Blame - docs/dyn/dlp_v2.projects.dlpJobs.html - platform/external/python/google-api-python-client

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

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

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

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

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

90

<code><a href="#list">list(parent, pageSize=None, filter=None, type=None, orderBy=None, pageToken=None, locationId=None, x__xgafv=None)</a></code></p>

Bu Sun Kim

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

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

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

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

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.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

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 `{}`.

}</pre>

</div>

Dan O'Meara

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

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:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

143

parent: string, Required. The parent resource name, for example projects/my-project-id. (required)

144

body: object, The request body.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

145

The object takes the form of:

146

147

{ # Request message for CreateDlpJobRequest. Used to initiate long running

148

# jobs such as calculating risk metrics or inspecting Google Cloud

149

# Storage.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

150

"jobId": "A String", # The job id can contain uppercase and lowercase letters,

151

# numbers, and hyphens; that is, it must match the regular

152

# expression: `[a-zA-Z\\d-_]+`. The maximum length is 100

153

# characters. Can be empty to allow the system to generate one.

154

"locationId": "A String", # The geographic location to store and process the job. Reserved for

155

# future extensions.

156

"inspectJob": { # Controls what and how to inspect for findings. # Set to control what and how to inspect.

157

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

158

# When used with redactContent only info_types and min_likelihood are currently

159

# used.

160

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

161

# included in the response; see Finding.quote.

162

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

163

# Exclusion rules, contained in the set are executed in the end, other

164

# rules are executed in the order they are specified for each info type.

165

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

166

# circumstances, depending on the specific details of the rules within the set.

167

"infoTypes": [ # List of infoTypes this rule set is applied to.

168

{ # Type of information detected by the API.

169

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

170

# creating a CustomInfoType, or one of the names listed

171

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

172

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

173

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

174

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

175

],

176

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

177

{ # A single inspection rule to be applied to infoTypes, specified in

178

# `InspectionRuleSet`.

179

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

180

# proximity of hotwords.

181

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

182

# part of a detection rule.

183

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

184

# levels. For example, if a finding would be `POSSIBLE` without the

185

# detection rule and `relative_likelihood` is 1, then it is upgraded to

186

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

187

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

188

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

189

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

190

# a final likelihood of `LIKELY`.

191

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

192

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

193

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

194

"groupIndexes": [ # The index of the submatch to extract as findings. When not

195

# specified, the entire match is returned. No more than 3 may be included.

196

42,

197

],

198

"pattern": "A String", # Pattern defining the regular expression. Its syntax

199

# (https://github.com/google/re2/wiki/Syntax) can be found under the

200

# google/re2 repository on GitHub.

201

},

202

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

203

# The total length of the window cannot exceed 1000 characters. Note that

204

# the finding itself will be included in the window, so that hotwords may

205

# be used to match substrings of the finding itself. For example, the

206

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

207

# adjusted upwards if the area code is known to be the local area code of

208

# a company office using the hotword regex "\(xxx\)", where "xxx"

209

# is the area code in question.

210

# rule.

211

"windowBefore": 42, # Number of characters before the finding to consider.

212

"windowAfter": 42, # Number of characters after the finding to consider.

213

},

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

214

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

215

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

216

# `InspectionRuleSet` are removed from results.

217

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

218

# be used to match sensitive information specific to the data, such as a list

219

# of employee IDs or job titles.

220

#

221

# Dictionary words are case-insensitive and all characters other than letters

222

# and digits in the unicode [Basic Multilingual

223

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

224

# will be replaced with whitespace when scanning for matches, so the

225

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

226

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

227

# surrounding any match must be of a different type than the adjacent

228

# characters within the word, so letters must be next to non-letters and

229

# digits next to non-digits. For example, the dictionary word "jen" will

230

# match the first three letters of the text "jen123" but will return no

231

# matches for "jennifer".

232

#

233

# Dictionary words containing a large number of characters that are not

234

# letters or digits may result in unexpected findings because such characters

235

# are treated as whitespace. The

236

# [limits](https://cloud.google.com/dlp/limits) page contains details about

237

# the size limits of dictionaries. For dictionaries that do not fit within

238

# these constraints, consider using `LargeCustomDictionaryConfig` in the

239

# `StoredInfoType` API.

240

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

241

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

242

# at least one phrase and every phrase must contain at least 2 characters

243

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

248

# is accepted.

249

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

250

# Example: gs://[BUCKET_NAME]/dictionary.txt

251

},

252

},

253

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

254

"groupIndexes": [ # The index of the submatch to extract as findings. When not

255

# specified, the entire match is returned. No more than 3 may be included.

256

42,

257

],

258

"pattern": "A String", # Pattern defining the regular expression. Its syntax

259

# (https://github.com/google/re2/wiki/Syntax) can be found under the

260

# google/re2 repository on GitHub.

261

},

262

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

263

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

264

# contained within with a finding of an infoType from this list. For

265

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

266

# `exclusion_rule` containing `exclude_info_types.info_types` with

267

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

268

# with EMAIL_ADDRESS finding.

269

# That leads to "555-222-2222@example.org" to generate only a single

270

# finding, namely email address.

271

{ # Type of information detected by the API.

272

"name": "A String", # Name of the information type. Either a name of your choosing when

273

# creating a CustomInfoType, or one of the names listed

274

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

275

# a built-in type. InfoType names should conform to the pattern

276

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

281

},

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

282

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

283

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

284

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

285

],

286

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

287

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

288

# When set within `InspectJobConfig`,

289

# the maximum returned is 2000 regardless if this is set higher.

290

# When set within `InspectContentRequest`, this field is ignored.

291

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

292

{ # Max findings configuration per infoType, per content item or long

293

# running DlpJob.

294

"maxFindings": 42, # Max findings limit for the given infoType.

295

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

296

# info_type should be provided. If InfoTypeLimit does not have an

297

# info_type, the DLP API applies the limit against all info_types that

298

# are found but not specified in another InfoTypeLimit.

299

"name": "A String", # Name of the information type. Either a name of your choosing when

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

300

# creating a CustomInfoType, or one of the names listed

301

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

302

# a built-in type. InfoType names should conform to the pattern

303

# `[a-zA-Z0-9_]{1,64}`.

304

},

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

305

},

306

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

307

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

308

# When set within `InspectContentRequest`, the maximum returned is 2000

309

# regardless if this is set higher.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

310

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

311

"contentOptions": [ # List of options defining data content to scan.

312

# If empty, text, images, and other content will be included.

313

"A String",

314

],

315

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

316

# InfoType values returned by ListInfoTypes or listed at

317

# https://cloud.google.com/dlp/docs/infotypes-reference.

318

#

319

# When no InfoTypes or CustomInfoTypes are specified in a request, the

320

# system may automatically choose what detectors to run. By default this may

321

# be all types, but may change over time as detectors are updated.

322

#

323

# If you need precise control and predictability as to what detectors are

324

# run you should specify specific InfoTypes listed in the reference,

325

# otherwise a default list will be used, which may change over time.

326

{ # Type of information detected by the API.

327

"name": "A String", # Name of the information type. Either a name of your choosing when

328

# creating a CustomInfoType, or one of the names listed

329

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

330

# a built-in type. InfoType names should conform to the pattern

331

# `[a-zA-Z0-9_]{1,64}`.

332

},

333

],

334

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

335

# POSSIBLE.

336

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

337

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

338

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

339

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

340

{ # Custom information type provided by the user. Used to find domain-specific

341

# sensitive information configurable to the data in question.

342

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

343

# altered by a detection rule if the finding meets the criteria specified by

344

# the rule. Defaults to `VERY_LIKELY` if not specified.

345

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

346

# infoType, when the name matches one of existing infoTypes and that infoType

347

# is specified in `InspectContent.info_types` field. Specifying the latter

348

# adds findings to the one detected by the system. If built-in info type is

349

# not specified in `InspectContent.info_types` list then the name is treated

350

# as a custom info type.

351

"name": "A String", # Name of the information type. Either a name of your choosing when

352

# creating a CustomInfoType, or one of the names listed

353

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

354

# a built-in type. InfoType names should conform to the pattern

355

# `[a-zA-Z0-9_]{1,64}`.

356

},

357

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

358

"groupIndexes": [ # The index of the submatch to extract as findings. When not

359

# specified, the entire match is returned. No more than 3 may be included.

360

42,

361

],

362

"pattern": "A String", # Pattern defining the regular expression. Its syntax

363

# (https://github.com/google/re2/wiki/Syntax) can be found under the

364

# google/re2 repository on GitHub.

365

},

366

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

367

# Rules are applied in order that they are specified. Not supported for the

368

# `surrogate_type` CustomInfoType.

369

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

370

# `CustomInfoType` to alter behavior under certain circumstances, depending

371

# on the specific details of the rule. Not supported for the `surrogate_type`

372

# custom infoType.

373

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

374

# proximity of hotwords.

375

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

376

# part of a detection rule.

377

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

378

# levels. For example, if a finding would be `POSSIBLE` without the

379

# detection rule and `relative_likelihood` is 1, then it is upgraded to

380

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

381

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

382

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

383

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

384

# a final likelihood of `LIKELY`.

385

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

386

},

387

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

388

"groupIndexes": [ # The index of the submatch to extract as findings. When not

389

# specified, the entire match is returned. No more than 3 may be included.

390

42,

391

],

392

"pattern": "A String", # Pattern defining the regular expression. Its syntax

393

# (https://github.com/google/re2/wiki/Syntax) can be found under the

394

# google/re2 repository on GitHub.

395

},

396

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

397

# The total length of the window cannot exceed 1000 characters. Note that

398

# the finding itself will be included in the window, so that hotwords may

399

# be used to match substrings of the finding itself. For example, the

400

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

401

# adjusted upwards if the area code is known to be the local area code of

402

# a company office using the hotword regex "\(xxx\)", where "xxx"

403

# is the area code in question.

404

# rule.

405

"windowBefore": 42, # Number of characters before the finding to consider.

406

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

412

# to be returned. It still can be used for rules matching.

413

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

414

# be used to match sensitive information specific to the data, such as a list

415

# of employee IDs or job titles.

416

#

417

# Dictionary words are case-insensitive and all characters other than letters

418

# and digits in the unicode [Basic Multilingual

419

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

420

# will be replaced with whitespace when scanning for matches, so the

421

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

422

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

423

# surrounding any match must be of a different type than the adjacent

424

# characters within the word, so letters must be next to non-letters and

425

# digits next to non-digits. For example, the dictionary word "jen" will

426

# match the first three letters of the text "jen123" but will return no

427

# matches for "jennifer".

428

#

429

# Dictionary words containing a large number of characters that are not

430

# letters or digits may result in unexpected findings because such characters

431

# are treated as whitespace. The

432

# [limits](https://cloud.google.com/dlp/limits) page contains details about

433

# the size limits of dictionaries. For dictionaries that do not fit within

434

# these constraints, consider using `LargeCustomDictionaryConfig` in the

435

# `StoredInfoType` API.

436

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

437

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

438

# at least one phrase and every phrase must contain at least 2 characters

439

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

444

# is accepted.

445

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

446

# Example: gs://[BUCKET_NAME]/dictionary.txt

447

},

448

},

449

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

450

# `InspectDataSource`. Not currently supported in `InspectContent`.

451

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

452

# `organizations/433245324/storedInfoTypes/432452342` or

453

# `projects/project-id/storedInfoTypes/432452342`.

454

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

455

# inspection was created. Output-only field, populated by the system.

456

},

457

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

458

# support reversing.

459

# such as

460

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

461

# These types of transformations are

462

# those that perform pseudonymization, thereby producing a "surrogate" as

463

# output. This should be used in conjunction with a field on the

464

# transformation such as `surrogate_info_type`. This CustomInfoType does

465

# not support the use of `detection_rules`.

466

},

467

},

468

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

469

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

470

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

471

{ # A task to execute on the completion of a job.

472

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

473

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

474

# Command Center (CSCC Alpha).

475

# This action is only available for projects which are parts of

476

# an organization and whitelisted for the alpha Cloud Security Command

477

# Center.

478

# The action will publish count of finding instances and their info types.

479

# The summary of findings will be persisted in CSCC and are governed by CSCC

480

# service-specific policy, see https://cloud.google.com/terms/service-terms

481

# Only a single instance of this action can be specified.

482

# Compatible with: Inspect

483

},

484

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

485

# completion/failure.

486

# completion/failure.

487

},

488

"saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

489

# OutputStorageConfig. Only a single instance of this action can be

490

# specified.

491

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

492

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

493

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

494

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

495

# from the `Finding` object. If appending to an existing table, any columns

496

# from the predefined schema that are missing will be added. No columns in

497

# the existing table will be deleted.

498

#

499

# If unspecified, then all available columns will be used for a new table or

500

# an (existing) table with no schema, and no changes will be made to an

501

# existing table that has a schema.

502

# Only for use with external storage.

503

"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

2019-06-14 16:50:42 -0700

[diff] [blame]

504

# dataset. If table_id is not set a new one will be generated

505

# for you with the following format:

506

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

507

# generating the date details.

508

#

509

# For Inspect, each column in an existing output table must have the same

510

# name, type, and mode of a field in the `Finding` object.

511

#

512

# For Risk, an existing output table should be the output of a previous

513

# Risk analysis job run on the same source table, with the same privacy

514

# metric and quasi-identifiers. Risk jobs that analyze the same table but

515

# compute a different privacy metric, or use different sets of

516

# quasi-identifiers, cannot store their results in the same table.

517

# identified by its project_id, dataset_id, and table_name. Within a query

518

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

519

# `<project_id>:<dataset_id>.<table_id>` or

520

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

521

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

522

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

523

"datasetId": "A String", # Dataset ID of the table.

524

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

525

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

526

},

527

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

528

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

529

# message contains a single field, `DlpJobName`, which is equal to the

530

# finished job's

531

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

532

# Compatible with: Inspect, Risk

533

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

534

# publishing access rights to the DLP API service account executing

535

# the long running DlpJob sending the notifications.

536

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

537

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

538

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

539

# results of the DlpJob will be applied to the entry for the resource scanned

540

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

541

# be deleted. InfoType naming patterns are strictly enforced when using this

542

# feature. Note that the findings will be persisted in Cloud Data Catalog

543

# storage and are governed by Data Catalog service-specific policy, see

544

# https://cloud.google.com/terms/service-terms

545

# Only a single instance of this action can be specified and only allowed if

546

# all resources being scanned are BigQuery tables.

547

# Compatible with: Inspect

548

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

549

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

550

# will publish a metric to stack driver on each infotype requested and

551

# how many findings were found for it. CustomDetectors will be bucketed

552

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

553

},

554

},

555

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

556

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

557

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

558

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

559

# by project and namespace, however the namespace ID may be empty.

560

# A partition ID identifies a grouping of entities. The grouping is always

561

# by project and namespace, however the namespace ID may be empty.

562

#

563

# A partition ID contains several dimensions:

564

# project ID and namespace ID.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

565

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

566

"projectId": "A String", # The ID of the project to which the entities belong.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

567

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

568

"kind": { # A representation of a Datastore kind. # The kind to process.

569

"name": "A String", # The name of the kind.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

570

},

571

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

572

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

573

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

574

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

575

# Used for data sources like Datastore and BigQuery.

576

#

577

# For BigQuery:

578

# Required to filter out rows based on the given start and

579

# end times. If not specified and the table was modified between the given

580

# start and end times, the entire table will be scanned.

581

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

582

# `TIMESTAMP`, or `DATETIME` BigQuery column.

583

#

584

# For Datastore.

585

# Valid data types of the timestamp field are: `TIMESTAMP`.

586

# Datastore entity will be scanned if the timestamp property does not

587

# exist or its value is empty or invalid.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

588

"name": "A String", # Name describing the field.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

589

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

590

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

591

# a valid start_time to avoid scanning files that have not been modified

592

# since the last time the JobTrigger executed. This will be based on the

593

# time of the execution of the last run of the JobTrigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

594

"endTime": "A String", # Exclude files or rows newer than this value.

595

# If set to zero, no upper time limit is applied.

596

"startTime": "A String", # Exclude files or rows older than this value.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

597

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

598

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

599

# bucket.

600

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

601

# Number of files scanned is rounded down. Must be between 0 and 100,

602

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

603

"fileTypes": [ # List of file type groups to include in the scan.

604

# If empty, all files are scanned and available data format processors

605

# are applied. In addition, the binary content of the selected files

606

# is always scanned as well.

607

# Images are scanned only as binary if the specified region

608

# does not support image inspection and no file_types were specified.

609

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

610

"A String",

611

],

612

"sampleMethod": "A String",

613

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

614

# number of bytes scanned is rounded down. Must be between 0 and 100,

615

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

616

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

617

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

618

# than this value then the rest of the bytes are omitted. Only one

619

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

620

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

621

"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

622

# `regex_file_set` must be set.

623

# expressions are used to allow fine-grained control over which files in the

624

# bucket to include.

625

#

626

# Included files are those that match at least one item in `include_regex` and

627

# do not match any items in `exclude_regex`. Note that a file that matches

628

# items from both lists will _not_ be included. For a match to occur, the

629

# entire file path (i.e., everything in the url after the bucket name) must

630

# match the regular expression.

631

#

632

# For example, given the input `{bucket_name: "mybucket", include_regex:

633

# ["directory1/.*"], exclude_regex:

634

# ["directory1/excluded.*"]}`:

635

#

636

# * `gs://mybucket/directory1/myfile` will be included

637

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

638

# across `/`)

639

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

640

# full path doesn't match any items in `include_regex`)

641

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

642

# matches an item in `exclude_regex`)

643

#

644

# If `include_regex` is left empty, it will match all files by default

645

# (this is equivalent to setting `include_regex: [".*"]`).

646

#

647

# Some other common use cases:

648

#

649

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

650

# files in `mybucket` except for .pdf files

651

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

652

# include all files directly under `gs://mybucket/directory/`, without matching

653

# across `/`

654

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

655

# the bucket that match at least one of these regular expressions will be

656

# excluded from the scan.

657

#

658

# Regular expressions use RE2

659

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

660

# under the google/re2 repository on GitHub.

661

"A String",

662

],

663

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

664

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

665

# the bucket that match at least one of these regular expressions will be

666

# included in the set of files, except for those that also match an item in

667

# `exclude_regex`. Leaving this field empty will match all files by default

668

# (this is equivalent to including `.*` in the list).

669

#

670

# Regular expressions use RE2

671

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

672

# under the google/re2 repository on GitHub.

"A String",

],

},

"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format

677

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

678

#

679

# If the url ends in a trailing slash, the bucket or directory represented

680

# by the url will be scanned non-recursively (content in sub-directories

681

# will not be scanned). This means that `gs://mybucket/` is equivalent to

682

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

683

# `gs://mybucket/directory/*`.

684

#

685

# Exactly one of `url` or `regex_file_set` must be set.

686

},

687

},

688

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

689

"sampleMethod": "A String",

690

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

691

# identified by its project_id, dataset_id, and table_name. Within a query

692

# a table is often referenced with a string in the format of:

693

# `<project_id>:<dataset_id>.<table_id>` or

694

# `<project_id>.<dataset_id>.<table_id>`.

695

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

696

# If omitted, project ID is inferred from the API call.

697

"datasetId": "A String", # Dataset ID of the table.

698

"tableId": "A String", # Name of the table.

699

},

700

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

701

# `actions.saveFindings.outputConfig.table` is specified, the values of

702

# columns specified here are available in the output table under

703

# `location.content_locations.record_location.record_key.id_values`. Nested

704

# fields such as `person.birthdate.year` are allowed.

705

{ # General identifier of a data field in a storage service.

706

"name": "A String", # Name describing the field.

707

},

708

],

709

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

710

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

711

# 100 means no limit. Defaults to 0. Only one of rows_limit and

712

# rows_limit_percent can be specified. Cannot be used in conjunction with

713

# TimespanConfig.

714

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

715

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

716

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

717

# Cannot be used in conjunction with TimespanConfig.

718

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

719

# inspection of entire columns which you know have no findings.

720

{ # General identifier of a data field in a storage service.

721

"name": "A String", # Name describing the field.

},

],

},

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

726

# Early access feature is in a pre-release state and might change or have

727

# limited support. For more information, see

728

# https://cloud.google.com/products#product-launch-stages.

729

# of Google Cloud Platform.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

730

"labels": { # To organize findings, these labels will be added to each finding.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

731

#

732

# Label keys must be between 1 and 63 characters long and must conform

733

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

734

#

735

# Label values must be between 0 and 63 characters long and must conform

736

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

737

#

738

# No more than 10 labels can be associated with a given finding.

739

#

740

# Examples:

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

741

# * `"environment" : "production"`

742

# * `"pipeline" : "etl"`

743

"a_key": "A String",

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

744

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

745

"description": "A String", # A short description of where the data is coming from. Will be stored once

746

# in the job. 256 max length.

747

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

748

# meaningful such as the columns that are primary keys.

749

"identifyingFields": [ # The columns that are the primary keys for table objects included in

750

# ContentItem. A copy of this cell's value will stored alongside alongside

751

# each finding so that the finding can be traced to the specific row it came

752

# from. No more than 3 may be provided.

753

{ # General identifier of a data field in a storage service.

754

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

759

# 'finding_labels' map. Request may contain others, but any missing one of

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

760

# these will be rejected.

761

#

762

# Label keys must be between 1 and 63 characters long and must conform

763

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

764

#

765

# No more than 10 keys can be required.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

766

"A String",

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

767

],

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

768

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

769

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

770

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

771

# `inspect_config` will be merged into the values persisted as part of the

772

# template.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

773

},

774

"riskJob": { # Configuration for a risk analysis job. See # Set to choose what metric to calculate.

775

# https://cloud.google.com/dlp/docs/concepts-risk-analysis to learn more.

776

"privacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.

777

"categoricalStatsConfig": { # Compute numerical stats over an individual column, including # Categorical stats

778

# number of distinct values and value count distribution.

779

"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are

780

# supported except for arrays and structs. However, it may be more

781

# informative to use NumericalStats when the field type is supported,

782

# depending on the data.

783

"name": "A String", # Name describing the field.

784

},

785

},

786

"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity

787

"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are

788

# specified, they are considered a single composite key. Structs and

789

# repeated data types are not supported; however, nested fields are

790

# supported so long as they are not structs themselves or nested within

791

# a repeated field.

792

{ # General identifier of a data field in a storage service.

793

"name": "A String", # Name describing the field.

794

},

795

],

796

"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

797

# single individual. If the same entity_id is associated to multiple

798

# quasi-identifier tuples over distinct rows, we consider the entire

799

# collection of tuples as the composite quasi-identifier. This collection

800

# is a multiset: the order in which the different tuples appear in the

801

# dataset is ignored, but their frequency is taken into account.

802

#

803

# Important note: a maximum of 1000 rows can be associated to a single

804

# entity ID. If more rows are associated with the same entity ID, some

805

# might be ignored.

806

# single person. For example, in medical records the `EntityId` might be a

807

# patient identifier, or for financial records it might be an account

808

# identifier. This message is used when generalizations or analysis must take

809

# into account that multiple rows correspond to the same entity.

810

"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.

811

"name": "A String", # Name describing the field.

},

},

},

"numericalStatsConfig": { # Compute numerical stats over an individual column, including # Numerical stats

816

# min, max, and quantiles.

817

"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are

818

# integer, float, date, datetime, timestamp, time.

819

"name": "A String", # Name describing the field.

820

},

821

},

822

"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what # k-map

823

# is called "journalist risk" in the literature, except the attack dataset is

824

# statistically modeled instead of being perfectly known. This can be done

825

# using publicly available data (like the US Census), or using a custom

826

# statistical model (indicated as one or several BigQuery tables), or by

827

# extrapolating from the distribution of values in the input dataset.

828

"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.

829

# Set if no column is tagged with a region-specific InfoType (like

830

# US_ZIP_5) or a region code.

831

"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag

832

# used to tag a quasi-identifiers column must appear in exactly one column

833

# of one auxiliary table.

834

{ # An auxiliary table contains statistical information on the relative

835

# frequency of different quasi-identifiers values. It has one or several

836

# quasi-identifiers columns, and one column that indicates the relative

837

# frequency of each quasi-identifier tuple.

838

# If a tuple is present in the data but not in the auxiliary table, the

839

# corresponding relative frequency is assumed to be zero (and thus, the

840

# tuple is highly reidentifiable).

841

"table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location.

842

# identified by its project_id, dataset_id, and table_name. Within a query

843

# a table is often referenced with a string in the format of:

844

# `<project_id>:<dataset_id>.<table_id>` or

845

# `<project_id>.<dataset_id>.<table_id>`.

846

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

847

# If omitted, project ID is inferred from the API call.

848

"datasetId": "A String", # Dataset ID of the table.

849

"tableId": "A String", # Name of the table.

850

},

851

"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number

852

# between 0 and 1 (inclusive). Null values are assumed to be zero.

853

"name": "A String", # Name describing the field.

854

},

855

"quasiIds": [ # Required. Quasi-identifier columns.

856

{ # A quasi-identifier column has a custom_tag, used to know which column

857

# in the data corresponds to which column in the statistical model.

858

"customTag": "A String", # A auxiliary field.

859

"field": { # General identifier of a data field in a storage service. # Identifies the column.

860

"name": "A String", # Name describing the field.

},

},

],

},

],

"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the

867

# same tag.

868

{ # A column with a semantic tag attached.

869

"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.

870

"name": "A String", # Name describing the field.

871

},

872

"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public

873

# dataset as a statistical model of population, if available. We

874

# currently support US ZIP codes, region codes, ages and genders.

875

# To programmatically obtain the list of supported InfoTypes, use

876

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

877

"name": "A String", # Name of the information type. Either a name of your choosing when

878

# creating a CustomInfoType, or one of the names listed

879

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

880

# a built-in type. InfoType names should conform to the pattern

881

# `[a-zA-Z0-9_]{1,64}`.

882

},

883

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

884

# indicate an auxiliary table that contains statistical information on

885

# the possible values of this column (below).

886

"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

887

# the distribution of values in the input data

888

# empty messages in your APIs. A typical example is to use it as the request

889

# or the response type of an API method. For instance:

890

#

891

# service Foo {

892

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

893

# }

894

#

895

# The JSON representation for `Empty` is empty JSON object `{}`.

},

},

],

},

"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity

901

"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are

902

# defined for the l-diversity computation. When multiple fields are

903

# specified, they are considered a single composite key.

904

{ # General identifier of a data field in a storage service.

905

"name": "A String", # Name describing the field.

906

},

907

],

908

"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.

909

"name": "A String", # Name describing the field.

910

},

911

},

912

"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to # delta-presence

913

# figure out that one given individual appears in a de-identified dataset.

914

# Similarly to the k-map metric, we cannot compute δ-presence exactly without

915

# knowing the attack dataset, so we use a statistical model instead.

916

"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the

917

# same tag.

918

{ # A column with a semantic tag attached.

919

"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.

920

"name": "A String", # Name describing the field.

921

},

922

"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public

923

# dataset as a statistical model of population, if available. We

924

# currently support US ZIP codes, region codes, ages and genders.

925

# To programmatically obtain the list of supported InfoTypes, use

926

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

927

"name": "A String", # Name of the information type. Either a name of your choosing when

928

# creating a CustomInfoType, or one of the names listed

929

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

930

# a built-in type. InfoType names should conform to the pattern

931

# `[a-zA-Z0-9_]{1,64}`.

932

},

933

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

934

# indicate an auxiliary table that contains statistical information on

935

# the possible values of this column (below).

936

"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

937

# the distribution of values in the input data

938

# empty messages in your APIs. A typical example is to use it as the request

939

# or the response type of an API method. For instance:

940

#

941

# service Foo {

942

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

943

# }

944

#

945

# The JSON representation for `Empty` is empty JSON object `{}`.

},

},

],

"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.

950

# Set if no column is tagged with a region-specific InfoType (like

951

# US_ZIP_5) or a region code.

952

"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag

953

# used to tag a quasi-identifiers field must appear in exactly one

954

# field of one auxiliary table.

955

{ # An auxiliary table containing statistical information on the relative

956

# frequency of different quasi-identifiers values. It has one or several

957

# quasi-identifiers columns, and one column that indicates the relative

958

# frequency of each quasi-identifier tuple.

959

# If a tuple is present in the data but not in the auxiliary table, the

960

# corresponding relative frequency is assumed to be zero (and thus, the

961

# tuple is highly reidentifiable).

962

"table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location.

963

# identified by its project_id, dataset_id, and table_name. Within a query

964

# a table is often referenced with a string in the format of:

965

# `<project_id>:<dataset_id>.<table_id>` or

966

# `<project_id>.<dataset_id>.<table_id>`.

967

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

968

# If omitted, project ID is inferred from the API call.

969

"datasetId": "A String", # Dataset ID of the table.

970

"tableId": "A String", # Name of the table.

971

},

972

"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number

973

# between 0 and 1 (inclusive). Null values are assumed to be zero.

974

"name": "A String", # Name describing the field.

975

},

976

"quasiIds": [ # Required. Quasi-identifier columns.

977

{ # A quasi-identifier column has a custom_tag, used to know which column

978

# in the data corresponds to which column in the statistical model.

979

"field": { # General identifier of a data field in a storage service. # Identifies the column.

980

"name": "A String", # Name describing the field.

981

},

982

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

983

# indicate an auxiliary table that contains statistical information on

984

# the possible values of this column (below).

},

],

},

],

},

},

"actions": [ # Actions to execute at the completion of the job. Are executed in the order

992

# provided.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

993

{ # A task to execute on the completion of a job.

994

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

995

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

996

# Command Center (CSCC Alpha).

997

# This action is only available for projects which are parts of

998

# an organization and whitelisted for the alpha Cloud Security Command

999

# Center.

1000

# The action will publish count of finding instances and their info types.

1001

# The summary of findings will be persisted in CSCC and are governed by CSCC

1002

# service-specific policy, see https://cloud.google.com/terms/service-terms

1003

# Only a single instance of this action can be specified.

1004

# Compatible with: Inspect

1005

},

1006

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

1007

# completion/failure.

1008

# completion/failure.

1009

},

1010

"saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1011

# OutputStorageConfig. Only a single instance of this action can be

1012

# specified.

1013

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1014

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

1015

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

1016

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

1017

# from the `Finding` object. If appending to an existing table, any columns

1018

# from the predefined schema that are missing will be added. No columns in

1019

# the existing table will be deleted.

1020

#

1021

# If unspecified, then all available columns will be used for a new table or

1022

# an (existing) table with no schema, and no changes will be made to an

1023

# existing table that has a schema.

1024

# Only for use with external storage.

1025

"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

2019-06-14 16:50:42 -0700

[diff] [blame]

1026

# dataset. If table_id is not set a new one will be generated

1027

# for you with the following format:

1028

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

1029

# generating the date details.

1030

#

1031

# For Inspect, each column in an existing output table must have the same

1032

# name, type, and mode of a field in the `Finding` object.

1033

#

1034

# For Risk, an existing output table should be the output of a previous

1035

# Risk analysis job run on the same source table, with the same privacy

1036

# metric and quasi-identifiers. Risk jobs that analyze the same table but

1037

# compute a different privacy metric, or use different sets of

1038

# quasi-identifiers, cannot store their results in the same table.

1039

# identified by its project_id, dataset_id, and table_name. Within a query

1040

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1041

# `<project_id>:<dataset_id>.<table_id>` or

1042

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1043

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1044

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1045

"datasetId": "A String", # Dataset ID of the table.

1046

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1047

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1048

},

1049

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1050

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

1051

# message contains a single field, `DlpJobName`, which is equal to the

1052

# finished job's

1053

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

1054

# Compatible with: Inspect, Risk

1055

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

1056

# publishing access rights to the DLP API service account executing

1057

# the long running DlpJob sending the notifications.

1058

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1059

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1060

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1061

# results of the DlpJob will be applied to the entry for the resource scanned

1062

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

1063

# be deleted. InfoType naming patterns are strictly enforced when using this

1064

# feature. Note that the findings will be persisted in Cloud Data Catalog

1065

# storage and are governed by Data Catalog service-specific policy, see

1066

# https://cloud.google.com/terms/service-terms

1067

# Only a single instance of this action can be specified and only allowed if

1068

# all resources being scanned are BigQuery tables.

1069

# Compatible with: Inspect

1070

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1071

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

1072

# will publish a metric to stack driver on each infotype requested and

1073

# how many findings were found for it. CustomDetectors will be bucketed

1074

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1075

},

1076

},

1077

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1078

"sourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over.

1079

# identified by its project_id, dataset_id, and table_name. Within a query

1080

# a table is often referenced with a string in the format of:

1081

# `<project_id>:<dataset_id>.<table_id>` or

1082

# `<project_id>.<dataset_id>.<table_id>`.

1083

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

1084

# If omitted, project ID is inferred from the API call.

1085

"datasetId": "A String", # Dataset ID of the table.

1086

"tableId": "A String", # Name of the table.

1087

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

},

}

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

1098

1099

{ # Combines all of the information about a DLP job.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1100

"createTime": "A String", # Time when the job was created.

1101

"state": "A String", # State of a job.

1102

"riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source.

1103

"numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result

1104

"minValue": { # Set of primitive values supported by the system. # Minimum value appearing in the column.

1105

# Note that for the purposes of inspection or transformation, the number

1106

# of bytes considered to comprise a 'Value' is based on its representation

1107

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1108

# 123456789, the number of bytes would be counted as 9, even though an

1109

# int64 only holds up to 8 bytes of data.

1110

"booleanValue": True or False, # boolean

1111

"floatValue": 3.14, # float

1112

"dayOfWeekValue": "A String", # day of week

1113

"timestampValue": "A String", # timestamp

1114

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1115

# and time zone are either specified elsewhere or are not significant. The date

1116

# is relative to the Proleptic Gregorian Calendar. This can represent:

1117

#

1118

# * A full date, with non-zero year, month and day values

1119

# * A month and day value, with a zero year, e.g. an anniversary

1120

# * A year on its own, with zero month and day values

1121

# * A year and month value, with a zero day, e.g. a credit card expiration date

1122

#

1123

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1124

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1125

# a year.

1126

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1127

# month and day.

1128

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1129

# if specifying a year by itself or a year and month where the day is not

1130

# significant.

1131

},

1132

"stringValue": "A String", # string

1133

"integerValue": "A String", # integer

1134

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1135

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1136

# types are google.type.Date and `google.protobuf.Timestamp`.

1137

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1138

# allow the value 60 if it allows leap-seconds.

1139

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1140

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1141

# to allow the value "24:00:00" for scenarios like business closing time.

1142

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

1143

},

1144

},

1145

"maxValue": { # Set of primitive values supported by the system. # Maximum value appearing in the column.

1146

# Note that for the purposes of inspection or transformation, the number

1147

# of bytes considered to comprise a 'Value' is based on its representation

1148

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1149

# 123456789, the number of bytes would be counted as 9, even though an

1150

# int64 only holds up to 8 bytes of data.

1151

"booleanValue": True or False, # boolean

1152

"floatValue": 3.14, # float

1153

"dayOfWeekValue": "A String", # day of week

1154

"timestampValue": "A String", # timestamp

1155

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1156

# and time zone are either specified elsewhere or are not significant. The date

1157

# is relative to the Proleptic Gregorian Calendar. This can represent:

1158

#

1159

# * A full date, with non-zero year, month and day values

1160

# * A month and day value, with a zero year, e.g. an anniversary

1161

# * A year on its own, with zero month and day values

1162

# * A year and month value, with a zero day, e.g. a credit card expiration date

1163

#

1164

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1165

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1166

# a year.

1167

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1168

# month and day.

1169

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1170

# if specifying a year by itself or a year and month where the day is not

1171

# significant.

1172

},

1173

"stringValue": "A String", # string

1174

"integerValue": "A String", # integer

1175

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1176

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1177

# types are google.type.Date and `google.protobuf.Timestamp`.

1178

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1179

# allow the value 60 if it allows leap-seconds.

1180

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1181

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1182

# to allow the value "24:00:00" for scenarios like business closing time.

1183

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

1184

},

1185

},

1186

"quantileValues": [ # List of 99 values that partition the set of field values into 100 equal

1187

# sized buckets.

1188

{ # Set of primitive values supported by the system.

1189

# Note that for the purposes of inspection or transformation, the number

1190

# of bytes considered to comprise a 'Value' is based on its representation

1191

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1192

# 123456789, the number of bytes would be counted as 9, even though an

1193

# int64 only holds up to 8 bytes of data.

1194

"booleanValue": True or False, # boolean

1195

"floatValue": 3.14, # float

1196

"dayOfWeekValue": "A String", # day of week

1197

"timestampValue": "A String", # timestamp

1198

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1199

# and time zone are either specified elsewhere or are not significant. The date

1200

# is relative to the Proleptic Gregorian Calendar. This can represent:

1201

#

1202

# * A full date, with non-zero year, month and day values

1203

# * A month and day value, with a zero year, e.g. an anniversary

1204

# * A year on its own, with zero month and day values

1205

# * A year and month value, with a zero day, e.g. a credit card expiration date

1206

#

1207

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1208

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1209

# a year.

1210

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1211

# month and day.

1212

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1213

# if specifying a year by itself or a year and month where the day is not

1214

# significant.

1215

},

1216

"stringValue": "A String", # string

1217

"integerValue": "A String", # integer

1218

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1219

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1220

# types are google.type.Date and `google.protobuf.Timestamp`.

1221

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1222

# allow the value 60 if it allows leap-seconds.

1223

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1224

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1225

# to allow the value "24:00:00" for scenarios like business closing time.

1226

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

},

"lDiversityResult": { # Result of the l-diversity computation. # L-divesity result

1232

"sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.

1233

{ # Histogram of l-diversity equivalence class sensitive value frequencies.

1234

"sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence

1235

# classes in this bucket.

1236

"sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence

1237

# classes in this bucket.

1238

"bucketSize": "A String", # Total number of equivalence classes in this bucket.

1239

"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.

1240

"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of

1241

# classes returned per bucket is capped at 20.

1242

{ # The set of columns' values that share the same ldiversity value.

1243

"quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence

1244

# class. The order is always the same as the original request.

1245

{ # Set of primitive values supported by the system.

1246

# Note that for the purposes of inspection or transformation, the number

1247

# of bytes considered to comprise a 'Value' is based on its representation

1248

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1249

# 123456789, the number of bytes would be counted as 9, even though an

1250

# int64 only holds up to 8 bytes of data.

1251

"booleanValue": True or False, # boolean

1252

"floatValue": 3.14, # float

1253

"dayOfWeekValue": "A String", # day of week

1254

"timestampValue": "A String", # timestamp

1255

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1256

# and time zone are either specified elsewhere or are not significant. The date

1257

# is relative to the Proleptic Gregorian Calendar. This can represent:

1258

#

1259

# * A full date, with non-zero year, month and day values

1260

# * A month and day value, with a zero year, e.g. an anniversary

1261

# * A year on its own, with zero month and day values

1262

# * A year and month value, with a zero day, e.g. a credit card expiration date

1263

#

1264

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1265

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1266

# a year.

1267

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1268

# month and day.

1269

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1270

# if specifying a year by itself or a year and month where the day is not

1271

# significant.

1272

},

1273

"stringValue": "A String", # string

1274

"integerValue": "A String", # integer

1275

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1276

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1277

# types are google.type.Date and `google.protobuf.Timestamp`.

1278

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1279

# allow the value 60 if it allows leap-seconds.

1280

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1281

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1282

# to allow the value "24:00:00" for scenarios like business closing time.

1283

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

"equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.

1288

"numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class.

1289

"topSensitiveValues": [ # Estimated frequencies of top sensitive values.

1290

{ # A value of a field, including its frequency.

1291

"value": { # Set of primitive values supported by the system. # A value contained in the field in question.

1292

# Note that for the purposes of inspection or transformation, the number

1293

# of bytes considered to comprise a 'Value' is based on its representation

1294

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1295

# 123456789, the number of bytes would be counted as 9, even though an

1296

# int64 only holds up to 8 bytes of data.

1297

"booleanValue": True or False, # boolean

1298

"floatValue": 3.14, # float

1299

"dayOfWeekValue": "A String", # day of week

1300

"timestampValue": "A String", # timestamp

1301

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1302

# and time zone are either specified elsewhere or are not significant. The date

1303

# is relative to the Proleptic Gregorian Calendar. This can represent:

1304

#

1305

# * A full date, with non-zero year, month and day values

1306

# * A month and day value, with a zero year, e.g. an anniversary

1307

# * A year on its own, with zero month and day values

1308

# * A year and month value, with a zero day, e.g. a credit card expiration date

1309

#

1310

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1311

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1312

# a year.

1313

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1314

# month and day.

1315

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1316

# if specifying a year by itself or a year and month where the day is not

1317

# significant.

1318

},

1319

"stringValue": "A String", # string

1320

"integerValue": "A String", # integer

1321

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1322

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1323

# types are google.type.Date and `google.protobuf.Timestamp`.

1324

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1325

# allow the value 60 if it allows leap-seconds.

1326

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1327

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1328

# to allow the value "24:00:00" for scenarios like business closing time.

1329

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

1330

},

1331

},

1332

"count": "A String", # How many times the value is contained in the field.

},

],

},

],

},

],

},

"requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.

1341

"categoricalStatsConfig": { # Compute numerical stats over an individual column, including # Categorical stats

1342

# number of distinct values and value count distribution.

1343

"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are

1344

# supported except for arrays and structs. However, it may be more

1345

# informative to use NumericalStats when the field type is supported,

1346

# depending on the data.

1347

"name": "A String", # Name describing the field.

1348

},

1349

},

1350

"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity

1351

"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are

1352

# specified, they are considered a single composite key. Structs and

1353

# repeated data types are not supported; however, nested fields are

1354

# supported so long as they are not structs themselves or nested within

1355

# a repeated field.

1356

{ # General identifier of a data field in a storage service.

1357

"name": "A String", # Name describing the field.

1358

},

1359

],

1360

"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

1361

# single individual. If the same entity_id is associated to multiple

1362

# quasi-identifier tuples over distinct rows, we consider the entire

1363

# collection of tuples as the composite quasi-identifier. This collection

1364

# is a multiset: the order in which the different tuples appear in the

1365

# dataset is ignored, but their frequency is taken into account.

1366

#

1367

# Important note: a maximum of 1000 rows can be associated to a single

1368

# entity ID. If more rows are associated with the same entity ID, some

1369

# might be ignored.

1370

# single person. For example, in medical records the `EntityId` might be a

1371

# patient identifier, or for financial records it might be an account

1372

# identifier. This message is used when generalizations or analysis must take

1373

# into account that multiple rows correspond to the same entity.

1374

"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.

1375

"name": "A String", # Name describing the field.

},

},

},

"numericalStatsConfig": { # Compute numerical stats over an individual column, including # Numerical stats

1380

# min, max, and quantiles.

1381

"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are

1382

# integer, float, date, datetime, timestamp, time.

1383

"name": "A String", # Name describing the field.

1384

},

1385

},

1386

"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what # k-map

1387

# is called "journalist risk" in the literature, except the attack dataset is

1388

# statistically modeled instead of being perfectly known. This can be done

1389

# using publicly available data (like the US Census), or using a custom

1390

# statistical model (indicated as one or several BigQuery tables), or by

1391

# extrapolating from the distribution of values in the input dataset.

1392

"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.

1393

# Set if no column is tagged with a region-specific InfoType (like

1394

# US_ZIP_5) or a region code.

1395

"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag

1396

# used to tag a quasi-identifiers column must appear in exactly one column

1397

# of one auxiliary table.

1398

{ # An auxiliary table contains statistical information on the relative

1399

# frequency of different quasi-identifiers values. It has one or several

1400

# quasi-identifiers columns, and one column that indicates the relative

1401

# frequency of each quasi-identifier tuple.

1402

# If a tuple is present in the data but not in the auxiliary table, the

1403

# corresponding relative frequency is assumed to be zero (and thus, the

1404

# tuple is highly reidentifiable).

1405

"table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location.

1406

# identified by its project_id, dataset_id, and table_name. Within a query

1407

# a table is often referenced with a string in the format of:

1408

# `<project_id>:<dataset_id>.<table_id>` or

1409

# `<project_id>.<dataset_id>.<table_id>`.

1410

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

1411

# If omitted, project ID is inferred from the API call.

1412

"datasetId": "A String", # Dataset ID of the table.

1413

"tableId": "A String", # Name of the table.

1414

},

1415

"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number

1416

# between 0 and 1 (inclusive). Null values are assumed to be zero.

1417

"name": "A String", # Name describing the field.

1418

},

1419

"quasiIds": [ # Required. Quasi-identifier columns.

1420

{ # A quasi-identifier column has a custom_tag, used to know which column

1421

# in the data corresponds to which column in the statistical model.

1422

"customTag": "A String", # A auxiliary field.

1423

"field": { # General identifier of a data field in a storage service. # Identifies the column.

1424

"name": "A String", # Name describing the field.

},

},

],

},

],

"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the

1431

# same tag.

1432

{ # A column with a semantic tag attached.

1433

"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.

1434

"name": "A String", # Name describing the field.

1435

},

1436

"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public

1437

# dataset as a statistical model of population, if available. We

1438

# currently support US ZIP codes, region codes, ages and genders.

1439

# To programmatically obtain the list of supported InfoTypes, use

1440

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

1441

"name": "A String", # Name of the information type. Either a name of your choosing when

1442

# creating a CustomInfoType, or one of the names listed

1443

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1444

# a built-in type. InfoType names should conform to the pattern

1445

# `[a-zA-Z0-9_]{1,64}`.

1446

},

1447

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

1448

# indicate an auxiliary table that contains statistical information on

1449

# the possible values of this column (below).

1450

"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

1451

# the distribution of values in the input data

1452

# empty messages in your APIs. A typical example is to use it as the request

1453

# or the response type of an API method. For instance:

1454

#

1455

# service Foo {

1456

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

1457

# }

1458

#

1459

# The JSON representation for `Empty` is empty JSON object `{}`.

},

},

],

},

"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity

1465

"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are

1466

# defined for the l-diversity computation. When multiple fields are

1467

# specified, they are considered a single composite key.

1468

{ # General identifier of a data field in a storage service.

1469

"name": "A String", # Name describing the field.

1470

},

1471

],

1472

"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.

1473

"name": "A String", # Name describing the field.

1474

},

1475

},

1476

"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to # delta-presence

1477

# figure out that one given individual appears in a de-identified dataset.

1478

# Similarly to the k-map metric, we cannot compute δ-presence exactly without

1479

# knowing the attack dataset, so we use a statistical model instead.

1480

"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the

1481

# same tag.

1482

{ # A column with a semantic tag attached.

1483

"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.

1484

"name": "A String", # Name describing the field.

1485

},

1486

"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public

1487

# dataset as a statistical model of population, if available. We

1488

# currently support US ZIP codes, region codes, ages and genders.

1489

# To programmatically obtain the list of supported InfoTypes, use

1490

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

1491

"name": "A String", # Name of the information type. Either a name of your choosing when

1492

# creating a CustomInfoType, or one of the names listed

1493

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1494

# a built-in type. InfoType names should conform to the pattern

1495

# `[a-zA-Z0-9_]{1,64}`.

1496

},

1497

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

1498

# indicate an auxiliary table that contains statistical information on

1499

# the possible values of this column (below).

1500

"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

1501

# the distribution of values in the input data

1502

# empty messages in your APIs. A typical example is to use it as the request

1503

# or the response type of an API method. For instance:

1504

#

1505

# service Foo {

1506

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

1507

# }

1508

#

1509

# The JSON representation for `Empty` is empty JSON object `{}`.

},

},

],

"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.

1514

# Set if no column is tagged with a region-specific InfoType (like

1515

# US_ZIP_5) or a region code.

1516

"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag

1517

# used to tag a quasi-identifiers field must appear in exactly one

1518

# field of one auxiliary table.

1519

{ # An auxiliary table containing statistical information on the relative

1520

# frequency of different quasi-identifiers values. It has one or several

1521

# quasi-identifiers columns, and one column that indicates the relative

1522

# frequency of each quasi-identifier tuple.

1523

# If a tuple is present in the data but not in the auxiliary table, the

1524

# corresponding relative frequency is assumed to be zero (and thus, the

1525

# tuple is highly reidentifiable).

1526

"table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location.

1527

# identified by its project_id, dataset_id, and table_name. Within a query

1528

# a table is often referenced with a string in the format of:

1529

# `<project_id>:<dataset_id>.<table_id>` or

1530

# `<project_id>.<dataset_id>.<table_id>`.

1531

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

1532

# If omitted, project ID is inferred from the API call.

1533

"datasetId": "A String", # Dataset ID of the table.

1534

"tableId": "A String", # Name of the table.

1535

},

1536

"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number

1537

# between 0 and 1 (inclusive). Null values are assumed to be zero.

1538

"name": "A String", # Name describing the field.

1539

},

1540

"quasiIds": [ # Required. Quasi-identifier columns.

1541

{ # A quasi-identifier column has a custom_tag, used to know which column

1542

# in the data corresponds to which column in the statistical model.

1543

"field": { # General identifier of a data field in a storage service. # Identifies the column.

1544

"name": "A String", # Name describing the field.

1545

},

1546

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

1547

# indicate an auxiliary table that contains statistical information on

1548

# the possible values of this column (below).

},

],

},

],

},

},

"categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result

1556

"valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.

1557

{ # Histogram of value frequencies in the column.

1558

"bucketValues": [ # Sample of value frequencies in this bucket. The total number of

1559

# values returned per bucket is capped at 20.

1560

{ # A value of a field, including its frequency.

1561

"value": { # Set of primitive values supported by the system. # A value contained in the field in question.

1562

# Note that for the purposes of inspection or transformation, the number

1563

# of bytes considered to comprise a 'Value' is based on its representation

1564

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1565

# 123456789, the number of bytes would be counted as 9, even though an

1566

# int64 only holds up to 8 bytes of data.

1567

"booleanValue": True or False, # boolean

1568

"floatValue": 3.14, # float

1569

"dayOfWeekValue": "A String", # day of week

1570

"timestampValue": "A String", # timestamp

1571

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1572

# and time zone are either specified elsewhere or are not significant. The date

1573

# is relative to the Proleptic Gregorian Calendar. This can represent:

1574

#

1575

# * A full date, with non-zero year, month and day values

1576

# * A month and day value, with a zero year, e.g. an anniversary

1577

# * A year on its own, with zero month and day values

1578

# * A year and month value, with a zero day, e.g. a credit card expiration date

1579

#

1580

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1581

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1582

# a year.

1583

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1584

# month and day.

1585

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1586

# if specifying a year by itself or a year and month where the day is not

1587

# significant.

1588

},

1589

"stringValue": "A String", # string

1590

"integerValue": "A String", # integer

1591

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1592

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1593

# types are google.type.Date and `google.protobuf.Timestamp`.

1594

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1595

# allow the value 60 if it allows leap-seconds.

1596

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1597

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1598

# to allow the value "24:00:00" for scenarios like business closing time.

1599

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

1600

},

1601

},

1602

"count": "A String", # How many times the value is contained in the field.

1603

},

1604

],

1605

"valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.

1606

"valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.

1607

"bucketSize": "A String", # Total number of values in this bucket.

1608

"bucketValueCount": "A String", # Total number of distinct values in this bucket.

},

],

},

"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an # K-map result

1613

# estimation, not exact values.

1614

"kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value

1615

# doesn't correspond to any such interval, the associated frequency is

1616

# zero. For example, the following records:

1617

# {min_anonymity: 1, max_anonymity: 1, frequency: 17}

1618

# {min_anonymity: 2, max_anonymity: 3, frequency: 42}

1619

# {min_anonymity: 5, max_anonymity: 10, frequency: 99}

1620

# mean that there are no record with an estimated anonymity of 4, 5, or

1621

# larger than 10.

1622

{ # A KMapEstimationHistogramBucket message with the following values:

# min_anonymity: 3

# max_anonymity: 5

# frequency: 42

# means that there are 42 records whose quasi-identifier values correspond

1627

# to 3, 4 or 5 people in the overlying population. An important particular

1628

# case is when min_anonymity = max_anonymity = 1: the frequency field then

1629

# corresponds to the number of uniquely identifiable records.

1630

"bucketSize": "A String", # Number of records within these anonymity bounds.

1631

"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.

1632

"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.

1633

"minAnonymity": "A String", # Always positive.

1634

"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total

1635

# number of classes returned per bucket is capped at 20.

1636

{ # A tuple of values for the quasi-identifier columns.

1637

"estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values.

1638

"quasiIdsValues": [ # The quasi-identifier values.

1639

{ # Set of primitive values supported by the system.

1640

# Note that for the purposes of inspection or transformation, the number

1641

# of bytes considered to comprise a 'Value' is based on its representation

1642

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1643

# 123456789, the number of bytes would be counted as 9, even though an

1644

# int64 only holds up to 8 bytes of data.

1645

"booleanValue": True or False, # boolean

1646

"floatValue": 3.14, # float

1647

"dayOfWeekValue": "A String", # day of week

1648

"timestampValue": "A String", # timestamp

1649

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1650

# and time zone are either specified elsewhere or are not significant. The date

1651

# is relative to the Proleptic Gregorian Calendar. This can represent:

1652

#

1653

# * A full date, with non-zero year, month and day values

1654

# * A month and day value, with a zero year, e.g. an anniversary

1655

# * A year on its own, with zero month and day values

1656

# * A year and month value, with a zero day, e.g. a credit card expiration date

1657

#

1658

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1659

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1660

# a year.

1661

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1662

# month and day.

1663

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1664

# if specifying a year by itself or a year and month where the day is not

1665

# significant.

1666

},

1667

"stringValue": "A String", # string

1668

"integerValue": "A String", # integer

1669

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1670

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1671

# types are google.type.Date and `google.protobuf.Timestamp`.

1672

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1673

# allow the value 60 if it allows leap-seconds.

1674

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1675

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1676

# to allow the value "24:00:00" for scenarios like business closing time.

1677

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

},

],

},

],

},

"kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result

1687

"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.

1688

{ # Histogram of k-anonymity equivalence classes.

1689

"bucketSize": "A String", # Total number of equivalence classes in this bucket.

1690

"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.

1691

"equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket.

1692

"equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket.

1693

"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of

1694

# classes returned per bucket is capped at 20.

1695

{ # The set of columns' values that share the same ldiversity value

1696

"quasiIdsValues": [ # Set of values defining the equivalence class. One value per

1697

# quasi-identifier column in the original KAnonymity metric message.

1698

# The order is always the same as the original request.

1699

{ # Set of primitive values supported by the system.

1700

# Note that for the purposes of inspection or transformation, the number

1701

# of bytes considered to comprise a 'Value' is based on its representation

1702

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1703

# 123456789, the number of bytes would be counted as 9, even though an

1704

# int64 only holds up to 8 bytes of data.

1705

"booleanValue": True or False, # boolean

1706

"floatValue": 3.14, # float

1707

"dayOfWeekValue": "A String", # day of week

1708

"timestampValue": "A String", # timestamp

1709

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1710

# and time zone are either specified elsewhere or are not significant. The date

1711

# is relative to the Proleptic Gregorian Calendar. This can represent:

1712

#

1713

# * A full date, with non-zero year, month and day values

1714

# * A month and day value, with a zero year, e.g. an anniversary

1715

# * A year on its own, with zero month and day values

1716

# * A year and month value, with a zero day, e.g. a credit card expiration date

1717

#

1718

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1719

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1720

# a year.

1721

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1722

# month and day.

1723

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1724

# if specifying a year by itself or a year and month where the day is not

1725

# significant.

1726

},

1727

"stringValue": "A String", # string

1728

"integerValue": "A String", # integer

1729

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1730

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1731

# types are google.type.Date and `google.protobuf.Timestamp`.

1732

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1733

# allow the value 60 if it allows leap-seconds.

1734

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1735

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1736

# to allow the value "24:00:00" for scenarios like business closing time.

1737

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the

1742

# above set of values.

},

],

},

],

},

"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an # Delta-presence result

1749

# estimation, not exact values.

1750

"deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a

1751

# value doesn't correspond to any such interval, the associated frequency

1752

# is zero. For example, the following records:

1753

# {min_probability: 0, max_probability: 0.1, frequency: 17}

1754

# {min_probability: 0.2, max_probability: 0.3, frequency: 42}

1755

# {min_probability: 0.3, max_probability: 0.4, frequency: 99}

1756

# mean that there are no record with an estimated probability in [0.1, 0.2)

1757

# nor larger or equal to 0.4.

1758

{ # A DeltaPresenceEstimationHistogramBucket message with the following

1759

# values:

1760

# min_probability: 0.1

1761

# max_probability: 0.2

1762

# frequency: 42

1763

# means that there are 42 records for which δ is in [0.1, 0.2). An

1764

# important particular case is when min_probability = max_probability = 1:

1765

# then, every individual who shares this quasi-identifier combination is in

1766

# the dataset.

1767

"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total

1768

# number of classes returned per bucket is capped at 20.

1769

{ # A tuple of values for the quasi-identifier columns.

1770

"quasiIdsValues": [ # The quasi-identifier values.

1771

{ # Set of primitive values supported by the system.

1772

# Note that for the purposes of inspection or transformation, the number

1773

# of bytes considered to comprise a 'Value' is based on its representation

1774

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1775

# 123456789, the number of bytes would be counted as 9, even though an

1776

# int64 only holds up to 8 bytes of data.

1777

"booleanValue": True or False, # boolean

1778

"floatValue": 3.14, # float

1779

"dayOfWeekValue": "A String", # day of week

1780

"timestampValue": "A String", # timestamp

1781

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1782

# and time zone are either specified elsewhere or are not significant. The date

1783

# is relative to the Proleptic Gregorian Calendar. This can represent:

1784

#

1785

# * A full date, with non-zero year, month and day values

1786

# * A month and day value, with a zero year, e.g. an anniversary

1787

# * A year on its own, with zero month and day values

1788

# * A year and month value, with a zero day, e.g. a credit card expiration date

1789

#

1790

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1791

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1792

# a year.

1793

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1794

# month and day.

1795

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1796

# if specifying a year by itself or a year and month where the day is not

1797

# significant.

1798

},

1799

"stringValue": "A String", # string

1800

"integerValue": "A String", # integer

1801

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1802

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1803

# types are google.type.Date and `google.protobuf.Timestamp`.

1804

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1805

# allow the value 60 if it allows leap-seconds.

1806

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1807

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1808

# to allow the value "24:00:00" for scenarios like business closing time.

1809

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

"estimatedProbability": 3.14, # The estimated probability that a given individual sharing these

1814

# quasi-identifier values is in the dataset. This value, typically called

1815

# δ, is the ratio between the number of records in the dataset with these

1816

# quasi-identifier values, and the total number of individuals (inside

1817

# *and* outside the dataset) with these quasi-identifier values.

1818

# For example, if there are 15 individuals in the dataset who share the

1819

# same quasi-identifier values, and an estimated 100 people in the entire

1820

# population with these values, then δ is 0.15.

1821

},

1822

],

1823

"minProbability": 3.14, # Between 0 and 1.

1824

"maxProbability": 3.14, # Always greater than or equal to min_probability.

1825

"bucketSize": "A String", # Number of records within these probability bounds.

1826

"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.

},

],

},

"requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over.

1831

# identified by its project_id, dataset_id, and table_name. Within a query

1832

# a table is often referenced with a string in the format of:

1833

# `<project_id>:<dataset_id>.<table_id>` or

1834

# `<project_id>.<dataset_id>.<table_id>`.

1835

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

1836

# If omitted, project ID is inferred from the API call.

1837

"datasetId": "A String", # Dataset ID of the table.

1838

"tableId": "A String", # Name of the table.

1839

},

1840

},

1841

"jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that

1842

# instantiated the job.

1843

"errors": [ # A stream of errors encountered running the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1844

{ # Details information about an error encountered during job execution or

1845

# the results of an unsuccessful activation of the JobTrigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1846

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1847

# different programming environments, including REST APIs and RPC APIs. It is

1848

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

1849

# three pieces of data: error code, error message, and error details.

1850

#

1851

# You can find out more about this error model and how to work with it in the

1852

# [API Design Guide](https://cloud.google.com/apis/design/errors).

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1853

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

1854

"message": "A String", # A developer-facing error message, which should be in English. Any

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1855

# user-facing error message should be localized and sent in the

1856

# google.rpc.Status.details field, or localized by the client.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1857

"details": [ # A list of messages that carry the error details. There is a common set of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1858

# message types for APIs to use.

1859

{

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1860

"a_key": "", # Properties of the object. Contains field @type with type URL.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1861

},

1862

],

1863

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1864

"timestamps": [ # The times the error occurred.

1865

"A String",

1866

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1867

},

1868

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1869

"name": "A String", # The server-assigned name.

1870

"type": "A String", # The type of job.

1871

"endTime": "A String", # Time when the job finished.

1872

"startTime": "A String", # Time when the job started.

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

"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

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1876

# this run.

1877

# to be detected) to be used anywhere you otherwise would normally specify

1878

# InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates

1879

# to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1880

"displayName": "A String", # Display name (max 256 chars).

1881

"inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1882

# When used with redactContent only info_types and min_likelihood are currently

1883

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1884

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

1885

# included in the response; see Finding.quote.

1886

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

1887

# Exclusion rules, contained in the set are executed in the end, other

1888

# rules are executed in the order they are specified for each info type.

1889

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

1890

# circumstances, depending on the specific details of the rules within the set.

1891

"infoTypes": [ # List of infoTypes this rule set is applied to.

1892

{ # Type of information detected by the API.

1893

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1894

# creating a CustomInfoType, or one of the names listed

1895

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1896

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1897

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1898

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1899

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1900

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1901

{ # A single inspection rule to be applied to infoTypes, specified in

1902

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1903

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1904

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1905

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1906

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1907

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1908

# levels. For example, if a finding would be `POSSIBLE` without the

1909

# detection rule and `relative_likelihood` is 1, then it is upgraded to

1910

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

1911

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

1912

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

1913

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

1914

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1915

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1916

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1917

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

1918

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1919

# specified, the entire match is returned. No more than 3 may be included.

1920

42,

1921

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1922

"pattern": "A String", # Pattern defining the regular expression. Its syntax

1923

# (https://github.com/google/re2/wiki/Syntax) can be found under the

1924

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1925

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1926

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

1927

# The total length of the window cannot exceed 1000 characters. Note that

1928

# the finding itself will be included in the window, so that hotwords may

1929

# be used to match substrings of the finding itself. For example, the

1930

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

1931

# adjusted upwards if the area code is known to be the local area code of

1932

# a company office using the hotword regex "\(xxx\)", where "xxx"

1933

# is the area code in question.

1934

# rule.

1935

"windowBefore": 42, # Number of characters before the finding to consider.

1936

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1937

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1938

},

1939

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

1940

# `InspectionRuleSet` are removed from results.

1941

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1942

# be used to match sensitive information specific to the data, such as a list

1943

# of employee IDs or job titles.

1944

#

1945

# Dictionary words are case-insensitive and all characters other than letters

1946

# and digits in the unicode [Basic Multilingual

1947

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

1948

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1949

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

1950

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1951

# surrounding any match must be of a different type than the adjacent

1952

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1953

# digits next to non-digits. For example, the dictionary word "jen" will

1954

# match the first three letters of the text "jen123" but will return no

1955

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1956

#

1957

# Dictionary words containing a large number of characters that are not

1958

# letters or digits may result in unexpected findings because such characters

1959

# are treated as whitespace. The

1960

# [limits](https://cloud.google.com/dlp/limits) page contains details about

1961

# the size limits of dictionaries. For dictionaries that do not fit within

1962

# these constraints, consider using `LargeCustomDictionaryConfig` in the

1963

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1964

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

1965

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1966

# at least one phrase and every phrase must contain at least 2 characters

1967

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1968

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1969

],

1970

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1971

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1972

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1973

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1974

# Example: gs://[BUCKET_NAME]/dictionary.txt

1975

},

1976

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1977

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

1978

"groupIndexes": [ # The index of the submatch to extract as findings. When not

1979

# specified, the entire match is returned. No more than 3 may be included.

1980

42,

1981

],

1982

"pattern": "A String", # Pattern defining the regular expression. Its syntax

1983

# (https://github.com/google/re2/wiki/Syntax) can be found under the

1984

# google/re2 repository on GitHub.

1985

},

1986

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

1987

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

1988

# contained within with a finding of an infoType from this list. For

1989

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

1990

# `exclusion_rule` containing `exclude_info_types.info_types` with

1991

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

1992

# with EMAIL_ADDRESS finding.

1993

# That leads to "555-222-2222@example.org" to generate only a single

1994

# finding, namely email address.

1995

{ # Type of information detected by the API.

1996

"name": "A String", # Name of the information type. Either a name of your choosing when

1997

# creating a CustomInfoType, or one of the names listed

1998

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1999

# a built-in type. InfoType names should conform to the pattern

2000

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2005

},

2006

},

2007

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2008

},

2009

],

2010

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

2011

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

2012

# When set within `InspectJobConfig`,

2013

# the maximum returned is 2000 regardless if this is set higher.

2014

# When set within `InspectContentRequest`, this field is ignored.

2015

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

2016

{ # Max findings configuration per infoType, per content item or long

2017

# running DlpJob.

2018

"maxFindings": 42, # Max findings limit for the given infoType.

2019

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

2020

# info_type should be provided. If InfoTypeLimit does not have an

2021

# info_type, the DLP API applies the limit against all info_types that

2022

# are found but not specified in another InfoTypeLimit.

2023

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2024

# creating a CustomInfoType, or one of the names listed

2025

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2026

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2027

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2028

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2029

},

2030

],

2031

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

2032

# When set within `InspectContentRequest`, the maximum returned is 2000

2033

# regardless if this is set higher.

2034

},

2035

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2036

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2037

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2038

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2039

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2040

# InfoType values returned by ListInfoTypes or listed at

2041

# https://cloud.google.com/dlp/docs/infotypes-reference.

2042

#

2043

# When no InfoTypes or CustomInfoTypes are specified in a request, the

2044

# system may automatically choose what detectors to run. By default this may

2045

# be all types, but may change over time as detectors are updated.

2046

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2047

# If you need precise control and predictability as to what detectors are

2048

# run you should specify specific InfoTypes listed in the reference,

2049

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2050

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2051

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2052

# creating a CustomInfoType, or one of the names listed

2053

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2054

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2055

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2056

},

2057

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2058

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

2059

# POSSIBLE.

2060

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

2061

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

2062

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

2063

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

2064

{ # Custom information type provided by the user. Used to find domain-specific

2065

# sensitive information configurable to the data in question.

2066

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

2067

# altered by a detection rule if the finding meets the criteria specified by

2068

# the rule. Defaults to `VERY_LIKELY` if not specified.

2069

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

2070

# infoType, when the name matches one of existing infoTypes and that infoType

2071

# is specified in `InspectContent.info_types` field. Specifying the latter

2072

# adds findings to the one detected by the system. If built-in info type is

2073

# not specified in `InspectContent.info_types` list then the name is treated

2074

# as a custom info type.

2075

"name": "A String", # Name of the information type. Either a name of your choosing when

2076

# creating a CustomInfoType, or one of the names listed

2077

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2078

# a built-in type. InfoType names should conform to the pattern

2079

# `[a-zA-Z0-9_]{1,64}`.

2080

},

2081

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

2082

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2083

# specified, the entire match is returned. No more than 3 may be included.

2084

42,

2085

],

2086

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2087

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2088

# google/re2 repository on GitHub.

2089

},

2090

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

2091

# Rules are applied in order that they are specified. Not supported for the

2092

# `surrogate_type` CustomInfoType.

2093

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

2094

# `CustomInfoType` to alter behavior under certain circumstances, depending

2095

# on the specific details of the rule. Not supported for the `surrogate_type`

2096

# custom infoType.

2097

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

2098

# proximity of hotwords.

2099

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

2100

# part of a detection rule.

2101

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

2102

# levels. For example, if a finding would be `POSSIBLE` without the

2103

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2104

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2105

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2106

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2107

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2108

# a final likelihood of `LIKELY`.

2109

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

2110

},

2111

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2112

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2113

# specified, the entire match is returned. No more than 3 may be included.

2114

42,

2115

],

2116

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2117

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2118

# google/re2 repository on GitHub.

2119

},

2120

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2121

# The total length of the window cannot exceed 1000 characters. Note that

2122

# the finding itself will be included in the window, so that hotwords may

2123

# be used to match substrings of the finding itself. For example, the

2124

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

2125

# adjusted upwards if the area code is known to be the local area code of

2126

# a company office using the hotword regex "\(xxx\)", where "xxx"

2127

# is the area code in question.

2128

# rule.

2129

"windowBefore": 42, # Number of characters before the finding to consider.

2130

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

2136

# to be returned. It still can be used for rules matching.

2137

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

2138

# be used to match sensitive information specific to the data, such as a list

2139

# of employee IDs or job titles.

2140

#

2141

# Dictionary words are case-insensitive and all characters other than letters

2142

# and digits in the unicode [Basic Multilingual

2143

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2144

# will be replaced with whitespace when scanning for matches, so the

2145

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2146

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

2147

# surrounding any match must be of a different type than the adjacent

2148

# characters within the word, so letters must be next to non-letters and

2149

# digits next to non-digits. For example, the dictionary word "jen" will

2150

# match the first three letters of the text "jen123" but will return no

2151

# matches for "jennifer".

2152

#

2153

# Dictionary words containing a large number of characters that are not

2154

# letters or digits may result in unexpected findings because such characters

2155

# are treated as whitespace. The

2156

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2157

# the size limits of dictionaries. For dictionaries that do not fit within

2158

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2159

# `StoredInfoType` API.

2160

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2161

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

2162

# at least one phrase and every phrase must contain at least 2 characters

2163

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

2168

# is accepted.

2169

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

2170

# Example: gs://[BUCKET_NAME]/dictionary.txt

2171

},

2172

},

2173

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

2174

# `InspectDataSource`. Not currently supported in `InspectContent`.

2175

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

2176

# `organizations/433245324/storedInfoTypes/432452342` or

2177

# `projects/project-id/storedInfoTypes/432452342`.

2178

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

2179

# inspection was created. Output-only field, populated by the system.

2180

},

2181

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

2182

# support reversing.

2183

# such as

2184

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

2185

# These types of transformations are

2186

# those that perform pseudonymization, thereby producing a "surrogate" as

2187

# output. This should be used in conjunction with a field on the

2188

# transformation such as `surrogate_info_type`. This CustomInfoType does

2189

# not support the use of `detection_rules`.

2190

},

2191

},

2192

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2193

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2194

"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.

2195

"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.

2196

"name": "A String", # Output only. The template name.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2197

#

2198

# The template will have one of the following formats:

2199

# `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2200

# `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`;

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2201

"description": "A String", # Short description (max 256 chars).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2202

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2203

"jobConfig": { # Controls what and how to inspect for findings. # Inspect config.

2204

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2205

# When used with redactContent only info_types and min_likelihood are currently

2206

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2207

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

2208

# included in the response; see Finding.quote.

2209

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

2210

# Exclusion rules, contained in the set are executed in the end, other

2211

# rules are executed in the order they are specified for each info type.

2212

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

2213

# circumstances, depending on the specific details of the rules within the set.

2214

"infoTypes": [ # List of infoTypes this rule set is applied to.

2215

{ # Type of information detected by the API.

2216

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2217

# creating a CustomInfoType, or one of the names listed

2218

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2219

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2220

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2221

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2222

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2223

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2224

{ # A single inspection rule to be applied to infoTypes, specified in

2225

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2226

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2227

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2228

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2229

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2230

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2231

# levels. For example, if a finding would be `POSSIBLE` without the

2232

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2233

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2234

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2235

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2236

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2237

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2238

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2239

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2240

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2241

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2242

# specified, the entire match is returned. No more than 3 may be included.

2243

42,

2244

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2245

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2246

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2247

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2248

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2249

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2250

# The total length of the window cannot exceed 1000 characters. Note that

2251

# the finding itself will be included in the window, so that hotwords may

2252

# be used to match substrings of the finding itself. For example, the

2253

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

2254

# adjusted upwards if the area code is known to be the local area code of

2255

# a company office using the hotword regex "\(xxx\)", where "xxx"

2256

# is the area code in question.

2257

# rule.

2258

"windowBefore": 42, # Number of characters before the finding to consider.

2259

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2260

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2261

},

2262

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

2263

# `InspectionRuleSet` are removed from results.

2264

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2265

# be used to match sensitive information specific to the data, such as a list

2266

# of employee IDs or job titles.

2267

#

2268

# Dictionary words are case-insensitive and all characters other than letters

2269

# and digits in the unicode [Basic Multilingual

2270

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2271

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2272

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2273

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2274

# surrounding any match must be of a different type than the adjacent

2275

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2276

# digits next to non-digits. For example, the dictionary word "jen" will

2277

# match the first three letters of the text "jen123" but will return no

2278

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2279

#

2280

# Dictionary words containing a large number of characters that are not

2281

# letters or digits may result in unexpected findings because such characters

2282

# are treated as whitespace. The

2283

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2284

# the size limits of dictionaries. For dictionaries that do not fit within

2285

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2286

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2287

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2288

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2289

# at least one phrase and every phrase must contain at least 2 characters

2290

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2291

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2292

],

2293

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2294

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2295

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2296

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2297

# Example: gs://[BUCKET_NAME]/dictionary.txt

2298

},

2299

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2300

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

2301

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2302

# specified, the entire match is returned. No more than 3 may be included.

2303

42,

2304

],

2305

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2306

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2307

# google/re2 repository on GitHub.

2308

},

2309

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

2310

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

2311

# contained within with a finding of an infoType from this list. For

2312

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

2313

# `exclusion_rule` containing `exclude_info_types.info_types` with

2314

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

2315

# with EMAIL_ADDRESS finding.

2316

# That leads to "555-222-2222@example.org" to generate only a single

2317

# finding, namely email address.

2318

{ # Type of information detected by the API.

2319

"name": "A String", # Name of the information type. Either a name of your choosing when

2320

# creating a CustomInfoType, or one of the names listed

2321

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2322

# a built-in type. InfoType names should conform to the pattern

2323

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2328

},

2329

},

2330

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2331

},

2332

],

2333

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

2334

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

2335

# When set within `InspectJobConfig`,

2336

# the maximum returned is 2000 regardless if this is set higher.

2337

# When set within `InspectContentRequest`, this field is ignored.

2338

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

2339

{ # Max findings configuration per infoType, per content item or long

2340

# running DlpJob.

2341

"maxFindings": 42, # Max findings limit for the given infoType.

2342

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

2343

# info_type should be provided. If InfoTypeLimit does not have an

2344

# info_type, the DLP API applies the limit against all info_types that

2345

# are found but not specified in another InfoTypeLimit.

2346

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2347

# creating a CustomInfoType, or one of the names listed

2348

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2349

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2350

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2351

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2352

},

2353

],

2354

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

2355

# When set within `InspectContentRequest`, the maximum returned is 2000

2356

# regardless if this is set higher.

2357

},

2358

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2359

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2360

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2361

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2362

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2363

# InfoType values returned by ListInfoTypes or listed at

2364

# https://cloud.google.com/dlp/docs/infotypes-reference.

2365

#

2366

# When no InfoTypes or CustomInfoTypes are specified in a request, the

2367

# system may automatically choose what detectors to run. By default this may

2368

# be all types, but may change over time as detectors are updated.

2369

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2370

# If you need precise control and predictability as to what detectors are

2371

# run you should specify specific InfoTypes listed in the reference,

2372

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2373

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2374

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2375

# creating a CustomInfoType, or one of the names listed

2376

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2377

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2378

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2379

},

2380

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2381

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

2382

# POSSIBLE.

2383

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

2384

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

2385

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

2386

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

2387

{ # Custom information type provided by the user. Used to find domain-specific

2388

# sensitive information configurable to the data in question.

2389

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

2390

# altered by a detection rule if the finding meets the criteria specified by

2391

# the rule. Defaults to `VERY_LIKELY` if not specified.

2392

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

2393

# infoType, when the name matches one of existing infoTypes and that infoType

2394

# is specified in `InspectContent.info_types` field. Specifying the latter

2395

# adds findings to the one detected by the system. If built-in info type is

2396

# not specified in `InspectContent.info_types` list then the name is treated

2397

# as a custom info type.

2398

"name": "A String", # Name of the information type. Either a name of your choosing when

2399

# creating a CustomInfoType, or one of the names listed

2400

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2401

# a built-in type. InfoType names should conform to the pattern

2402

# `[a-zA-Z0-9_]{1,64}`.

2403

},

2404

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

2405

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2406

# specified, the entire match is returned. No more than 3 may be included.

2407

42,

2408

],

2409

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2410

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2411

# google/re2 repository on GitHub.

2412

},

2413

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

2414

# Rules are applied in order that they are specified. Not supported for the

2415

# `surrogate_type` CustomInfoType.

2416

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

2417

# `CustomInfoType` to alter behavior under certain circumstances, depending

2418

# on the specific details of the rule. Not supported for the `surrogate_type`

2419

# custom infoType.

2420

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

2421

# proximity of hotwords.

2422

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

2423

# part of a detection rule.

2424

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

2425

# levels. For example, if a finding would be `POSSIBLE` without the

2426

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2427

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2428

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2429

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2430

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2431

# a final likelihood of `LIKELY`.

2432

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

2433

},

2434

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2435

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2436

# specified, the entire match is returned. No more than 3 may be included.

2437

42,

2438

],

2439

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2440

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2441

# google/re2 repository on GitHub.

2442

},

2443

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2444

# The total length of the window cannot exceed 1000 characters. Note that

2445

# the finding itself will be included in the window, so that hotwords may

2446

# be used to match substrings of the finding itself. For example, the

2447

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

2448

# adjusted upwards if the area code is known to be the local area code of

2449

# a company office using the hotword regex "\(xxx\)", where "xxx"

2450

# is the area code in question.

2451

# rule.

2452

"windowBefore": 42, # Number of characters before the finding to consider.

2453

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

2459

# to be returned. It still can be used for rules matching.

2460

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

2461

# be used to match sensitive information specific to the data, such as a list

2462

# of employee IDs or job titles.

2463

#

2464

# Dictionary words are case-insensitive and all characters other than letters

2465

# and digits in the unicode [Basic Multilingual

2466

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2467

# will be replaced with whitespace when scanning for matches, so the

2468

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2469

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

2470

# surrounding any match must be of a different type than the adjacent

2471

# characters within the word, so letters must be next to non-letters and

2472

# digits next to non-digits. For example, the dictionary word "jen" will

2473

# match the first three letters of the text "jen123" but will return no

2474

# matches for "jennifer".

2475

#

2476

# Dictionary words containing a large number of characters that are not

2477

# letters or digits may result in unexpected findings because such characters

2478

# are treated as whitespace. The

2479

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2480

# the size limits of dictionaries. For dictionaries that do not fit within

2481

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2482

# `StoredInfoType` API.

2483

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2484

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

2485

# at least one phrase and every phrase must contain at least 2 characters

2486

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

2491

# is accepted.

2492

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

2493

# Example: gs://[BUCKET_NAME]/dictionary.txt

2494

},

2495

},

2496

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

2497

# `InspectDataSource`. Not currently supported in `InspectContent`.

2498

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

2499

# `organizations/433245324/storedInfoTypes/432452342` or

2500

# `projects/project-id/storedInfoTypes/432452342`.

2501

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

2502

# inspection was created. Output-only field, populated by the system.

2503

},

2504

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

2505

# support reversing.

2506

# such as

2507

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

2508

# These types of transformations are

2509

# those that perform pseudonymization, thereby producing a "surrogate" as

2510

# output. This should be used in conjunction with a field on the

2511

# transformation such as `surrogate_info_type`. This CustomInfoType does

2512

# not support the use of `detection_rules`.

2513

},

2514

},

2515

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2516

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2517

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2518

{ # A task to execute on the completion of a job.

2519

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2520

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

2521

# Command Center (CSCC Alpha).

2522

# This action is only available for projects which are parts of

2523

# an organization and whitelisted for the alpha Cloud Security Command

2524

# Center.

2525

# The action will publish count of finding instances and their info types.

2526

# The summary of findings will be persisted in CSCC and are governed by CSCC

2527

# service-specific policy, see https://cloud.google.com/terms/service-terms

2528

# Only a single instance of this action can be specified.

2529

# Compatible with: Inspect

2530

},

2531

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

2532

# completion/failure.

2533

# completion/failure.

2534

},

2535

"saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2536

# OutputStorageConfig. Only a single instance of this action can be

2537

# specified.

2538

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2539

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

2540

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

2541

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

2542

# from the `Finding` object. If appending to an existing table, any columns

2543

# from the predefined schema that are missing will be added. No columns in

2544

# the existing table will be deleted.

2545

#

2546

# If unspecified, then all available columns will be used for a new table or

2547

# an (existing) table with no schema, and no changes will be made to an

2548

# existing table that has a schema.

2549

# Only for use with external storage.

2550

"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

2019-06-14 16:50:42 -0700

[diff] [blame]

2551

# dataset. If table_id is not set a new one will be generated

2552

# for you with the following format:

2553

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

2554

# generating the date details.

2555

#

2556

# For Inspect, each column in an existing output table must have the same

2557

# name, type, and mode of a field in the `Finding` object.

2558

#

2559

# For Risk, an existing output table should be the output of a previous

2560

# Risk analysis job run on the same source table, with the same privacy

2561

# metric and quasi-identifiers. Risk jobs that analyze the same table but

2562

# compute a different privacy metric, or use different sets of

2563

# quasi-identifiers, cannot store their results in the same table.

2564

# identified by its project_id, dataset_id, and table_name. Within a query

2565

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2566

# `<project_id>:<dataset_id>.<table_id>` or

2567

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2568

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2569

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2570

"datasetId": "A String", # Dataset ID of the table.

2571

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2572

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2573

},

2574

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2575

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

2576

# message contains a single field, `DlpJobName`, which is equal to the

2577

# finished job's

2578

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

2579

# Compatible with: Inspect, Risk

2580

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

2581

# publishing access rights to the DLP API service account executing

2582

# the long running DlpJob sending the notifications.

2583

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2584

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2585

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2586

# results of the DlpJob will be applied to the entry for the resource scanned

2587

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

2588

# be deleted. InfoType naming patterns are strictly enforced when using this

2589

# feature. Note that the findings will be persisted in Cloud Data Catalog

2590

# storage and are governed by Data Catalog service-specific policy, see

2591

# https://cloud.google.com/terms/service-terms

2592

# Only a single instance of this action can be specified and only allowed if

2593

# all resources being scanned are BigQuery tables.

2594

# Compatible with: Inspect

2595

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2596

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

2597

# will publish a metric to stack driver on each infotype requested and

2598

# how many findings were found for it. CustomDetectors will be bucketed

2599

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2600

},

2601

},

2602

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2603

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

2604

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

2605

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

2606

# by project and namespace, however the namespace ID may be empty.

2607

# A partition ID identifies a grouping of entities. The grouping is always

2608

# by project and namespace, however the namespace ID may be empty.

2609

#

2610

# A partition ID contains several dimensions:

2611

# project ID and namespace ID.

2612

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

2613

"projectId": "A String", # The ID of the project to which the entities belong.

2614

},

2615

"kind": { # A representation of a Datastore kind. # The kind to process.

2616

"name": "A String", # The name of the kind.

2617

},

2618

},

2619

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

2620

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

2621

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

2622

# Used for data sources like Datastore and BigQuery.

2623

#

2624

# For BigQuery:

2625

# Required to filter out rows based on the given start and

2626

# end times. If not specified and the table was modified between the given

2627

# start and end times, the entire table will be scanned.

2628

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

2629

# `TIMESTAMP`, or `DATETIME` BigQuery column.

2630

#

2631

# For Datastore.

2632

# Valid data types of the timestamp field are: `TIMESTAMP`.

2633

# Datastore entity will be scanned if the timestamp property does not

2634

# exist or its value is empty or invalid.

2635

"name": "A String", # Name describing the field.

2636

},

2637

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

2638

# a valid start_time to avoid scanning files that have not been modified

2639

# since the last time the JobTrigger executed. This will be based on the

2640

# time of the execution of the last run of the JobTrigger.

2641

"endTime": "A String", # Exclude files or rows newer than this value.

2642

# If set to zero, no upper time limit is applied.

2643

"startTime": "A String", # Exclude files or rows older than this value.

2644

},

2645

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

2646

# bucket.

2647

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

2648

# Number of files scanned is rounded down. Must be between 0 and 100,

2649

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

2650

"fileTypes": [ # List of file type groups to include in the scan.

2651

# If empty, all files are scanned and available data format processors

2652

# are applied. In addition, the binary content of the selected files

2653

# is always scanned as well.

2654

# Images are scanned only as binary if the specified region

2655

# does not support image inspection and no file_types were specified.

2656

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

2657

"A String",

2658

],

2659

"sampleMethod": "A String",

2660

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

2661

# number of bytes scanned is rounded down. Must be between 0 and 100,

2662

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

2663

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

2664

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

2665

# than this value then the rest of the bytes are omitted. Only one

2666

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

2667

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

2668

"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

2669

# `regex_file_set` must be set.

2670

# expressions are used to allow fine-grained control over which files in the

2671

# bucket to include.

2672

#

2673

# Included files are those that match at least one item in `include_regex` and

2674

# do not match any items in `exclude_regex`. Note that a file that matches

2675

# items from both lists will _not_ be included. For a match to occur, the

2676

# entire file path (i.e., everything in the url after the bucket name) must

2677

# match the regular expression.

2678

#

2679

# For example, given the input `{bucket_name: "mybucket", include_regex:

2680

# ["directory1/.*"], exclude_regex:

2681

# ["directory1/excluded.*"]}`:

2682

#

2683

# * `gs://mybucket/directory1/myfile` will be included

2684

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

2685

# across `/`)

2686

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

2687

# full path doesn't match any items in `include_regex`)

2688

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

2689

# matches an item in `exclude_regex`)

2690

#

2691

# If `include_regex` is left empty, it will match all files by default

2692

# (this is equivalent to setting `include_regex: [".*"]`).

2693

#

2694

# Some other common use cases:

2695

#

2696

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

2697

# files in `mybucket` except for .pdf files

2698

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

2699

# include all files directly under `gs://mybucket/directory/`, without matching

2700

# across `/`

2701

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

2702

# the bucket that match at least one of these regular expressions will be

2703

# excluded from the scan.

2704

#

2705

# Regular expressions use RE2

2706

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

2707

# under the google/re2 repository on GitHub.

2708

"A String",

2709

],

2710

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

2711

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

2712

# the bucket that match at least one of these regular expressions will be

2713

# included in the set of files, except for those that also match an item in

2714

# `exclude_regex`. Leaving this field empty will match all files by default

2715

# (this is equivalent to including `.*` in the list).

2716

#

2717

# Regular expressions use RE2

2718

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

2719

# under the google/re2 repository on GitHub.

"A String",

],

},

"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format

2724

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

2725

#

2726

# If the url ends in a trailing slash, the bucket or directory represented

2727

# by the url will be scanned non-recursively (content in sub-directories

2728

# will not be scanned). This means that `gs://mybucket/` is equivalent to

2729

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

2730

# `gs://mybucket/directory/*`.

2731

#

2732

# Exactly one of `url` or `regex_file_set` must be set.

2733

},

2734

},

2735

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

2736

"sampleMethod": "A String",

2737

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

2738

# identified by its project_id, dataset_id, and table_name. Within a query

2739

# a table is often referenced with a string in the format of:

2740

# `<project_id>:<dataset_id>.<table_id>` or

2741

# `<project_id>.<dataset_id>.<table_id>`.

2742

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

2743

# If omitted, project ID is inferred from the API call.

2744

"datasetId": "A String", # Dataset ID of the table.

2745

"tableId": "A String", # Name of the table.

2746

},

2747

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

2748

# `actions.saveFindings.outputConfig.table` is specified, the values of

2749

# columns specified here are available in the output table under

2750

# `location.content_locations.record_location.record_key.id_values`. Nested

2751

# fields such as `person.birthdate.year` are allowed.

2752

{ # General identifier of a data field in a storage service.

2753

"name": "A String", # Name describing the field.

2754

},

2755

],

2756

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

2757

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

2758

# 100 means no limit. Defaults to 0. Only one of rows_limit and

2759

# rows_limit_percent can be specified. Cannot be used in conjunction with

2760

# TimespanConfig.

2761

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

2762

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

2763

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

2764

# Cannot be used in conjunction with TimespanConfig.

2765

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

2766

# inspection of entire columns which you know have no findings.

2767

{ # General identifier of a data field in a storage service.

2768

"name": "A String", # Name describing the field.

},

],

},

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

2773

# Early access feature is in a pre-release state and might change or have

2774

# limited support. For more information, see

2775

# https://cloud.google.com/products#product-launch-stages.

2776

# of Google Cloud Platform.

2777

"labels": { # To organize findings, these labels will be added to each finding.

2778

#

2779

# Label keys must be between 1 and 63 characters long and must conform

2780

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

2781

#

2782

# Label values must be between 0 and 63 characters long and must conform

2783

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

2784

#

2785

# No more than 10 labels can be associated with a given finding.

2786

#

2787

# Examples:

2788

# * `"environment" : "production"`

2789

# * `"pipeline" : "etl"`

2790

"a_key": "A String",

2791

},

2792

"description": "A String", # A short description of where the data is coming from. Will be stored once

2793

# in the job. 256 max length.

2794

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

2795

# meaningful such as the columns that are primary keys.

2796

"identifyingFields": [ # The columns that are the primary keys for table objects included in

2797

# ContentItem. A copy of this cell's value will stored alongside alongside

2798

# each finding so that the finding can be traced to the specific row it came

2799

# from. No more than 3 may be provided.

2800

{ # General identifier of a data field in a storage service.

2801

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

2806

# 'finding_labels' map. Request may contain others, but any missing one of

2807

# these will be rejected.

2808

#

2809

# Label keys must be between 1 and 63 characters long and must conform

2810

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

2811

#

2812

# No more than 10 keys can be required.

"A String",

],

},

},

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

2818

# `inspect_config` will be merged into the values persisted as part of the

2819

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2820

},

2821

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

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

"abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran

2828

# out of quota or was ended before they could be processed.

2829

"pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated

2830

# when called via method `getDlpJob`.

2831

# A burst of traffic may cause hybrid inspect requests to be enqueued.

2832

# Processing will take place as quickly as possible, but resource limitations

2833

# may impact how long a request is enqueued for.

2834

"processedCount": "A String", # The number of hybrid inspection requests processed within this job.

2835

},

2836

"infoTypeStats": [ # Statistics of how many instances of each info type were found during

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2837

# inspect job.

2838

{ # Statistics regarding a specific InfoType.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2839

"count": "A String", # Number of findings for this 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

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

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. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2845

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2846

},

2847

},

2848

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2849

"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.

2850

"processedBytes": "A String", # Total size in bytes that were processed.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2851

},

2852

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

}</pre>

</div>

<code class="details" id="delete">delete(name, x__xgafv=None)</code>

2858

<pre>Deletes a long-running DlpJob. This method indicates that the client is

2859

no longer interested in the DlpJob result. The job will be cancelled if

2860

possible.

2861

See https://cloud.google.com/dlp/docs/inspecting-storage and

2862

https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more.

2863

2864

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2865

name: string, Required. The name of the DlpJob resource to be deleted. (required)

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2866

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

2873

2874

{ # A generic empty message that you can re-use to avoid defining duplicated

2875

# empty messages in your APIs. A typical example is to use it as the request

2876

# or the response type of an API method. For instance:

2877

#

2878

# service Foo {

2879

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

2880

# }

2881

#

2882

# The JSON representation for `Empty` is empty JSON object `{}`.

}</pre>

</div>

<code class="details" id="get">get(name, x__xgafv=None)</code>

2888

<pre>Gets the latest state of a long-running DlpJob.

2889

See https://cloud.google.com/dlp/docs/inspecting-storage and

2890

https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more.

2891

2892

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2893

name: string, Required. The name of the DlpJob resource. (required)

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2894

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

2901

2902

{ # Combines all of the information about a DLP job.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2903

"createTime": "A String", # Time when the job was created.

2904

"state": "A String", # State of a job.

2905

"riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source.

2906

"numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result

2907

"minValue": { # Set of primitive values supported by the system. # Minimum value appearing in the column.

2908

# Note that for the purposes of inspection or transformation, the number

2909

# of bytes considered to comprise a 'Value' is based on its representation

2910

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

2911

# 123456789, the number of bytes would be counted as 9, even though an

2912

# int64 only holds up to 8 bytes of data.

2913

"booleanValue": True or False, # boolean

2914

"floatValue": 3.14, # float

2915

"dayOfWeekValue": "A String", # day of week

2916

"timestampValue": "A String", # timestamp

2917

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

2918

# and time zone are either specified elsewhere or are not significant. The date

2919

# is relative to the Proleptic Gregorian Calendar. This can represent:

2920

#

2921

# * A full date, with non-zero year, month and day values

2922

# * A month and day value, with a zero year, e.g. an anniversary

2923

# * A year on its own, with zero month and day values

2924

# * A year and month value, with a zero day, e.g. a credit card expiration date

2925

#

2926

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

2927

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

2928

# a year.

2929

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

2930

# month and day.

2931

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

2932

# if specifying a year by itself or a year and month where the day is not

2933

# significant.

2934

},

2935

"stringValue": "A String", # string

2936

"integerValue": "A String", # integer

2937

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

2938

# or are specified elsewhere. An API may choose to allow leap seconds. Related

2939

# types are google.type.Date and `google.protobuf.Timestamp`.

2940

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

2941

# allow the value 60 if it allows leap-seconds.

2942

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

2943

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

2944

# to allow the value "24:00:00" for scenarios like business closing time.

2945

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

2946

},

2947

},

2948

"maxValue": { # Set of primitive values supported by the system. # Maximum value appearing in the column.

2949

# Note that for the purposes of inspection or transformation, the number

2950

# of bytes considered to comprise a 'Value' is based on its representation

2951

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

2952

# 123456789, the number of bytes would be counted as 9, even though an

2953

# int64 only holds up to 8 bytes of data.

2954

"booleanValue": True or False, # boolean

2955

"floatValue": 3.14, # float

2956

"dayOfWeekValue": "A String", # day of week

2957

"timestampValue": "A String", # timestamp

2958

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

2959

# and time zone are either specified elsewhere or are not significant. The date

2960

# is relative to the Proleptic Gregorian Calendar. This can represent:

2961

#

2962

# * A full date, with non-zero year, month and day values

2963

# * A month and day value, with a zero year, e.g. an anniversary

2964

# * A year on its own, with zero month and day values

2965

# * A year and month value, with a zero day, e.g. a credit card expiration date

2966

#

2967

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

2968

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

2969

# a year.

2970

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

2971

# month and day.

2972

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

2973

# if specifying a year by itself or a year and month where the day is not

2974

# significant.

2975

},

2976

"stringValue": "A String", # string

2977

"integerValue": "A String", # integer

2978

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

2979

# or are specified elsewhere. An API may choose to allow leap seconds. Related

2980

# types are google.type.Date and `google.protobuf.Timestamp`.

2981

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

2982

# allow the value 60 if it allows leap-seconds.

2983

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

2984

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

2985

# to allow the value "24:00:00" for scenarios like business closing time.

2986

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

2987

},

2988

},

2989

"quantileValues": [ # List of 99 values that partition the set of field values into 100 equal

2990

# sized buckets.

2991

{ # Set of primitive values supported by the system.

2992

# Note that for the purposes of inspection or transformation, the number

2993

# of bytes considered to comprise a 'Value' is based on its representation

2994

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

2995

# 123456789, the number of bytes would be counted as 9, even though an

2996

# int64 only holds up to 8 bytes of data.

2997

"booleanValue": True or False, # boolean

2998

"floatValue": 3.14, # float

2999

"dayOfWeekValue": "A String", # day of week

3000

"timestampValue": "A String", # timestamp

3001

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

3002

# and time zone are either specified elsewhere or are not significant. The date

3003

# is relative to the Proleptic Gregorian Calendar. This can represent:

3004

#

3005

# * A full date, with non-zero year, month and day values

3006

# * A month and day value, with a zero year, e.g. an anniversary

3007

# * A year on its own, with zero month and day values

3008

# * A year and month value, with a zero day, e.g. a credit card expiration date

3009

#

3010

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

3011

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

3012

# a year.

3013

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

3014

# month and day.

3015

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

3016

# if specifying a year by itself or a year and month where the day is not

3017

# significant.

3018

},

3019

"stringValue": "A String", # string

3020

"integerValue": "A String", # integer

3021

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

3022

# or are specified elsewhere. An API may choose to allow leap seconds. Related

3023

# types are google.type.Date and `google.protobuf.Timestamp`.

3024

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

3025

# allow the value 60 if it allows leap-seconds.

3026

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

3027

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

3028

# to allow the value "24:00:00" for scenarios like business closing time.

3029

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

},

"lDiversityResult": { # Result of the l-diversity computation. # L-divesity result

3035

"sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.

3036

{ # Histogram of l-diversity equivalence class sensitive value frequencies.

3037

"sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence

3038

# classes in this bucket.

3039

"sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence

3040

# classes in this bucket.

3041

"bucketSize": "A String", # Total number of equivalence classes in this bucket.

3042

"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.

3043

"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of

3044

# classes returned per bucket is capped at 20.

3045

{ # The set of columns' values that share the same ldiversity value.

3046

"quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence

3047

# class. The order is always the same as the original request.

3048

{ # Set of primitive values supported by the system.

3049

# Note that for the purposes of inspection or transformation, the number

3050

# of bytes considered to comprise a 'Value' is based on its representation

3051

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

3052

# 123456789, the number of bytes would be counted as 9, even though an

3053

# int64 only holds up to 8 bytes of data.

3054

"booleanValue": True or False, # boolean

3055

"floatValue": 3.14, # float

3056

"dayOfWeekValue": "A String", # day of week

3057

"timestampValue": "A String", # timestamp

3058

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

3059

# and time zone are either specified elsewhere or are not significant. The date

3060

# is relative to the Proleptic Gregorian Calendar. This can represent:

3061

#

3062

# * A full date, with non-zero year, month and day values

3063

# * A month and day value, with a zero year, e.g. an anniversary

3064

# * A year on its own, with zero month and day values

3065

# * A year and month value, with a zero day, e.g. a credit card expiration date

3066

#

3067

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

3068

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

3069

# a year.

3070

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

3071

# month and day.

3072

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

3073

# if specifying a year by itself or a year and month where the day is not

3074

# significant.

3075

},

3076

"stringValue": "A String", # string

3077

"integerValue": "A String", # integer

3078

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

3079

# or are specified elsewhere. An API may choose to allow leap seconds. Related

3080

# types are google.type.Date and `google.protobuf.Timestamp`.

3081

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

3082

# allow the value 60 if it allows leap-seconds.

3083

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

3084

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

3085

# to allow the value "24:00:00" for scenarios like business closing time.

3086

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

"equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.

3091

"numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class.

3092

"topSensitiveValues": [ # Estimated frequencies of top sensitive values.

3093

{ # A value of a field, including its frequency.

3094

"value": { # Set of primitive values supported by the system. # A value contained in the field in question.

3095

# Note that for the purposes of inspection or transformation, the number

3096

# of bytes considered to comprise a 'Value' is based on its representation

3097

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

3098

# 123456789, the number of bytes would be counted as 9, even though an

3099

# int64 only holds up to 8 bytes of data.

3100

"booleanValue": True or False, # boolean

3101

"floatValue": 3.14, # float

3102

"dayOfWeekValue": "A String", # day of week

3103

"timestampValue": "A String", # timestamp

3104

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

3105

# and time zone are either specified elsewhere or are not significant. The date

3106

# is relative to the Proleptic Gregorian Calendar. This can represent:

3107

#

3108

# * A full date, with non-zero year, month and day values

3109

# * A month and day value, with a zero year, e.g. an anniversary

3110

# * A year on its own, with zero month and day values

3111

# * A year and month value, with a zero day, e.g. a credit card expiration date

3112

#

3113

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

3114

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

3115

# a year.

3116

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

3117

# month and day.

3118

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

3119

# if specifying a year by itself or a year and month where the day is not

3120

# significant.

3121

},

3122

"stringValue": "A String", # string

3123

"integerValue": "A String", # integer

3124

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

3125

# or are specified elsewhere. An API may choose to allow leap seconds. Related

3126

# types are google.type.Date and `google.protobuf.Timestamp`.

3127

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

3128

# allow the value 60 if it allows leap-seconds.

3129

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

3130

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

3131

# to allow the value "24:00:00" for scenarios like business closing time.

3132

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

3133

},

3134

},

3135

"count": "A String", # How many times the value is contained in the field.

},

],

},

],

},

],

},

"requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.

3144

"categoricalStatsConfig": { # Compute numerical stats over an individual column, including # Categorical stats

3145

# number of distinct values and value count distribution.

3146

"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are

3147

# supported except for arrays and structs. However, it may be more

3148

# informative to use NumericalStats when the field type is supported,

3149

# depending on the data.

3150

"name": "A String", # Name describing the field.

3151

},

3152

},

3153

"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity

3154

"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are

3155

# specified, they are considered a single composite key. Structs and

3156

# repeated data types are not supported; however, nested fields are

3157

# supported so long as they are not structs themselves or nested within

3158

# a repeated field.

3159

{ # General identifier of a data field in a storage service.

3160

"name": "A String", # Name describing the field.

3161

},

3162

],

3163

"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

3164

# single individual. If the same entity_id is associated to multiple

3165

# quasi-identifier tuples over distinct rows, we consider the entire

3166

# collection of tuples as the composite quasi-identifier. This collection

3167

# is a multiset: the order in which the different tuples appear in the

3168

# dataset is ignored, but their frequency is taken into account.

3169

#

3170

# Important note: a maximum of 1000 rows can be associated to a single

3171

# entity ID. If more rows are associated with the same entity ID, some

3172

# might be ignored.

3173

# single person. For example, in medical records the `EntityId` might be a

3174

# patient identifier, or for financial records it might be an account

3175

# identifier. This message is used when generalizations or analysis must take

3176

# into account that multiple rows correspond to the same entity.

3177

"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.

3178

"name": "A String", # Name describing the field.

},

},

},

"numericalStatsConfig": { # Compute numerical stats over an individual column, including # Numerical stats

3183

# min, max, and quantiles.

3184

"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are

3185

# integer, float, date, datetime, timestamp, time.

3186

"name": "A String", # Name describing the field.

3187

},

3188

},

3189

"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what # k-map

3190

# is called "journalist risk" in the literature, except the attack dataset is

3191

# statistically modeled instead of being perfectly known. This can be done

3192

# using publicly available data (like the US Census), or using a custom

3193

# statistical model (indicated as one or several BigQuery tables), or by

3194

# extrapolating from the distribution of values in the input dataset.

3195

"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.

3196

# Set if no column is tagged with a region-specific InfoType (like

3197

# US_ZIP_5) or a region code.

3198

"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag

3199

# used to tag a quasi-identifiers column must appear in exactly one column

3200

# of one auxiliary table.

3201

{ # An auxiliary table contains statistical information on the relative

3202

# frequency of different quasi-identifiers values. It has one or several

3203

# quasi-identifiers columns, and one column that indicates the relative

3204

# frequency of each quasi-identifier tuple.

3205

# If a tuple is present in the data but not in the auxiliary table, the

3206

# corresponding relative frequency is assumed to be zero (and thus, the

3207

# tuple is highly reidentifiable).

3208

"table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location.

3209

# identified by its project_id, dataset_id, and table_name. Within a query

3210

# a table is often referenced with a string in the format of:

3211

# `<project_id>:<dataset_id>.<table_id>` or

3212

# `<project_id>.<dataset_id>.<table_id>`.

3213

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

3214

# If omitted, project ID is inferred from the API call.

3215

"datasetId": "A String", # Dataset ID of the table.

3216

"tableId": "A String", # Name of the table.

3217

},

3218

"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number

3219

# between 0 and 1 (inclusive). Null values are assumed to be zero.

3220

"name": "A String", # Name describing the field.

3221

},

3222

"quasiIds": [ # Required. Quasi-identifier columns.

3223

{ # A quasi-identifier column has a custom_tag, used to know which column

3224

# in the data corresponds to which column in the statistical model.

3225

"customTag": "A String", # A auxiliary field.

3226

"field": { # General identifier of a data field in a storage service. # Identifies the column.

3227

"name": "A String", # Name describing the field.

},

},

],

},

],

"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the

3234

# same tag.

3235

{ # A column with a semantic tag attached.

3236

"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.

3237

"name": "A String", # Name describing the field.

3238

},

3239

"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public

3240

# dataset as a statistical model of population, if available. We

3241

# currently support US ZIP codes, region codes, ages and genders.

3242

# To programmatically obtain the list of supported InfoTypes, use

3243

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

3244

"name": "A String", # Name of the information type. Either a name of your choosing when

3245

# creating a CustomInfoType, or one of the names listed

3246

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3247

# a built-in type. InfoType names should conform to the pattern

3248

# `[a-zA-Z0-9_]{1,64}`.

3249

},

3250

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

3251

# indicate an auxiliary table that contains statistical information on

3252

# the possible values of this column (below).

3253

"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

3254

# the distribution of values in the input data

3255

# empty messages in your APIs. A typical example is to use it as the request

3256

# or the response type of an API method. For instance:

3257

#

3258

# service Foo {

3259

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

3260

# }

3261

#

3262

# The JSON representation for `Empty` is empty JSON object `{}`.

},

},

],

},

"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity

3268

"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are

3269

# defined for the l-diversity computation. When multiple fields are

3270

# specified, they are considered a single composite key.

3271

{ # General identifier of a data field in a storage service.

3272

"name": "A String", # Name describing the field.

3273

},

3274

],

3275

"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.

3276

"name": "A String", # Name describing the field.

3277

},

3278

},

3279

"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to # delta-presence

3280

# figure out that one given individual appears in a de-identified dataset.

3281

# Similarly to the k-map metric, we cannot compute δ-presence exactly without

3282

# knowing the attack dataset, so we use a statistical model instead.

3283

"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the

3284

# same tag.

3285

{ # A column with a semantic tag attached.

3286

"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.

3287

"name": "A String", # Name describing the field.

3288

},

3289

"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public

3290

# dataset as a statistical model of population, if available. We

3291

# currently support US ZIP codes, region codes, ages and genders.

3292

# To programmatically obtain the list of supported InfoTypes, use

3293

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

3294

"name": "A String", # Name of the information type. Either a name of your choosing when

3295

# creating a CustomInfoType, or one of the names listed

3296

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3297

# a built-in type. InfoType names should conform to the pattern

3298

# `[a-zA-Z0-9_]{1,64}`.

3299

},

3300

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

3301

# indicate an auxiliary table that contains statistical information on

3302

# the possible values of this column (below).

3303

"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

3304

# the distribution of values in the input data

3305

# empty messages in your APIs. A typical example is to use it as the request

3306

# or the response type of an API method. For instance:

3307

#

3308

# service Foo {

3309

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

3310

# }

3311

#

3312

# The JSON representation for `Empty` is empty JSON object `{}`.

},

},

],

"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.

3317

# Set if no column is tagged with a region-specific InfoType (like

3318

# US_ZIP_5) or a region code.

3319

"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag

3320

# used to tag a quasi-identifiers field must appear in exactly one

3321

# field of one auxiliary table.

3322

{ # An auxiliary table containing statistical information on the relative

3323

# frequency of different quasi-identifiers values. It has one or several

3324

# quasi-identifiers columns, and one column that indicates the relative

3325

# frequency of each quasi-identifier tuple.

3326

# If a tuple is present in the data but not in the auxiliary table, the

3327

# corresponding relative frequency is assumed to be zero (and thus, the

3328

# tuple is highly reidentifiable).

3329

"table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location.

3330

# identified by its project_id, dataset_id, and table_name. Within a query

3331

# a table is often referenced with a string in the format of:

3332

# `<project_id>:<dataset_id>.<table_id>` or

3333

# `<project_id>.<dataset_id>.<table_id>`.

3334

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

3335

# If omitted, project ID is inferred from the API call.

3336

"datasetId": "A String", # Dataset ID of the table.

3337

"tableId": "A String", # Name of the table.

3338

},

3339

"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number

3340

# between 0 and 1 (inclusive). Null values are assumed to be zero.

3341

"name": "A String", # Name describing the field.

3342

},

3343

"quasiIds": [ # Required. Quasi-identifier columns.

3344

{ # A quasi-identifier column has a custom_tag, used to know which column

3345

# in the data corresponds to which column in the statistical model.

3346

"field": { # General identifier of a data field in a storage service. # Identifies the column.

3347

"name": "A String", # Name describing the field.

3348

},

3349

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

3350

# indicate an auxiliary table that contains statistical information on

3351

# the possible values of this column (below).

},

],

},

],

},

},

"categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result

3359

"valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.

3360

{ # Histogram of value frequencies in the column.

3361

"bucketValues": [ # Sample of value frequencies in this bucket. The total number of

3362

# values returned per bucket is capped at 20.

3363

{ # A value of a field, including its frequency.

3364

"value": { # Set of primitive values supported by the system. # A value contained in the field in question.

3365

# Note that for the purposes of inspection or transformation, the number

3366

# of bytes considered to comprise a 'Value' is based on its representation

3367

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

3368

# 123456789, the number of bytes would be counted as 9, even though an

3369

# int64 only holds up to 8 bytes of data.

3370

"booleanValue": True or False, # boolean

3371

"floatValue": 3.14, # float

3372

"dayOfWeekValue": "A String", # day of week

3373

"timestampValue": "A String", # timestamp

3374

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

3375

# and time zone are either specified elsewhere or are not significant. The date

3376

# is relative to the Proleptic Gregorian Calendar. This can represent:

3377

#

3378

# * A full date, with non-zero year, month and day values

3379

# * A month and day value, with a zero year, e.g. an anniversary

3380

# * A year on its own, with zero month and day values

3381

# * A year and month value, with a zero day, e.g. a credit card expiration date

3382

#

3383

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

3384

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

3385

# a year.

3386

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

3387

# month and day.

3388

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

3389

# if specifying a year by itself or a year and month where the day is not

3390

# significant.

3391

},

3392

"stringValue": "A String", # string

3393

"integerValue": "A String", # integer

3394

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

3395

# or are specified elsewhere. An API may choose to allow leap seconds. Related

3396

# types are google.type.Date and `google.protobuf.Timestamp`.

3397

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

3398

# allow the value 60 if it allows leap-seconds.

3399

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

3400

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

3401

# to allow the value "24:00:00" for scenarios like business closing time.

3402

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

3403

},

3404

},

3405

"count": "A String", # How many times the value is contained in the field.

3406

},

3407

],

3408

"valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.

3409

"valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.

3410

"bucketSize": "A String", # Total number of values in this bucket.

3411

"bucketValueCount": "A String", # Total number of distinct values in this bucket.

},

],

},

"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an # K-map result

3416

# estimation, not exact values.

3417

"kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value

3418

# doesn't correspond to any such interval, the associated frequency is

3419

# zero. For example, the following records:

3420

# {min_anonymity: 1, max_anonymity: 1, frequency: 17}

3421

# {min_anonymity: 2, max_anonymity: 3, frequency: 42}

3422

# {min_anonymity: 5, max_anonymity: 10, frequency: 99}

3423

# mean that there are no record with an estimated anonymity of 4, 5, or

3424

# larger than 10.

3425

{ # A KMapEstimationHistogramBucket message with the following values:

# min_anonymity: 3

# max_anonymity: 5

# frequency: 42

# means that there are 42 records whose quasi-identifier values correspond

3430

# to 3, 4 or 5 people in the overlying population. An important particular

3431

# case is when min_anonymity = max_anonymity = 1: the frequency field then

3432

# corresponds to the number of uniquely identifiable records.

3433

"bucketSize": "A String", # Number of records within these anonymity bounds.

3434

"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.

3435

"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.

3436

"minAnonymity": "A String", # Always positive.

3437

"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total

3438

# number of classes returned per bucket is capped at 20.

3439

{ # A tuple of values for the quasi-identifier columns.

3440

"estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values.

3441

"quasiIdsValues": [ # The quasi-identifier values.

3442

{ # Set of primitive values supported by the system.

3443

# Note that for the purposes of inspection or transformation, the number

3444

# of bytes considered to comprise a 'Value' is based on its representation

3445

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

3446

# 123456789, the number of bytes would be counted as 9, even though an

3447

# int64 only holds up to 8 bytes of data.

3448

"booleanValue": True or False, # boolean

3449

"floatValue": 3.14, # float

3450

"dayOfWeekValue": "A String", # day of week

3451

"timestampValue": "A String", # timestamp

3452

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

3453

# and time zone are either specified elsewhere or are not significant. The date

3454

# is relative to the Proleptic Gregorian Calendar. This can represent:

3455

#

3456

# * A full date, with non-zero year, month and day values

3457

# * A month and day value, with a zero year, e.g. an anniversary

3458

# * A year on its own, with zero month and day values

3459

# * A year and month value, with a zero day, e.g. a credit card expiration date

3460

#

3461

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

3462

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

3463

# a year.

3464

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

3465

# month and day.

3466

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

3467

# if specifying a year by itself or a year and month where the day is not

3468

# significant.

3469

},

3470

"stringValue": "A String", # string

3471

"integerValue": "A String", # integer

3472

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

3473

# or are specified elsewhere. An API may choose to allow leap seconds. Related

3474

# types are google.type.Date and `google.protobuf.Timestamp`.

3475

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

3476

# allow the value 60 if it allows leap-seconds.

3477

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

3478

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

3479

# to allow the value "24:00:00" for scenarios like business closing time.

3480

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

},

],

},

],

},

"kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result

3490

"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.

3491

{ # Histogram of k-anonymity equivalence classes.

3492

"bucketSize": "A String", # Total number of equivalence classes in this bucket.

3493

"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.

3494

"equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket.

3495

"equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket.

3496

"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of

3497

# classes returned per bucket is capped at 20.

3498

{ # The set of columns' values that share the same ldiversity value

3499

"quasiIdsValues": [ # Set of values defining the equivalence class. One value per

3500

# quasi-identifier column in the original KAnonymity metric message.

3501

# The order is always the same as the original request.

3502

{ # Set of primitive values supported by the system.

3503

# Note that for the purposes of inspection or transformation, the number

3504

# of bytes considered to comprise a 'Value' is based on its representation

3505

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

3506

# 123456789, the number of bytes would be counted as 9, even though an

3507

# int64 only holds up to 8 bytes of data.

3508

"booleanValue": True or False, # boolean

3509

"floatValue": 3.14, # float

3510

"dayOfWeekValue": "A String", # day of week

3511

"timestampValue": "A String", # timestamp

3512

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

3513

# and time zone are either specified elsewhere or are not significant. The date

3514

# is relative to the Proleptic Gregorian Calendar. This can represent:

3515

#

3516

# * A full date, with non-zero year, month and day values

3517

# * A month and day value, with a zero year, e.g. an anniversary

3518

# * A year on its own, with zero month and day values

3519

# * A year and month value, with a zero day, e.g. a credit card expiration date

3520

#

3521

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

3522

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

3523

# a year.

3524

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

3525

# month and day.

3526

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

3527

# if specifying a year by itself or a year and month where the day is not

3528

# significant.

3529

},

3530

"stringValue": "A String", # string

3531

"integerValue": "A String", # integer

3532

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

3533

# or are specified elsewhere. An API may choose to allow leap seconds. Related

3534

# types are google.type.Date and `google.protobuf.Timestamp`.

3535

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

3536

# allow the value 60 if it allows leap-seconds.

3537

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

3538

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

3539

# to allow the value "24:00:00" for scenarios like business closing time.

3540

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the

3545

# above set of values.

},

],

},

],

},

"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an # Delta-presence result

3552

# estimation, not exact values.

3553

"deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a

3554

# value doesn't correspond to any such interval, the associated frequency

3555

# is zero. For example, the following records:

3556

# {min_probability: 0, max_probability: 0.1, frequency: 17}

3557

# {min_probability: 0.2, max_probability: 0.3, frequency: 42}

3558

# {min_probability: 0.3, max_probability: 0.4, frequency: 99}

3559

# mean that there are no record with an estimated probability in [0.1, 0.2)

3560

# nor larger or equal to 0.4.

3561

{ # A DeltaPresenceEstimationHistogramBucket message with the following

3562

# values:

3563

# min_probability: 0.1

3564

# max_probability: 0.2

3565

# frequency: 42

3566

# means that there are 42 records for which δ is in [0.1, 0.2). An

3567

# important particular case is when min_probability = max_probability = 1:

3568

# then, every individual who shares this quasi-identifier combination is in

3569

# the dataset.

3570

"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total

3571

# number of classes returned per bucket is capped at 20.

3572

{ # A tuple of values for the quasi-identifier columns.

3573

"quasiIdsValues": [ # The quasi-identifier values.

3574

{ # Set of primitive values supported by the system.

3575

# Note that for the purposes of inspection or transformation, the number

3576

# of bytes considered to comprise a 'Value' is based on its representation

3577

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

3578

# 123456789, the number of bytes would be counted as 9, even though an

3579

# int64 only holds up to 8 bytes of data.

3580

"booleanValue": True or False, # boolean

3581

"floatValue": 3.14, # float

3582

"dayOfWeekValue": "A String", # day of week

3583

"timestampValue": "A String", # timestamp

3584

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

3585

# and time zone are either specified elsewhere or are not significant. The date

3586

# is relative to the Proleptic Gregorian Calendar. This can represent:

3587

#

3588

# * A full date, with non-zero year, month and day values

3589

# * A month and day value, with a zero year, e.g. an anniversary

3590

# * A year on its own, with zero month and day values

3591

# * A year and month value, with a zero day, e.g. a credit card expiration date

3592

#

3593

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

3594

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

3595

# a year.

3596

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

3597

# month and day.

3598

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

3599

# if specifying a year by itself or a year and month where the day is not

3600

# significant.

3601

},

3602

"stringValue": "A String", # string

3603

"integerValue": "A String", # integer

3604

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

3605

# or are specified elsewhere. An API may choose to allow leap seconds. Related

3606

# types are google.type.Date and `google.protobuf.Timestamp`.

3607

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

3608

# allow the value 60 if it allows leap-seconds.

3609

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

3610

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

3611

# to allow the value "24:00:00" for scenarios like business closing time.

3612

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

"estimatedProbability": 3.14, # The estimated probability that a given individual sharing these

3617

# quasi-identifier values is in the dataset. This value, typically called

3618

# δ, is the ratio between the number of records in the dataset with these

3619

# quasi-identifier values, and the total number of individuals (inside

3620

# *and* outside the dataset) with these quasi-identifier values.

3621

# For example, if there are 15 individuals in the dataset who share the

3622

# same quasi-identifier values, and an estimated 100 people in the entire

3623

# population with these values, then δ is 0.15.

3624

},

3625

],

3626

"minProbability": 3.14, # Between 0 and 1.

3627

"maxProbability": 3.14, # Always greater than or equal to min_probability.

3628

"bucketSize": "A String", # Number of records within these probability bounds.

3629

"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.

},

],

},

"requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over.

3634

# identified by its project_id, dataset_id, and table_name. Within a query

3635

# a table is often referenced with a string in the format of:

3636

# `<project_id>:<dataset_id>.<table_id>` or

3637

# `<project_id>.<dataset_id>.<table_id>`.

3638

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

3639

# If omitted, project ID is inferred from the API call.

3640

"datasetId": "A String", # Dataset ID of the table.

3641

"tableId": "A String", # Name of the table.

3642

},

3643

},

3644

"jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that

3645

# instantiated the job.

3646

"errors": [ # A stream of errors encountered running the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3647

{ # Details information about an error encountered during job execution or

3648

# the results of an unsuccessful activation of the JobTrigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3649

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3650

# different programming environments, including REST APIs and RPC APIs. It is

3651

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

3652

# three pieces of data: error code, error message, and error details.

3653

#

3654

# You can find out more about this error model and how to work with it in the

3655

# [API Design Guide](https://cloud.google.com/apis/design/errors).

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3656

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

3657

"message": "A String", # A developer-facing error message, which should be in English. Any

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3658

# user-facing error message should be localized and sent in the

3659

# google.rpc.Status.details field, or localized by the client.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3660

"details": [ # A list of messages that carry the error details. There is a common set of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3661

# message types for APIs to use.

3662

{

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3663

"a_key": "", # Properties of the object. Contains field @type with type URL.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3664

},

3665

],

3666

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3667

"timestamps": [ # The times the error occurred.

3668

"A String",

3669

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3670

},

3671

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3672

"name": "A String", # The server-assigned name.

3673

"type": "A String", # The type of job.

3674

"endTime": "A String", # Time when the job finished.

3675

"startTime": "A String", # Time when the job started.

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

"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

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3679

# this run.

3680

# to be detected) to be used anywhere you otherwise would normally specify

3681

# InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates

3682

# to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3683

"displayName": "A String", # Display name (max 256 chars).

3684

"inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3685

# When used with redactContent only info_types and min_likelihood are currently

3686

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3687

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

3688

# included in the response; see Finding.quote.

3689

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

3690

# Exclusion rules, contained in the set are executed in the end, other

3691

# rules are executed in the order they are specified for each info type.

3692

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

3693

# circumstances, depending on the specific details of the rules within the set.

3694

"infoTypes": [ # List of infoTypes this rule set is applied to.

3695

{ # Type of information detected by the API.

3696

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3697

# creating a CustomInfoType, or one of the names listed

3698

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3699

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3700

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3701

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3702

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3703

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3704

{ # A single inspection rule to be applied to infoTypes, specified in

3705

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3706

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3707

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3708

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3709

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3710

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3711

# levels. For example, if a finding would be `POSSIBLE` without the

3712

# detection rule and `relative_likelihood` is 1, then it is upgraded to

3713

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

3714

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

3715

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

3716

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

3717

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3718

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3719

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3720

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

3721

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3722

# specified, the entire match is returned. No more than 3 may be included.

3723

42,

3724

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3725

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3726

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3727

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3728

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3729

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

3730

# The total length of the window cannot exceed 1000 characters. Note that

3731

# the finding itself will be included in the window, so that hotwords may

3732

# be used to match substrings of the finding itself. For example, the

3733

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

3734

# adjusted upwards if the area code is known to be the local area code of

3735

# a company office using the hotword regex "\(xxx\)", where "xxx"

3736

# is the area code in question.

3737

# rule.

3738

"windowBefore": 42, # Number of characters before the finding to consider.

3739

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3740

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3741

},

3742

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

3743

# `InspectionRuleSet` are removed from results.

3744

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3745

# be used to match sensitive information specific to the data, such as a list

3746

# of employee IDs or job titles.

3747

#

3748

# Dictionary words are case-insensitive and all characters other than letters

3749

# and digits in the unicode [Basic Multilingual

3750

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

3751

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3752

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

3753

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3754

# surrounding any match must be of a different type than the adjacent

3755

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3756

# digits next to non-digits. For example, the dictionary word "jen" will

3757

# match the first three letters of the text "jen123" but will return no

3758

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3759

#

3760

# Dictionary words containing a large number of characters that are not

3761

# letters or digits may result in unexpected findings because such characters

3762

# are treated as whitespace. The

3763

# [limits](https://cloud.google.com/dlp/limits) page contains details about

3764

# the size limits of dictionaries. For dictionaries that do not fit within

3765

# these constraints, consider using `LargeCustomDictionaryConfig` in the

3766

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3767

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

3768

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3769

# at least one phrase and every phrase must contain at least 2 characters

3770

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3771

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3772

],

3773

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3774

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3775

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3776

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3777

# Example: gs://[BUCKET_NAME]/dictionary.txt

3778

},

3779

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3780

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

3781

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3782

# specified, the entire match is returned. No more than 3 may be included.

3783

42,

3784

],

3785

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3786

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3787

# google/re2 repository on GitHub.

3788

},

3789

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

3790

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

3791

# contained within with a finding of an infoType from this list. For

3792

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

3793

# `exclusion_rule` containing `exclude_info_types.info_types` with

3794

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

3795

# with EMAIL_ADDRESS finding.

3796

# That leads to "555-222-2222@example.org" to generate only a single

3797

# finding, namely email address.

3798

{ # Type of information detected by the API.

3799

"name": "A String", # Name of the information type. Either a name of your choosing when

3800

# creating a CustomInfoType, or one of the names listed

3801

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3802

# a built-in type. InfoType names should conform to the pattern

3803

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3808

},

3809

},

3810

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3811

},

3812

],

3813

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

3814

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

3815

# When set within `InspectJobConfig`,

3816

# the maximum returned is 2000 regardless if this is set higher.

3817

# When set within `InspectContentRequest`, this field is ignored.

3818

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

3819

{ # Max findings configuration per infoType, per content item or long

3820

# running DlpJob.

3821

"maxFindings": 42, # Max findings limit for the given infoType.

3822

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

3823

# info_type should be provided. If InfoTypeLimit does not have an

3824

# info_type, the DLP API applies the limit against all info_types that

3825

# are found but not specified in another InfoTypeLimit.

3826

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3827

# creating a CustomInfoType, or one of the names listed

3828

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3829

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3830

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3831

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3832

},

3833

],

3834

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

3835

# When set within `InspectContentRequest`, the maximum returned is 2000

3836

# regardless if this is set higher.

3837

},

3838

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3839

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3840

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3841

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3842

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3843

# InfoType values returned by ListInfoTypes or listed at

3844

# https://cloud.google.com/dlp/docs/infotypes-reference.

3845

#

3846

# When no InfoTypes or CustomInfoTypes are specified in a request, the

3847

# system may automatically choose what detectors to run. By default this may

3848

# be all types, but may change over time as detectors are updated.

3849

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3850

# If you need precise control and predictability as to what detectors are

3851

# run you should specify specific InfoTypes listed in the reference,

3852

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3853

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3854

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3855

# creating a CustomInfoType, or one of the names listed

3856

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3857

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3858

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3859

},

3860

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3861

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

3862

# POSSIBLE.

3863

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

3864

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

3865

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

3866

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

3867

{ # Custom information type provided by the user. Used to find domain-specific

3868

# sensitive information configurable to the data in question.

3869

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

3870

# altered by a detection rule if the finding meets the criteria specified by

3871

# the rule. Defaults to `VERY_LIKELY` if not specified.

3872

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

3873

# infoType, when the name matches one of existing infoTypes and that infoType

3874

# is specified in `InspectContent.info_types` field. Specifying the latter

3875

# adds findings to the one detected by the system. If built-in info type is

3876

# not specified in `InspectContent.info_types` list then the name is treated

3877

# as a custom info type.

3878

"name": "A String", # Name of the information type. Either a name of your choosing when

3879

# creating a CustomInfoType, or one of the names listed

3880

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3881

# a built-in type. InfoType names should conform to the pattern

3882

# `[a-zA-Z0-9_]{1,64}`.

3883

},

3884

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

3885

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3886

# specified, the entire match is returned. No more than 3 may be included.

3887

42,

3888

],

3889

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3890

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3891

# google/re2 repository on GitHub.

3892

},

3893

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

3894

# Rules are applied in order that they are specified. Not supported for the

3895

# `surrogate_type` CustomInfoType.

3896

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

3897

# `CustomInfoType` to alter behavior under certain circumstances, depending

3898

# on the specific details of the rule. Not supported for the `surrogate_type`

3899

# custom infoType.

3900

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

3901

# proximity of hotwords.

3902

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

3903

# part of a detection rule.

3904

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

3905

# levels. For example, if a finding would be `POSSIBLE` without the

3906

# detection rule and `relative_likelihood` is 1, then it is upgraded to

3907

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

3908

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

3909

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

3910

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

3911

# a final likelihood of `LIKELY`.

3912

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

3913

},

3914

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

3915

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3916

# specified, the entire match is returned. No more than 3 may be included.

3917

42,

3918

],

3919

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3920

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3921

# google/re2 repository on GitHub.

3922

},

3923

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

3924

# The total length of the window cannot exceed 1000 characters. Note that

3925

# the finding itself will be included in the window, so that hotwords may

3926

# be used to match substrings of the finding itself. For example, the

3927

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

3928

# adjusted upwards if the area code is known to be the local area code of

3929

# a company office using the hotword regex "\(xxx\)", where "xxx"

3930

# is the area code in question.

3931

# rule.

3932

"windowBefore": 42, # Number of characters before the finding to consider.

3933

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

3939

# to be returned. It still can be used for rules matching.

3940

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

3941

# be used to match sensitive information specific to the data, such as a list

3942

# of employee IDs or job titles.

3943

#

3944

# Dictionary words are case-insensitive and all characters other than letters

3945

# and digits in the unicode [Basic Multilingual

3946

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

3947

# will be replaced with whitespace when scanning for matches, so the

3948

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

3949

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

3950

# surrounding any match must be of a different type than the adjacent

3951

# characters within the word, so letters must be next to non-letters and

3952

# digits next to non-digits. For example, the dictionary word "jen" will

3953

# match the first three letters of the text "jen123" but will return no

3954

# matches for "jennifer".

3955

#

3956

# Dictionary words containing a large number of characters that are not

3957

# letters or digits may result in unexpected findings because such characters

3958

# are treated as whitespace. The

3959

# [limits](https://cloud.google.com/dlp/limits) page contains details about

3960

# the size limits of dictionaries. For dictionaries that do not fit within

3961

# these constraints, consider using `LargeCustomDictionaryConfig` in the

3962

# `StoredInfoType` API.

3963

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

3964

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

3965

# at least one phrase and every phrase must contain at least 2 characters

3966

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

3971

# is accepted.

3972

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

3973

# Example: gs://[BUCKET_NAME]/dictionary.txt

3974

},

3975

},

3976

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

3977

# `InspectDataSource`. Not currently supported in `InspectContent`.

3978

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

3979

# `organizations/433245324/storedInfoTypes/432452342` or

3980

# `projects/project-id/storedInfoTypes/432452342`.

3981

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

3982

# inspection was created. Output-only field, populated by the system.

3983

},

3984

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

3985

# support reversing.

3986

# such as

3987

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

3988

# These types of transformations are

3989

# those that perform pseudonymization, thereby producing a "surrogate" as

3990

# output. This should be used in conjunction with a field on the

3991

# transformation such as `surrogate_info_type`. This CustomInfoType does

3992

# not support the use of `detection_rules`.

3993

},

3994

},

3995

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3996

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3997

"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.

3998

"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.

3999

"name": "A String", # Output only. The template name.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4000

#

4001

# The template will have one of the following formats:

4002

# `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4003

# `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`;

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4004

"description": "A String", # Short description (max 256 chars).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4005

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4006

"jobConfig": { # Controls what and how to inspect for findings. # Inspect config.

4007

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4008

# When used with redactContent only info_types and min_likelihood are currently

4009

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4010

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

4011

# included in the response; see Finding.quote.

4012

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

4013

# Exclusion rules, contained in the set are executed in the end, other

4014

# rules are executed in the order they are specified for each info type.

4015

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

4016

# circumstances, depending on the specific details of the rules within the set.

4017

"infoTypes": [ # List of infoTypes this rule set is applied to.

4018

{ # Type of information detected by the API.

4019

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4020

# creating a CustomInfoType, or one of the names listed

4021

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4022

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4023

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4024

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4025

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4026

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4027

{ # A single inspection rule to be applied to infoTypes, specified in

4028

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4029

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4030

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4031

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4032

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4033

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4034

# levels. For example, if a finding would be `POSSIBLE` without the

4035

# detection rule and `relative_likelihood` is 1, then it is upgraded to

4036

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

4037

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

4038

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

4039

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

4040

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4041

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4042

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4043

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

4044

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4045

# specified, the entire match is returned. No more than 3 may be included.

4046

42,

4047

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4048

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4049

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4050

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4051

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4052

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

4053

# The total length of the window cannot exceed 1000 characters. Note that

4054

# the finding itself will be included in the window, so that hotwords may

4055

# be used to match substrings of the finding itself. For example, the

4056

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

4057

# adjusted upwards if the area code is known to be the local area code of

4058

# a company office using the hotword regex "\(xxx\)", where "xxx"

4059

# is the area code in question.

4060

# rule.

4061

"windowBefore": 42, # Number of characters before the finding to consider.

4062

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4063

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4064

},

4065

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

4066

# `InspectionRuleSet` are removed from results.

4067

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4068

# be used to match sensitive information specific to the data, such as a list

4069

# of employee IDs or job titles.

4070

#

4071

# Dictionary words are case-insensitive and all characters other than letters

4072

# and digits in the unicode [Basic Multilingual

4073

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

4074

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4075

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

4076

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4077

# surrounding any match must be of a different type than the adjacent

4078

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4079

# digits next to non-digits. For example, the dictionary word "jen" will

4080

# match the first three letters of the text "jen123" but will return no

4081

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4082

#

4083

# Dictionary words containing a large number of characters that are not

4084

# letters or digits may result in unexpected findings because such characters

4085

# are treated as whitespace. The

4086

# [limits](https://cloud.google.com/dlp/limits) page contains details about

4087

# the size limits of dictionaries. For dictionaries that do not fit within

4088

# these constraints, consider using `LargeCustomDictionaryConfig` in the

4089

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4090

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

4091

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4092

# at least one phrase and every phrase must contain at least 2 characters

4093

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4094

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4095

],

4096

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4097

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4098

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4099

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4100

# Example: gs://[BUCKET_NAME]/dictionary.txt

4101

},

4102

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4103

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

4104

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4105

# specified, the entire match is returned. No more than 3 may be included.

4106

42,

4107

],

4108

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4109

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4110

# google/re2 repository on GitHub.

4111

},

4112

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

4113

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

4114

# contained within with a finding of an infoType from this list. For

4115

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

4116

# `exclusion_rule` containing `exclude_info_types.info_types` with

4117

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

4118

# with EMAIL_ADDRESS finding.

4119

# That leads to "555-222-2222@example.org" to generate only a single

4120

# finding, namely email address.

4121

{ # Type of information detected by the API.

4122

"name": "A String", # Name of the information type. Either a name of your choosing when

4123

# creating a CustomInfoType, or one of the names listed

4124

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4125

# a built-in type. InfoType names should conform to the pattern

4126

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4131

},

4132

},

4133

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4134

},

4135

],

4136

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

4137

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

4138

# When set within `InspectJobConfig`,

4139

# the maximum returned is 2000 regardless if this is set higher.

4140

# When set within `InspectContentRequest`, this field is ignored.

4141

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

4142

{ # Max findings configuration per infoType, per content item or long

4143

# running DlpJob.

4144

"maxFindings": 42, # Max findings limit for the given infoType.

4145

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

4146

# info_type should be provided. If InfoTypeLimit does not have an

4147

# info_type, the DLP API applies the limit against all info_types that

4148

# are found but not specified in another InfoTypeLimit.

4149

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4150

# creating a CustomInfoType, or one of the names listed

4151

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4152

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4153

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4154

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4155

},

4156

],

4157

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

4158

# When set within `InspectContentRequest`, the maximum returned is 2000

4159

# regardless if this is set higher.

4160

},

4161

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4162

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4163

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4164

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4165

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4166

# InfoType values returned by ListInfoTypes or listed at

4167

# https://cloud.google.com/dlp/docs/infotypes-reference.

4168

#

4169

# When no InfoTypes or CustomInfoTypes are specified in a request, the

4170

# system may automatically choose what detectors to run. By default this may

4171

# be all types, but may change over time as detectors are updated.

4172

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4173

# If you need precise control and predictability as to what detectors are

4174

# run you should specify specific InfoTypes listed in the reference,

4175

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4176

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4177

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4178

# creating a CustomInfoType, or one of the names listed

4179

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4180

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4181

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4182

},

4183

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4184

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

4185

# POSSIBLE.

4186

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

4187

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

4188

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

4189

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

4190

{ # Custom information type provided by the user. Used to find domain-specific

4191

# sensitive information configurable to the data in question.

4192

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

4193

# altered by a detection rule if the finding meets the criteria specified by

4194

# the rule. Defaults to `VERY_LIKELY` if not specified.

4195

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

4196

# infoType, when the name matches one of existing infoTypes and that infoType

4197

# is specified in `InspectContent.info_types` field. Specifying the latter

4198

# adds findings to the one detected by the system. If built-in info type is

4199

# not specified in `InspectContent.info_types` list then the name is treated

4200

# as a custom info type.

4201

"name": "A String", # Name of the information type. Either a name of your choosing when

4202

# creating a CustomInfoType, or one of the names listed

4203

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4204

# a built-in type. InfoType names should conform to the pattern

4205

# `[a-zA-Z0-9_]{1,64}`.

4206

},

4207

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

4208

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4209

# specified, the entire match is returned. No more than 3 may be included.

4210

42,

4211

],

4212

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4213

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4214

# google/re2 repository on GitHub.

4215

},

4216

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

4217

# Rules are applied in order that they are specified. Not supported for the

4218

# `surrogate_type` CustomInfoType.

4219

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

4220

# `CustomInfoType` to alter behavior under certain circumstances, depending

4221

# on the specific details of the rule. Not supported for the `surrogate_type`

4222

# custom infoType.

4223

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

4224

# proximity of hotwords.

4225

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

4226

# part of a detection rule.

4227

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

4228

# levels. For example, if a finding would be `POSSIBLE` without the

4229

# detection rule and `relative_likelihood` is 1, then it is upgraded to

4230

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

4231

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

4232

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

4233

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

4234

# a final likelihood of `LIKELY`.

4235

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

4236

},

4237

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

4238

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4239

# specified, the entire match is returned. No more than 3 may be included.

4240

42,

4241

],

4242

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4243

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4244

# google/re2 repository on GitHub.

4245

},

4246

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

4247

# The total length of the window cannot exceed 1000 characters. Note that

4248

# the finding itself will be included in the window, so that hotwords may

4249

# be used to match substrings of the finding itself. For example, the

4250

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

4251

# adjusted upwards if the area code is known to be the local area code of

4252

# a company office using the hotword regex "\(xxx\)", where "xxx"

4253

# is the area code in question.

4254

# rule.

4255

"windowBefore": 42, # Number of characters before the finding to consider.

4256

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

4262

# to be returned. It still can be used for rules matching.

4263

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

4264

# be used to match sensitive information specific to the data, such as a list

4265

# of employee IDs or job titles.

4266

#

4267

# Dictionary words are case-insensitive and all characters other than letters

4268

# and digits in the unicode [Basic Multilingual

4269

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

4270

# will be replaced with whitespace when scanning for matches, so the

4271

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

4272

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

4273

# surrounding any match must be of a different type than the adjacent

4274

# characters within the word, so letters must be next to non-letters and

4275

# digits next to non-digits. For example, the dictionary word "jen" will

4276

# match the first three letters of the text "jen123" but will return no

4277

# matches for "jennifer".

4278

#

4279

# Dictionary words containing a large number of characters that are not

4280

# letters or digits may result in unexpected findings because such characters

4281

# are treated as whitespace. The

4282

# [limits](https://cloud.google.com/dlp/limits) page contains details about

4283

# the size limits of dictionaries. For dictionaries that do not fit within

4284

# these constraints, consider using `LargeCustomDictionaryConfig` in the

4285

# `StoredInfoType` API.

4286

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

4287

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

4288

# at least one phrase and every phrase must contain at least 2 characters

4289

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

4294

# is accepted.

4295

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

4296

# Example: gs://[BUCKET_NAME]/dictionary.txt

4297

},

4298

},

4299

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

4300

# `InspectDataSource`. Not currently supported in `InspectContent`.

4301

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

4302

# `organizations/433245324/storedInfoTypes/432452342` or

4303

# `projects/project-id/storedInfoTypes/432452342`.

4304

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

4305

# inspection was created. Output-only field, populated by the system.

4306

},

4307

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

4308

# support reversing.

4309

# such as

4310

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

4311

# These types of transformations are

4312

# those that perform pseudonymization, thereby producing a "surrogate" as

4313

# output. This should be used in conjunction with a field on the

4314

# transformation such as `surrogate_info_type`. This CustomInfoType does

4315

# not support the use of `detection_rules`.

4316

},

4317

},

4318

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4319

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4320

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4321

{ # A task to execute on the completion of a job.

4322

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4323

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

4324

# Command Center (CSCC Alpha).

4325

# This action is only available for projects which are parts of

4326

# an organization and whitelisted for the alpha Cloud Security Command

4327

# Center.

4328

# The action will publish count of finding instances and their info types.

4329

# The summary of findings will be persisted in CSCC and are governed by CSCC

4330

# service-specific policy, see https://cloud.google.com/terms/service-terms

4331

# Only a single instance of this action can be specified.

4332

# Compatible with: Inspect

4333

},

4334

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

4335

# completion/failure.

4336

# completion/failure.

4337

},

4338

"saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4339

# OutputStorageConfig. Only a single instance of this action can be

4340

# specified.

4341

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4342

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

4343

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

4344

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

4345

# from the `Finding` object. If appending to an existing table, any columns

4346

# from the predefined schema that are missing will be added. No columns in

4347

# the existing table will be deleted.

4348

#

4349

# If unspecified, then all available columns will be used for a new table or

4350

# an (existing) table with no schema, and no changes will be made to an

4351

# existing table that has a schema.

4352

# Only for use with external storage.

4353

"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

2019-06-14 16:50:42 -0700

[diff] [blame]

4354

# dataset. If table_id is not set a new one will be generated

4355

# for you with the following format:

4356

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

4357

# generating the date details.

4358

#

4359

# For Inspect, each column in an existing output table must have the same

4360

# name, type, and mode of a field in the `Finding` object.

4361

#

4362

# For Risk, an existing output table should be the output of a previous

4363

# Risk analysis job run on the same source table, with the same privacy

4364

# metric and quasi-identifiers. Risk jobs that analyze the same table but

4365

# compute a different privacy metric, or use different sets of

4366

# quasi-identifiers, cannot store their results in the same table.

4367

# identified by its project_id, dataset_id, and table_name. Within a query

4368

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4369

# `<project_id>:<dataset_id>.<table_id>` or

4370

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4371

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4372

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4373

"datasetId": "A String", # Dataset ID of the table.

4374

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4375

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4376

},

4377

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4378

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

4379

# message contains a single field, `DlpJobName`, which is equal to the

4380

# finished job's

4381

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

4382

# Compatible with: Inspect, Risk

4383

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

4384

# publishing access rights to the DLP API service account executing

4385

# the long running DlpJob sending the notifications.

4386

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4387

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4388

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4389

# results of the DlpJob will be applied to the entry for the resource scanned

4390

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

4391

# be deleted. InfoType naming patterns are strictly enforced when using this

4392

# feature. Note that the findings will be persisted in Cloud Data Catalog

4393

# storage and are governed by Data Catalog service-specific policy, see

4394

# https://cloud.google.com/terms/service-terms

4395

# Only a single instance of this action can be specified and only allowed if

4396

# all resources being scanned are BigQuery tables.

4397

# Compatible with: Inspect

4398

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4399

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

4400

# will publish a metric to stack driver on each infotype requested and

4401

# how many findings were found for it. CustomDetectors will be bucketed

4402

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4403

},

4404

},

4405

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4406

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

4407

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

4408

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

4409

# by project and namespace, however the namespace ID may be empty.

4410

# A partition ID identifies a grouping of entities. The grouping is always

4411

# by project and namespace, however the namespace ID may be empty.

4412

#

4413

# A partition ID contains several dimensions:

4414

# project ID and namespace ID.

4415

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

4416

"projectId": "A String", # The ID of the project to which the entities belong.

4417

},

4418

"kind": { # A representation of a Datastore kind. # The kind to process.

4419

"name": "A String", # The name of the kind.

4420

},

4421

},

4422

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

4423

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

4424

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

4425

# Used for data sources like Datastore and BigQuery.

4426

#

4427

# For BigQuery:

4428

# Required to filter out rows based on the given start and

4429

# end times. If not specified and the table was modified between the given

4430

# start and end times, the entire table will be scanned.

4431

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

4432

# `TIMESTAMP`, or `DATETIME` BigQuery column.

4433

#

4434

# For Datastore.

4435

# Valid data types of the timestamp field are: `TIMESTAMP`.

4436

# Datastore entity will be scanned if the timestamp property does not

4437

# exist or its value is empty or invalid.

4438

"name": "A String", # Name describing the field.

4439

},

4440

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

4441

# a valid start_time to avoid scanning files that have not been modified

4442

# since the last time the JobTrigger executed. This will be based on the

4443

# time of the execution of the last run of the JobTrigger.

4444

"endTime": "A String", # Exclude files or rows newer than this value.

4445

# If set to zero, no upper time limit is applied.

4446

"startTime": "A String", # Exclude files or rows older than this value.

4447

},

4448

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

4449

# bucket.

4450

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

4451

# Number of files scanned is rounded down. Must be between 0 and 100,

4452

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

4453

"fileTypes": [ # List of file type groups to include in the scan.

4454

# If empty, all files are scanned and available data format processors

4455

# are applied. In addition, the binary content of the selected files

4456

# is always scanned as well.

4457

# Images are scanned only as binary if the specified region

4458

# does not support image inspection and no file_types were specified.

4459

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

4460

"A String",

4461

],

4462

"sampleMethod": "A String",

4463

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

4464

# number of bytes scanned is rounded down. Must be between 0 and 100,

4465

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

4466

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

4467

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

4468

# than this value then the rest of the bytes are omitted. Only one

4469

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

4470

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

4471

"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

4472

# `regex_file_set` must be set.

4473

# expressions are used to allow fine-grained control over which files in the

4474

# bucket to include.

4475

#

4476

# Included files are those that match at least one item in `include_regex` and

4477

# do not match any items in `exclude_regex`. Note that a file that matches

4478

# items from both lists will _not_ be included. For a match to occur, the

4479

# entire file path (i.e., everything in the url after the bucket name) must

4480

# match the regular expression.

4481

#

4482

# For example, given the input `{bucket_name: "mybucket", include_regex:

4483

# ["directory1/.*"], exclude_regex:

4484

# ["directory1/excluded.*"]}`:

4485

#

4486

# * `gs://mybucket/directory1/myfile` will be included

4487

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

4488

# across `/`)

4489

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

4490

# full path doesn't match any items in `include_regex`)

4491

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

4492

# matches an item in `exclude_regex`)

4493

#

4494

# If `include_regex` is left empty, it will match all files by default

4495

# (this is equivalent to setting `include_regex: [".*"]`).

4496

#

4497

# Some other common use cases:

4498

#

4499

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

4500

# files in `mybucket` except for .pdf files

4501

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

4502

# include all files directly under `gs://mybucket/directory/`, without matching

4503

# across `/`

4504

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

4505

# the bucket that match at least one of these regular expressions will be

4506

# excluded from the scan.

4507

#

4508

# Regular expressions use RE2

4509

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

4510

# under the google/re2 repository on GitHub.

4511

"A String",

4512

],

4513

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

4514

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

4515

# the bucket that match at least one of these regular expressions will be

4516

# included in the set of files, except for those that also match an item in

4517

# `exclude_regex`. Leaving this field empty will match all files by default

4518

# (this is equivalent to including `.*` in the list).

4519

#

4520

# Regular expressions use RE2

4521

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

4522

# under the google/re2 repository on GitHub.

"A String",

],

},

"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format

4527

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

4528

#

4529

# If the url ends in a trailing slash, the bucket or directory represented

4530

# by the url will be scanned non-recursively (content in sub-directories

4531

# will not be scanned). This means that `gs://mybucket/` is equivalent to

4532

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

4533

# `gs://mybucket/directory/*`.

4534

#

4535

# Exactly one of `url` or `regex_file_set` must be set.

4536

},

4537

},

4538

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

4539

"sampleMethod": "A String",

4540

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

4541

# identified by its project_id, dataset_id, and table_name. Within a query

4542

# a table is often referenced with a string in the format of:

4543

# `<project_id>:<dataset_id>.<table_id>` or

4544

# `<project_id>.<dataset_id>.<table_id>`.

4545

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

4546

# If omitted, project ID is inferred from the API call.

4547

"datasetId": "A String", # Dataset ID of the table.

4548

"tableId": "A String", # Name of the table.

4549

},

4550

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

4551

# `actions.saveFindings.outputConfig.table` is specified, the values of

4552

# columns specified here are available in the output table under

4553

# `location.content_locations.record_location.record_key.id_values`. Nested

4554

# fields such as `person.birthdate.year` are allowed.

4555

{ # General identifier of a data field in a storage service.

4556

"name": "A String", # Name describing the field.

4557

},

4558

],

4559

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

4560

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

4561

# 100 means no limit. Defaults to 0. Only one of rows_limit and

4562

# rows_limit_percent can be specified. Cannot be used in conjunction with

4563

# TimespanConfig.

4564

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

4565

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

4566

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

4567

# Cannot be used in conjunction with TimespanConfig.

4568

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

4569

# inspection of entire columns which you know have no findings.

4570

{ # General identifier of a data field in a storage service.

4571

"name": "A String", # Name describing the field.

},

],

},

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

4576

# Early access feature is in a pre-release state and might change or have

4577

# limited support. For more information, see

4578

# https://cloud.google.com/products#product-launch-stages.

4579

# of Google Cloud Platform.

4580

"labels": { # To organize findings, these labels will be added to each finding.

4581

#

4582

# Label keys must be between 1 and 63 characters long and must conform

4583

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

4584

#

4585

# Label values must be between 0 and 63 characters long and must conform

4586

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

4587

#

4588

# No more than 10 labels can be associated with a given finding.

4589

#

4590

# Examples:

4591

# * `"environment" : "production"`

4592

# * `"pipeline" : "etl"`

4593

"a_key": "A String",

4594

},

4595

"description": "A String", # A short description of where the data is coming from. Will be stored once

4596

# in the job. 256 max length.

4597

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

4598

# meaningful such as the columns that are primary keys.

4599

"identifyingFields": [ # The columns that are the primary keys for table objects included in

4600

# ContentItem. A copy of this cell's value will stored alongside alongside

4601

# each finding so that the finding can be traced to the specific row it came

4602

# from. No more than 3 may be provided.

4603

{ # General identifier of a data field in a storage service.

4604

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

4609

# 'finding_labels' map. Request may contain others, but any missing one of

4610

# these will be rejected.

4611

#

4612

# Label keys must be between 1 and 63 characters long and must conform

4613

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

4614

#

4615

# No more than 10 keys can be required.

"A String",

],

},

},

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

4621

# `inspect_config` will be merged into the values persisted as part of the

4622

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4623

},

4624

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

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

"abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran

4631

# out of quota or was ended before they could be processed.

4632

"pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated

4633

# when called via method `getDlpJob`.

4634

# A burst of traffic may cause hybrid inspect requests to be enqueued.

4635

# Processing will take place as quickly as possible, but resource limitations

4636

# may impact how long a request is enqueued for.

4637

"processedCount": "A String", # The number of hybrid inspection requests processed within this job.

4638

},

4639

"infoTypeStats": [ # Statistics of how many instances of each info type were found during

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4640

# inspect job.

4641

{ # Statistics regarding a specific InfoType.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4642

"count": "A String", # Number of findings for this 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

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

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. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4648

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4649

},

4650

},

4651

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4652

"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.

4653

"processedBytes": "A String", # Total size in bytes that were processed.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4654

},

4655

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

}</pre>

</div>

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4660

<code class="details" id="list">list(parent, pageSize=None, filter=None, type=None, orderBy=None, pageToken=None, locationId=None, x__xgafv=None)</code>

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4661

<pre>Lists DlpJobs that match the specified filter in the request.

4662

See https://cloud.google.com/dlp/docs/inspecting-storage and

4663

https://cloud.google.com/dlp/docs/compute-risk-analysis to learn more.

4664

4665

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4666

parent: string, Required. The parent resource name, for example projects/my-project-id. (required)

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4667

pageSize: integer, The standard list page size.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4668

filter: string, Allows filtering.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

Supported syntax:

* Filter expressions are made up of one or more restrictions.

4673

* Restrictions can be combined by `AND` or `OR` logical operators. A

4674

sequence of restrictions implicitly uses `AND`.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4675

* A restriction has the form of `{field} {operator} {value}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4676

* Supported fields/values for inspect jobs:

4677

- `state` - PENDING|RUNNING|CANCELED|FINISHED|FAILED

4678

- `inspected_storage` - DATASTORE|CLOUD_STORAGE|BIGQUERY

4679

- `trigger_name` - The resource name of the trigger that created job.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4680

- 'end_time` - Corresponds to time the job finished.

4681

- 'start_time` - Corresponds to time the job finished.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4682

* Supported fields for risk analysis jobs:

4683

- `state` - RUNNING|CANCELED|FINISHED|FAILED

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4684

- 'end_time` - Corresponds to time the job finished.

4685

- 'start_time` - Corresponds to time the job finished.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4686

* The operator must be `=` or `!=`.

Examples:

* inspected_storage = cloud_storage AND state = done

4691

* inspected_storage = cloud_storage OR inspected_storage = bigquery

4692

* inspected_storage = cloud_storage AND (state = done OR state = canceled)

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4693

* end_time > \"2017-12-12T00:00:00+00:00\"

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4694

4695

The length of this field should be no more than 500 characters.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4696

type: string, The type of job. Defaults to `DlpJobType.INSPECT`

4697

orderBy: string, Comma separated list of fields to order by,

4698

followed by `asc` or `desc` postfix. This list is case-insensitive,

4699

default sorting order is ascending, redundant space characters are

4700

insignificant.

4701

4702

Example: `name asc, end_time asc, create_time desc`

4703

4704

Supported fields are:

4705

4706

- `create_time`: corresponds to time the job was created.

4707

- `end_time`: corresponds to time the job ended.

4708

- `name`: corresponds to job's name.

4709

- `state`: corresponds to `state`

4710

pageToken: string, The standard list page token.

4711

locationId: string, The geographic location where jobs will be retrieved from.

4712

Use `-` for all locations. Reserved for future extensions.

4713

x__xgafv: string, V1 error format.

4714

Allowed values

4715

1 - v1 error format

4716

2 - v2 error format

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4717

4718

Returns:

4719

An object of the form:

4720

4721

{ # The response message for listing DLP jobs.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4722

"nextPageToken": "A String", # The standard List next-page token.

4723

"jobs": [ # A list of DlpJobs that matches the specified filter in the request.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4724

{ # Combines all of the information about a DLP job.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4725

"createTime": "A String", # Time when the job was created.

4726

"state": "A String", # State of a job.

4727

"riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source.

4728

"numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result

4729

"minValue": { # Set of primitive values supported by the system. # Minimum value appearing in the column.

4730

# Note that for the purposes of inspection or transformation, the number

4731

# of bytes considered to comprise a 'Value' is based on its representation

4732

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

4733

# 123456789, the number of bytes would be counted as 9, even though an

4734

# int64 only holds up to 8 bytes of data.

4735

"booleanValue": True or False, # boolean

4736

"floatValue": 3.14, # float

4737

"dayOfWeekValue": "A String", # day of week

4738

"timestampValue": "A String", # timestamp

4739

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

4740

# and time zone are either specified elsewhere or are not significant. The date

4741

# is relative to the Proleptic Gregorian Calendar. This can represent:

4742

#

4743

# * A full date, with non-zero year, month and day values

4744

# * A month and day value, with a zero year, e.g. an anniversary

4745

# * A year on its own, with zero month and day values

4746

# * A year and month value, with a zero day, e.g. a credit card expiration date

4747

#

4748

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

4749

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

4750

# a year.

4751

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

4752

# month and day.

4753

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

4754

# if specifying a year by itself or a year and month where the day is not

4755

# significant.

4756

},

4757

"stringValue": "A String", # string

4758

"integerValue": "A String", # integer

4759

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

4760

# or are specified elsewhere. An API may choose to allow leap seconds. Related

4761

# types are google.type.Date and `google.protobuf.Timestamp`.

4762

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

4763

# allow the value 60 if it allows leap-seconds.

4764

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

4765

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

4766

# to allow the value "24:00:00" for scenarios like business closing time.

4767

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

4768

},

4769

},

4770

"maxValue": { # Set of primitive values supported by the system. # Maximum value appearing in the column.

4771

# Note that for the purposes of inspection or transformation, the number

4772

# of bytes considered to comprise a 'Value' is based on its representation

4773

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

4774

# 123456789, the number of bytes would be counted as 9, even though an

4775

# int64 only holds up to 8 bytes of data.

4776

"booleanValue": True or False, # boolean

4777

"floatValue": 3.14, # float

4778

"dayOfWeekValue": "A String", # day of week

4779

"timestampValue": "A String", # timestamp

4780

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

4781

# and time zone are either specified elsewhere or are not significant. The date

4782

# is relative to the Proleptic Gregorian Calendar. This can represent:

4783

#

4784

# * A full date, with non-zero year, month and day values

4785

# * A month and day value, with a zero year, e.g. an anniversary

4786

# * A year on its own, with zero month and day values

4787

# * A year and month value, with a zero day, e.g. a credit card expiration date

4788

#

4789

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

4790

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

4791

# a year.

4792

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

4793

# month and day.

4794

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

4795

# if specifying a year by itself or a year and month where the day is not

4796

# significant.

4797

},

4798

"stringValue": "A String", # string

4799

"integerValue": "A String", # integer

4800

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

4801

# or are specified elsewhere. An API may choose to allow leap seconds. Related

4802

# types are google.type.Date and `google.protobuf.Timestamp`.

4803

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

4804

# allow the value 60 if it allows leap-seconds.

4805

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

4806

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

4807

# to allow the value "24:00:00" for scenarios like business closing time.

4808

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

4809

},

4810

},

4811

"quantileValues": [ # List of 99 values that partition the set of field values into 100 equal

4812

# sized buckets.

4813

{ # Set of primitive values supported by the system.

4814

# Note that for the purposes of inspection or transformation, the number

4815

# of bytes considered to comprise a 'Value' is based on its representation

4816

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

4817

# 123456789, the number of bytes would be counted as 9, even though an

4818

# int64 only holds up to 8 bytes of data.

4819

"booleanValue": True or False, # boolean

4820

"floatValue": 3.14, # float

4821

"dayOfWeekValue": "A String", # day of week

4822

"timestampValue": "A String", # timestamp

4823

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

4824

# and time zone are either specified elsewhere or are not significant. The date

4825

# is relative to the Proleptic Gregorian Calendar. This can represent:

4826

#

4827

# * A full date, with non-zero year, month and day values

4828

# * A month and day value, with a zero year, e.g. an anniversary

4829

# * A year on its own, with zero month and day values

4830

# * A year and month value, with a zero day, e.g. a credit card expiration date

4831

#

4832

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

4833

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

4834

# a year.

4835

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

4836

# month and day.

4837

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

4838

# if specifying a year by itself or a year and month where the day is not

4839

# significant.

4840

},

4841

"stringValue": "A String", # string

4842

"integerValue": "A String", # integer

4843

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

4844

# or are specified elsewhere. An API may choose to allow leap seconds. Related

4845

# types are google.type.Date and `google.protobuf.Timestamp`.

4846

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

4847

# allow the value 60 if it allows leap-seconds.

4848

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

4849

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

4850

# to allow the value "24:00:00" for scenarios like business closing time.

4851

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

},

"lDiversityResult": { # Result of the l-diversity computation. # L-divesity result

4857

"sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.

4858

{ # Histogram of l-diversity equivalence class sensitive value frequencies.

4859

"sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence

4860

# classes in this bucket.

4861

"sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence

4862

# classes in this bucket.

4863

"bucketSize": "A String", # Total number of equivalence classes in this bucket.

4864

"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.

4865

"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of

4866

# classes returned per bucket is capped at 20.

4867

{ # The set of columns' values that share the same ldiversity value.

4868

"quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence

4869

# class. The order is always the same as the original request.

4870

{ # Set of primitive values supported by the system.

4871

# Note that for the purposes of inspection or transformation, the number

4872

# of bytes considered to comprise a 'Value' is based on its representation

4873

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

4874

# 123456789, the number of bytes would be counted as 9, even though an

4875

# int64 only holds up to 8 bytes of data.

4876

"booleanValue": True or False, # boolean

4877

"floatValue": 3.14, # float

4878

"dayOfWeekValue": "A String", # day of week

4879

"timestampValue": "A String", # timestamp

4880

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

4881

# and time zone are either specified elsewhere or are not significant. The date

4882

# is relative to the Proleptic Gregorian Calendar. This can represent:

4883

#

4884

# * A full date, with non-zero year, month and day values

4885

# * A month and day value, with a zero year, e.g. an anniversary

4886

# * A year on its own, with zero month and day values

4887

# * A year and month value, with a zero day, e.g. a credit card expiration date

4888

#

4889

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

4890

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

4891

# a year.

4892

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

4893

# month and day.

4894

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

4895

# if specifying a year by itself or a year and month where the day is not

4896

# significant.

4897

},

4898

"stringValue": "A String", # string

4899

"integerValue": "A String", # integer

4900

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

4901

# or are specified elsewhere. An API may choose to allow leap seconds. Related

4902

# types are google.type.Date and `google.protobuf.Timestamp`.

4903

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

4904

# allow the value 60 if it allows leap-seconds.

4905

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

4906

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

4907

# to allow the value "24:00:00" for scenarios like business closing time.

4908

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

"equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.

4913

"numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class.

4914

"topSensitiveValues": [ # Estimated frequencies of top sensitive values.

4915

{ # A value of a field, including its frequency.

4916

"value": { # Set of primitive values supported by the system. # A value contained in the field in question.

4917

# Note that for the purposes of inspection or transformation, the number

4918

# of bytes considered to comprise a 'Value' is based on its representation

4919

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

4920

# 123456789, the number of bytes would be counted as 9, even though an

4921

# int64 only holds up to 8 bytes of data.

4922

"booleanValue": True or False, # boolean

4923

"floatValue": 3.14, # float

4924

"dayOfWeekValue": "A String", # day of week

4925

"timestampValue": "A String", # timestamp

4926

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

4927

# and time zone are either specified elsewhere or are not significant. The date

4928

# is relative to the Proleptic Gregorian Calendar. This can represent:

4929

#

4930

# * A full date, with non-zero year, month and day values

4931

# * A month and day value, with a zero year, e.g. an anniversary

4932

# * A year on its own, with zero month and day values

4933

# * A year and month value, with a zero day, e.g. a credit card expiration date

4934

#

4935

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

4936

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

4937

# a year.

4938

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

4939

# month and day.

4940

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

4941

# if specifying a year by itself or a year and month where the day is not

4942

# significant.

4943

},

4944

"stringValue": "A String", # string

4945

"integerValue": "A String", # integer

4946

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

4947

# or are specified elsewhere. An API may choose to allow leap seconds. Related

4948

# types are google.type.Date and `google.protobuf.Timestamp`.

4949

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

4950

# allow the value 60 if it allows leap-seconds.

4951

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

4952

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

4953

# to allow the value "24:00:00" for scenarios like business closing time.

4954

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

4955

},

4956

},

4957

"count": "A String", # How many times the value is contained in the field.

},

],

},

],

},

],

},

"requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.

4966

"categoricalStatsConfig": { # Compute numerical stats over an individual column, including # Categorical stats

4967

# number of distinct values and value count distribution.

4968

"field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are

4969

# supported except for arrays and structs. However, it may be more

4970

# informative to use NumericalStats when the field type is supported,

4971

# depending on the data.

4972

"name": "A String", # Name describing the field.

4973

},

4974

},

4975

"kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity

4976

"quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are

4977

# specified, they are considered a single composite key. Structs and

4978

# repeated data types are not supported; however, nested fields are

4979

# supported so long as they are not structs themselves or nested within

4980

# a repeated field.

4981

{ # General identifier of a data field in a storage service.

4982

"name": "A String", # Name describing the field.

4983

},

4984

],

4985

"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

4986

# single individual. If the same entity_id is associated to multiple

4987

# quasi-identifier tuples over distinct rows, we consider the entire

4988

# collection of tuples as the composite quasi-identifier. This collection

4989

# is a multiset: the order in which the different tuples appear in the

4990

# dataset is ignored, but their frequency is taken into account.

4991

#

4992

# Important note: a maximum of 1000 rows can be associated to a single

4993

# entity ID. If more rows are associated with the same entity ID, some

4994

# might be ignored.

4995

# single person. For example, in medical records the `EntityId` might be a

4996

# patient identifier, or for financial records it might be an account

4997

# identifier. This message is used when generalizations or analysis must take

4998

# into account that multiple rows correspond to the same entity.

4999

"field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.

5000

"name": "A String", # Name describing the field.

},

},

},

"numericalStatsConfig": { # Compute numerical stats over an individual column, including # Numerical stats

5005

# min, max, and quantiles.

5006

"field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are

5007

# integer, float, date, datetime, timestamp, time.

5008

"name": "A String", # Name describing the field.

5009

},

5010

},

5011

"kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what # k-map

5012

# is called "journalist risk" in the literature, except the attack dataset is

5013

# statistically modeled instead of being perfectly known. This can be done

5014

# using publicly available data (like the US Census), or using a custom

5015

# statistical model (indicated as one or several BigQuery tables), or by

5016

# extrapolating from the distribution of values in the input dataset.

5017

"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.

5018

# Set if no column is tagged with a region-specific InfoType (like

5019

# US_ZIP_5) or a region code.

5020

"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag

5021

# used to tag a quasi-identifiers column must appear in exactly one column

5022

# of one auxiliary table.

5023

{ # An auxiliary table contains statistical information on the relative

5024

# frequency of different quasi-identifiers values. It has one or several

5025

# quasi-identifiers columns, and one column that indicates the relative

5026

# frequency of each quasi-identifier tuple.

5027

# If a tuple is present in the data but not in the auxiliary table, the

5028

# corresponding relative frequency is assumed to be zero (and thus, the

5029

# tuple is highly reidentifiable).

5030

"table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location.

5031

# identified by its project_id, dataset_id, and table_name. Within a query

5032

# a table is often referenced with a string in the format of:

5033

# `<project_id>:<dataset_id>.<table_id>` or

5034

# `<project_id>.<dataset_id>.<table_id>`.

5035

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

5036

# If omitted, project ID is inferred from the API call.

5037

"datasetId": "A String", # Dataset ID of the table.

5038

"tableId": "A String", # Name of the table.

5039

},

5040

"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number

5041

# between 0 and 1 (inclusive). Null values are assumed to be zero.

5042

"name": "A String", # Name describing the field.

5043

},

5044

"quasiIds": [ # Required. Quasi-identifier columns.

5045

{ # A quasi-identifier column has a custom_tag, used to know which column

5046

# in the data corresponds to which column in the statistical model.

5047

"customTag": "A String", # A auxiliary field.

5048

"field": { # General identifier of a data field in a storage service. # Identifies the column.

5049

"name": "A String", # Name describing the field.

},

},

],

},

],

"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the

5056

# same tag.

5057

{ # A column with a semantic tag attached.

5058

"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.

5059

"name": "A String", # Name describing the field.

5060

},

5061

"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public

5062

# dataset as a statistical model of population, if available. We

5063

# currently support US ZIP codes, region codes, ages and genders.

5064

# To programmatically obtain the list of supported InfoTypes, use

5065

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

5066

"name": "A String", # Name of the information type. Either a name of your choosing when

5067

# creating a CustomInfoType, or one of the names listed

5068

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5069

# a built-in type. InfoType names should conform to the pattern

5070

# `[a-zA-Z0-9_]{1,64}`.

5071

},

5072

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

5073

# indicate an auxiliary table that contains statistical information on

5074

# the possible values of this column (below).

5075

"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

5076

# the distribution of values in the input data

5077

# empty messages in your APIs. A typical example is to use it as the request

5078

# or the response type of an API method. For instance:

5079

#

5080

# service Foo {

5081

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

5082

# }

5083

#

5084

# The JSON representation for `Empty` is empty JSON object `{}`.

},

},

],

},

"lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity

5090

"quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are

5091

# defined for the l-diversity computation. When multiple fields are

5092

# specified, they are considered a single composite key.

5093

{ # General identifier of a data field in a storage service.

5094

"name": "A String", # Name describing the field.

5095

},

5096

],

5097

"sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.

5098

"name": "A String", # Name describing the field.

5099

},

5100

},

5101

"deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to # delta-presence

5102

# figure out that one given individual appears in a de-identified dataset.

5103

# Similarly to the k-map metric, we cannot compute δ-presence exactly without

5104

# knowing the attack dataset, so we use a statistical model instead.

5105

"quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the

5106

# same tag.

5107

{ # A column with a semantic tag attached.

5108

"field": { # General identifier of a data field in a storage service. # Required. Identifies the column.

5109

"name": "A String", # Name describing the field.

5110

},

5111

"infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public

5112

# dataset as a statistical model of population, if available. We

5113

# currently support US ZIP codes, region codes, ages and genders.

5114

# To programmatically obtain the list of supported InfoTypes, use

5115

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

5116

"name": "A String", # Name of the information type. Either a name of your choosing when

5117

# creating a CustomInfoType, or one of the names listed

5118

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5119

# a built-in type. InfoType names should conform to the pattern

5120

# `[a-zA-Z0-9_]{1,64}`.

5121

},

5122

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

5123

# indicate an auxiliary table that contains statistical information on

5124

# the possible values of this column (below).

5125

"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

5126

# the distribution of values in the input data

5127

# empty messages in your APIs. A typical example is to use it as the request

5128

# or the response type of an API method. For instance:

5129

#

5130

# service Foo {

5131

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

5132

# }

5133

#

5134

# The JSON representation for `Empty` is empty JSON object `{}`.

},

},

],

"regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.

5139

# Set if no column is tagged with a region-specific InfoType (like

5140

# US_ZIP_5) or a region code.

5141

"auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag

5142

# used to tag a quasi-identifiers field must appear in exactly one

5143

# field of one auxiliary table.

5144

{ # An auxiliary table containing statistical information on the relative

5145

# frequency of different quasi-identifiers values. It has one or several

5146

# quasi-identifiers columns, and one column that indicates the relative

5147

# frequency of each quasi-identifier tuple.

5148

# If a tuple is present in the data but not in the auxiliary table, the

5149

# corresponding relative frequency is assumed to be zero (and thus, the

5150

# tuple is highly reidentifiable).

5151

"table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location.

5152

# identified by its project_id, dataset_id, and table_name. Within a query

5153

# a table is often referenced with a string in the format of:

5154

# `<project_id>:<dataset_id>.<table_id>` or

5155

# `<project_id>.<dataset_id>.<table_id>`.

5156

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

5157

# If omitted, project ID is inferred from the API call.

5158

"datasetId": "A String", # Dataset ID of the table.

5159

"tableId": "A String", # Name of the table.

5160

},

5161

"relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number

5162

# between 0 and 1 (inclusive). Null values are assumed to be zero.

5163

"name": "A String", # Name describing the field.

5164

},

5165

"quasiIds": [ # Required. Quasi-identifier columns.

5166

{ # A quasi-identifier column has a custom_tag, used to know which column

5167

# in the data corresponds to which column in the statistical model.

5168

"field": { # General identifier of a data field in a storage service. # Identifies the column.

5169

"name": "A String", # Name describing the field.

5170

},

5171

"customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must

5172

# indicate an auxiliary table that contains statistical information on

5173

# the possible values of this column (below).

},

],

},

],

},

},

"categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result

5181

"valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.

5182

{ # Histogram of value frequencies in the column.

5183

"bucketValues": [ # Sample of value frequencies in this bucket. The total number of

5184

# values returned per bucket is capped at 20.

5185

{ # A value of a field, including its frequency.

5186

"value": { # Set of primitive values supported by the system. # A value contained in the field in question.

5187

# Note that for the purposes of inspection or transformation, the number

5188

# of bytes considered to comprise a 'Value' is based on its representation

5189

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

5190

# 123456789, the number of bytes would be counted as 9, even though an

5191

# int64 only holds up to 8 bytes of data.

5192

"booleanValue": True or False, # boolean

5193

"floatValue": 3.14, # float

5194

"dayOfWeekValue": "A String", # day of week

5195

"timestampValue": "A String", # timestamp

5196

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

5197

# and time zone are either specified elsewhere or are not significant. The date

5198

# is relative to the Proleptic Gregorian Calendar. This can represent:

5199

#

5200

# * A full date, with non-zero year, month and day values

5201

# * A month and day value, with a zero year, e.g. an anniversary

5202

# * A year on its own, with zero month and day values

5203

# * A year and month value, with a zero day, e.g. a credit card expiration date

5204

#

5205

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

5206

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

5207

# a year.

5208

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

5209

# month and day.

5210

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

5211

# if specifying a year by itself or a year and month where the day is not

5212

# significant.

5213

},

5214

"stringValue": "A String", # string

5215

"integerValue": "A String", # integer

5216

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

5217

# or are specified elsewhere. An API may choose to allow leap seconds. Related

5218

# types are google.type.Date and `google.protobuf.Timestamp`.

5219

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

5220

# allow the value 60 if it allows leap-seconds.

5221

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

5222

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

5223

# to allow the value "24:00:00" for scenarios like business closing time.

5224

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

5225

},

5226

},

5227

"count": "A String", # How many times the value is contained in the field.

5228

},

5229

],

5230

"valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.

5231

"valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.

5232

"bucketSize": "A String", # Total number of values in this bucket.

5233

"bucketValueCount": "A String", # Total number of distinct values in this bucket.

},

],

},

"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an # K-map result

5238

# estimation, not exact values.

5239

"kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value

5240

# doesn't correspond to any such interval, the associated frequency is

5241

# zero. For example, the following records:

5242

# {min_anonymity: 1, max_anonymity: 1, frequency: 17}

5243

# {min_anonymity: 2, max_anonymity: 3, frequency: 42}

5244

# {min_anonymity: 5, max_anonymity: 10, frequency: 99}

5245

# mean that there are no record with an estimated anonymity of 4, 5, or

5246

# larger than 10.

5247

{ # A KMapEstimationHistogramBucket message with the following values:

# min_anonymity: 3

# max_anonymity: 5

# frequency: 42

# means that there are 42 records whose quasi-identifier values correspond

5252

# to 3, 4 or 5 people in the overlying population. An important particular

5253

# case is when min_anonymity = max_anonymity = 1: the frequency field then

5254

# corresponds to the number of uniquely identifiable records.

5255

"bucketSize": "A String", # Number of records within these anonymity bounds.

5256

"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.

5257

"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.

5258

"minAnonymity": "A String", # Always positive.

5259

"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total

5260

# number of classes returned per bucket is capped at 20.

5261

{ # A tuple of values for the quasi-identifier columns.

5262

"estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values.

5263

"quasiIdsValues": [ # The quasi-identifier values.

5264

{ # Set of primitive values supported by the system.

5265

# Note that for the purposes of inspection or transformation, the number

5266

# of bytes considered to comprise a 'Value' is based on its representation

5267

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

5268

# 123456789, the number of bytes would be counted as 9, even though an

5269

# int64 only holds up to 8 bytes of data.

5270

"booleanValue": True or False, # boolean

5271

"floatValue": 3.14, # float

5272

"dayOfWeekValue": "A String", # day of week

5273

"timestampValue": "A String", # timestamp

5274

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

5275

# and time zone are either specified elsewhere or are not significant. The date

5276

# is relative to the Proleptic Gregorian Calendar. This can represent:

5277

#

5278

# * A full date, with non-zero year, month and day values

5279

# * A month and day value, with a zero year, e.g. an anniversary

5280

# * A year on its own, with zero month and day values

5281

# * A year and month value, with a zero day, e.g. a credit card expiration date

5282

#

5283

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

5284

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

5285

# a year.

5286

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

5287

# month and day.

5288

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

5289

# if specifying a year by itself or a year and month where the day is not

5290

# significant.

5291

},

5292

"stringValue": "A String", # string

5293

"integerValue": "A String", # integer

5294

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

5295

# or are specified elsewhere. An API may choose to allow leap seconds. Related

5296

# types are google.type.Date and `google.protobuf.Timestamp`.

5297

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

5298

# allow the value 60 if it allows leap-seconds.

5299

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

5300

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

5301

# to allow the value "24:00:00" for scenarios like business closing time.

5302

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

},

],

},

],

},

"kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result

5312

"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.

5313

{ # Histogram of k-anonymity equivalence classes.

5314

"bucketSize": "A String", # Total number of equivalence classes in this bucket.

5315

"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.

5316

"equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket.

5317

"equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket.

5318

"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of

5319

# classes returned per bucket is capped at 20.

5320

{ # The set of columns' values that share the same ldiversity value

5321

"quasiIdsValues": [ # Set of values defining the equivalence class. One value per

5322

# quasi-identifier column in the original KAnonymity metric message.

5323

# The order is always the same as the original request.

5324

{ # Set of primitive values supported by the system.

5325

# Note that for the purposes of inspection or transformation, the number

5326

# of bytes considered to comprise a 'Value' is based on its representation

5327

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

5328

# 123456789, the number of bytes would be counted as 9, even though an

5329

# int64 only holds up to 8 bytes of data.

5330

"booleanValue": True or False, # boolean

5331

"floatValue": 3.14, # float

5332

"dayOfWeekValue": "A String", # day of week

5333

"timestampValue": "A String", # timestamp

5334

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

5335

# and time zone are either specified elsewhere or are not significant. The date

5336

# is relative to the Proleptic Gregorian Calendar. This can represent:

5337

#

5338

# * A full date, with non-zero year, month and day values

5339

# * A month and day value, with a zero year, e.g. an anniversary

5340

# * A year on its own, with zero month and day values

5341

# * A year and month value, with a zero day, e.g. a credit card expiration date

5342

#

5343

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

5344

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

5345

# a year.

5346

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

5347

# month and day.

5348

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

5349

# if specifying a year by itself or a year and month where the day is not

5350

# significant.

5351

},

5352

"stringValue": "A String", # string

5353

"integerValue": "A String", # integer

5354

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

5355

# or are specified elsewhere. An API may choose to allow leap seconds. Related

5356

# types are google.type.Date and `google.protobuf.Timestamp`.

5357

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

5358

# allow the value 60 if it allows leap-seconds.

5359

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

5360

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

5361

# to allow the value "24:00:00" for scenarios like business closing time.

5362

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the

5367

# above set of values.

},

],

},

],

},

"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an # Delta-presence result

5374

# estimation, not exact values.

5375

"deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a

5376

# value doesn't correspond to any such interval, the associated frequency

5377

# is zero. For example, the following records:

5378

# {min_probability: 0, max_probability: 0.1, frequency: 17}

5379

# {min_probability: 0.2, max_probability: 0.3, frequency: 42}

5380

# {min_probability: 0.3, max_probability: 0.4, frequency: 99}

5381

# mean that there are no record with an estimated probability in [0.1, 0.2)

5382

# nor larger or equal to 0.4.

5383

{ # A DeltaPresenceEstimationHistogramBucket message with the following

5384

# values:

5385

# min_probability: 0.1

5386

# max_probability: 0.2

5387

# frequency: 42

5388

# means that there are 42 records for which δ is in [0.1, 0.2). An

5389

# important particular case is when min_probability = max_probability = 1:

5390

# then, every individual who shares this quasi-identifier combination is in

5391

# the dataset.

5392

"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total

5393

# number of classes returned per bucket is capped at 20.

5394

{ # A tuple of values for the quasi-identifier columns.

5395

"quasiIdsValues": [ # The quasi-identifier values.

5396

{ # Set of primitive values supported by the system.

5397

# Note that for the purposes of inspection or transformation, the number

5398

# of bytes considered to comprise a 'Value' is based on its representation

5399

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

5400

# 123456789, the number of bytes would be counted as 9, even though an

5401

# int64 only holds up to 8 bytes of data.

5402

"booleanValue": True or False, # boolean

5403

"floatValue": 3.14, # float

5404

"dayOfWeekValue": "A String", # day of week

5405

"timestampValue": "A String", # timestamp

5406

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

5407

# and time zone are either specified elsewhere or are not significant. The date

5408

# is relative to the Proleptic Gregorian Calendar. This can represent:

5409

#

5410

# * A full date, with non-zero year, month and day values

5411

# * A month and day value, with a zero year, e.g. an anniversary

5412

# * A year on its own, with zero month and day values

5413

# * A year and month value, with a zero day, e.g. a credit card expiration date

5414

#

5415

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

5416

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

5417

# a year.

5418

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

5419

# month and day.

5420

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

5421

# if specifying a year by itself or a year and month where the day is not

5422

# significant.

5423

},

5424

"stringValue": "A String", # string

5425

"integerValue": "A String", # integer

5426

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

5427

# or are specified elsewhere. An API may choose to allow leap seconds. Related

5428

# types are google.type.Date and `google.protobuf.Timestamp`.

5429

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

5430

# allow the value 60 if it allows leap-seconds.

5431

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

5432

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

5433

# to allow the value "24:00:00" for scenarios like business closing time.

5434

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

},

},

],

"estimatedProbability": 3.14, # The estimated probability that a given individual sharing these

5439

# quasi-identifier values is in the dataset. This value, typically called

5440

# δ, is the ratio between the number of records in the dataset with these

5441

# quasi-identifier values, and the total number of individuals (inside

5442

# *and* outside the dataset) with these quasi-identifier values.

5443

# For example, if there are 15 individuals in the dataset who share the

5444

# same quasi-identifier values, and an estimated 100 people in the entire

5445

# population with these values, then δ is 0.15.

5446

},

5447

],

5448

"minProbability": 3.14, # Between 0 and 1.

5449

"maxProbability": 3.14, # Always greater than or equal to min_probability.

5450

"bucketSize": "A String", # Number of records within these probability bounds.

5451

"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.

},

],

},

"requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over.

5456

# identified by its project_id, dataset_id, and table_name. Within a query

5457

# a table is often referenced with a string in the format of:

5458

# `<project_id>:<dataset_id>.<table_id>` or

5459

# `<project_id>.<dataset_id>.<table_id>`.

5460

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

5461

# If omitted, project ID is inferred from the API call.

5462

"datasetId": "A String", # Dataset ID of the table.

5463

"tableId": "A String", # Name of the table.

5464

},

5465

},

5466

"jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that

5467

# instantiated the job.

5468

"errors": [ # A stream of errors encountered running the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5469

{ # Details information about an error encountered during job execution or

5470

# the results of an unsuccessful activation of the JobTrigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5471

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5472

# different programming environments, including REST APIs and RPC APIs. It is

5473

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

5474

# three pieces of data: error code, error message, and error details.

5475

#

5476

# You can find out more about this error model and how to work with it in the

5477

# [API Design Guide](https://cloud.google.com/apis/design/errors).

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5478

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

5479

"message": "A String", # A developer-facing error message, which should be in English. Any

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5480

# user-facing error message should be localized and sent in the

5481

# google.rpc.Status.details field, or localized by the client.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5482

"details": [ # A list of messages that carry the error details. There is a common set of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5483

# message types for APIs to use.

5484

{

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5485

"a_key": "", # Properties of the object. Contains field @type with type URL.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5486

},

5487

],

5488

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5489

"timestamps": [ # The times the error occurred.

5490

"A String",

5491

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5492

},

5493

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5494

"name": "A String", # The server-assigned name.

5495

"type": "A String", # The type of job.

5496

"endTime": "A String", # Time when the job finished.

5497

"startTime": "A String", # Time when the job started.

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

"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

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5501

# this run.

5502

# to be detected) to be used anywhere you otherwise would normally specify

5503

# InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates

5504

# to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5505

"displayName": "A String", # Display name (max 256 chars).

5506

"inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5507

# When used with redactContent only info_types and min_likelihood are currently

5508

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5509

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

5510

# included in the response; see Finding.quote.

5511

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

5512

# Exclusion rules, contained in the set are executed in the end, other

5513

# rules are executed in the order they are specified for each info type.

5514

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

5515

# circumstances, depending on the specific details of the rules within the set.

5516

"infoTypes": [ # List of infoTypes this rule set is applied to.

5517

{ # Type of information detected by the API.

5518

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5519

# creating a CustomInfoType, or one of the names listed

5520

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5521

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5522

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5523

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5524

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5525

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5526

{ # A single inspection rule to be applied to infoTypes, specified in

5527

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5528

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5529

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5530

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5531

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5532

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5533

# levels. For example, if a finding would be `POSSIBLE` without the

5534

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5535

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5536

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5537

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5538

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5539

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5540

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5541

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5542

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5543

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5544

# specified, the entire match is returned. No more than 3 may be included.

5545

42,

5546

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5547

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5548

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5549

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5550

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5551

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5552

# The total length of the window cannot exceed 1000 characters. Note that

5553

# the finding itself will be included in the window, so that hotwords may

5554

# be used to match substrings of the finding itself. For example, the

5555

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

5556

# adjusted upwards if the area code is known to be the local area code of

5557

# a company office using the hotword regex "\(xxx\)", where "xxx"

5558

# is the area code in question.

5559

# rule.

5560

"windowBefore": 42, # Number of characters before the finding to consider.

5561

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5562

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5563

},

5564

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

5565

# `InspectionRuleSet` are removed from results.

5566

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5567

# be used to match sensitive information specific to the data, such as a list

5568

# of employee IDs or job titles.

5569

#

5570

# Dictionary words are case-insensitive and all characters other than letters

5571

# and digits in the unicode [Basic Multilingual

5572

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5573

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5574

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5575

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5576

# surrounding any match must be of a different type than the adjacent

5577

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5578

# digits next to non-digits. For example, the dictionary word "jen" will

5579

# match the first three letters of the text "jen123" but will return no

5580

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5581

#

5582

# Dictionary words containing a large number of characters that are not

5583

# letters or digits may result in unexpected findings because such characters

5584

# are treated as whitespace. The

5585

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5586

# the size limits of dictionaries. For dictionaries that do not fit within

5587

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5588

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5589

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5590

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5591

# at least one phrase and every phrase must contain at least 2 characters

5592

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5593

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5594

],

5595

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5596

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5597

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5598

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5599

# Example: gs://[BUCKET_NAME]/dictionary.txt

5600

},

5601

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5602

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

5603

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5604

# specified, the entire match is returned. No more than 3 may be included.

5605

42,

5606

],

5607

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5608

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5609

# google/re2 repository on GitHub.

5610

},

5611

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

5612

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

5613

# contained within with a finding of an infoType from this list. For

5614

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

5615

# `exclusion_rule` containing `exclude_info_types.info_types` with

5616

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

5617

# with EMAIL_ADDRESS finding.

5618

# That leads to "555-222-2222@example.org" to generate only a single

5619

# finding, namely email address.

5620

{ # Type of information detected by the API.

5621

"name": "A String", # Name of the information type. Either a name of your choosing when

5622

# creating a CustomInfoType, or one of the names listed

5623

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5624

# a built-in type. InfoType names should conform to the pattern

5625

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5630

},

5631

},

5632

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5633

},

5634

],

5635

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

5636

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

5637

# When set within `InspectJobConfig`,

5638

# the maximum returned is 2000 regardless if this is set higher.

5639

# When set within `InspectContentRequest`, this field is ignored.

5640

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

5641

{ # Max findings configuration per infoType, per content item or long

5642

# running DlpJob.

5643

"maxFindings": 42, # Max findings limit for the given infoType.

5644

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

5645

# info_type should be provided. If InfoTypeLimit does not have an

5646

# info_type, the DLP API applies the limit against all info_types that

5647

# are found but not specified in another InfoTypeLimit.

5648

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5649

# creating a CustomInfoType, or one of the names listed

5650

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5651

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5652

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5653

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5654

},

5655

],

5656

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

5657

# When set within `InspectContentRequest`, the maximum returned is 2000

5658

# regardless if this is set higher.

5659

},

5660

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5661

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5662

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5663

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5664

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5665

# InfoType values returned by ListInfoTypes or listed at

5666

# https://cloud.google.com/dlp/docs/infotypes-reference.

5667

#

5668

# When no InfoTypes or CustomInfoTypes are specified in a request, the

5669

# system may automatically choose what detectors to run. By default this may

5670

# be all types, but may change over time as detectors are updated.

5671

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5672

# If you need precise control and predictability as to what detectors are

5673

# run you should specify specific InfoTypes listed in the reference,

5674

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5675

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5676

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5677

# creating a CustomInfoType, or one of the names listed

5678

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5679

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5680

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5681

},

5682

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5683

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

5684

# POSSIBLE.

5685

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

5686

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

5687

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

5688

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

5689

{ # Custom information type provided by the user. Used to find domain-specific

5690

# sensitive information configurable to the data in question.

5691

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

5692

# altered by a detection rule if the finding meets the criteria specified by

5693

# the rule. Defaults to `VERY_LIKELY` if not specified.

5694

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

5695

# infoType, when the name matches one of existing infoTypes and that infoType

5696

# is specified in `InspectContent.info_types` field. Specifying the latter

5697

# adds findings to the one detected by the system. If built-in info type is

5698

# not specified in `InspectContent.info_types` list then the name is treated

5699

# as a custom info type.

5700

"name": "A String", # Name of the information type. Either a name of your choosing when

5701

# creating a CustomInfoType, or one of the names listed

5702

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5703

# a built-in type. InfoType names should conform to the pattern

5704

# `[a-zA-Z0-9_]{1,64}`.

5705

},

5706

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

5707

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5708

# specified, the entire match is returned. No more than 3 may be included.

5709

42,

5710

],

5711

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5712

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5713

# google/re2 repository on GitHub.

5714

},

5715

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

5716

# Rules are applied in order that they are specified. Not supported for the

5717

# `surrogate_type` CustomInfoType.

5718

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

5719

# `CustomInfoType` to alter behavior under certain circumstances, depending

5720

# on the specific details of the rule. Not supported for the `surrogate_type`

5721

# custom infoType.

5722

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

5723

# proximity of hotwords.

5724

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

5725

# part of a detection rule.

5726

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

5727

# levels. For example, if a finding would be `POSSIBLE` without the

5728

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5729

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5730

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5731

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5732

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5733

# a final likelihood of `LIKELY`.

5734

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

5735

},

5736

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5737

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5738

# specified, the entire match is returned. No more than 3 may be included.

5739

42,

5740

],

5741

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5742

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5743

# google/re2 repository on GitHub.

5744

},

5745

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5746

# The total length of the window cannot exceed 1000 characters. Note that

5747

# the finding itself will be included in the window, so that hotwords may

5748

# be used to match substrings of the finding itself. For example, the

5749

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

5750

# adjusted upwards if the area code is known to be the local area code of

5751

# a company office using the hotword regex "\(xxx\)", where "xxx"

5752

# is the area code in question.

5753

# rule.

5754

"windowBefore": 42, # Number of characters before the finding to consider.

5755

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

5761

# to be returned. It still can be used for rules matching.

5762

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

5763

# be used to match sensitive information specific to the data, such as a list

5764

# of employee IDs or job titles.

5765

#

5766

# Dictionary words are case-insensitive and all characters other than letters

5767

# and digits in the unicode [Basic Multilingual

5768

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5769

# will be replaced with whitespace when scanning for matches, so the

5770

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5771

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

5772

# surrounding any match must be of a different type than the adjacent

5773

# characters within the word, so letters must be next to non-letters and

5774

# digits next to non-digits. For example, the dictionary word "jen" will

5775

# match the first three letters of the text "jen123" but will return no

5776

# matches for "jennifer".

5777

#

5778

# Dictionary words containing a large number of characters that are not

5779

# letters or digits may result in unexpected findings because such characters

5780

# are treated as whitespace. The

5781

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5782

# the size limits of dictionaries. For dictionaries that do not fit within

5783

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5784

# `StoredInfoType` API.

5785

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5786

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

5787

# at least one phrase and every phrase must contain at least 2 characters

5788

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

5793

# is accepted.

5794

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

5795

# Example: gs://[BUCKET_NAME]/dictionary.txt

5796

},

5797

},

5798

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

5799

# `InspectDataSource`. Not currently supported in `InspectContent`.

5800

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

5801

# `organizations/433245324/storedInfoTypes/432452342` or

5802

# `projects/project-id/storedInfoTypes/432452342`.

5803

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

5804

# inspection was created. Output-only field, populated by the system.

5805

},

5806

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

5807

# support reversing.

5808

# such as

5809

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

5810

# These types of transformations are

5811

# those that perform pseudonymization, thereby producing a "surrogate" as

5812

# output. This should be used in conjunction with a field on the

5813

# transformation such as `surrogate_info_type`. This CustomInfoType does

5814

# not support the use of `detection_rules`.

5815

},

5816

},

5817

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5818

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5819

"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.

5820

"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.

5821

"name": "A String", # Output only. The template name.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5822

#

5823

# The template will have one of the following formats:

5824

# `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5825

# `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`;

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5826

"description": "A String", # Short description (max 256 chars).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5827

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5828

"jobConfig": { # Controls what and how to inspect for findings. # Inspect config.

5829

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5830

# When used with redactContent only info_types and min_likelihood are currently

5831

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5832

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

5833

# included in the response; see Finding.quote.

5834

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

5835

# Exclusion rules, contained in the set are executed in the end, other

5836

# rules are executed in the order they are specified for each info type.

5837

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

5838

# circumstances, depending on the specific details of the rules within the set.

5839

"infoTypes": [ # List of infoTypes this rule set is applied to.

5840

{ # Type of information detected by the API.

5841

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5842

# creating a CustomInfoType, or one of the names listed

5843

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5844

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5845

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5846

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5847

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5848

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5849

{ # A single inspection rule to be applied to infoTypes, specified in

5850

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5851

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5852

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5853

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5854

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5855

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5856

# levels. For example, if a finding would be `POSSIBLE` without the

5857

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5858

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5859

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5860

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5861

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5862

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5863

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5864

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5865

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5866

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5867

# specified, the entire match is returned. No more than 3 may be included.

5868

42,

5869

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5870

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5871

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5872

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5873

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5874

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5875

# The total length of the window cannot exceed 1000 characters. Note that

5876

# the finding itself will be included in the window, so that hotwords may

5877

# be used to match substrings of the finding itself. For example, the

5878

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

5879

# adjusted upwards if the area code is known to be the local area code of

5880

# a company office using the hotword regex "\(xxx\)", where "xxx"

5881

# is the area code in question.

5882

# rule.

5883

"windowBefore": 42, # Number of characters before the finding to consider.

5884

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5885

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5886

},

5887

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

5888

# `InspectionRuleSet` are removed from results.

5889

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5890

# be used to match sensitive information specific to the data, such as a list

5891

# of employee IDs or job titles.

5892

#

5893

# Dictionary words are case-insensitive and all characters other than letters

5894

# and digits in the unicode [Basic Multilingual

5895

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5896

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5897

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5898

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5899

# surrounding any match must be of a different type than the adjacent

5900

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5901

# digits next to non-digits. For example, the dictionary word "jen" will

5902

# match the first three letters of the text "jen123" but will return no

5903

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5904

#

5905

# Dictionary words containing a large number of characters that are not

5906

# letters or digits may result in unexpected findings because such characters

5907

# are treated as whitespace. The

5908

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5909

# the size limits of dictionaries. For dictionaries that do not fit within

5910

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5911

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5912

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5913

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5914

# at least one phrase and every phrase must contain at least 2 characters

5915

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5916

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5917

],

5918

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5919

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5920

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5921

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5922

# Example: gs://[BUCKET_NAME]/dictionary.txt

5923

},

5924

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5925

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

5926

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5927

# specified, the entire match is returned. No more than 3 may be included.

5928

42,

5929

],

5930

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5931

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5932

# google/re2 repository on GitHub.

5933

},

5934

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

5935

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

5936

# contained within with a finding of an infoType from this list. For

5937

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

5938

# `exclusion_rule` containing `exclude_info_types.info_types` with

5939

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

5940

# with EMAIL_ADDRESS finding.

5941

# That leads to "555-222-2222@example.org" to generate only a single

5942

# finding, namely email address.

5943

{ # Type of information detected by the API.

5944

"name": "A String", # Name of the information type. Either a name of your choosing when

5945

# creating a CustomInfoType, or one of the names listed

5946

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5947

# a built-in type. InfoType names should conform to the pattern

5948

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5953

},

5954

},

5955

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5956

},

5957

],

5958

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

5959

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

5960

# When set within `InspectJobConfig`,

5961

# the maximum returned is 2000 regardless if this is set higher.

5962

# When set within `InspectContentRequest`, this field is ignored.

5963

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

5964

{ # Max findings configuration per infoType, per content item or long

5965

# running DlpJob.

5966

"maxFindings": 42, # Max findings limit for the given infoType.

5967

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

5968

# info_type should be provided. If InfoTypeLimit does not have an

5969

# info_type, the DLP API applies the limit against all info_types that

5970

# are found but not specified in another InfoTypeLimit.

5971

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5972

# creating a CustomInfoType, or one of the names listed

5973

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5974

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5975

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5976

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5977

},

5978

],

5979

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

5980

# When set within `InspectContentRequest`, the maximum returned is 2000

5981

# regardless if this is set higher.

5982

},

5983

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5984

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5985

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5986

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5987

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5988

# InfoType values returned by ListInfoTypes or listed at

5989

# https://cloud.google.com/dlp/docs/infotypes-reference.

5990

#

5991

# When no InfoTypes or CustomInfoTypes are specified in a request, the

5992

# system may automatically choose what detectors to run. By default this may

5993

# be all types, but may change over time as detectors are updated.

5994

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5995

# If you need precise control and predictability as to what detectors are

5996

# run you should specify specific InfoTypes listed in the reference,

5997

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5998

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5999

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6000

# creating a CustomInfoType, or one of the names listed

6001

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

6002

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

6003

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6004

},

6005

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6006

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

6007

# POSSIBLE.

6008

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

6009

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

6010

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

6011

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

6012

{ # Custom information type provided by the user. Used to find domain-specific

6013

# sensitive information configurable to the data in question.

6014

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

6015

# altered by a detection rule if the finding meets the criteria specified by

6016

# the rule. Defaults to `VERY_LIKELY` if not specified.

6017

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

6018

# infoType, when the name matches one of existing infoTypes and that infoType

6019

# is specified in `InspectContent.info_types` field. Specifying the latter

6020

# adds findings to the one detected by the system. If built-in info type is

6021

# not specified in `InspectContent.info_types` list then the name is treated

6022

# as a custom info type.

6023

"name": "A String", # Name of the information type. Either a name of your choosing when

6024

# creating a CustomInfoType, or one of the names listed

6025

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

6026

# a built-in type. InfoType names should conform to the pattern

6027

# `[a-zA-Z0-9_]{1,64}`.

6028

},

6029

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

6030

"groupIndexes": [ # The index of the submatch to extract as findings. When not

6031

# specified, the entire match is returned. No more than 3 may be included.

6032

42,

6033

],

6034

"pattern": "A String", # Pattern defining the regular expression. Its syntax

6035

# (https://github.com/google/re2/wiki/Syntax) can be found under the

6036

# google/re2 repository on GitHub.

6037

},

6038

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

6039

# Rules are applied in order that they are specified. Not supported for the

6040

# `surrogate_type` CustomInfoType.

6041

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

6042

# `CustomInfoType` to alter behavior under certain circumstances, depending

6043

# on the specific details of the rule. Not supported for the `surrogate_type`

6044

# custom infoType.

6045

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

6046

# proximity of hotwords.

6047

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

6048

# part of a detection rule.

6049

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

6050

# levels. For example, if a finding would be `POSSIBLE` without the

6051

# detection rule and `relative_likelihood` is 1, then it is upgraded to

6052

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

6053

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

6054

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

6055

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

6056

# a final likelihood of `LIKELY`.

6057

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

6058

},

6059

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

6060

"groupIndexes": [ # The index of the submatch to extract as findings. When not

6061

# specified, the entire match is returned. No more than 3 may be included.

6062

42,

6063

],

6064

"pattern": "A String", # Pattern defining the regular expression. Its syntax

6065

# (https://github.com/google/re2/wiki/Syntax) can be found under the

6066

# google/re2 repository on GitHub.

6067

},

6068

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

6069

# The total length of the window cannot exceed 1000 characters. Note that

6070

# the finding itself will be included in the window, so that hotwords may

6071

# be used to match substrings of the finding itself. For example, the

6072

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

6073

# adjusted upwards if the area code is known to be the local area code of

6074

# a company office using the hotword regex "\(xxx\)", where "xxx"

6075

# is the area code in question.

6076

# rule.

6077

"windowBefore": 42, # Number of characters before the finding to consider.

6078

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

6084

# to be returned. It still can be used for rules matching.

6085

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

6086

# be used to match sensitive information specific to the data, such as a list

6087

# of employee IDs or job titles.

6088

#

6089

# Dictionary words are case-insensitive and all characters other than letters

6090

# and digits in the unicode [Basic Multilingual

6091

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

6092

# will be replaced with whitespace when scanning for matches, so the

6093

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

6094

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

6095

# surrounding any match must be of a different type than the adjacent

6096

# characters within the word, so letters must be next to non-letters and

6097

# digits next to non-digits. For example, the dictionary word "jen" will

6098

# match the first three letters of the text "jen123" but will return no

6099

# matches for "jennifer".

6100

#

6101

# Dictionary words containing a large number of characters that are not

6102

# letters or digits may result in unexpected findings because such characters

6103

# are treated as whitespace. The

6104

# [limits](https://cloud.google.com/dlp/limits) page contains details about

6105

# the size limits of dictionaries. For dictionaries that do not fit within

6106

# these constraints, consider using `LargeCustomDictionaryConfig` in the

6107

# `StoredInfoType` API.

6108

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

6109

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

6110

# at least one phrase and every phrase must contain at least 2 characters

6111

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

6116

# is accepted.

6117

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

6118

# Example: gs://[BUCKET_NAME]/dictionary.txt

6119

},

6120

},

6121

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

6122

# `InspectDataSource`. Not currently supported in `InspectContent`.

6123

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

6124

# `organizations/433245324/storedInfoTypes/432452342` or

6125

# `projects/project-id/storedInfoTypes/432452342`.

6126

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

6127

# inspection was created. Output-only field, populated by the system.

6128

},

6129

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

6130

# support reversing.

6131

# such as

6132

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

6133

# These types of transformations are

6134

# those that perform pseudonymization, thereby producing a "surrogate" as

6135

# output. This should be used in conjunction with a field on the

6136

# transformation such as `surrogate_info_type`. This CustomInfoType does

6137

# not support the use of `detection_rules`.

6138

},

6139

},

6140

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6141

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6142

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6143

{ # A task to execute on the completion of a job.

6144

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6145

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

6146

# Command Center (CSCC Alpha).

6147

# This action is only available for projects which are parts of

6148

# an organization and whitelisted for the alpha Cloud Security Command

6149

# Center.

6150

# The action will publish count of finding instances and their info types.

6151

# The summary of findings will be persisted in CSCC and are governed by CSCC

6152

# service-specific policy, see https://cloud.google.com/terms/service-terms

6153

# Only a single instance of this action can be specified.

6154

# Compatible with: Inspect

6155

},

6156

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

6157

# completion/failure.

6158

# completion/failure.

6159

},

6160

"saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6161

# OutputStorageConfig. Only a single instance of this action can be

6162

# specified.

6163

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6164

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

6165

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

6166

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

6167

# from the `Finding` object. If appending to an existing table, any columns

6168

# from the predefined schema that are missing will be added. No columns in

6169

# the existing table will be deleted.

6170

#

6171

# If unspecified, then all available columns will be used for a new table or

6172

# an (existing) table with no schema, and no changes will be made to an

6173

# existing table that has a schema.

6174

# Only for use with external storage.

6175

"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

2019-06-14 16:50:42 -0700

[diff] [blame]

6176

# dataset. If table_id is not set a new one will be generated

6177

# for you with the following format:

6178

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

6179

# generating the date details.

6180

#

6181

# For Inspect, each column in an existing output table must have the same

6182

# name, type, and mode of a field in the `Finding` object.

6183

#

6184

# For Risk, an existing output table should be the output of a previous

6185

# Risk analysis job run on the same source table, with the same privacy

6186

# metric and quasi-identifiers. Risk jobs that analyze the same table but

6187

# compute a different privacy metric, or use different sets of

6188

# quasi-identifiers, cannot store their results in the same table.

6189

# identified by its project_id, dataset_id, and table_name. Within a query

6190

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

6191

# `<project_id>:<dataset_id>.<table_id>` or

6192

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6193

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6194

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6195

"datasetId": "A String", # Dataset ID of the table.

6196

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6197

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6198

},

6199

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6200

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

6201

# message contains a single field, `DlpJobName`, which is equal to the

6202

# finished job's

6203

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

6204

# Compatible with: Inspect, Risk

6205

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

6206

# publishing access rights to the DLP API service account executing

6207

# the long running DlpJob sending the notifications.

6208

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6209

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6210

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

6211

# results of the DlpJob will be applied to the entry for the resource scanned

6212

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

6213

# be deleted. InfoType naming patterns are strictly enforced when using this

6214

# feature. Note that the findings will be persisted in Cloud Data Catalog

6215

# storage and are governed by Data Catalog service-specific policy, see

6216

# https://cloud.google.com/terms/service-terms

6217

# Only a single instance of this action can be specified and only allowed if

6218

# all resources being scanned are BigQuery tables.

6219

# Compatible with: Inspect

6220

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6221

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

6222

# will publish a metric to stack driver on each infotype requested and

6223

# how many findings were found for it. CustomDetectors will be bucketed

6224

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6225

},

6226

},

6227

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6228

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

6229

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

6230

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

6231

# by project and namespace, however the namespace ID may be empty.

6232

# A partition ID identifies a grouping of entities. The grouping is always

6233

# by project and namespace, however the namespace ID may be empty.

6234

#

6235

# A partition ID contains several dimensions:

6236

# project ID and namespace ID.

6237

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

6238

"projectId": "A String", # The ID of the project to which the entities belong.

6239

},

6240

"kind": { # A representation of a Datastore kind. # The kind to process.

6241

"name": "A String", # The name of the kind.

6242

},

6243

},

6244

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

6245

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

6246

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

6247

# Used for data sources like Datastore and BigQuery.

6248

#

6249

# For BigQuery:

6250

# Required to filter out rows based on the given start and

6251

# end times. If not specified and the table was modified between the given

6252

# start and end times, the entire table will be scanned.

6253

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

6254

# `TIMESTAMP`, or `DATETIME` BigQuery column.

6255

#

6256

# For Datastore.

6257

# Valid data types of the timestamp field are: `TIMESTAMP`.

6258

# Datastore entity will be scanned if the timestamp property does not

6259

# exist or its value is empty or invalid.

6260

"name": "A String", # Name describing the field.

6261

},

6262

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

6263

# a valid start_time to avoid scanning files that have not been modified

6264

# since the last time the JobTrigger executed. This will be based on the

6265

# time of the execution of the last run of the JobTrigger.

6266

"endTime": "A String", # Exclude files or rows newer than this value.

6267

# If set to zero, no upper time limit is applied.

6268

"startTime": "A String", # Exclude files or rows older than this value.

6269

},

6270

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

6271

# bucket.

6272

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

6273

# Number of files scanned is rounded down. Must be between 0 and 100,

6274

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

6275

"fileTypes": [ # List of file type groups to include in the scan.

6276

# If empty, all files are scanned and available data format processors

6277

# are applied. In addition, the binary content of the selected files

6278

# is always scanned as well.

6279

# Images are scanned only as binary if the specified region

6280

# does not support image inspection and no file_types were specified.

6281

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

6282

"A String",

6283

],

6284

"sampleMethod": "A String",

6285

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

6286

# number of bytes scanned is rounded down. Must be between 0 and 100,

6287

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

6288

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

6289

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

6290

# than this value then the rest of the bytes are omitted. Only one

6291

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

6292

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

6293

"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

6294

# `regex_file_set` must be set.

6295

# expressions are used to allow fine-grained control over which files in the

6296

# bucket to include.

6297

#

6298

# Included files are those that match at least one item in `include_regex` and

6299

# do not match any items in `exclude_regex`. Note that a file that matches

6300

# items from both lists will _not_ be included. For a match to occur, the

6301

# entire file path (i.e., everything in the url after the bucket name) must

6302

# match the regular expression.

6303

#

6304

# For example, given the input `{bucket_name: "mybucket", include_regex:

6305

# ["directory1/.*"], exclude_regex:

6306

# ["directory1/excluded.*"]}`:

6307

#

6308

# * `gs://mybucket/directory1/myfile` will be included

6309

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

6310

# across `/`)

6311

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

6312

# full path doesn't match any items in `include_regex`)

6313

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

6314

# matches an item in `exclude_regex`)

6315

#

6316

# If `include_regex` is left empty, it will match all files by default

6317

# (this is equivalent to setting `include_regex: [".*"]`).

6318

#

6319

# Some other common use cases:

6320

#

6321

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

6322

# files in `mybucket` except for .pdf files

6323

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

6324

# include all files directly under `gs://mybucket/directory/`, without matching

6325

# across `/`

6326

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

6327

# the bucket that match at least one of these regular expressions will be

6328

# excluded from the scan.

6329

#

6330

# Regular expressions use RE2

6331

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

6332

# under the google/re2 repository on GitHub.

6333

"A String",

6334

],

6335

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

6336

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

6337

# the bucket that match at least one of these regular expressions will be

6338

# included in the set of files, except for those that also match an item in

6339

# `exclude_regex`. Leaving this field empty will match all files by default

6340

# (this is equivalent to including `.*` in the list).

6341

#

6342

# Regular expressions use RE2

6343

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

6344

# under the google/re2 repository on GitHub.

"A String",

],

},

"url": "A String", # The Cloud Storage url of the file(s) to scan, in the format

6349

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

6350

#

6351

# If the url ends in a trailing slash, the bucket or directory represented

6352

# by the url will be scanned non-recursively (content in sub-directories

6353

# will not be scanned). This means that `gs://mybucket/` is equivalent to

6354

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

6355

# `gs://mybucket/directory/*`.

6356

#

6357

# Exactly one of `url` or `regex_file_set` must be set.

6358

},

6359

},

6360

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

6361

"sampleMethod": "A String",

6362

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

6363

# identified by its project_id, dataset_id, and table_name. Within a query

6364

# a table is often referenced with a string in the format of:

6365

# `<project_id>:<dataset_id>.<table_id>` or

6366

# `<project_id>.<dataset_id>.<table_id>`.

6367

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

6368

# If omitted, project ID is inferred from the API call.

6369

"datasetId": "A String", # Dataset ID of the table.

6370

"tableId": "A String", # Name of the table.

6371

},

6372

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

6373

# `actions.saveFindings.outputConfig.table` is specified, the values of

6374

# columns specified here are available in the output table under

6375

# `location.content_locations.record_location.record_key.id_values`. Nested

6376

# fields such as `person.birthdate.year` are allowed.

6377

{ # General identifier of a data field in a storage service.

6378

"name": "A String", # Name describing the field.

6379

},

6380

],

6381

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

6382

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

6383

# 100 means no limit. Defaults to 0. Only one of rows_limit and

6384

# rows_limit_percent can be specified. Cannot be used in conjunction with

6385

# TimespanConfig.

6386

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

6387

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

6388

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

6389

# Cannot be used in conjunction with TimespanConfig.

6390

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

6391

# inspection of entire columns which you know have no findings.

6392

{ # General identifier of a data field in a storage service.

6393

"name": "A String", # Name describing the field.

},

],

},

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

6398

# Early access feature is in a pre-release state and might change or have

6399

# limited support. For more information, see

6400

# https://cloud.google.com/products#product-launch-stages.

6401

# of Google Cloud Platform.

6402

"labels": { # To organize findings, these labels will be added to each finding.

6403

#

6404

# Label keys must be between 1 and 63 characters long and must conform

6405

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

6406

#

6407

# Label values must be between 0 and 63 characters long and must conform

6408

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

6409

#

6410

# No more than 10 labels can be associated with a given finding.

6411

#

6412

# Examples:

6413

# * `"environment" : "production"`

6414

# * `"pipeline" : "etl"`

6415

"a_key": "A String",

6416

},

6417

"description": "A String", # A short description of where the data is coming from. Will be stored once

6418

# in the job. 256 max length.

6419

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

6420

# meaningful such as the columns that are primary keys.

6421

"identifyingFields": [ # The columns that are the primary keys for table objects included in

6422

# ContentItem. A copy of this cell's value will stored alongside alongside

6423

# each finding so that the finding can be traced to the specific row it came

6424

# from. No more than 3 may be provided.

6425

{ # General identifier of a data field in a storage service.

6426

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

6431

# 'finding_labels' map. Request may contain others, but any missing one of

6432

# these will be rejected.

6433

#

6434

# Label keys must be between 1 and 63 characters long and must conform

6435

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

6436

#

6437

# No more than 10 keys can be required.

"A String",

],

},

},

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

6443

# `inspect_config` will be merged into the values persisted as part of the

6444

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6445

},

6446

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

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

"abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran

6453

# out of quota or was ended before they could be processed.

6454

"pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated

6455

# when called via method `getDlpJob`.

6456

# A burst of traffic may cause hybrid inspect requests to be enqueued.

6457

# Processing will take place as quickly as possible, but resource limitations

6458

# may impact how long a request is enqueued for.

6459

"processedCount": "A String", # The number of hybrid inspection requests processed within this job.

6460

},

6461

"infoTypeStats": [ # Statistics of how many instances of each info type were found during

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6462

# inspect job.

6463

{ # Statistics regarding a specific InfoType.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6464

"count": "A String", # Number of findings for this 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

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

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. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

6470

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6471

},

6472

},

6473

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6474

"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.

6475

"processedBytes": "A String", # Total size in bytes that were processed.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6476

},

6477

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

},

],

}</pre>

</div>

<code class="details" id="list_next">list_next(previous_request, previous_response)</code>

6485

<pre>Retrieves the next page of results.

6486

6487

Args:

6488

previous_request: The request for the previous page. (required)

6489

previous_response: The response from the request for the previous page. (required)

6490

6491

Returns:

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6492

A request object that you can call 'execute()' on to request the next

Bu Sun Kim