maximum returned is 2000 regardless if this is set higher. |
| 4142 | # When set within `InspectContentRequest`, this field is ignored. |
| 4143 | }, |
| 4144 | "excludeInfoTypes": True or False, # When true, excludes type information of the findings. |
| 4145 | "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is |
| 4146 | # included in the response; see Finding.quote. |
| 4147 | "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. |
| 4148 | # Exclusion rules, contained in the set are executed in the end, other |
| 4149 | # rules are executed in the order they are specified for each info type. |
| 4150 | { # Rule set for modifying a set of infoTypes to alter behavior under certain |
| 4151 | # circumstances, depending on the specific details of the rules within the set. |
| 4152 | "infoTypes": [ # List of infoTypes this rule set is applied to. |
| 4153 | { # Type of information detected by the API. |
| 4154 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 4155 | # creating a CustomInfoType, or one of the names listed |
| 4156 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 4157 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 4158 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 4159 | }, |
| 4160 | ], |
| 4161 | "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order. |
| 4162 | { # A single inspection rule to be applied to infoTypes, specified in |
| 4163 | # `InspectionRuleSet`. |
| 4164 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 4165 | # proximity of hotwords. |
| 4166 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 4167 | # The total length of the window cannot exceed 1000 characters. Note that |
| 4168 | # the finding itself will be included in the window, so that hotwords may |
| 4169 | # be used to match substrings of the finding itself. For example, the |
| 4170 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 4171 | # adjusted upwards if the area code is known to be the local area code of |
| 4172 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 4173 | # is the area code in question. |
| 4174 | # rule. |
| 4175 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 4176 | "windowBefore": 42, # Number of characters before the finding to consider. |
| 4177 | }, |
| 4178 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 4179 | # part of a detection rule. |
| 4180 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 4181 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 4182 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 4183 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 4184 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 4185 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 4186 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 4187 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 4188 | # a final likelihood of `LIKELY`. |
| 4189 | }, |
| 4190 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 4191 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 4192 | # specified, the entire match is returned. No more than 3 may be included. |
| 4193 | 42, |
| 4194 | ], |
| 4195 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 4196 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 4197 | # google/re2 repository on GitHub. |
| 4198 | }, |
| 4199 | }, |
| 4200 | "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule. |
| 4201 | # `InspectionRuleSet` are removed from results. |
| 4202 | "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details. |
| 4203 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule. |
| 4204 | # be used to match sensitive information specific to the data, such as a list |
| 4205 | # of employee IDs or job titles. |
| 4206 | # |
| 4207 | # Dictionary words are case-insensitive and all characters other than letters |
| 4208 | # and digits in the unicode [Basic Multilingual |
| 4209 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 4210 | # will be replaced with whitespace when scanning for matches, so the |
| 4211 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 4212 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 4213 | # surrounding any match must be of a different type than the adjacent |
| 4214 | # characters within the word, so letters must be next to non-letters and |
| 4215 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 4216 | # match the first three letters of the text "jen123" but will return no |
| 4217 | # matches for "jennifer". |
| 4218 | # |
| 4219 | # Dictionary words containing a large number of characters that are not |
| 4220 | # letters or digits may result in unexpected findings because such characters |
| 4221 | # are treated as whitespace. The |
| 4222 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 4223 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 4224 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 4225 | # `StoredInfoType` API. |
| 4226 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 4227 | # is accepted. |
| 4228 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 4229 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 4230 | }, |
| 4231 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 4232 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 4233 | # at least one phrase and every phrase must contain at least 2 characters |
| 4234 | # that are letters or digits. [required] |
| 4235 | "A String", |
| 4236 | ], |
| 4237 | }, |
| 4238 | }, |
| 4239 | "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule. |
| 4240 | "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or |
| 4241 | # contained within with a finding of an infoType from this list. For |
| 4242 | # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and |
| 4243 | # `exclusion_rule` containing `exclude_info_types.info_types` with |
| 4244 | # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap |
| 4245 | # with EMAIL_ADDRESS finding. |
| 4246 | # That leads to "555-222-2222@example.org" to generate only a single |
| 4247 | # finding, namely email address. |
| 4248 | { # Type of information detected by the API. |
| 4249 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 4250 | # creating a CustomInfoType, or one of the names listed |
| 4251 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 4252 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 4253 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 4254 | }, |
| 4255 | ], |
| 4256 | }, |
| 4257 | "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule. |
| 4258 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 4259 | # specified, the entire match is returned. No more than 3 may be included. |
| 4260 | 42, |
| 4261 | ], |
| 4262 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 4263 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 4264 | # google/re2 repository on GitHub. |
| 4265 | }, |
| 4266 | }, |
| 4267 | }, |
| 4268 | ], |
| 4269 | }, |
| 4270 | ], |
| 4271 | "contentOptions": [ # List of options defining data content to scan. |
| 4272 | # If empty, text, images, and other content will be included. |
| 4273 | "A String", |
| 4274 | ], |
| 4275 | "infoTypes": [ # Restricts what info_types to look for. The values must correspond to |
| 4276 | # InfoType values returned by ListInfoTypes or listed at |
| 4277 | # https://cloud.google.com/dlp/docs/infotypes-reference. |
| 4278 | # |
| 4279 | # When no InfoTypes or CustomInfoTypes are specified in a request, the |
| 4280 | # system may automatically choose what detectors to run. By default this may |
| 4281 | # be all types, but may change over time as detectors are updated. |
| 4282 | # |
| 4283 | # If you need precise control and predictability as to what detectors are |
| 4284 | # run you should specify specific InfoTypes listed in the reference, |
| 4285 | # otherwise a default list will be used, which may change over time. |
| 4286 | { # Type of information detected by the API. |
| 4287 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 4288 | # creating a CustomInfoType, or one of the names listed |
| 4289 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 4290 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 4291 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 4292 | }, |
| 4293 | ], |
| 4294 | }, |
| 4295 | }, |
| 4296 | "snapshotInspectTemplate": { # The inspectTemplate contains a configuration (set of types of sensitive data # If run with an InspectTemplate, a snapshot of its state at the time of |
| 4297 | # this run. |
| 4298 | # to be detected) to be used anywhere you otherwise would normally specify |
| 4299 | # InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates |
| 4300 | # to learn more. |
| 4301 | "description": "A String", # Short description (max 256 chars). |
| 4302 | "displayName": "A String", # Display name (max 256 chars). |
| 4303 | "createTime": "A String", # Output only. The creation timestamp of an inspectTemplate. |
| 4304 | "updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate. |
| 4305 | "name": "A String", # Output only. The template name. |
| 4306 | # |
| 4307 | # The template will have one of the following formats: |
| 4308 | # `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR |
| 4309 | # `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`; |
| 4310 | "inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process. |
| 4311 | # When used with redactContent only info_types and min_likelihood are currently |
| 4312 | # used. |
| 4313 | "customInfoTypes": [ # CustomInfoTypes provided by the user. See |
| 4314 | # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more. |
| 4315 | { # Custom information type provided by the user. Used to find domain-specific |
| 4316 | # sensitive information configurable to the data in question. |
| 4317 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType. |
| 4318 | # be used to match sensitive information specific to the data, such as a list |
| 4319 | # of employee IDs or job titles. |
| 4320 | # |
| 4321 | # Dictionary words are case-insensitive and all characters other than letters |
| 4322 | # and digits in the unicode [Basic Multilingual |
| 4323 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 4324 | # will be replaced with whitespace when scanning for matches, so the |
| 4325 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 4326 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 4327 | # surrounding any match must be of a different type than the adjacent |
| 4328 | # characters within the word, so letters must be next to non-letters and |
| 4329 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 4330 | # match the first three letters of the text "jen123" but will return no |
| 4331 | # matches for "jennifer". |
| 4332 | # |
| 4333 | # Dictionary words containing a large number of characters that are not |
| 4334 | # letters or digits may result in unexpected findings because such characters |
| 4335 | # are treated as whitespace. The |
| 4336 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 4337 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 4338 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 4339 | # `StoredInfoType` API. |
| 4340 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 4341 | # is accepted. |
| 4342 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 4343 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 4344 | }, |
| 4345 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 4346 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 4347 | # at least one phrase and every phrase must contain at least 2 characters |
| 4348 | # that are letters or digits. [required] |
| 4349 | "A String", |
| 4350 | ], |
| 4351 | }, |
| 4352 | }, |
| 4353 | "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in |
| 4354 | # infoType, when the name matches one of existing infoTypes and that infoType |
| 4355 | # is specified in `InspectContent.info_types` field. Specifying the latter |
| 4356 | # adds findings to the one detected by the system. If built-in info type is |
| 4357 | # not specified in `InspectContent.info_types` list then the name is treated |
| 4358 | # as a custom info type. |
| 4359 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 4360 | # creating a CustomInfoType, or one of the names listed |
| 4361 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 4362 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 4363 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 4364 | }, |
| 4365 | "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be |
| 4366 | # altered by a detection rule if the finding meets the criteria specified by |
| 4367 | # the rule. Defaults to `VERY_LIKELY` if not specified. |
| 4368 | "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. |
| 4369 | # Rules are applied in order that they are specified. Not supported for the |
| 4370 | # `surrogate_type` CustomInfoType. |
| 4371 | { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a |
| 4372 | # `CustomInfoType` to alter behavior under certain circumstances, depending |
| 4373 | # on the specific details of the rule. Not supported for the `surrogate_type` |
| 4374 | # custom infoType. |
| 4375 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 4376 | # proximity of hotwords. |
| 4377 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 4378 | # The total length of the window cannot exceed 1000 characters. Note that |
| 4379 | # the finding itself will be included in the window, so that hotwords may |
| 4380 | # be used to match substrings of the finding itself. For example, the |
| 4381 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 4382 | # adjusted upwards if the area code is known to be the local area code of |
| 4383 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 4384 | # is the area code in question. |
| 4385 | # rule. |
| 4386 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 4387 | "windowBefore": 42, # Number of characters before the finding to consider. |
| 4388 | }, |
| 4389 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 4390 | # part of a detection rule. |
| 4391 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 4392 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 4393 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 4394 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 4395 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 4396 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 4397 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 4398 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 4399 | # a final likelihood of `LIKELY`. |
| 4400 | }, |
| 4401 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 4402 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 4403 | # specified, the entire match is returned. No more than 3 may be included. |
| 4404 | 42, |
| 4405 | ], |
| 4406 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 4407 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 4408 | # google/re2 repository on GitHub. |
| 4409 | }, |
| 4410 | }, |
| 4411 | }, |
| 4412 | ], |
| 4413 | "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that |
| 4414 | # support reversing. |
| 4415 | # such as |
| 4416 | # [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). |
| 4417 | # These types of transformations are |
| 4418 | # those that perform pseudonymization, thereby producing a "surrogate" as |
| 4419 | # output. This should be used in conjunction with a field on the |
| 4420 | # transformation such as `surrogate_info_type`. This CustomInfoType does |
| 4421 | # not support the use of `detection_rules`. |
| 4422 | }, |
| 4423 | "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType. |
| 4424 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 4425 | # specified, the entire match is returned. No more than 3 may be included. |
| 4426 | 42, |
| 4427 | ], |
| 4428 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 4429 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 4430 | # google/re2 repository on GitHub. |
| 4431 | }, |
| 4432 | "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in |
| 4433 | # `InspectDataSource`. Not currently supported in `InspectContent`. |
| 4434 | "name": "A String", # Resource name of the requested `StoredInfoType`, for example |
| 4435 | # `organizations/433245324/storedInfoTypes/432452342` or |
| 4436 | # `projects/project-id/storedInfoTypes/432452342`. |
| 4437 | "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for |
| 4438 | # inspection was created. Output-only field, populated by the system. |
| 4439 | }, |
| 4440 | "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding |
| 4441 | # to be returned. It still can be used for rules matching. |
| 4442 | }, |
| 4443 | ], |
| 4444 | "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is |
| 4445 | # POSSIBLE. |
| 4446 | # See https://cloud.google.com/dlp/docs/likelihood to learn more. |
| 4447 | "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned. |
| 4448 | "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job. |
| 4449 | # When set within `InspectContentRequest`, the maximum returned is 2000 |
| 4450 | # regardless if this is set higher. |
| 4451 | "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes. |
| 4452 | { # Max findings configuration per infoType, per content item or long |
| 4453 | # running DlpJob. |
| 4454 | "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per |
| 4455 | # info_type should be provided. If InfoTypeLimit does not have an |
| 4456 | # info_type, the DLP API applies the limit against all info_types that |
| 4457 | # are found but not specified in another InfoTypeLimit. |
| 4458 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 4459 | # creating a CustomInfoType, or one of the names listed |
| 4460 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 4461 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 4462 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 4463 | }, |
| 4464 | "maxFindings": 42, # Max findings limit for the given infoType. |
| 4465 | }, |
| 4466 | ], |
| 4467 | "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned. |
| 4468 | # When set within `InspectJobConfig`, |
| 4469 | # the maximum returned is 2000 regardless if this is set higher. |
| 4470 | # When set within `InspectContentRequest`, this field is ignored. |
| 4471 | }, |
| 4472 | "excludeInfoTypes": True or False, # When true, excludes type information of the findings. |
| 4473 | "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is |
| 4474 | # included in the response; see Finding.quote. |
| 4475 | "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. |
| 4476 | # Exclusion rules, contained in the set are executed in the end, other |
| 4477 | # rules are executed in the order they are specified for each info type. |
| 4478 | { # Rule set for modifying a set of infoTypes to alter behavior under certain |
| 4479 | # circumstances, depending on the specific details of the rules within the set. |
| 4480 | "infoTypes": [ # List of infoTypes this rule set is applied to. |
| 4481 | { # Type of information detected by the API. |
| 4482 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 4483 | # creating a CustomInfoType, or one of the names listed |
| 4484 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 4485 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 4486 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 4487 | }, |
| 4488 | ], |
| 4489 | "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order. |
| 4490 | { # A single inspection rule to be applied to infoTypes, specified in |
| 4491 | # `InspectionRuleSet`. |
| 4492 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 4493 | # proximity of hotwords. |
| 4494 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 4495 | # The total length of the window cannot exceed 1000 characters. Note that |
| 4496 | # the finding itself will be included in the window, so that hotwords may |
| 4497 | # be used to match substrings of the finding itself. For example, the |
| 4498 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 4499 | # adjusted upwards if the area code is known to be the local area code of |
| 4500 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 4501 | # is the area code in question. |
| 4502 | # rule. |
| 4503 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 4504 | "windowBefore": 42, # Number of characters before the finding to consider. |
| 4505 | }, |
| 4506 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 4507 | # part of a detection rule. |
| 4508 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 4509 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 4510 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 4511 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 4512 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 4513 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 4514 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 4515 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 4516 | # a final likelihood of `LIKELY`. |
| 4517 | }, |
| 4518 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 4519 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 4520 | # specified, the entire match is returned. No more than 3 may be included. |
| 4521 | 42, |
| 4522 | ], |
| 4523 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 4524 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 4525 | # google/re2 repository on GitHub. |
| 4526 | }, |
| 4527 | }, |
| 4528 | "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule. |
| 4529 | # `InspectionRuleSet` are removed from results. |
| 4530 | "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details. |
| 4531 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule. |
| 4532 | # be used to match sensitive information specific to the data, such as a list |
| 4533 | # of employee IDs or job titles. |
| 4534 | # |
| 4535 | # Dictionary words are case-insensitive and all characters other than letters |
| 4536 | # and digits in the unicode [Basic Multilingual |
| 4537 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 4538 | # will be replaced with whitespace when scanning for matches, so the |
| 4539 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 4540 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 4541 | # surrounding any match must be of a different type than the adjacent |
| 4542 | # characters within the word, so letters must be next to non-letters and |
| 4543 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 4544 | # match the first three letters of the text "jen123" but will return no |
| 4545 | # matches for "jennifer". |
| 4546 | # |
| 4547 | # Dictionary words containing a large number of characters that are not |
| 4548 | # letters or digits may result in unexpected findings because such characters |
| 4549 | # are treated as whitespace. The |
| 4550 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 4551 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 4552 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 4553 | # `StoredInfoType` API. |
| 4554 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 4555 | # is accepted. |
| 4556 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 4557 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 4558 | }, |
| 4559 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 4560 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 4561 | # at least one phrase and every phrase must contain at least 2 characters |
| 4562 | # that are letters or digits. [required] |
| 4563 | "A String", |
| 4564 | ], |
| 4565 | }, |
| 4566 | }, |
| 4567 | "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule. |
| 4568 | "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or |
| 4569 | # contained within with a finding of an infoType from this list. For |
| 4570 | # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and |
| 4571 | # `exclusion_rule` containing `exclude_info_types.info_types` with |
| 4572 | # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap |
| 4573 | # with EMAIL_ADDRESS finding. |
| 4574 | # That leads to "555-222-2222@example.org" to generate only a single |
| 4575 | # finding, namely email address. |
| 4576 | { # Type of information detected by the API. |
| 4577 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 4578 | # creating a CustomInfoType, or one of the names listed |
| 4579 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 4580 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 4581 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 4582 | }, |
| 4583 | ], |
| 4584 | }, |
| 4585 | "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule. |
| 4586 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 4587 | # specified, the entire match is returned. No more than 3 may be included. |
| 4588 | 42, |
| 4589 | ], |
| 4590 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 4591 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 4592 | # google/re2 repository on GitHub. |
| 4593 | }, |
| 4594 | }, |
| 4595 | }, |
| 4596 | ], |
| 4597 | }, |
| 4598 | ], |
| 4599 | "contentOptions": [ # List of options defining data content to scan. |
| 4600 | # If empty, text, images, and other content will be included. |
| 4601 | "A String", |
| 4602 | ], |
| 4603 | "infoTypes": [ # Restricts what info_types to look for. The values must correspond to |
| 4604 | # InfoType values returned by ListInfoTypes or listed at |
| 4605 | # https://cloud.google.com/dlp/docs/infotypes-reference. |
| 4606 | # |
| 4607 | # When no InfoTypes or CustomInfoTypes are specified in a request, the |
| 4608 | # system may automatically choose what detectors to run. By default this may |
| 4609 | # be all types, but may change over time as detectors are updated. |
| 4610 | # |
| 4611 | # If you need precise control and predictability as to what detectors are |
| 4612 | # run you should specify specific InfoTypes listed in the reference, |
| 4613 | # otherwise a default list will be used, which may change over time. |
| 4614 | { # Type of information detected by the API. |
| 4615 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 4616 | # creating a CustomInfoType, or one of the names listed |
| 4617 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 4618 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 4619 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 4620 | }, |
| 4621 | ], |
| 4622 | }, |
| 4623 | }, |
| 4624 | }, |
| 4625 | "result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspect job. |
| 4626 | "hybridStats": { # Statistics related to processing hybrid inspect requests. # Statistics related to the processing of hybrid inspect. |
| 4627 | # Early access feature is in a pre-release state and might change or have |
| 4628 | # limited support. For more information, see |
| 4629 | # https://cloud.google.com/products#product-launch-stages. |
| 4630 | "processedCount": "A String", # The number of hybrid inspection requests processed within this job. |
| 4631 | "abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran |
| 4632 | # out of quota or was ended before they could be processed. |
| 4633 | "pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated |
| 4634 | # when called via method `getDlpJob`. |
| 4635 | # A burst of traffic may cause hybrid inspect requests to be enqueued. |
| 4636 | # Processing will take place as quickly as possible, but resource limitations |
| 4637 | # may impact how long a request is enqueued for. |
| 4638 | }, |
| 4639 | "totalEstimatedBytes": "A String", # Estimate of the number of bytes to process. |
| 4640 | "infoTypeStats": [ # Statistics of how many instances of each info type were found during |
| 4641 | # inspect job. |
| 4642 | { # Statistics regarding a specific InfoType. |
| 4643 | "infoType": { # Type of information detected by the API. # The type of finding this stat is for. |
| 4644 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 4645 | # creating a CustomInfoType, or one of the names listed |
| 4646 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 4647 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 4648 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 4649 | }, |
| 4650 | "count": "A String", # Number of findings for this infoType. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 4651 | }, |
| 4652 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4653 | "processedBytes": "A String", # Total size in bytes that were processed. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 4654 | }, |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 4655 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 4656 | "name": "A String", # The server-assigned name. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 4657 | }</pre> |
| 4658 | </div> |
| 4659 | |
| 4660 | <div class="method"> |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4661 | <code class="details" id="list">list(parent, orderBy=None, type=None, filter=None, pageToken=None, locationId=None, pageSize=None, x__xgafv=None)</code> |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 4662 | <pre>Lists DlpJobs that match the specified filter in the request. |
| 4663 | See https://cloud.google.com/dlp/docs/inspecting-storage and |
| 4664 | https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more. |
| 4665 | |
| 4666 | Args: |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4667 | parent: string, Required. Parent resource name. |
| 4668 | - Format:projects/[PROJECT-ID] |
| 4669 | - Format:projects/[PROJECT-ID]/locations/[LOCATION-ID] (required) |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 4670 | orderBy: string, Comma separated list of fields to order by, |
| 4671 | followed by `asc` or `desc` postfix. This list is case-insensitive, |
| 4672 | default sorting order is ascending, redundant space characters are |
| 4673 | insignificant. |
| 4674 | |
| 4675 | Example: `name asc, end_time asc, create_time desc` |
| 4676 | |
| 4677 | Supported fields are: |
| 4678 | |
| 4679 | - `create_time`: corresponds to time the job was created. |
| 4680 | - `end_time`: corresponds to time the job ended. |
| 4681 | - `name`: corresponds to job's name. |
| 4682 | - `state`: corresponds to `state` |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4683 | type: string, The type of job. Defaults to `DlpJobType.INSPECT` |
| Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 4684 | filter: string, Allows filtering. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 4685 | |
| 4686 | Supported syntax: |
| 4687 | |
| 4688 | * Filter expressions are made up of one or more restrictions. |
| 4689 | * Restrictions can be combined by `AND` or `OR` logical operators. A |
| 4690 | sequence of restrictions implicitly uses `AND`. |
| Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 4691 | * A restriction has the form of `{field} {operator} {value}`. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 4692 | * Supported fields/values for inspect jobs: |
| 4693 | - `state` - PENDING|RUNNING|CANCELED|FINISHED|FAILED |
| 4694 | - `inspected_storage` - DATASTORE|CLOUD_STORAGE|BIGQUERY |
| 4695 | - `trigger_name` - The resource name of the trigger that created job. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 4696 | - 'end_time` - Corresponds to time the job finished. |
| 4697 | - 'start_time` - Corresponds to time the job finished. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 4698 | * Supported fields for risk analysis jobs: |
| 4699 | - `state` - RUNNING|CANCELED|FINISHED|FAILED |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 4700 | - 'end_time` - Corresponds to time the job finished. |
| 4701 | - 'start_time` - Corresponds to time the job finished. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 4702 | * The operator must be `=` or `!=`. |
| 4703 | |
| 4704 | Examples: |
| 4705 | |
| 4706 | * inspected_storage = cloud_storage AND state = done |
| 4707 | * inspected_storage = cloud_storage OR inspected_storage = bigquery |
| 4708 | * inspected_storage = cloud_storage AND (state = done OR state = canceled) |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 4709 | * end_time > \"2017-12-12T00:00:00+00:00\" |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 4710 | |
| 4711 | The length of this field should be no more than 500 characters. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4712 | pageToken: string, The standard list page token. |
| 4713 | locationId: string, Deprecated. This field has no effect. |
| 4714 | pageSize: integer, The standard list page size. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 4715 | x__xgafv: string, V1 error format. |
| 4716 | Allowed values |
| 4717 | 1 - v1 error format |
| 4718 | 2 - v2 error format |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 4719 | |
| 4720 | Returns: |
| 4721 | An object of the form: |
| 4722 | |
| 4723 | { # The response message for listing DLP jobs. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 4724 | "jobs": [ # A list of DlpJobs that matches the specified filter in the request. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 4725 | { # Combines all of the information about a DLP job. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4726 | "errors": [ # A stream of errors encountered running the job. |
| 4727 | { # Details information about an error encountered during job execution or |
| 4728 | # the results of an unsuccessful activation of the JobTrigger. |
| 4729 | "timestamps": [ # The times the error occurred. |
| 4730 | "A String", |
| 4731 | ], |
| 4732 | "details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages. |
| 4733 | # different programming environments, including REST APIs and RPC APIs. It is |
| 4734 | # used by [gRPC](https://github.com/grpc). Each `Status` message contains |
| 4735 | # three pieces of data: error code, error message, and error details. |
| 4736 | # |
| 4737 | # You can find out more about this error model and how to work with it in the |
| 4738 | # [API Design Guide](https://cloud.google.com/apis/design/errors). |
| 4739 | "code": 42, # The status code, which should be an enum value of google.rpc.Code. |
| 4740 | "details": [ # A list of messages that carry the error details. There is a common set of |
| 4741 | # message types for APIs to use. |
| 4742 | { |
| 4743 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 4744 | }, |
| 4745 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4746 | "message": "A String", # A developer-facing error message, which should be in English. Any |
| 4747 | # user-facing error message should be localized and sent in the |
| 4748 | # google.rpc.Status.details field, or localized by the client. |
| 4749 | }, |
| 4750 | }, |
| 4751 | ], |
| 4752 | "createTime": "A String", # Time when the job was created. |
| 4753 | "state": "A String", # State of a job. |
| 4754 | "riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source. |
| 4755 | "kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an # K-map result |
| 4756 | # estimation, not exact values. |
| 4757 | "kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value |
| 4758 | # doesn't correspond to any such interval, the associated frequency is |
| 4759 | # zero. For example, the following records: |
| 4760 | # {min_anonymity: 1, max_anonymity: 1, frequency: 17} |
| 4761 | # {min_anonymity: 2, max_anonymity: 3, frequency: 42} |
| 4762 | # {min_anonymity: 5, max_anonymity: 10, frequency: 99} |
| 4763 | # mean that there are no record with an estimated anonymity of 4, 5, or |
| 4764 | # larger than 10. |
| 4765 | { # A KMapEstimationHistogramBucket message with the following values: |
| 4766 | # min_anonymity: 3 |
| 4767 | # max_anonymity: 5 |
| 4768 | # frequency: 42 |
| 4769 | # means that there are 42 records whose quasi-identifier values correspond |
| 4770 | # to 3, 4 or 5 people in the overlying population. An important particular |
| 4771 | # case is when min_anonymity = max_anonymity = 1: the frequency field then |
| 4772 | # corresponds to the number of uniquely identifiable records. |
| 4773 | "maxAnonymity": "A String", # Always greater than or equal to min_anonymity. |
| 4774 | "bucketSize": "A String", # Number of records within these anonymity bounds. |
| 4775 | "bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket. |
| 4776 | "bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total |
| 4777 | # number of classes returned per bucket is capped at 20. |
| 4778 | { # A tuple of values for the quasi-identifier columns. |
| 4779 | "estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values. |
| 4780 | "quasiIdsValues": [ # The quasi-identifier values. |
| 4781 | { # Set of primitive values supported by the system. |
| 4782 | # Note that for the purposes of inspection or transformation, the number |
| 4783 | # of bytes considered to comprise a 'Value' is based on its representation |
| 4784 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 4785 | # 123456789, the number of bytes would be counted as 9, even though an |
| 4786 | # int64 only holds up to 8 bytes of data. |
| 4787 | "integerValue": "A String", # integer |
| 4788 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 4789 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 4790 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 4791 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 4792 | # allow the value 60 if it allows leap-seconds. |
| 4793 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 4794 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 4795 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 4796 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 4797 | }, |
| 4798 | "dayOfWeekValue": "A String", # day of week |
| 4799 | "floatValue": 3.14, # float |
| 4800 | "stringValue": "A String", # string |
| 4801 | "timestampValue": "A String", # timestamp |
| 4802 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 4803 | # and time zone are either specified elsewhere or are not significant. The date |
| 4804 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 4805 | # |
| 4806 | # * A full date, with non-zero year, month and day values |
| 4807 | # * A month and day value, with a zero year, e.g. an anniversary |
| 4808 | # * A year on its own, with zero month and day values |
| 4809 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 4810 | # |
| 4811 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 4812 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 4813 | # month and day. |
| 4814 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 4815 | # a year. |
| 4816 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 4817 | # if specifying a year by itself or a year and month where the day is not |
| 4818 | # significant. |
| 4819 | }, |
| 4820 | "booleanValue": True or False, # boolean |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 4821 | }, |
| 4822 | ], |
| 4823 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4824 | ], |
| 4825 | "minAnonymity": "A String", # Always positive. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 4826 | }, |
| 4827 | ], |
| 4828 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 4829 | "deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an # Delta-presence result |
| 4830 | # estimation, not exact values. |
| 4831 | "deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a |
| 4832 | # value doesn't correspond to any such interval, the associated frequency |
| 4833 | # is zero. For example, the following records: |
| 4834 | # {min_probability: 0, max_probability: 0.1, frequency: 17} |
| 4835 | # {min_probability: 0.2, max_probability: 0.3, frequency: 42} |
| 4836 | # {min_probability: 0.3, max_probability: 0.4, frequency: 99} |
| 4837 | # mean that there are no record with an estimated probability in [0.1, 0.2) |
| 4838 | # nor larger or equal to 0.4. |
| 4839 | { # A DeltaPresenceEstimationHistogramBucket message with the following |
| 4840 | # values: |
| 4841 | # min_probability: 0.1 |
| 4842 | # max_probability: 0.2 |
| 4843 | # frequency: 42 |
| 4844 | # means that there are 42 records for which δ is in [0.1, 0.2). An |
| 4845 | # important particular case is when min_probability = max_probability = 1: |
| 4846 | # then, every individual who shares this quasi-identifier combination is in |
| 4847 | # the dataset. |
| 4848 | "maxProbability": 3.14, # Always greater than or equal to min_probability. |
| 4849 | "bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket. |
| 4850 | "bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total |
| 4851 | # number of classes returned per bucket is capped at 20. |
| 4852 | { # A tuple of values for the quasi-identifier columns. |
| 4853 | "estimatedProbability": 3.14, # The estimated probability that a given individual sharing these |
| 4854 | # quasi-identifier values is in the dataset. This value, typically called |
| 4855 | # δ, is the ratio between the number of records in the dataset with these |
| 4856 | # quasi-identifier values, and the total number of individuals (inside |
| 4857 | # *and* outside the dataset) with these quasi-identifier values. |
| 4858 | # For example, if there are 15 individuals in the dataset who share the |
| 4859 | # same quasi-identifier values, and an estimated 100 people in the entire |
| 4860 | # population with these values, then δ is 0.15. |
| 4861 | "quasiIdsValues": [ # The quasi-identifier values. |
| 4862 | { # Set of primitive values supported by the system. |
| 4863 | # Note that for the purposes of inspection or transformation, the number |
| 4864 | # of bytes considered to comprise a 'Value' is based on its representation |
| 4865 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 4866 | # 123456789, the number of bytes would be counted as 9, even though an |
| 4867 | # int64 only holds up to 8 bytes of data. |
| 4868 | "integerValue": "A String", # integer |
| 4869 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 4870 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 4871 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 4872 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 4873 | # allow the value 60 if it allows leap-seconds. |
| 4874 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 4875 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 4876 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 4877 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 4878 | }, |
| 4879 | "dayOfWeekValue": "A String", # day of week |
| 4880 | "floatValue": 3.14, # float |
| 4881 | "stringValue": "A String", # string |
| 4882 | "timestampValue": "A String", # timestamp |
| 4883 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 4884 | # and time zone are either specified elsewhere or are not significant. The date |
| 4885 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 4886 | # |
| 4887 | # * A full date, with non-zero year, month and day values |
| 4888 | # * A month and day value, with a zero year, e.g. an anniversary |
| 4889 | # * A year on its own, with zero month and day values |
| 4890 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 4891 | # |
| 4892 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 4893 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 4894 | # month and day. |
| 4895 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 4896 | # a year. |
| 4897 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 4898 | # if specifying a year by itself or a year and month where the day is not |
| 4899 | # significant. |
| 4900 | }, |
| 4901 | "booleanValue": True or False, # boolean |
| 4902 | }, |
| 4903 | ], |
| 4904 | }, |
| 4905 | ], |
| 4906 | "minProbability": 3.14, # Between 0 and 1. |
| 4907 | "bucketSize": "A String", # Number of records within these probability bounds. |
| 4908 | }, |
| 4909 | ], |
| 4910 | }, |
| 4911 | "categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result |
| 4912 | "valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column. |
| 4913 | { # Histogram of value frequencies in the column. |
| 4914 | "valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket. |
| 4915 | "bucketValueCount": "A String", # Total number of distinct values in this bucket. |
| 4916 | "bucketSize": "A String", # Total number of values in this bucket. |
| 4917 | "valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket. |
| 4918 | "bucketValues": [ # Sample of value frequencies in this bucket. The total number of |
| 4919 | # values returned per bucket is capped at 20. |
| 4920 | { # A value of a field, including its frequency. |
| 4921 | "count": "A String", # How many times the value is contained in the field. |
| 4922 | "value": { # Set of primitive values supported by the system. # A value contained in the field in question. |
| 4923 | # Note that for the purposes of inspection or transformation, the number |
| 4924 | # of bytes considered to comprise a 'Value' is based on its representation |
| 4925 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 4926 | # 123456789, the number of bytes would be counted as 9, even though an |
| 4927 | # int64 only holds up to 8 bytes of data. |
| 4928 | "integerValue": "A String", # integer |
| 4929 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 4930 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 4931 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 4932 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 4933 | # allow the value 60 if it allows leap-seconds. |
| 4934 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 4935 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 4936 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 4937 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 4938 | }, |
| 4939 | "dayOfWeekValue": "A String", # day of week |
| 4940 | "floatValue": 3.14, # float |
| 4941 | "stringValue": "A String", # string |
| 4942 | "timestampValue": "A String", # timestamp |
| 4943 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 4944 | # and time zone are either specified elsewhere or are not significant. The date |
| 4945 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 4946 | # |
| 4947 | # * A full date, with non-zero year, month and day values |
| 4948 | # * A month and day value, with a zero year, e.g. an anniversary |
| 4949 | # * A year on its own, with zero month and day values |
| 4950 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 4951 | # |
| 4952 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 4953 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 4954 | # month and day. |
| 4955 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 4956 | # a year. |
| 4957 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 4958 | # if specifying a year by itself or a year and month where the day is not |
| 4959 | # significant. |
| 4960 | }, |
| 4961 | "booleanValue": True or False, # boolean |
| 4962 | }, |
| 4963 | }, |
| 4964 | ], |
| 4965 | }, |
| 4966 | ], |
| 4967 | }, |
| 4968 | "numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result |
| 4969 | "quantileValues": [ # List of 99 values that partition the set of field values into 100 equal |
| 4970 | # sized buckets. |
| 4971 | { # Set of primitive values supported by the system. |
| 4972 | # Note that for the purposes of inspection or transformation, the number |
| 4973 | # of bytes considered to comprise a 'Value' is based on its representation |
| 4974 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 4975 | # 123456789, the number of bytes would be counted as 9, even though an |
| 4976 | # int64 only holds up to 8 bytes of data. |
| 4977 | "integerValue": "A String", # integer |
| 4978 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 4979 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 4980 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 4981 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 4982 | # allow the value 60 if it allows leap-seconds. |
| 4983 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 4984 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 4985 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 4986 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 4987 | }, |
| 4988 | "dayOfWeekValue": "A String", # day of week |
| 4989 | "floatValue": 3.14, # float |
| 4990 | "stringValue": "A String", # string |
| 4991 | "timestampValue": "A String", # timestamp |
| 4992 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 4993 | # and time zone are either specified elsewhere or are not significant. The date |
| 4994 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 4995 | # |
| 4996 | # * A full date, with non-zero year, month and day values |
| 4997 | # * A month and day value, with a zero year, e.g. an anniversary |
| 4998 | # * A year on its own, with zero month and day values |
| 4999 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 5000 | # |
| 5001 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 5002 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 5003 | # month and day. |
| 5004 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 5005 | # a year. |
| 5006 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 5007 | # if specifying a year by itself or a year and month where the day is not |
| 5008 | # significant. |
| 5009 | }, |
| 5010 | "booleanValue": True or False, # boolean |
| 5011 | }, |
| 5012 | ], |
| 5013 | "minValue": { # Set of primitive values supported by the system. # Minimum value appearing in the column. |
| 5014 | # Note that for the purposes of inspection or transformation, the number |
| 5015 | # of bytes considered to comprise a 'Value' is based on its representation |
| 5016 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 5017 | # 123456789, the number of bytes would be counted as 9, even though an |
| 5018 | # int64 only holds up to 8 bytes of data. |
| 5019 | "integerValue": "A String", # integer |
| 5020 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 5021 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 5022 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 5023 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 5024 | # allow the value 60 if it allows leap-seconds. |
| 5025 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 5026 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 5027 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 5028 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 5029 | }, |
| 5030 | "dayOfWeekValue": "A String", # day of week |
| 5031 | "floatValue": 3.14, # float |
| 5032 | "stringValue": "A String", # string |
| 5033 | "timestampValue": "A String", # timestamp |
| 5034 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 5035 | # and time zone are either specified elsewhere or are not significant. The date |
| 5036 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 5037 | # |
| 5038 | # * A full date, with non-zero year, month and day values |
| 5039 | # * A month and day value, with a zero year, e.g. an anniversary |
| 5040 | # * A year on its own, with zero month and day values |
| 5041 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 5042 | # |
| 5043 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 5044 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 5045 | # month and day. |
| 5046 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 5047 | # a year. |
| 5048 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 5049 | # if specifying a year by itself or a year and month where the day is not |
| 5050 | # significant. |
| 5051 | }, |
| 5052 | "booleanValue": True or False, # boolean |
| 5053 | }, |
| 5054 | "maxValue": { # Set of primitive values supported by the system. # Maximum value appearing in the column. |
| 5055 | # Note that for the purposes of inspection or transformation, the number |
| 5056 | # of bytes considered to comprise a 'Value' is based on its representation |
| 5057 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 5058 | # 123456789, the number of bytes would be counted as 9, even though an |
| 5059 | # int64 only holds up to 8 bytes of data. |
| 5060 | "integerValue": "A String", # integer |
| 5061 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 5062 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 5063 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 5064 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 5065 | # allow the value 60 if it allows leap-seconds. |
| 5066 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 5067 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 5068 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 5069 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 5070 | }, |
| 5071 | "dayOfWeekValue": "A String", # day of week |
| 5072 | "floatValue": 3.14, # float |
| 5073 | "stringValue": "A String", # string |
| 5074 | "timestampValue": "A String", # timestamp |
| 5075 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 5076 | # and time zone are either specified elsewhere or are not significant. The date |
| 5077 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 5078 | # |
| 5079 | # * A full date, with non-zero year, month and day values |
| 5080 | # * A month and day value, with a zero year, e.g. an anniversary |
| 5081 | # * A year on its own, with zero month and day values |
| 5082 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 5083 | # |
| 5084 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 5085 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 5086 | # month and day. |
| 5087 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 5088 | # a year. |
| 5089 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 5090 | # if specifying a year by itself or a year and month where the day is not |
| 5091 | # significant. |
| 5092 | }, |
| 5093 | "booleanValue": True or False, # boolean |
| 5094 | }, |
| 5095 | }, |
| 5096 | "kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result |
| 5097 | "equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes. |
| 5098 | { # Histogram of k-anonymity equivalence classes. |
| 5099 | "bucketValues": [ # Sample of equivalence classes in this bucket. The total number of |
| 5100 | # classes returned per bucket is capped at 20. |
| 5101 | { # The set of columns' values that share the same ldiversity value |
| 5102 | "quasiIdsValues": [ # Set of values defining the equivalence class. One value per |
| 5103 | # quasi-identifier column in the original KAnonymity metric message. |
| 5104 | # The order is always the same as the original request. |
| 5105 | { # Set of primitive values supported by the system. |
| 5106 | # Note that for the purposes of inspection or transformation, the number |
| 5107 | # of bytes considered to comprise a 'Value' is based on its representation |
| 5108 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 5109 | # 123456789, the number of bytes would be counted as 9, even though an |
| 5110 | # int64 only holds up to 8 bytes of data. |
| 5111 | "integerValue": "A String", # integer |
| 5112 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 5113 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 5114 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 5115 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 5116 | # allow the value 60 if it allows leap-seconds. |
| 5117 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 5118 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 5119 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 5120 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 5121 | }, |
| 5122 | "dayOfWeekValue": "A String", # day of week |
| 5123 | "floatValue": 3.14, # float |
| 5124 | "stringValue": "A String", # string |
| 5125 | "timestampValue": "A String", # timestamp |
| 5126 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 5127 | # and time zone are either specified elsewhere or are not significant. The date |
| 5128 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 5129 | # |
| 5130 | # * A full date, with non-zero year, month and day values |
| 5131 | # * A month and day value, with a zero year, e.g. an anniversary |
| 5132 | # * A year on its own, with zero month and day values |
| 5133 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 5134 | # |
| 5135 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 5136 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 5137 | # month and day. |
| 5138 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 5139 | # a year. |
| 5140 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 5141 | # if specifying a year by itself or a year and month where the day is not |
| 5142 | # significant. |
| 5143 | }, |
| 5144 | "booleanValue": True or False, # boolean |
| 5145 | }, |
| 5146 | ], |
| 5147 | "equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the |
| 5148 | # above set of values. |
| 5149 | }, |
| 5150 | ], |
| 5151 | "equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket. |
| 5152 | "equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket. |
| 5153 | "bucketSize": "A String", # Total number of equivalence classes in this bucket. |
| 5154 | "bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket. |
| 5155 | }, |
| 5156 | ], |
| 5157 | }, |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5158 | "requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5159 | "categoricalStatsConfig": { # Compute numerical stats over an individual column, including # Categorical stats |
| 5160 | # number of distinct values and value count distribution. |
| 5161 | "field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are |
| 5162 | # supported except for arrays and structs. However, it may be more |
| 5163 | # informative to use NumericalStats when the field type is supported, |
| 5164 | # depending on the data. |
| 5165 | "name": "A String", # Name describing the field. |
| 5166 | }, |
| 5167 | }, |
| 5168 | "lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity |
| 5169 | "sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value. |
| 5170 | "name": "A String", # Name describing the field. |
| 5171 | }, |
| 5172 | "quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are |
| 5173 | # defined for the l-diversity computation. When multiple fields are |
| 5174 | # specified, they are considered a single composite key. |
| 5175 | { # General identifier of a data field in a storage service. |
| 5176 | "name": "A String", # Name describing the field. |
| 5177 | }, |
| 5178 | ], |
| 5179 | }, |
| 5180 | "kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what # k-map |
| 5181 | # is called "journalist risk" in the literature, except the attack dataset is |
| 5182 | # statistically modeled instead of being perfectly known. This can be done |
| 5183 | # using publicly available data (like the US Census), or using a custom |
| 5184 | # statistical model (indicated as one or several BigQuery tables), or by |
| 5185 | # extrapolating from the distribution of values in the input dataset. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5186 | "regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. |
| 5187 | # Set if no column is tagged with a region-specific InfoType (like |
| 5188 | # US_ZIP_5) or a region code. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5189 | "quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the |
| 5190 | # same tag. |
| 5191 | { # A column with a semantic tag attached. |
| 5192 | "field": { # General identifier of a data field in a storage service. # Required. Identifies the column. |
| 5193 | "name": "A String", # Name describing the field. |
| 5194 | }, |
| 5195 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 5196 | # indicate an auxiliary table that contains statistical information on |
| 5197 | # the possible values of this column (below). |
| 5198 | "infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public |
| 5199 | # dataset as a statistical model of population, if available. We |
| 5200 | # currently support US ZIP codes, region codes, ages and genders. |
| 5201 | # To programmatically obtain the list of supported InfoTypes, use |
| 5202 | # ListInfoTypes with the supported_by=RISK_ANALYSIS filter. |
| 5203 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 5204 | # creating a CustomInfoType, or one of the names listed |
| 5205 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 5206 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 5207 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 5208 | }, |
| 5209 | "inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from |
| 5210 | # the distribution of values in the input data |
| 5211 | # empty messages in your APIs. A typical example is to use it as the request |
| 5212 | # or the response type of an API method. For instance: |
| 5213 | # |
| 5214 | # service Foo { |
| 5215 | # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); |
| 5216 | # } |
| 5217 | # |
| 5218 | # The JSON representation for `Empty` is empty JSON object `{}`. |
| 5219 | }, |
| 5220 | }, |
| 5221 | ], |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5222 | "auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5223 | # used to tag a quasi-identifiers column must appear in exactly one column |
| 5224 | # of one auxiliary table. |
| 5225 | { # An auxiliary table contains statistical information on the relative |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5226 | # frequency of different quasi-identifiers values. It has one or several |
| 5227 | # quasi-identifiers columns, and one column that indicates the relative |
| 5228 | # frequency of each quasi-identifier tuple. |
| 5229 | # If a tuple is present in the data but not in the auxiliary table, the |
| 5230 | # corresponding relative frequency is assumed to be zero (and thus, the |
| 5231 | # tuple is highly reidentifiable). |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5232 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location. |
| 5233 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 5234 | # a table is often referenced with a string in the format of: |
| 5235 | # `<project_id>:<dataset_id>.<table_id>` or |
| 5236 | # `<project_id>.<dataset_id>.<table_id>`. |
| 5237 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 5238 | # If omitted, project ID is inferred from the API call. |
| 5239 | "datasetId": "A String", # Dataset ID of the table. |
| 5240 | "tableId": "A String", # Name of the table. |
| 5241 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5242 | "quasiIds": [ # Required. Quasi-identifier columns. |
| 5243 | { # A quasi-identifier column has a custom_tag, used to know which column |
| 5244 | # in the data corresponds to which column in the statistical model. |
| 5245 | "customTag": "A String", # A auxiliary field. |
| 5246 | "field": { # General identifier of a data field in a storage service. # Identifies the column. |
| 5247 | "name": "A String", # Name describing the field. |
| 5248 | }, |
| 5249 | }, |
| 5250 | ], |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5251 | "relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number |
| 5252 | # between 0 and 1 (inclusive). Null values are assumed to be zero. |
| 5253 | "name": "A String", # Name describing the field. |
| 5254 | }, |
| 5255 | }, |
| 5256 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5257 | }, |
| 5258 | "deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to # delta-presence |
| 5259 | # figure out that one given individual appears in a de-identified dataset. |
| 5260 | # Similarly to the k-map metric, we cannot compute δ-presence exactly without |
| 5261 | # knowing the attack dataset, so we use a statistical model instead. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5262 | "quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the |
| 5263 | # same tag. |
| 5264 | { # A column with a semantic tag attached. |
| 5265 | "field": { # General identifier of a data field in a storage service. # Required. Identifies the column. |
| 5266 | "name": "A String", # Name describing the field. |
| 5267 | }, |
| 5268 | "infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public |
| 5269 | # dataset as a statistical model of population, if available. We |
| 5270 | # currently support US ZIP codes, region codes, ages and genders. |
| 5271 | # To programmatically obtain the list of supported InfoTypes, use |
| 5272 | # ListInfoTypes with the supported_by=RISK_ANALYSIS filter. |
| 5273 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 5274 | # creating a CustomInfoType, or one of the names listed |
| 5275 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5276 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 5277 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5278 | }, |
| 5279 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 5280 | # indicate an auxiliary table that contains statistical information on |
| 5281 | # the possible values of this column (below). |
| 5282 | "inferred": { # A generic empty message that you can re-use to avoid defining duplicated # If no semantic tag is indicated, we infer the statistical model from |
| 5283 | # the distribution of values in the input data |
| 5284 | # empty messages in your APIs. A typical example is to use it as the request |
| 5285 | # or the response type of an API method. For instance: |
| 5286 | # |
| 5287 | # service Foo { |
| 5288 | # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); |
| 5289 | # } |
| 5290 | # |
| 5291 | # The JSON representation for `Empty` is empty JSON object `{}`. |
| 5292 | }, |
| 5293 | }, |
| 5294 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5295 | "auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag |
| 5296 | # used to tag a quasi-identifiers field must appear in exactly one |
| 5297 | # field of one auxiliary table. |
| 5298 | { # An auxiliary table containing statistical information on the relative |
| 5299 | # frequency of different quasi-identifiers values. It has one or several |
| 5300 | # quasi-identifiers columns, and one column that indicates the relative |
| 5301 | # frequency of each quasi-identifier tuple. |
| 5302 | # If a tuple is present in the data but not in the auxiliary table, the |
| 5303 | # corresponding relative frequency is assumed to be zero (and thus, the |
| 5304 | # tuple is highly reidentifiable). |
| 5305 | "relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number |
| 5306 | # between 0 and 1 (inclusive). Null values are assumed to be zero. |
| 5307 | "name": "A String", # Name describing the field. |
| 5308 | }, |
| 5309 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location. |
| 5310 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 5311 | # a table is often referenced with a string in the format of: |
| 5312 | # `<project_id>:<dataset_id>.<table_id>` or |
| 5313 | # `<project_id>.<dataset_id>.<table_id>`. |
| 5314 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 5315 | # If omitted, project ID is inferred from the API call. |
| 5316 | "datasetId": "A String", # Dataset ID of the table. |
| 5317 | "tableId": "A String", # Name of the table. |
| 5318 | }, |
| 5319 | "quasiIds": [ # Required. Quasi-identifier columns. |
| 5320 | { # A quasi-identifier column has a custom_tag, used to know which column |
| 5321 | # in the data corresponds to which column in the statistical model. |
| 5322 | "field": { # General identifier of a data field in a storage service. # Identifies the column. |
| 5323 | "name": "A String", # Name describing the field. |
| 5324 | }, |
| 5325 | "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must |
| 5326 | # indicate an auxiliary table that contains statistical information on |
| 5327 | # the possible values of this column (below). |
| 5328 | }, |
| 5329 | ], |
| 5330 | }, |
| 5331 | ], |
| 5332 | "regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling. |
| 5333 | # Set if no column is tagged with a region-specific InfoType (like |
| 5334 | # US_ZIP_5) or a region code. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5335 | }, |
| 5336 | "kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5337 | "entityId": { # An entity in a dataset is a field or set of fields that correspond to a # Message indicating that multiple rows might be associated to a |
| 5338 | # single individual. If the same entity_id is associated to multiple |
| 5339 | # quasi-identifier tuples over distinct rows, we consider the entire |
| 5340 | # collection of tuples as the composite quasi-identifier. This collection |
| 5341 | # is a multiset: the order in which the different tuples appear in the |
| 5342 | # dataset is ignored, but their frequency is taken into account. |
| 5343 | # |
| 5344 | # Important note: a maximum of 1000 rows can be associated to a single |
| 5345 | # entity ID. If more rows are associated with the same entity ID, some |
| 5346 | # might be ignored. |
| 5347 | # single person. For example, in medical records the `EntityId` might be a |
| 5348 | # patient identifier, or for financial records it might be an account |
| 5349 | # identifier. This message is used when generalizations or analysis must take |
| 5350 | # into account that multiple rows correspond to the same entity. |
| 5351 | "field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier. |
| 5352 | "name": "A String", # Name describing the field. |
| 5353 | }, |
| 5354 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5355 | "quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are |
| 5356 | # specified, they are considered a single composite key. Structs and |
| 5357 | # repeated data types are not supported; however, nested fields are |
| 5358 | # supported so long as they are not structs themselves or nested within |
| 5359 | # a repeated field. |
| 5360 | { # General identifier of a data field in a storage service. |
| 5361 | "name": "A String", # Name describing the field. |
| 5362 | }, |
| 5363 | ], |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5364 | }, |
| 5365 | "numericalStatsConfig": { # Compute numerical stats over an individual column, including # Numerical stats |
| 5366 | # min, max, and quantiles. |
| 5367 | "field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are |
| 5368 | # integer, float, date, datetime, timestamp, time. |
| 5369 | "name": "A String", # Name describing the field. |
| 5370 | }, |
| 5371 | }, |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5372 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5373 | "lDiversityResult": { # Result of the l-diversity computation. # L-divesity result |
| 5374 | "sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies. |
| 5375 | { # Histogram of l-diversity equivalence class sensitive value frequencies. |
| 5376 | "bucketSize": "A String", # Total number of equivalence classes in this bucket. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5377 | "bucketValues": [ # Sample of equivalence classes in this bucket. The total number of |
| 5378 | # classes returned per bucket is capped at 20. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5379 | { # The set of columns' values that share the same ldiversity value. |
| 5380 | "quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence |
| 5381 | # class. The order is always the same as the original request. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5382 | { # Set of primitive values supported by the system. |
| 5383 | # Note that for the purposes of inspection or transformation, the number |
| 5384 | # of bytes considered to comprise a 'Value' is based on its representation |
| 5385 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 5386 | # 123456789, the number of bytes would be counted as 9, even though an |
| 5387 | # int64 only holds up to 8 bytes of data. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5388 | "integerValue": "A String", # integer |
| 5389 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 5390 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 5391 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 5392 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 5393 | # allow the value 60 if it allows leap-seconds. |
| 5394 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 5395 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 5396 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 5397 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 5398 | }, |
| 5399 | "dayOfWeekValue": "A String", # day of week |
| 5400 | "floatValue": 3.14, # float |
| 5401 | "stringValue": "A String", # string |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5402 | "timestampValue": "A String", # timestamp |
| 5403 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 5404 | # and time zone are either specified elsewhere or are not significant. The date |
| 5405 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 5406 | # |
| 5407 | # * A full date, with non-zero year, month and day values |
| 5408 | # * A month and day value, with a zero year, e.g. an anniversary |
| 5409 | # * A year on its own, with zero month and day values |
| 5410 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 5411 | # |
| 5412 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5413 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 5414 | # month and day. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5415 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 5416 | # a year. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5417 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 5418 | # if specifying a year by itself or a year and month where the day is not |
| 5419 | # significant. |
| 5420 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5421 | "booleanValue": True or False, # boolean |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5422 | }, |
| 5423 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5424 | "topSensitiveValues": [ # Estimated frequencies of top sensitive values. |
| 5425 | { # A value of a field, including its frequency. |
| 5426 | "count": "A String", # How many times the value is contained in the field. |
| 5427 | "value": { # Set of primitive values supported by the system. # A value contained in the field in question. |
| 5428 | # Note that for the purposes of inspection or transformation, the number |
| 5429 | # of bytes considered to comprise a 'Value' is based on its representation |
| 5430 | # as a UTF-8 encoded string. For example, if 'integer_value' is set to |
| 5431 | # 123456789, the number of bytes would be counted as 9, even though an |
| 5432 | # int64 only holds up to 8 bytes of data. |
| 5433 | "integerValue": "A String", # integer |
| 5434 | "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day |
| 5435 | # or are specified elsewhere. An API may choose to allow leap seconds. Related |
| 5436 | # types are google.type.Date and `google.protobuf.Timestamp`. |
| 5437 | "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may |
| 5438 | # allow the value 60 if it allows leap-seconds. |
| 5439 | "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999. |
| 5440 | "minutes": 42, # Minutes of hour of day. Must be from 0 to 59. |
| 5441 | "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose |
| 5442 | # to allow the value "24:00:00" for scenarios like business closing time. |
| 5443 | }, |
| 5444 | "dayOfWeekValue": "A String", # day of week |
| 5445 | "floatValue": 3.14, # float |
| 5446 | "stringValue": "A String", # string |
| 5447 | "timestampValue": "A String", # timestamp |
| 5448 | "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date |
| 5449 | # and time zone are either specified elsewhere or are not significant. The date |
| 5450 | # is relative to the Proleptic Gregorian Calendar. This can represent: |
| 5451 | # |
| 5452 | # * A full date, with non-zero year, month and day values |
| 5453 | # * A month and day value, with a zero year, e.g. an anniversary |
| 5454 | # * A year on its own, with zero month and day values |
| 5455 | # * A year and month value, with a zero day, e.g. a credit card expiration date |
| 5456 | # |
| 5457 | # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`. |
| 5458 | "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a |
| 5459 | # month and day. |
| 5460 | "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without |
| 5461 | # a year. |
| 5462 | "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0 |
| 5463 | # if specifying a year by itself or a year and month where the day is not |
| 5464 | # significant. |
| 5465 | }, |
| 5466 | "booleanValue": True or False, # boolean |
| 5467 | }, |
| 5468 | }, |
| 5469 | ], |
| 5470 | "equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class. |
| 5471 | "numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5472 | }, |
| 5473 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5474 | "sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence |
| 5475 | # classes in this bucket. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5476 | "bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket. |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5477 | "sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence |
| 5478 | # classes in this bucket. |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 5479 | }, |
| 5480 | ], |
| 5481 | }, |
| 5482 | "requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over. |
| 5483 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 5484 | # a table is often referenced with a string in the format of: |
| 5485 | # `<project_id>:<dataset_id>.<table_id>` or |
| 5486 | # `<project_id>.<dataset_id>.<table_id>`. |
| 5487 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 5488 | # If omitted, project ID is inferred from the API call. |
| 5489 | "datasetId": "A String", # Dataset ID of the table. |
| 5490 | "tableId": "A String", # Name of the table. |
| 5491 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5492 | }, |
| 5493 | "type": "A String", # The type of job. |
| 5494 | "endTime": "A String", # Time when the job finished. |
| 5495 | "startTime": "A String", # Time when the job started. |
| 5496 | "jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that |
| 5497 | # instantiated the job. |
| 5498 | "inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source. |
| 5499 | "requestedOptions": { # Snapshot of the inspection configuration. # The configuration used for this job. |
| 5500 | "jobConfig": { # Controls what and how to inspect for findings. # Inspect config. |
| 5501 | "inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig. |
| 5502 | # `inspect_config` will be merged into the values persisted as part of the |
| 5503 | # template. |
| 5504 | "actions": [ # Actions to execute at the completion of the job. |
| 5505 | { # A task to execute on the completion of a job. |
| 5506 | # See https://cloud.google.com/dlp/docs/concepts-actions to learn more. |
| 5507 | "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count. |
| 5508 | # will publish a metric to stack driver on each infotype requested and |
| 5509 | # how many findings were found for it. CustomDetectors will be bucketed |
| 5510 | # as 'Custom' under the Stackdriver label 'info_type'. |
| 5511 | }, |
| 5512 | "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub. |
| 5513 | # results of the DlpJob will be applied to the entry for the resource scanned |
| 5514 | # in Cloud Data Catalog. Any labels previously written by another DlpJob will |
| 5515 | # be deleted. InfoType naming patterns are strictly enforced when using this |
| 5516 | # feature. Note that the findings will be persisted in Cloud Data Catalog |
| 5517 | # storage and are governed by Data Catalog service-specific policy, see |
| 5518 | # https://cloud.google.com/terms/service-terms |
| 5519 | # Only a single instance of this action can be specified and only allowed if |
| 5520 | # all resources being scanned are BigQuery tables. |
| 5521 | # Compatible with: Inspect |
| 5522 | }, |
| 5523 | "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's |
| 5524 | # completion/failure. |
| 5525 | # completion/failure. |
| 5526 | }, |
| 5527 | "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic. |
| 5528 | # message contains a single field, `DlpJobName`, which is equal to the |
| 5529 | # finished job's |
| 5530 | # [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob). |
| 5531 | # Compatible with: Inspect, Risk |
| 5532 | "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given |
| 5533 | # publishing access rights to the DLP API service account executing |
| 5534 | # the long running DlpJob sending the notifications. |
| 5535 | # Format is projects/{project}/topics/{topic}. |
| 5536 | }, |
| 5537 | "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location. |
| 5538 | # OutputStorageConfig. Only a single instance of this action can be |
| 5539 | # specified. |
| 5540 | # Compatible with: Inspect, Risk |
| 5541 | "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP. |
| 5542 | "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only |
| 5543 | # used for Inspect and must be unspecified for Risk jobs. Columns are derived |
| 5544 | # from the `Finding` object. If appending to an existing table, any columns |
| 5545 | # from the predefined schema that are missing will be added. No columns in |
| 5546 | # the existing table will be deleted. |
| 5547 | # |
| 5548 | # If unspecified, then all available columns will be used for a new table or |
| 5549 | # an (existing) table with no schema, and no changes will be made to an |
| 5550 | # existing table that has a schema. |
| 5551 | # Only for use with external storage. |
| 5552 | "table": { # Message defining the location of a BigQuery table. A table is uniquely # Store findings in an existing table or a new table in an existing |
| 5553 | # dataset. If table_id is not set a new one will be generated |
| 5554 | # for you with the following format: |
| 5555 | # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for |
| 5556 | # generating the date details. |
| 5557 | # |
| 5558 | # For Inspect, each column in an existing output table must have the same |
| 5559 | # name, type, and mode of a field in the `Finding` object. |
| 5560 | # |
| 5561 | # For Risk, an existing output table should be the output of a previous |
| 5562 | # Risk analysis job run on the same source table, with the same privacy |
| 5563 | # metric and quasi-identifiers. Risk jobs that analyze the same table but |
| 5564 | # compute a different privacy metric, or use different sets of |
| 5565 | # quasi-identifiers, cannot store their results in the same table. |
| 5566 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 5567 | # a table is often referenced with a string in the format of: |
| 5568 | # `<project_id>:<dataset_id>.<table_id>` or |
| 5569 | # `<project_id>.<dataset_id>.<table_id>`. |
| 5570 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 5571 | # If omitted, project ID is inferred from the API call. |
| 5572 | "datasetId": "A String", # Dataset ID of the table. |
| 5573 | "tableId": "A String", # Name of the table. |
| 5574 | }, |
| 5575 | }, |
| 5576 | }, |
| 5577 | "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha). |
| 5578 | # Command Center (CSCC Alpha). |
| 5579 | # This action is only available for projects which are parts of |
| 5580 | # an organization and whitelisted for the alpha Cloud Security Command |
| 5581 | # Center. |
| 5582 | # The action will publish count of finding instances and their info types. |
| 5583 | # The summary of findings will be persisted in CSCC and are governed by CSCC |
| 5584 | # service-specific policy, see https://cloud.google.com/terms/service-terms |
| 5585 | # Only a single instance of this action can be specified. |
| 5586 | # Compatible with: Inspect |
| 5587 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5588 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5589 | ], |
| 5590 | "storageConfig": { # Shared message indicating Cloud storage type. # The data to scan. |
| 5591 | "cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options. |
| 5592 | # bucket. |
| 5593 | "bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The |
| 5594 | # number of bytes scanned is rounded down. Must be between 0 and 100, |
| 5595 | # inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one |
| 5596 | # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. |
| 5597 | "fileTypes": [ # List of file type groups to include in the scan. |
| 5598 | # If empty, all files are scanned and available data format processors |
| 5599 | # are applied. In addition, the binary content of the selected files |
| 5600 | # is always scanned as well. |
| 5601 | # Images are scanned only as binary if the specified region |
| 5602 | # does not support image inspection and no file_types were specified. |
| 5603 | # Image inspection is restricted to 'global', 'us', 'asia', and 'europe'. |
| 5604 | "A String", |
| 5605 | ], |
| 5606 | "bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger |
| 5607 | # than this value then the rest of the bytes are omitted. Only one |
| 5608 | # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified. |
| 5609 | "filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet. |
| 5610 | # Number of files scanned is rounded down. Must be between 0 and 100, |
| 5611 | # inclusively. Both 0 and 100 means no limit. Defaults to 0. |
| 5612 | "fileSet": { # Set of files to scan. # The set of one or more files to scan. |
| 5613 | "regexFileSet": { # Message representing a set of files in a Cloud Storage bucket. Regular # The regex-filtered set of files to scan. Exactly one of `url` or |
| 5614 | # `regex_file_set` must be set. |
| 5615 | # expressions are used to allow fine-grained control over which files in the |
| 5616 | # bucket to include. |
| 5617 | # |
| 5618 | # Included files are those that match at least one item in `include_regex` and |
| 5619 | # do not match any items in `exclude_regex`. Note that a file that matches |
| 5620 | # items from both lists will _not_ be included. For a match to occur, the |
| 5621 | # entire file path (i.e., everything in the url after the bucket name) must |
| 5622 | # match the regular expression. |
| 5623 | # |
| 5624 | # For example, given the input `{bucket_name: "mybucket", include_regex: |
| 5625 | # ["directory1/.*"], exclude_regex: |
| 5626 | # ["directory1/excluded.*"]}`: |
| 5627 | # |
| 5628 | # * `gs://mybucket/directory1/myfile` will be included |
| 5629 | # * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches |
| 5630 | # across `/`) |
| 5631 | # * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the |
| 5632 | # full path doesn't match any items in `include_regex`) |
| 5633 | # * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path |
| 5634 | # matches an item in `exclude_regex`) |
| 5635 | # |
| 5636 | # If `include_regex` is left empty, it will match all files by default |
| 5637 | # (this is equivalent to setting `include_regex: [".*"]`). |
| 5638 | # |
| 5639 | # Some other common use cases: |
| 5640 | # |
| 5641 | # * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all |
| 5642 | # files in `mybucket` except for .pdf files |
| 5643 | # * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will |
| 5644 | # include all files directly under `gs://mybucket/directory/`, without matching |
| 5645 | # across `/` |
| 5646 | "bucketName": "A String", # The name of a Cloud Storage bucket. Required. |
| 5647 | "excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in |
| 5648 | # the bucket that match at least one of these regular expressions will be |
| 5649 | # excluded from the scan. |
| 5650 | # |
| 5651 | # Regular expressions use RE2 |
| 5652 | # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found |
| 5653 | # under the google/re2 repository on GitHub. |
| 5654 | "A String", |
| 5655 | ], |
| 5656 | "includeRegex": [ # A list of regular expressions matching file paths to include. All files in |
| 5657 | # the bucket that match at least one of these regular expressions will be |
| 5658 | # included in the set of files, except for those that also match an item in |
| 5659 | # `exclude_regex`. Leaving this field empty will match all files by default |
| 5660 | # (this is equivalent to including `.*` in the list). |
| 5661 | # |
| 5662 | # Regular expressions use RE2 |
| 5663 | # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found |
| 5664 | # under the google/re2 repository on GitHub. |
| 5665 | "A String", |
| 5666 | ], |
| 5667 | }, |
| 5668 | "url": "A String", # The Cloud Storage url of the file(s) to scan, in the format |
| 5669 | # `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed. |
| 5670 | # |
| 5671 | # If the url ends in a trailing slash, the bucket or directory represented |
| 5672 | # by the url will be scanned non-recursively (content in sub-directories |
| 5673 | # will not be scanned). This means that `gs://mybucket/` is equivalent to |
| 5674 | # `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to |
| 5675 | # `gs://mybucket/directory/*`. |
| 5676 | # |
| 5677 | # Exactly one of `url` or `regex_file_set` must be set. |
| 5678 | }, |
| 5679 | "sampleMethod": "A String", |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5680 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5681 | "bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options. |
| 5682 | "sampleMethod": "A String", |
| 5683 | "tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference. |
| 5684 | # identified by its project_id, dataset_id, and table_name. Within a query |
| 5685 | # a table is often referenced with a string in the format of: |
| 5686 | # `<project_id>:<dataset_id>.<table_id>` or |
| 5687 | # `<project_id>.<dataset_id>.<table_id>`. |
| 5688 | "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table. |
| 5689 | # If omitted, project ID is inferred from the API call. |
| 5690 | "datasetId": "A String", # Dataset ID of the table. |
| 5691 | "tableId": "A String", # Name of the table. |
| 5692 | }, |
| 5693 | "rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows |
| 5694 | # scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and |
| 5695 | # 100 means no limit. Defaults to 0. Only one of rows_limit and |
| 5696 | # rows_limit_percent can be specified. Cannot be used in conjunction with |
| 5697 | # TimespanConfig. |
| 5698 | "rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the |
| 5699 | # rest of the rows are omitted. If not set, or if set to 0, all rows will be |
| 5700 | # scanned. Only one of rows_limit and rows_limit_percent can be specified. |
| 5701 | # Cannot be used in conjunction with TimespanConfig. |
| 5702 | "identifyingFields": [ # Table fields that may uniquely identify a row within the table. When |
| 5703 | # `actions.saveFindings.outputConfig.table` is specified, the values of |
| 5704 | # columns specified here are available in the output table under |
| 5705 | # `location.content_locations.record_location.record_key.id_values`. Nested |
| 5706 | # fields such as `person.birthdate.year` are allowed. |
| 5707 | { # General identifier of a data field in a storage service. |
| 5708 | "name": "A String", # Name describing the field. |
| 5709 | }, |
| 5710 | ], |
| 5711 | "excludedFields": [ # References to fields excluded from scanning. This allows you to skip |
| 5712 | # inspection of entire columns which you know have no findings. |
| 5713 | { # General identifier of a data field in a storage service. |
| 5714 | "name": "A String", # Name describing the field. |
| 5715 | }, |
| 5716 | ], |
| 5717 | }, |
| 5718 | "timespanConfig": { # Configuration of the timespan of the items to include in scanning. |
| 5719 | # Currently only supported when inspecting Google Cloud Storage and BigQuery. |
| 5720 | "timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items. |
| 5721 | # Used for data sources like Datastore and BigQuery. |
| 5722 | # |
| 5723 | # For BigQuery: |
| 5724 | # Required to filter out rows based on the given start and |
| 5725 | # end times. If not specified and the table was modified between the given |
| 5726 | # start and end times, the entire table will be scanned. |
| 5727 | # The valid data types of the timestamp field are: `INTEGER`, `DATE`, |
| 5728 | # `TIMESTAMP`, or `DATETIME` BigQuery column. |
| 5729 | # |
| 5730 | # For Datastore. |
| 5731 | # Valid data types of the timestamp field are: `TIMESTAMP`. |
| 5732 | # Datastore entity will be scanned if the timestamp property does not |
| 5733 | # exist or its value is empty or invalid. |
| 5734 | "name": "A String", # Name describing the field. |
| 5735 | }, |
| 5736 | "enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out |
| 5737 | # a valid start_time to avoid scanning files that have not been modified |
| 5738 | # since the last time the JobTrigger executed. This will be based on the |
| 5739 | # time of the execution of the last run of the JobTrigger. |
| 5740 | "startTime": "A String", # Exclude files or rows older than this value. |
| 5741 | "endTime": "A String", # Exclude files or rows newer than this value. |
| 5742 | # If set to zero, no upper time limit is applied. |
| 5743 | }, |
| 5744 | "datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options. |
| 5745 | "kind": { # A representation of a Datastore kind. # The kind to process. |
| 5746 | "name": "A String", # The name of the kind. |
| 5747 | }, |
| 5748 | "partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always |
| 5749 | # by project and namespace, however the namespace ID may be empty. |
| 5750 | # A partition ID identifies a grouping of entities. The grouping is always |
| 5751 | # by project and namespace, however the namespace ID may be empty. |
| 5752 | # |
| 5753 | # A partition ID contains several dimensions: |
| 5754 | # project ID and namespace ID. |
| 5755 | "namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong. |
| 5756 | "projectId": "A String", # The ID of the project to which the entities belong. |
| 5757 | }, |
| 5758 | }, |
| 5759 | "hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options. |
| 5760 | # Early access feature is in a pre-release state and might change or have |
| 5761 | # limited support. For more information, see |
| 5762 | # https://cloud.google.com/products#product-launch-stages. |
| 5763 | # of Google Cloud Platform. |
| 5764 | "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings |
| 5765 | # meaningful such as the columns that are primary keys. |
| 5766 | "identifyingFields": [ # The columns that are the primary keys for table objects included in |
| 5767 | # ContentItem. A copy of this cell's value will stored alongside alongside |
| 5768 | # each finding so that the finding can be traced to the specific row it came |
| 5769 | # from. No more than 3 may be provided. |
| 5770 | { # General identifier of a data field in a storage service. |
| 5771 | "name": "A String", # Name describing the field. |
| 5772 | }, |
| 5773 | ], |
| 5774 | }, |
| 5775 | "requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their |
| 5776 | # 'finding_labels' map. Request may contain others, but any missing one of |
| 5777 | # these will be rejected. |
| 5778 | # |
| 5779 | # Label keys must be between 1 and 63 characters long and must conform |
| 5780 | # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. |
| 5781 | # |
| 5782 | # No more than 10 keys can be required. |
| 5783 | "A String", |
| 5784 | ], |
| 5785 | "labels": { # To organize findings, these labels will be added to each finding. |
| 5786 | # |
| 5787 | # Label keys must be between 1 and 63 characters long and must conform |
| 5788 | # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`. |
| 5789 | # |
| 5790 | # Label values must be between 0 and 63 characters long and must conform |
| 5791 | # to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`. |
| 5792 | # |
| 5793 | # No more than 10 labels can be associated with a given finding. |
| 5794 | # |
| 5795 | # Examples: |
| 5796 | # * `"environment" : "production"` |
| 5797 | # * `"pipeline" : "etl"` |
| 5798 | "a_key": "A String", |
| 5799 | }, |
| 5800 | "description": "A String", # A short description of where the data is coming from. Will be stored once |
| 5801 | # in the job. 256 max length. |
| 5802 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5803 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5804 | "inspectConfig": { # Configuration description of the scanning process. # How and what to scan for. |
| 5805 | # When used with redactContent only info_types and min_likelihood are currently |
| 5806 | # used. |
| 5807 | "customInfoTypes": [ # CustomInfoTypes provided by the user. See |
| 5808 | # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more. |
| 5809 | { # Custom information type provided by the user. Used to find domain-specific |
| 5810 | # sensitive information configurable to the data in question. |
| 5811 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType. |
| 5812 | # be used to match sensitive information specific to the data, such as a list |
| 5813 | # of employee IDs or job titles. |
| 5814 | # |
| 5815 | # Dictionary words are case-insensitive and all characters other than letters |
| 5816 | # and digits in the unicode [Basic Multilingual |
| 5817 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 5818 | # will be replaced with whitespace when scanning for matches, so the |
| 5819 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 5820 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 5821 | # surrounding any match must be of a different type than the adjacent |
| 5822 | # characters within the word, so letters must be next to non-letters and |
| 5823 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 5824 | # match the first three letters of the text "jen123" but will return no |
| 5825 | # matches for "jennifer". |
| 5826 | # |
| 5827 | # Dictionary words containing a large number of characters that are not |
| 5828 | # letters or digits may result in unexpected findings because such characters |
| 5829 | # are treated as whitespace. The |
| 5830 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 5831 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 5832 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 5833 | # `StoredInfoType` API. |
| 5834 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 5835 | # is accepted. |
| 5836 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 5837 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 5838 | }, |
| 5839 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 5840 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 5841 | # at least one phrase and every phrase must contain at least 2 characters |
| 5842 | # that are letters or digits. [required] |
| 5843 | "A String", |
| 5844 | ], |
| 5845 | }, |
| 5846 | }, |
| 5847 | "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in |
| 5848 | # infoType, when the name matches one of existing infoTypes and that infoType |
| 5849 | # is specified in `InspectContent.info_types` field. Specifying the latter |
| 5850 | # adds findings to the one detected by the system. If built-in info type is |
| 5851 | # not specified in `InspectContent.info_types` list then the name is treated |
| 5852 | # as a custom info type. |
| 5853 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 5854 | # creating a CustomInfoType, or one of the names listed |
| 5855 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 5856 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 5857 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 5858 | }, |
| 5859 | "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be |
| 5860 | # altered by a detection rule if the finding meets the criteria specified by |
| 5861 | # the rule. Defaults to `VERY_LIKELY` if not specified. |
| 5862 | "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. |
| 5863 | # Rules are applied in order that they are specified. Not supported for the |
| 5864 | # `surrogate_type` CustomInfoType. |
| 5865 | { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a |
| 5866 | # `CustomInfoType` to alter behavior under certain circumstances, depending |
| 5867 | # on the specific details of the rule. Not supported for the `surrogate_type` |
| 5868 | # custom infoType. |
| 5869 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 5870 | # proximity of hotwords. |
| 5871 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 5872 | # The total length of the window cannot exceed 1000 characters. Note that |
| 5873 | # the finding itself will be included in the window, so that hotwords may |
| 5874 | # be used to match substrings of the finding itself. For example, the |
| 5875 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 5876 | # adjusted upwards if the area code is known to be the local area code of |
| 5877 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 5878 | # is the area code in question. |
| 5879 | # rule. |
| 5880 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 5881 | "windowBefore": 42, # Number of characters before the finding to consider. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5882 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5883 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 5884 | # part of a detection rule. |
| 5885 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 5886 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 5887 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 5888 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 5889 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 5890 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 5891 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 5892 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 5893 | # a final likelihood of `LIKELY`. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5894 | }, |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5895 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 5896 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 5897 | # specified, the entire match is returned. No more than 3 may be included. |
| 5898 | 42, |
| 5899 | ], |
| 5900 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 5901 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 5902 | # google/re2 repository on GitHub. |
| 5903 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5904 | }, |
| 5905 | }, |
| 5906 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5907 | "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that |
| 5908 | # support reversing. |
| 5909 | # such as |
| 5910 | # [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). |
| 5911 | # These types of transformations are |
| 5912 | # those that perform pseudonymization, thereby producing a "surrogate" as |
| 5913 | # output. This should be used in conjunction with a field on the |
| 5914 | # transformation such as `surrogate_info_type`. This CustomInfoType does |
| 5915 | # not support the use of `detection_rules`. |
| 5916 | }, |
| 5917 | "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType. |
| 5918 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 5919 | # specified, the entire match is returned. No more than 3 may be included. |
| 5920 | 42, |
| 5921 | ], |
| 5922 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 5923 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 5924 | # google/re2 repository on GitHub. |
| 5925 | }, |
| 5926 | "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in |
| 5927 | # `InspectDataSource`. Not currently supported in `InspectContent`. |
| 5928 | "name": "A String", # Resource name of the requested `StoredInfoType`, for example |
| 5929 | # `organizations/433245324/storedInfoTypes/432452342` or |
| 5930 | # `projects/project-id/storedInfoTypes/432452342`. |
| 5931 | "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for |
| 5932 | # inspection was created. Output-only field, populated by the system. |
| 5933 | }, |
| 5934 | "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding |
| 5935 | # to be returned. It still can be used for rules matching. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 5936 | }, |
| 5937 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 5938 | "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is |
| 5939 | # POSSIBLE. |
| 5940 | # See https://cloud.google.com/dlp/docs/likelihood to learn more. |
| 5941 | "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned. |
| 5942 | "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job. |
| 5943 | # When set within `InspectContentRequest`, the maximum returned is 2000 |
| 5944 | # regardless if this is set higher. |
| 5945 | "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes. |
| 5946 | { # Max findings configuration per infoType, per content item or long |
| 5947 | # running DlpJob. |
| 5948 | "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per |
| 5949 | # info_type should be provided. If InfoTypeLimit does not have an |
| 5950 | # info_type, the DLP API applies the limit against all info_types that |
| 5951 | # are found but not specified in another InfoTypeLimit. |
| 5952 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 5953 | # creating a CustomInfoType, or one of the names listed |
| 5954 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 5955 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 5956 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 5957 | }, |
| 5958 | "maxFindings": 42, # Max findings limit for the given infoType. |
| 5959 | }, |
| 5960 | ], |
| 5961 | "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned. |
| 5962 | # When set within `InspectJobConfig`, |
| 5963 | # the maximum returned is 2000 regardless if this is set higher. |
| 5964 | # When set within `InspectContentRequest`, this field is ignored. |
| 5965 | }, |
| 5966 | "excludeInfoTypes": True or False, # When true, excludes type information of the findings. |
| 5967 | "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is |
| 5968 | # included in the response; see Finding.quote. |
| 5969 | "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. |
| 5970 | # Exclusion rules, contained in the set are executed in the end, other |
| 5971 | # rules are executed in the order they are specified for each info type. |
| 5972 | { # Rule set for modifying a set of infoTypes to alter behavior under certain |
| 5973 | # circumstances, depending on the specific details of the rules within the set. |
| 5974 | "infoTypes": [ # List of infoTypes this rule set is applied to. |
| 5975 | { # Type of information detected by the API. |
| 5976 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 5977 | # creating a CustomInfoType, or one of the names listed |
| 5978 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 5979 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 5980 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 5981 | }, |
| 5982 | ], |
| 5983 | "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order. |
| 5984 | { # A single inspection rule to be applied to infoTypes, specified in |
| 5985 | # `InspectionRuleSet`. |
| 5986 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 5987 | # proximity of hotwords. |
| 5988 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 5989 | # The total length of the window cannot exceed 1000 characters. Note that |
| 5990 | # the finding itself will be included in the window, so that hotwords may |
| 5991 | # be used to match substrings of the finding itself. For example, the |
| 5992 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 5993 | # adjusted upwards if the area code is known to be the local area code of |
| 5994 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 5995 | # is the area code in question. |
| 5996 | # rule. |
| 5997 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 5998 | "windowBefore": 42, # Number of characters before the finding to consider. |
| 5999 | }, |
| 6000 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 6001 | # part of a detection rule. |
| 6002 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 6003 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 6004 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 6005 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 6006 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 6007 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 6008 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 6009 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 6010 | # a final likelihood of `LIKELY`. |
| 6011 | }, |
| 6012 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 6013 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 6014 | # specified, the entire match is returned. No more than 3 may be included. |
| 6015 | 42, |
| 6016 | ], |
| 6017 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 6018 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 6019 | # google/re2 repository on GitHub. |
| 6020 | }, |
| 6021 | }, |
| 6022 | "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule. |
| 6023 | # `InspectionRuleSet` are removed from results. |
| 6024 | "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details. |
| 6025 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule. |
| 6026 | # be used to match sensitive information specific to the data, such as a list |
| 6027 | # of employee IDs or job titles. |
| 6028 | # |
| 6029 | # Dictionary words are case-insensitive and all characters other than letters |
| 6030 | # and digits in the unicode [Basic Multilingual |
| 6031 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 6032 | # will be replaced with whitespace when scanning for matches, so the |
| 6033 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 6034 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 6035 | # surrounding any match must be of a different type than the adjacent |
| 6036 | # characters within the word, so letters must be next to non-letters and |
| 6037 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 6038 | # match the first three letters of the text "jen123" but will return no |
| 6039 | # matches for "jennifer". |
| 6040 | # |
| 6041 | # Dictionary words containing a large number of characters that are not |
| 6042 | # letters or digits may result in unexpected findings because such characters |
| 6043 | # are treated as whitespace. The |
| 6044 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 6045 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 6046 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 6047 | # `StoredInfoType` API. |
| 6048 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 6049 | # is accepted. |
| 6050 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 6051 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 6052 | }, |
| 6053 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 6054 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 6055 | # at least one phrase and every phrase must contain at least 2 characters |
| 6056 | # that are letters or digits. [required] |
| 6057 | "A String", |
| 6058 | ], |
| 6059 | }, |
| 6060 | }, |
| 6061 | "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule. |
| 6062 | "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or |
| 6063 | # contained within with a finding of an infoType from this list. For |
| 6064 | # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and |
| 6065 | # `exclusion_rule` containing `exclude_info_types.info_types` with |
| 6066 | # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap |
| 6067 | # with EMAIL_ADDRESS finding. |
| 6068 | # That leads to "555-222-2222@example.org" to generate only a single |
| 6069 | # finding, namely email address. |
| 6070 | { # Type of information detected by the API. |
| 6071 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 6072 | # creating a CustomInfoType, or one of the names listed |
| 6073 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 6074 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 6075 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 6076 | }, |
| 6077 | ], |
| 6078 | }, |
| 6079 | "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule. |
| 6080 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 6081 | # specified, the entire match is returned. No more than 3 may be included. |
| 6082 | 42, |
| 6083 | ], |
| 6084 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 6085 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 6086 | # google/re2 repository on GitHub. |
| 6087 | }, |
| 6088 | }, |
| 6089 | }, |
| 6090 | ], |
| 6091 | }, |
| 6092 | ], |
| 6093 | "contentOptions": [ # List of options defining data content to scan. |
| 6094 | # If empty, text, images, and other content will be included. |
| 6095 | "A String", |
| 6096 | ], |
| 6097 | "infoTypes": [ # Restricts what info_types to look for. The values must correspond to |
| 6098 | # InfoType values returned by ListInfoTypes or listed at |
| 6099 | # https://cloud.google.com/dlp/docs/infotypes-reference. |
| 6100 | # |
| 6101 | # When no InfoTypes or CustomInfoTypes are specified in a request, the |
| 6102 | # system may automatically choose what detectors to run. By default this may |
| 6103 | # be all types, but may change over time as detectors are updated. |
| 6104 | # |
| 6105 | # If you need precise control and predictability as to what detectors are |
| 6106 | # run you should specify specific InfoTypes listed in the reference, |
| 6107 | # otherwise a default list will be used, which may change over time. |
| 6108 | { # Type of information detected by the API. |
| 6109 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 6110 | # creating a CustomInfoType, or one of the names listed |
| 6111 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 6112 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 6113 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 6114 | }, |
| 6115 | ], |
| 6116 | }, |
| 6117 | }, |
| 6118 | "snapshotInspectTemplate": { # The inspectTemplate contains a configuration (set of types of sensitive data # If run with an InspectTemplate, a snapshot of its state at the time of |
| 6119 | # this run. |
| 6120 | # to be detected) to be used anywhere you otherwise would normally specify |
| 6121 | # InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates |
| 6122 | # to learn more. |
| 6123 | "description": "A String", # Short description (max 256 chars). |
| 6124 | "displayName": "A String", # Display name (max 256 chars). |
| 6125 | "createTime": "A String", # Output only. The creation timestamp of an inspectTemplate. |
| 6126 | "updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate. |
| 6127 | "name": "A String", # Output only. The template name. |
| 6128 | # |
| 6129 | # The template will have one of the following formats: |
| 6130 | # `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR |
| 6131 | # `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`; |
| 6132 | "inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process. |
| 6133 | # When used with redactContent only info_types and min_likelihood are currently |
| 6134 | # used. |
| 6135 | "customInfoTypes": [ # CustomInfoTypes provided by the user. See |
| 6136 | # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more. |
| 6137 | { # Custom information type provided by the user. Used to find domain-specific |
| 6138 | # sensitive information configurable to the data in question. |
| 6139 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType. |
| 6140 | # be used to match sensitive information specific to the data, such as a list |
| 6141 | # of employee IDs or job titles. |
| 6142 | # |
| 6143 | # Dictionary words are case-insensitive and all characters other than letters |
| 6144 | # and digits in the unicode [Basic Multilingual |
| 6145 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 6146 | # will be replaced with whitespace when scanning for matches, so the |
| 6147 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 6148 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 6149 | # surrounding any match must be of a different type than the adjacent |
| 6150 | # characters within the word, so letters must be next to non-letters and |
| 6151 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 6152 | # match the first three letters of the text "jen123" but will return no |
| 6153 | # matches for "jennifer". |
| 6154 | # |
| 6155 | # Dictionary words containing a large number of characters that are not |
| 6156 | # letters or digits may result in unexpected findings because such characters |
| 6157 | # are treated as whitespace. The |
| 6158 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 6159 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 6160 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 6161 | # `StoredInfoType` API. |
| 6162 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 6163 | # is accepted. |
| 6164 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 6165 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 6166 | }, |
| 6167 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 6168 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 6169 | # at least one phrase and every phrase must contain at least 2 characters |
| 6170 | # that are letters or digits. [required] |
| 6171 | "A String", |
| 6172 | ], |
| 6173 | }, |
| 6174 | }, |
| 6175 | "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in |
| 6176 | # infoType, when the name matches one of existing infoTypes and that infoType |
| 6177 | # is specified in `InspectContent.info_types` field. Specifying the latter |
| 6178 | # adds findings to the one detected by the system. If built-in info type is |
| 6179 | # not specified in `InspectContent.info_types` list then the name is treated |
| 6180 | # as a custom info type. |
| 6181 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 6182 | # creating a CustomInfoType, or one of the names listed |
| 6183 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 6184 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 6185 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 6186 | }, |
| 6187 | "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be |
| 6188 | # altered by a detection rule if the finding meets the criteria specified by |
| 6189 | # the rule. Defaults to `VERY_LIKELY` if not specified. |
| 6190 | "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType. |
| 6191 | # Rules are applied in order that they are specified. Not supported for the |
| 6192 | # `surrogate_type` CustomInfoType. |
| 6193 | { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a |
| 6194 | # `CustomInfoType` to alter behavior under certain circumstances, depending |
| 6195 | # on the specific details of the rule. Not supported for the `surrogate_type` |
| 6196 | # custom infoType. |
| 6197 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 6198 | # proximity of hotwords. |
| 6199 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 6200 | # The total length of the window cannot exceed 1000 characters. Note that |
| 6201 | # the finding itself will be included in the window, so that hotwords may |
| 6202 | # be used to match substrings of the finding itself. For example, the |
| 6203 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 6204 | # adjusted upwards if the area code is known to be the local area code of |
| 6205 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 6206 | # is the area code in question. |
| 6207 | # rule. |
| 6208 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 6209 | "windowBefore": 42, # Number of characters before the finding to consider. |
| 6210 | }, |
| 6211 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 6212 | # part of a detection rule. |
| 6213 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 6214 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 6215 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 6216 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 6217 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 6218 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 6219 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 6220 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 6221 | # a final likelihood of `LIKELY`. |
| 6222 | }, |
| 6223 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 6224 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 6225 | # specified, the entire match is returned. No more than 3 may be included. |
| 6226 | 42, |
| 6227 | ], |
| 6228 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 6229 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 6230 | # google/re2 repository on GitHub. |
| 6231 | }, |
| 6232 | }, |
| 6233 | }, |
| 6234 | ], |
| 6235 | "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that |
| 6236 | # support reversing. |
| 6237 | # such as |
| 6238 | # [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig). |
| 6239 | # These types of transformations are |
| 6240 | # those that perform pseudonymization, thereby producing a "surrogate" as |
| 6241 | # output. This should be used in conjunction with a field on the |
| 6242 | # transformation such as `surrogate_info_type`. This CustomInfoType does |
| 6243 | # not support the use of `detection_rules`. |
| 6244 | }, |
| 6245 | "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType. |
| 6246 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 6247 | # specified, the entire match is returned. No more than 3 may be included. |
| 6248 | 42, |
| 6249 | ], |
| 6250 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 6251 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 6252 | # google/re2 repository on GitHub. |
| 6253 | }, |
| 6254 | "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in |
| 6255 | # `InspectDataSource`. Not currently supported in `InspectContent`. |
| 6256 | "name": "A String", # Resource name of the requested `StoredInfoType`, for example |
| 6257 | # `organizations/433245324/storedInfoTypes/432452342` or |
| 6258 | # `projects/project-id/storedInfoTypes/432452342`. |
| 6259 | "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for |
| 6260 | # inspection was created. Output-only field, populated by the system. |
| 6261 | }, |
| 6262 | "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding |
| 6263 | # to be returned. It still can be used for rules matching. |
| 6264 | }, |
| 6265 | ], |
| 6266 | "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is |
| 6267 | # POSSIBLE. |
| 6268 | # See https://cloud.google.com/dlp/docs/likelihood to learn more. |
| 6269 | "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned. |
| 6270 | "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job. |
| 6271 | # When set within `InspectContentRequest`, the maximum returned is 2000 |
| 6272 | # regardless if this is set higher. |
| 6273 | "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes. |
| 6274 | { # Max findings configuration per infoType, per content item or long |
| 6275 | # running DlpJob. |
| 6276 | "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per |
| 6277 | # info_type should be provided. If InfoTypeLimit does not have an |
| 6278 | # info_type, the DLP API applies the limit against all info_types that |
| 6279 | # are found but not specified in another InfoTypeLimit. |
| 6280 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 6281 | # creating a CustomInfoType, or one of the names listed |
| 6282 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 6283 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 6284 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 6285 | }, |
| 6286 | "maxFindings": 42, # Max findings limit for the given infoType. |
| 6287 | }, |
| 6288 | ], |
| 6289 | "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned. |
| 6290 | # When set within `InspectJobConfig`, |
| 6291 | # the maximum returned is 2000 regardless if this is set higher. |
| 6292 | # When set within `InspectContentRequest`, this field is ignored. |
| 6293 | }, |
| 6294 | "excludeInfoTypes": True or False, # When true, excludes type information of the findings. |
| 6295 | "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is |
| 6296 | # included in the response; see Finding.quote. |
| 6297 | "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig. |
| 6298 | # Exclusion rules, contained in the set are executed in the end, other |
| 6299 | # rules are executed in the order they are specified for each info type. |
| 6300 | { # Rule set for modifying a set of infoTypes to alter behavior under certain |
| 6301 | # circumstances, depending on the specific details of the rules within the set. |
| 6302 | "infoTypes": [ # List of infoTypes this rule set is applied to. |
| 6303 | { # Type of information detected by the API. |
| 6304 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 6305 | # creating a CustomInfoType, or one of the names listed |
| 6306 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 6307 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 6308 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 6309 | }, |
| 6310 | ], |
| 6311 | "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order. |
| 6312 | { # A single inspection rule to be applied to infoTypes, specified in |
| 6313 | # `InspectionRuleSet`. |
| 6314 | "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule. |
| 6315 | # proximity of hotwords. |
| 6316 | "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside. |
| 6317 | # The total length of the window cannot exceed 1000 characters. Note that |
| 6318 | # the finding itself will be included in the window, so that hotwords may |
| 6319 | # be used to match substrings of the finding itself. For example, the |
| 6320 | # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be |
| 6321 | # adjusted upwards if the area code is known to be the local area code of |
| 6322 | # a company office using the hotword regex "\(xxx\)", where "xxx" |
| 6323 | # is the area code in question. |
| 6324 | # rule. |
| 6325 | "windowAfter": 42, # Number of characters after the finding to consider. |
| 6326 | "windowBefore": 42, # Number of characters before the finding to consider. |
| 6327 | }, |
| 6328 | "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings. |
| 6329 | # part of a detection rule. |
| 6330 | "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value. |
| 6331 | "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of |
| 6332 | # levels. For example, if a finding would be `POSSIBLE` without the |
| 6333 | # detection rule and `relative_likelihood` is 1, then it is upgraded to |
| 6334 | # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`. |
| 6335 | # Likelihood may never drop below `VERY_UNLIKELY` or exceed |
| 6336 | # `VERY_LIKELY`, so applying an adjustment of 1 followed by an |
| 6337 | # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in |
| 6338 | # a final likelihood of `LIKELY`. |
| 6339 | }, |
| 6340 | "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword. |
| 6341 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 6342 | # specified, the entire match is returned. No more than 3 may be included. |
| 6343 | 42, |
| 6344 | ], |
| 6345 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 6346 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 6347 | # google/re2 repository on GitHub. |
| 6348 | }, |
| 6349 | }, |
| 6350 | "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule. |
| 6351 | # `InspectionRuleSet` are removed from results. |
| 6352 | "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details. |
| 6353 | "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule. |
| 6354 | # be used to match sensitive information specific to the data, such as a list |
| 6355 | # of employee IDs or job titles. |
| 6356 | # |
| 6357 | # Dictionary words are case-insensitive and all characters other than letters |
| 6358 | # and digits in the unicode [Basic Multilingual |
| 6359 | # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) |
| 6360 | # will be replaced with whitespace when scanning for matches, so the |
| 6361 | # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson", |
| 6362 | # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters |
| 6363 | # surrounding any match must be of a different type than the adjacent |
| 6364 | # characters within the word, so letters must be next to non-letters and |
| 6365 | # digits next to non-digits. For example, the dictionary word "jen" will |
| 6366 | # match the first three letters of the text "jen123" but will return no |
| 6367 | # matches for "jennifer". |
| 6368 | # |
| 6369 | # Dictionary words containing a large number of characters that are not |
| 6370 | # letters or digits may result in unexpected findings because such characters |
| 6371 | # are treated as whitespace. The |
| 6372 | # [limits](https://cloud.google.com/dlp/limits) page contains details about |
| 6373 | # the size limits of dictionaries. For dictionaries that do not fit within |
| 6374 | # these constraints, consider using `LargeCustomDictionaryConfig` in the |
| 6375 | # `StoredInfoType` API. |
| 6376 | "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file |
| 6377 | # is accepted. |
| 6378 | "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage. |
| 6379 | # Example: gs://[BUCKET_NAME]/dictionary.txt |
| 6380 | }, |
| 6381 | "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for. |
| 6382 | "words": [ # Words or phrases defining the dictionary. The dictionary must contain |
| 6383 | # at least one phrase and every phrase must contain at least 2 characters |
| 6384 | # that are letters or digits. [required] |
| 6385 | "A String", |
| 6386 | ], |
| 6387 | }, |
| 6388 | }, |
| 6389 | "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule. |
| 6390 | "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or |
| 6391 | # contained within with a finding of an infoType from this list. For |
| 6392 | # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and |
| 6393 | # `exclusion_rule` containing `exclude_info_types.info_types` with |
| 6394 | # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap |
| 6395 | # with EMAIL_ADDRESS finding. |
| 6396 | # That leads to "555-222-2222@example.org" to generate only a single |
| 6397 | # finding, namely email address. |
| 6398 | { # Type of information detected by the API. |
| 6399 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 6400 | # creating a CustomInfoType, or one of the names listed |
| 6401 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 6402 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 6403 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 6404 | }, |
| 6405 | ], |
| 6406 | }, |
| 6407 | "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule. |
| 6408 | "groupIndexes": [ # The index of the submatch to extract as findings. When not |
| 6409 | # specified, the entire match is returned. No more than 3 may be included. |
| 6410 | 42, |
| 6411 | ], |
| 6412 | "pattern": "A String", # Pattern defining the regular expression. Its syntax |
| 6413 | # (https://github.com/google/re2/wiki/Syntax) can be found under the |
| 6414 | # google/re2 repository on GitHub. |
| 6415 | }, |
| 6416 | }, |
| 6417 | }, |
| 6418 | ], |
| 6419 | }, |
| 6420 | ], |
| 6421 | "contentOptions": [ # List of options defining data content to scan. |
| 6422 | # If empty, text, images, and other content will be included. |
| 6423 | "A String", |
| 6424 | ], |
| 6425 | "infoTypes": [ # Restricts what info_types to look for. The values must correspond to |
| 6426 | # InfoType values returned by ListInfoTypes or listed at |
| 6427 | # https://cloud.google.com/dlp/docs/infotypes-reference. |
| 6428 | # |
| 6429 | # When no InfoTypes or CustomInfoTypes are specified in a request, the |
| 6430 | # system may automatically choose what detectors to run. By default this may |
| 6431 | # be all types, but may change over time as detectors are updated. |
| 6432 | # |
| 6433 | # If you need precise control and predictability as to what detectors are |
| 6434 | # run you should specify specific InfoTypes listed in the reference, |
| 6435 | # otherwise a default list will be used, which may change over time. |
| 6436 | { # Type of information detected by the API. |
| 6437 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 6438 | # creating a CustomInfoType, or one of the names listed |
| 6439 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 6440 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 6441 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 6442 | }, |
| 6443 | ], |
| 6444 | }, |
| 6445 | }, |
| 6446 | }, |
| 6447 | "result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspect job. |
| 6448 | "hybridStats": { # Statistics related to processing hybrid inspect requests. # Statistics related to the processing of hybrid inspect. |
| 6449 | # Early access feature is in a pre-release state and might change or have |
| 6450 | # limited support. For more information, see |
| 6451 | # https://cloud.google.com/products#product-launch-stages. |
| 6452 | "processedCount": "A String", # The number of hybrid inspection requests processed within this job. |
| 6453 | "abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran |
| 6454 | # out of quota or was ended before they could be processed. |
| 6455 | "pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated |
| 6456 | # when called via method `getDlpJob`. |
| 6457 | # A burst of traffic may cause hybrid inspect requests to be enqueued. |
| 6458 | # Processing will take place as quickly as possible, but resource limitations |
| 6459 | # may impact how long a request is enqueued for. |
| 6460 | }, |
| 6461 | "totalEstimatedBytes": "A String", # Estimate of the number of bytes to process. |
| 6462 | "infoTypeStats": [ # Statistics of how many instances of each info type were found during |
| 6463 | # inspect job. |
| 6464 | { # Statistics regarding a specific InfoType. |
| 6465 | "infoType": { # Type of information detected by the API. # The type of finding this stat is for. |
| 6466 | "name": "A String", # Name of the information type. Either a name of your choosing when |
| 6467 | # creating a CustomInfoType, or one of the names listed |
| 6468 | # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying |
| 6469 | # a built-in type. When sending Cloud DLP results to Data Catalog, infoType |
| 6470 | # names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`. |
| 6471 | }, |
| 6472 | "count": "A String", # Number of findings for this infoType. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 6473 | }, |
| 6474 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 6475 | "processedBytes": "A String", # Total size in bytes that were processed. |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 6476 | }, |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 6477 | }, |
| Bu Sun Kim | 4ed7d3f | 2020-05-27 12:20:54 -0700 | [diff] [blame] | 6478 | "name": "A String", # The server-assigned name. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 6479 | }, |
| 6480 | ], |
| Bu Sun Kim | d059ad8 | 2020-07-22 17:02:09 -0700 | [diff] [blame^] | 6481 | "nextPageToken": "A String", # The standard List next-page token. |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 6482 | }</pre> |
| 6483 | </div> |
| 6484 | |
| 6485 | <div class="method"> |
| 6486 | <code class="details" id="list_next">list_next(previous_request, previous_response)</code> |
| 6487 | <pre>Retrieves the next page of results. |
| 6488 | |
| 6489 | Args: |
| 6490 | previous_request: The request for the previous page. (required) |
| 6491 | previous_response: The response from the request for the previous page. (required) |
| 6492 | |
| 6493 | Returns: |
| Bu Sun Kim | 6502091 | 2020-05-20 12:08:20 -0700 | [diff] [blame] | 6494 | A request object that you can call 'execute()' on to request the next |
| Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 6495 | page. Returns None if there are no more items in the collection. |
| 6496 | </pre> |
| 6497 | </div> |
| 6498 | |
| 6499 | </body></html> |