Blame - docs/dyn/dlp_v2.projects.jobTriggers.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 job trigger to run DLP actions such as scanning storage for</p>

83

84

<code><a href="#delete">delete(name, x__xgafv=None)</a></code></p>

85

<p class="firstline">Deletes a job trigger.</p>

86

87

<code><a href="#get">get(name, x__xgafv=None)</a></code></p>

88

<p class="firstline">Gets a job trigger.</p>

89

Bu Sun Kim

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

[diff] [blame]

90

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

Bu Sun Kim

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

[diff] [blame]

91

<p class="firstline">Lists job triggers.</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

Dan O'Meara

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

[diff] [blame]

96

<code><a href="#patch">patch(name, body=None, x__xgafv=None)</a></code></p>

Bu Sun Kim

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

[diff] [blame]

97

<p class="firstline">Updates a job trigger.</p>

98

<h3>Method Details</h3>

99

100

<code class="details" id="activate">activate(name, body=None, x__xgafv=None)</code>

101

<pre>Activate a job trigger. Causes the immediate execute of a trigger

102

instead of waiting on the trigger event to occur.

103

104

Args:

Dan O'Meara

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

[diff] [blame]

105

name: string, Required. Resource name of the trigger to activate, for example

Bu Sun Kim

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

[diff] [blame]

106

`projects/dlp-test-project/jobTriggers/53234423`. (required)

107

body: object, The request body.

108

The object takes the form of:

109

110

{ # Request message for ActivateJobTrigger.

111

}

112

113

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

120

121

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

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

122

"type": "A String", # The type of job.

123

"endTime": "A String", # Time when the job finished.

124

"startTime": "A String", # Time when the job started.

125

"inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source.

126

"requestedOptions": { # Snapshot of the inspection configuration. # The configuration used for this job.

127

"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

128

# this run.

129

# to be detected) to be used anywhere you otherwise would normally specify

130

# InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates

131

# to learn more.

132

"name": "A String", # Output only. The template name.

Bu Sun Kim

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

[diff] [blame]

133

#

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

134

# The template will have one of the following formats:

135

# `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR

136

# `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`;

137

"description": "A String", # Short description (max 256 chars).

138

"displayName": "A String", # Display name (max 256 chars).

139

"inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process.

140

# When used with redactContent only info_types and min_likelihood are currently

141

# used.

142

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

143

# POSSIBLE.

144

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

145

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

146

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

147

"A String",

148

],

149

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

150

# InfoType values returned by ListInfoTypes or listed at

151

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

Bu Sun Kim

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

[diff] [blame]

152

#

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

153

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

154

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

155

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

Bu Sun Kim

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

[diff] [blame]

156

#

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

157

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

158

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

159

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

160

{ # Type of information detected by the API.

161

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

162

# creating a CustomInfoType, or one of the names listed

163

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

164

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

165

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

166

},

167

],

168

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

169

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

170

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

171

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

172

# sensitive information configurable to the data in question.

173

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

174

# support reversing.

175

# such as

176

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

177

# These types of transformations are

178

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

179

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

180

# transformation such as `surrogate_info_type`. This CustomInfoType does

181

# not support the use of `detection_rules`.

182

},

183

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

184

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

185

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

186

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

187

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

188

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

189

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

190

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

191

# as a custom info type.

192

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

193

# creating a CustomInfoType, or one of the names listed

194

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

195

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

196

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

197

},

198

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

199

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

200

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

201

42,

202

],

203

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

204

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

205

# google/re2 repository on GitHub.

206

},

207

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

208

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

209

# `surrogate_type` CustomInfoType.

210

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

211

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

212

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

213

# custom infoType.

214

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

215

# proximity of hotwords.

216

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

217

# part of a detection rule.

218

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

219

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

220

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

221

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

222

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

223

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

224

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

225

# a final likelihood of `LIKELY`.

226

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

227

},

228

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

229

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

230

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

231

42,

232

],

233

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

234

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

235

# google/re2 repository on GitHub.

236

},

237

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

238

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

239

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

240

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

241

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

242

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

243

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

244

# is the area code in question.

245

# rule.

246

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

247

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

248

},

Bu Sun Kim

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

[diff] [blame]

249

},

250

},

251

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

252

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

253

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

254

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

255

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

256

# of employee IDs or job titles.

257

#

258

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

259

# and digits in the unicode [Basic Multilingual

260

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

261

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

262

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

263

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

264

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

265

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

266

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

267

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

268

# matches for "jennifer".

269

#

270

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

271

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

272

# are treated as whitespace. The

273

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

274

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

275

# these constraints, consider using `LargeCustomDictionaryConfig` in the

276

# `StoredInfoType` API.

277

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

278

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

279

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

280

# 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

285

# is accepted.

286

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

287

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

288

},

289

},

290

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

291

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

292

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

293

# `organizations/433245324/storedInfoTypes/432452342` or

294

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

295

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

296

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

},

},

],

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

301

# included in the response; see Finding.quote.

302

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

303

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

304

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

305

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

306

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

307

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

308

{ # Type of information detected by the API.

309

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

310

# creating a CustomInfoType, or one of the names listed

311

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

312

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

313

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

314

},

315

],

316

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

317

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

318

# `InspectionRuleSet`.

319

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

320

# proximity of hotwords.

321

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

322

# part of a detection rule.

323

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

324

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

325

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

326

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

327

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

328

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

329

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

330

# a final likelihood of `LIKELY`.

331

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

Bu Sun Kim

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

[diff] [blame]

332

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

333

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

334

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

335

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

336

42,

337

],

338

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

339

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

340

# google/re2 repository on GitHub.

341

},

342

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

343

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

344

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

345

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

346

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

347

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

348

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

349

# is the area code in question.

350

# rule.

351

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

352

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

Bu Sun Kim

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

[diff] [blame]

353

},

354

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

355

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

356

# `InspectionRuleSet` are removed from results.

357

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

358

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

359

# of employee IDs or job titles.

360

#

361

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

362

# and digits in the unicode [Basic Multilingual

363

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

364

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

365

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

366

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

367

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

368

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

369

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

370

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

371

# matches for "jennifer".

372

#

373

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

374

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

375

# are treated as whitespace. The

376

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

377

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

378

# these constraints, consider using `LargeCustomDictionaryConfig` in the

379

# `StoredInfoType` API.

380

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

381

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

382

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

383

# 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

388

# is accepted.

389

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

390

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

391

},

392

},

393

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

394

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

395

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

396

42,

397

],

398

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

399

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

400

# google/re2 repository on GitHub.

401

},

402

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

403

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

404

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

405

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

406

# `exclusion_rule` containing `exclude_info_types.info_types` with

407

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

408

# with EMAIL_ADDRESS finding.

409

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

410

# finding, namely email address.

411

{ # Type of information detected by the API.

412

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

413

# creating a CustomInfoType, or one of the names listed

414

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

415

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

416

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

},

],

},

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

421

},

Bu Sun Kim

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

[diff] [blame]

},

],

},

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

426

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

427

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

428

# When set within `InspectJobConfig`,

429

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

430

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

431

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

432

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

433

# running DlpJob.

434

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

435

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

436

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

437

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

438

# are found but not specified in another InfoTypeLimit.

439

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

440

# creating a CustomInfoType, or one of the names listed

441

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

442

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

443

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

},

},

],

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

448

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

449

# regardless if this is set higher.

450

},

451

},

452

"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.

453

"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.

454

},

455

"jobConfig": { # Controls what and how to inspect for findings. # Inspect config.

456

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

457

# When used with redactContent only info_types and min_likelihood are currently

458

# used.

459

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

460

# POSSIBLE.

461

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

462

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

463

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

464

"A String",

465

],

466

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

467

# InfoType values returned by ListInfoTypes or listed at

468

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

469

#

470

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

471

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

472

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

473

#

474

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

475

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

476

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

477

{ # Type of information detected by the API.

478

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

479

# creating a CustomInfoType, or one of the names listed

480

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

481

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

482

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

483

},

484

],

485

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

486

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

487

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

488

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

489

# sensitive information configurable to the data in question.

490

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

491

# support reversing.

492

# such as

493

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

494

# These types of transformations are

495

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

496

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

497

# transformation such as `surrogate_info_type`. This CustomInfoType does

498

# not support the use of `detection_rules`.

499

},

500

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

501

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

502

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

503

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

504

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

505

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

506

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

507

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

508

# as a custom info type.

509

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

510

# creating a CustomInfoType, or one of the names listed

511

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

512

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

513

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

514

},

515

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

516

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

517

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

518

42,

519

],

520

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

521

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

522

# google/re2 repository on GitHub.

523

},

524

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

525

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

526

# `surrogate_type` CustomInfoType.

527

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

528

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

529

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

530

# custom infoType.

531

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

532

# proximity of hotwords.

533

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

534

# part of a detection rule.

535

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

536

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

537

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

538

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

539

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

540

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

541

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

542

# a final likelihood of `LIKELY`.

543

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

544

},

545

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

546

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

547

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

548

42,

549

],

550

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

551

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

552

# google/re2 repository on GitHub.

553

},

554

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

555

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

556

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

557

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

558

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

559

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

560

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

561

# is the area code in question.

562

# rule.

563

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

564

"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

570

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

571

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

572

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

573

# of employee IDs or job titles.

574

#

575

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

576

# and digits in the unicode [Basic Multilingual

577

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

578

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

579

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

580

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

581

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

582

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

583

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

584

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

585

# matches for "jennifer".

586

#

587

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

588

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

589

# are treated as whitespace. The

590

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

591

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

592

# these constraints, consider using `LargeCustomDictionaryConfig` in the

593

# `StoredInfoType` API.

594

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

595

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

596

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

597

# 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

602

# is accepted.

603

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

604

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

605

},

606

},

607

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

608

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

609

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

610

# `organizations/433245324/storedInfoTypes/432452342` or

611

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

612

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

613

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

},

},

],

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

618

# included in the response; see Finding.quote.

619

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

620

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

621

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

622

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

623

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

624

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

625

{ # Type of information detected by the API.

626

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

627

# creating a CustomInfoType, or one of the names listed

628

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

629

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

630

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

631

},

632

],

633

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

634

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

635

# `InspectionRuleSet`.

636

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

637

# proximity of hotwords.

638

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

639

# part of a detection rule.

640

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

641

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

642

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

643

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

644

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

645

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

646

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

647

# a final likelihood of `LIKELY`.

648

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

649

},

650

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

651

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

652

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

653

42,

654

],

655

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

656

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

657

# google/re2 repository on GitHub.

658

},

659

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

660

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

661

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

662

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

663

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

664

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

665

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

666

# is the area code in question.

667

# rule.

668

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

669

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

670

},

671

},

672

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

673

# `InspectionRuleSet` are removed from results.

674

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

675

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

676

# of employee IDs or job titles.

677

#

678

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

679

# and digits in the unicode [Basic Multilingual

680

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

681

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

682

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

683

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

684

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

685

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

686

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

687

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

688

# matches for "jennifer".

689

#

690

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

691

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

692

# are treated as whitespace. The

693

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

694

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

695

# these constraints, consider using `LargeCustomDictionaryConfig` in the

696

# `StoredInfoType` API.

697

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

698

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

699

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

700

# 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

705

# is accepted.

706

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

707

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

708

},

709

},

710

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

711

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

712

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

713

42,

714

],

715

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

716

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

717

# google/re2 repository on GitHub.

718

},

719

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

720

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

721

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

722

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

723

# `exclusion_rule` containing `exclude_info_types.info_types` with

724

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

725

# with EMAIL_ADDRESS finding.

726

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

727

# finding, namely email address.

728

{ # Type of information detected by the API.

729

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

730

# creating a CustomInfoType, or one of the names listed

731

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

732

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

733

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

},

],

},

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

},

},

],

},

],

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

744

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

745

# When set within `InspectJobConfig`,

746

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

747

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

748

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

749

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

750

# running DlpJob.

751

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

752

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

753

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

754

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

755

# are found but not specified in another InfoTypeLimit.

756

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

757

# creating a CustomInfoType, or one of the names listed

758

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

759

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

760

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

},

},

],

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

765

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

766

# regardless if this is set higher.

767

},

768

},

769

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

770

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

771

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

772

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

773

# Command Center (CSCC Alpha).

774

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

775

# an organization and whitelisted for the alpha Cloud Security Command

776

# Center.

777

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

778

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

779

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

780

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

781

# Compatible with: Inspect

782

},

783

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

784

# completion/failure.

785

# completion/failure.

786

},

787

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

788

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

789

# specified.

790

# Compatible with: Inspect, Risk

791

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

792

"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

793

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

794

# for you with the following format:

795

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

796

# generating the date details.

797

#

798

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

799

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

800

#

801

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

802

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

803

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

804

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

805

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

806

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

807

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

808

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

809

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

810

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

811

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

812

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

813

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

814

},

815

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

816

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

817

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

818

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

819

# the existing table will be deleted.

820

#

821

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

822

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

823

# existing table that has a schema.

824

# Only for use with external storage.

825

},

826

},

827

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

828

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

829

# finished job's

830

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

831

# Compatible with: Inspect, Risk

832

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

833

# publishing access rights to the DLP API service account executing

834

# the long running DlpJob sending the notifications.

835

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

836

},

837

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

838

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

839

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

840

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

841

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

842

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

843

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

844

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

845

# all resources being scanned are BigQuery tables.

846

# Compatible with: Inspect

847

},

848

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

849

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

850

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

851

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

},

},

],

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

856

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

857

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

858

# limited support. For more information, see

859

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

860

# of Google Cloud Platform.

861

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

862

#

863

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

864

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

865

#

866

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

867

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

868

#

869

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

870

#

871

# Examples:

872

# * `"environment" : "production"`

873

# * `"pipeline" : "etl"`

874

"a_key": "A String",

875

},

876

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

877

# in the job. 256 max length.

878

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

879

# meaningful such as the columns that are primary keys.

880

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

881

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

882

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

883

# from. No more than 3 may be provided.

884

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

885

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

},

],

},

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

890

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

891

# these will be rejected.

892

#

893

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

894

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

895

#

896

# No more than 10 keys can be required.

"A String",

],

},

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

901

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

902

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

903

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

904

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

905

#

906

# A partition ID contains several dimensions:

907

# project ID and namespace ID.

908

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

909

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

910

},

911

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

912

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

913

},

914

},

915

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

916

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

917

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

918

# Used for data sources like Datastore and BigQuery.

919

#

920

# For BigQuery:

921

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

922

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

923

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

924

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

925

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

926

#

927

# For Datastore.

928

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

929

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

930

# exist or its value is empty or invalid.

931

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

932

},

933

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

934

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

935

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

936

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

937

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

938

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

939

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

940

},

941

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

942

# bucket.

943

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

944

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

945

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

946

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

947

"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

948

# `regex_file_set` must be set.

949

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

950

# bucket to include.

951

#

952

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

953

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

954

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

955

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

956

# match the regular expression.

957

#

958

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

959

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

960

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

961

#

962

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

963

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

964

# across `/`)

965

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

966

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

967

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

968

# matches an item in `exclude_regex`)

969

#

970

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

971

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

972

#

973

# Some other common use cases:

974

#

975

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

976

# files in `mybucket` except for .pdf files

977

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

978

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

979

# across `/`

980

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

981

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

982

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

983

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

984

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

985

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

986

#

987

# Regular expressions use RE2

988

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

989

# under the google/re2 repository on GitHub.

990

"A String",

991

],

992

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

993

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

994

# excluded from the scan.

995

#

996

# Regular expressions use RE2

997

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

998

# 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

1003

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

1004

#

1005

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

1006

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

1007

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

1008

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

1009

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

1010

#

1011

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

1012

},

1013

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

1014

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

1015

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

1016

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

1017

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

1018

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

1019

# is always scanned as well.

1020

# Images are scanned only as binary if the specified region

1021

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

1022

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

1023

"A String",

1024

],

1025

"sampleMethod": "A String",

1026

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

1027

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

1028

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

1029

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

1030

},

1031

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

1032

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

1033

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

1034

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

1035

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

1036

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

1037

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

1038

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

1039

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

1040

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

1041

},

1042

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

1043

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

1044

# columns specified here are available in the output table under

1045

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

1046

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

1047

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

1048

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

1049

},

1050

],

1051

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

1052

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

1053

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

1054

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

1055

# TimespanConfig.

1056

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

1057

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

1058

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

1059

# Cannot be used in conjunction with TimespanConfig.

1060

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

1061

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

1062

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

1063

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

1064

},

1065

],

1066

"sampleMethod": "A String",

1067

},

1068

},

1069

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

1070

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

# template.

},

},

"result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspect job.

1075

"processedBytes": "A String", # Total size in bytes that were processed.

1076

"hybridStats": { # Statistics related to processing hybrid inspect requests. # Statistics related to the processing of hybrid inspect.

1077

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

1078

# limited support. For more information, see

1079

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

1080

"pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated

1081

# when called via method `getDlpJob`.

1082

# A burst of traffic may cause hybrid inspect requests to be enqueued.

1083

# Processing will take place as quickly as possible, but resource limitations

1084

# may impact how long a request is enqueued for.

1085

"processedCount": "A String", # The number of hybrid inspection requests processed within this job.

1086

"abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran

1087

# out of quota or was ended before they could be processed.

1088

},

1089

"infoTypeStats": [ # Statistics of how many instances of each info type were found during

1090

# inspect job.

1091

{ # Statistics regarding a specific InfoType.

1092

"infoType": { # Type of information detected by the API. # The type of finding this stat is for.

1093

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

1094

# creating a CustomInfoType, or one of the names listed

1095

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

1096

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

1097

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

1098

},

1099

"count": "A String", # Number of findings for this infoType.

Bu Sun Kim

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

[diff] [blame]

1100

},

1101

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1102

"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.

Bu Sun Kim

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

[diff] [blame]

1103

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1104

},

1105

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

1106

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

1107

"jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that

1108

# instantiated the job.

1109

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

Bu Sun Kim

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

[diff] [blame]

1110

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

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1111

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

1112

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

1113

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

1114

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

1115

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

1116

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

1117

# US_ZIP_5) or a region code.

1118

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

1119

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

1120

# field of one auxiliary table.

1121

{ # An auxiliary table containing statistical information on the relative

1122

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

1123

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

1124

# frequency of each quasi-identifier tuple.

1125

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

1126

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

1127

# tuple is highly reidentifiable).

1128

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

1129

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

1130

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

1131

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

1132

# indicate an auxiliary table that contains statistical information on

1133

# the possible values of this column (below).

1134

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

1135

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

},

},

],

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

1140

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

1141

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

1142

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

1143

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

1144

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

1145

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

1146

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

1147

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

1148

},

1149

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

1150

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

1151

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

},

},

],

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

1156

# same tag.

1157

{ # A column with a semantic tag attached.

1158

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

1159

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

1160

},

1161

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

1162

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

1163

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

1164

# To programmatically obtain the list of supported InfoTypes, use

1165

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

1166

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

1167

# creating a CustomInfoType, or one of the names listed

1168

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

1169

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

1170

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

1171

},

1172

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

1173

# indicate an auxiliary table that contains statistical information on

1174

# the possible values of this column (below).

1175

"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

1176

# the distribution of values in the input data

1177

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

1178

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

1179

#

1180

# service Foo {

1181

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

1182

# }

1183

#

1184

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

},

},

],

},

Bu Sun Kim

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

[diff] [blame]

1189

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

1190

# number of distinct values and value count distribution.

1191

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

1192

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

1193

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

1194

# depending on the data.

1195

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

1196

},

1197

},

1198

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

Bu Sun Kim

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

[diff] [blame]

1199

"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

1200

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

1201

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

1202

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

1203

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

1204

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

1205

#

1206

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

1207

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

1208

# might be ignored.

1209

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

1210

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

1211

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

1212

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

1213

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

1214

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

1215

},

1216

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1217

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

1218

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

1219

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

1220

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

1221

# a repeated field.

1222

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

1223

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

1224

},

1225

],

Bu Sun Kim

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

[diff] [blame]

1226

},

1227

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

1228

# min, max, and quantiles.

1229

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

1230

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

1231

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

1232

},

1233

},

1234

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

1235

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

1236

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

1237

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

1238

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

1239

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

1240

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

1241

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

1242

# US_ZIP_5) or a region code.

1243

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

1244

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

1245

# of one auxiliary table.

1246

{ # An auxiliary table contains statistical information on the relative

1247

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

1248

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

1249

# frequency of each quasi-identifier tuple.

1250

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

1251

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

1252

# tuple is highly reidentifiable).

1253

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

1254

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

1255

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

1256

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

1257

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

1258

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

1259

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

1260

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

1261

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

1262

},

1263

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

1264

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

1265

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

1266

},

1267

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

1268

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

1269

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

1270

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

1271

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

1272

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

},

},

],

},

],

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

1279

# same tag.

1280

{ # A column with a semantic tag attached.

Bu Sun Kim

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

[diff] [blame]

1281

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

1282

# indicate an auxiliary table that contains statistical information on

1283

# the possible values of this column (below).

1284

"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

1285

# the distribution of values in the input data

1286

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

1287

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

1288

#

1289

# service Foo {

1290

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

1291

# }

1292

#

1293

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

1294

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1295

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

1296

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

1297

},

1298

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

1299

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

1300

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

1301

# To programmatically obtain the list of supported InfoTypes, use

1302

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

1303

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

1304

# creating a CustomInfoType, or one of the names listed

1305

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

1306

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

1307

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

1308

},

Bu Sun Kim

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

[diff] [blame]

},

],

},

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

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1313

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

1314

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

1315

},

Bu Sun Kim

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

[diff] [blame]

1316

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

1317

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

1318

# specified, they are considered a single composite key.

1319

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

1320

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

1321

},

1322

],

Bu Sun Kim

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

[diff] [blame]

1323

},

1324

},

1325

"categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result

1326

"valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.

1327

{ # Histogram of value frequencies in the column.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1328

"valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.

1329

"valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.

1330

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

1331

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

Bu Sun Kim

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

[diff] [blame]

1332

"bucketValues": [ # Sample of value frequencies in this bucket. The total number of

1333

# values returned per bucket is capped at 20.

1334

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

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1335

"count": "A String", # How many times the value is contained in the field.

Bu Sun Kim

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

[diff] [blame]

1336

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

1337

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

1338

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

1339

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

1340

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

1341

# int64 only holds up to 8 bytes of data.

Bu Sun Kim

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

[diff] [blame]

1342

"timestampValue": "A String", # timestamp

1343

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

1344

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

1345

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

1346

#

1347

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

1348

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

1349

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

1350

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

1351

#

1352

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

1353

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

1354

# a year.

1355

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

1356

# month and day.

1357

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

1358

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

1359

# significant.

1360

},

1361

"stringValue": "A String", # string

1362

"integerValue": "A String", # integer

1363

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

1364

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

1365

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

Bu Sun Kim

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

[diff] [blame]

1366

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

1367

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

1368

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

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1369

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

1370

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

1371

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

Bu Sun Kim

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

[diff] [blame]

1372

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1373

"booleanValue": True or False, # boolean

1374

"floatValue": 3.14, # float

1375

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

Bu Sun Kim

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

[diff] [blame]

1376

},

Bu Sun Kim

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

[diff] [blame]

1377

},

1378

],

Bu Sun Kim

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

[diff] [blame]

},

],

},

"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an # K-map result

1383

# estimation, not exact values.

1384

"kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value

1385

# doesn't correspond to any such interval, the associated frequency is

1386

# zero. For example, the following records:

1387

# {min_anonymity: 1, max_anonymity: 1, frequency: 17}

1388

# {min_anonymity: 2, max_anonymity: 3, frequency: 42}

1389

# {min_anonymity: 5, max_anonymity: 10, frequency: 99}

1390

# mean that there are no record with an estimated anonymity of 4, 5, or

1391

# larger than 10.

1392

{ # 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

1397

# to 3, 4 or 5 people in the overlying population. An important particular

1398

# case is when min_anonymity = max_anonymity = 1: the frequency field then

1399

# corresponds to the number of uniquely identifiable records.

Bu Sun Kim

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

[diff] [blame]

1400

"minAnonymity": "A String", # Always positive.

1401

"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total

1402

# number of classes returned per bucket is capped at 20.

1403

{ # A tuple of values for the quasi-identifier columns.

Bu Sun Kim

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

[diff] [blame]

1404

"quasiIdsValues": [ # The quasi-identifier values.

1405

{ # Set of primitive values supported by the system.

1406

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

1407

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

1408

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

1409

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

1410

# int64 only holds up to 8 bytes of data.

Bu Sun Kim

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

[diff] [blame]

1411

"timestampValue": "A String", # timestamp

1412

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

1413

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

1414

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

1415

#

1416

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

1417

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

1418

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

1419

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

1420

#

1421

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

1422

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

1423

# a year.

1424

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

1425

# month and day.

1426

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

1427

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

1428

# significant.

1429

},

1430

"stringValue": "A String", # string

1431

"integerValue": "A String", # integer

1432

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

1433

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

1434

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

Bu Sun Kim

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

[diff] [blame]

1435

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

1436

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

1437

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

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1438

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

1439

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

1440

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

Bu Sun Kim

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

[diff] [blame]

1441

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1442

"booleanValue": True or False, # boolean

1443

"floatValue": 3.14, # float

1444

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

Bu Sun Kim

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

[diff] [blame]

1445

},

1446

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1447

"estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values.

Bu Sun Kim

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

[diff] [blame]

1448

},

1449

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1450

"bucketSize": "A String", # Number of records within these anonymity bounds.

1451

"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.

1452

"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.

Bu Sun Kim

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

[diff] [blame]

},

],

},

"kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result

1457

"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.

1458

{ # Histogram of k-anonymity equivalence classes.

Bu Sun Kim

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

[diff] [blame]

1459

"equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket.

1460

"equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket.

1461

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

1462

# classes returned per bucket is capped at 20.

1463

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

1464

"quasiIdsValues": [ # Set of values defining the equivalence class. One value per

1465

# quasi-identifier column in the original KAnonymity metric message.

1466

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

1467

{ # Set of primitive values supported by the system.

1468

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

1469

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

1470

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

1471

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

1472

# int64 only holds up to 8 bytes of data.

Bu Sun Kim

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

[diff] [blame]

1473

"timestampValue": "A String", # timestamp

1474

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

1475

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

1476

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

1477

#

1478

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

1479

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

1480

# * A year on its own, with zero month and day values

1481

# * A year and month value, with a zero day, e.g. a credit card expiration date

1482

#

1483

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1484

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1485

# a year.

1486

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1487

# month and day.

1488

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1489

# if specifying a year by itself or a year and month where the day is not

1490

# significant.

1491

},

1492

"stringValue": "A String", # string

1493

"integerValue": "A String", # integer

1494

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1495

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1496

# types are google.type.Date and `google.protobuf.Timestamp`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1497

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1498

# to allow the value "24:00:00" for scenarios like business closing time.

1499

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1500

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1501

# allow the value 60 if it allows leap-seconds.

1502

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1503

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1504

"booleanValue": True or False, # boolean

1505

"floatValue": 3.14, # float

1506

"dayOfWeekValue": "A String", # day of week

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1507

},

1508

],

1509

"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the

1510

# above set of values.

1511

},

1512

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1513

"bucketSize": "A String", # Total number of equivalence classes in this bucket.

1514

"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

},

],

},

"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an # Delta-presence result

1519

# estimation, not exact values.

1520

"deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a

1521

# value doesn't correspond to any such interval, the associated frequency

1522

# is zero. For example, the following records:

1523

# {min_probability: 0, max_probability: 0.1, frequency: 17}

1524

# {min_probability: 0.2, max_probability: 0.3, frequency: 42}

1525

# {min_probability: 0.3, max_probability: 0.4, frequency: 99}

1526

# mean that there are no record with an estimated probability in [0.1, 0.2)

1527

# nor larger or equal to 0.4.

1528

{ # A DeltaPresenceEstimationHistogramBucket message with the following

1529

# values:

1530

# min_probability: 0.1

1531

# max_probability: 0.2

1532

# frequency: 42

1533

# means that there are 42 records for which δ is in [0.1, 0.2). An

1534

# important particular case is when min_probability = max_probability = 1:

1535

# then, every individual who shares this quasi-identifier combination is in

1536

# the dataset.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1537

"minProbability": 3.14, # Between 0 and 1.

1538

"maxProbability": 3.14, # Always greater than or equal to min_probability.

1539

"bucketSize": "A String", # Number of records within these probability bounds.

1540

"bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1541

"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total

1542

# number of classes returned per bucket is capped at 20.

1543

{ # A tuple of values for the quasi-identifier columns.

1544

"quasiIdsValues": [ # The quasi-identifier values.

1545

{ # Set of primitive values supported by the system.

1546

# Note that for the purposes of inspection or transformation, the number

1547

# of bytes considered to comprise a 'Value' is based on its representation

1548

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1549

# 123456789, the number of bytes would be counted as 9, even though an

1550

# int64 only holds up to 8 bytes of data.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1551

"timestampValue": "A String", # timestamp

1552

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1553

# and time zone are either specified elsewhere or are not significant. The date

1554

# is relative to the Proleptic Gregorian Calendar. This can represent:

1555

#

1556

# * A full date, with non-zero year, month and day values

1557

# * A month and day value, with a zero year, e.g. an anniversary

1558

# * A year on its own, with zero month and day values

1559

# * A year and month value, with a zero day, e.g. a credit card expiration date

1560

#

1561

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1562

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1563

# a year.

1564

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1565

# month and day.

1566

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1567

# if specifying a year by itself or a year and month where the day is not

1568

# significant.

1569

},

1570

"stringValue": "A String", # string

1571

"integerValue": "A String", # integer

1572

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1573

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1574

# types are google.type.Date and `google.protobuf.Timestamp`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1575

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1576

# to allow the value "24:00:00" for scenarios like business closing time.

1577

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1578

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1579

# allow the value 60 if it allows leap-seconds.

1580

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1581

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1582

"booleanValue": True or False, # boolean

1583

"floatValue": 3.14, # float

1584

"dayOfWeekValue": "A String", # day of week

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1585

},

1586

],

1587

"estimatedProbability": 3.14, # The estimated probability that a given individual sharing these

1588

# quasi-identifier values is in the dataset. This value, typically called

1589

# δ, is the ratio between the number of records in the dataset with these

1590

# quasi-identifier values, and the total number of individuals (inside

1591

# *and* outside the dataset) with these quasi-identifier values.

1592

# For example, if there are 15 individuals in the dataset who share the

1593

# same quasi-identifier values, and an estimated 100 people in the entire

1594

# population with these values, then δ is 0.15.

1595

},

1596

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

},

],

},

"requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over.

1601

# identified by its project_id, dataset_id, and table_name. Within a query

1602

# a table is often referenced with a string in the format of:

1603

# `<project_id>:<dataset_id>.<table_id>` or

1604

# `<project_id>.<dataset_id>.<table_id>`.

1605

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

1606

# If omitted, project ID is inferred from the API call.

1607

"datasetId": "A String", # Dataset ID of the table.

1608

"tableId": "A String", # Name of the table.

1609

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1610

"numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result

1611

"minValue": { # Set of primitive values supported by the system. # Minimum value appearing in the column.

1612

# Note that for the purposes of inspection or transformation, the number

1613

# of bytes considered to comprise a 'Value' is based on its representation

1614

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1615

# 123456789, the number of bytes would be counted as 9, even though an

1616

# int64 only holds up to 8 bytes of data.

1617

"timestampValue": "A String", # timestamp

1618

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1619

# and time zone are either specified elsewhere or are not significant. The date

1620

# is relative to the Proleptic Gregorian Calendar. This can represent:

1621

#

1622

# * A full date, with non-zero year, month and day values

1623

# * A month and day value, with a zero year, e.g. an anniversary

1624

# * A year on its own, with zero month and day values

1625

# * A year and month value, with a zero day, e.g. a credit card expiration date

1626

#

1627

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1628

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1629

# a year.

1630

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1631

# month and day.

1632

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1633

# if specifying a year by itself or a year and month where the day is not

1634

# significant.

1635

},

1636

"stringValue": "A String", # string

1637

"integerValue": "A String", # integer

1638

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1639

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1640

# types are google.type.Date and `google.protobuf.Timestamp`.

1641

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1642

# to allow the value "24:00:00" for scenarios like business closing time.

1643

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

1644

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1645

# allow the value 60 if it allows leap-seconds.

1646

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1647

},

1648

"booleanValue": True or False, # boolean

1649

"floatValue": 3.14, # float

1650

"dayOfWeekValue": "A String", # day of week

1651

},

1652

"maxValue": { # Set of primitive values supported by the system. # Maximum value appearing in the column.

1653

# Note that for the purposes of inspection or transformation, the number

1654

# of bytes considered to comprise a 'Value' is based on its representation

1655

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1656

# 123456789, the number of bytes would be counted as 9, even though an

1657

# int64 only holds up to 8 bytes of data.

1658

"timestampValue": "A String", # timestamp

1659

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1660

# and time zone are either specified elsewhere or are not significant. The date

1661

# is relative to the Proleptic Gregorian Calendar. This can represent:

1662

#

1663

# * A full date, with non-zero year, month and day values

1664

# * A month and day value, with a zero year, e.g. an anniversary

1665

# * A year on its own, with zero month and day values

1666

# * A year and month value, with a zero day, e.g. a credit card expiration date

1667

#

1668

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1669

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1670

# a year.

1671

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1672

# month and day.

1673

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1674

# if specifying a year by itself or a year and month where the day is not

1675

# significant.

1676

},

1677

"stringValue": "A String", # string

1678

"integerValue": "A String", # integer

1679

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1680

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1681

# types are google.type.Date and `google.protobuf.Timestamp`.

1682

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1683

# to allow the value "24:00:00" for scenarios like business closing time.

1684

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

1685

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1686

# allow the value 60 if it allows leap-seconds.

1687

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1688

},

1689

"booleanValue": True or False, # boolean

1690

"floatValue": 3.14, # float

1691

"dayOfWeekValue": "A String", # day of week

1692

},

1693

"quantileValues": [ # List of 99 values that partition the set of field values into 100 equal

1694

# sized buckets.

1695

{ # Set of primitive values supported by the system.

1696

# Note that for the purposes of inspection or transformation, the number

1697

# of bytes considered to comprise a 'Value' is based on its representation

1698

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1699

# 123456789, the number of bytes would be counted as 9, even though an

1700

# int64 only holds up to 8 bytes of data.

1701

"timestampValue": "A String", # timestamp

1702

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1703

# and time zone are either specified elsewhere or are not significant. The date

1704

# is relative to the Proleptic Gregorian Calendar. This can represent:

1705

#

1706

# * A full date, with non-zero year, month and day values

1707

# * A month and day value, with a zero year, e.g. an anniversary

1708

# * A year on its own, with zero month and day values

1709

# * A year and month value, with a zero day, e.g. a credit card expiration date

1710

#

1711

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1712

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1713

# a year.

1714

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1715

# month and day.

1716

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1717

# if specifying a year by itself or a year and month where the day is not

1718

# significant.

1719

},

1720

"stringValue": "A String", # string

1721

"integerValue": "A String", # integer

1722

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1723

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1724

# types are google.type.Date and `google.protobuf.Timestamp`.

1725

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1726

# to allow the value "24:00:00" for scenarios like business closing time.

1727

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

1728

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1729

# allow the value 60 if it allows leap-seconds.

1730

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1731

},

1732

"booleanValue": True or False, # boolean

1733

"floatValue": 3.14, # float

1734

"dayOfWeekValue": "A String", # day of week

},

],

},

"lDiversityResult": { # Result of the l-diversity computation. # L-divesity result

1739

"sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.

1740

{ # Histogram of l-diversity equivalence class sensitive value frequencies.

1741

"bucketValues": [ # Sample of equivalence classes in this bucket. The total number of

1742

# classes returned per bucket is capped at 20.

1743

{ # The set of columns' values that share the same ldiversity value.

1744

"numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class.

1745

"topSensitiveValues": [ # Estimated frequencies of top sensitive values.

1746

{ # A value of a field, including its frequency.

1747

"count": "A String", # How many times the value is contained in the field.

1748

"value": { # Set of primitive values supported by the system. # A value contained in the field in question.

1749

# Note that for the purposes of inspection or transformation, the number

1750

# of bytes considered to comprise a 'Value' is based on its representation

1751

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1752

# 123456789, the number of bytes would be counted as 9, even though an

1753

# int64 only holds up to 8 bytes of data.

1754

"timestampValue": "A String", # timestamp

1755

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1756

# and time zone are either specified elsewhere or are not significant. The date

1757

# is relative to the Proleptic Gregorian Calendar. This can represent:

1758

#

1759

# * A full date, with non-zero year, month and day values

1760

# * A month and day value, with a zero year, e.g. an anniversary

1761

# * A year on its own, with zero month and day values

1762

# * A year and month value, with a zero day, e.g. a credit card expiration date

1763

#

1764

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1765

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1766

# a year.

1767

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1768

# month and day.

1769

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1770

# if specifying a year by itself or a year and month where the day is not

1771

# significant.

1772

},

1773

"stringValue": "A String", # string

1774

"integerValue": "A String", # integer

1775

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1776

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1777

# types are google.type.Date and `google.protobuf.Timestamp`.

1778

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1779

# to allow the value "24:00:00" for scenarios like business closing time.

1780

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

1781

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1782

# allow the value 60 if it allows leap-seconds.

1783

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1784

},

1785

"booleanValue": True or False, # boolean

1786

"floatValue": 3.14, # float

1787

"dayOfWeekValue": "A String", # day of week

},

},

],

"quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence

1792

# class. The order is always the same as the original request.

1793

{ # Set of primitive values supported by the system.

1794

# Note that for the purposes of inspection or transformation, the number

1795

# of bytes considered to comprise a 'Value' is based on its representation

1796

# as a UTF-8 encoded string. For example, if 'integer_value' is set to

1797

# 123456789, the number of bytes would be counted as 9, even though an

1798

# int64 only holds up to 8 bytes of data.

1799

"timestampValue": "A String", # timestamp

1800

"dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date

1801

# and time zone are either specified elsewhere or are not significant. The date

1802

# is relative to the Proleptic Gregorian Calendar. This can represent:

1803

#

1804

# * A full date, with non-zero year, month and day values

1805

# * A month and day value, with a zero year, e.g. an anniversary

1806

# * A year on its own, with zero month and day values

1807

# * A year and month value, with a zero day, e.g. a credit card expiration date

1808

#

1809

# Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.

1810

"year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without

1811

# a year.

1812

"month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a

1813

# month and day.

1814

"day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0

1815

# if specifying a year by itself or a year and month where the day is not

1816

# significant.

1817

},

1818

"stringValue": "A String", # string

1819

"integerValue": "A String", # integer

1820

"timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day

1821

# or are specified elsewhere. An API may choose to allow leap seconds. Related

1822

# types are google.type.Date and `google.protobuf.Timestamp`.

1823

"hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose

1824

# to allow the value "24:00:00" for scenarios like business closing time.

1825

"minutes": 42, # Minutes of hour of day. Must be from 0 to 59.

1826

"seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may

1827

# allow the value 60 if it allows leap-seconds.

1828

"nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.

1829

},

1830

"booleanValue": True or False, # boolean

1831

"floatValue": 3.14, # float

1832

"dayOfWeekValue": "A String", # day of week

1833

},

1834

],

1835

"equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.

1836

},

1837

],

1838

"sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence

1839

# classes in this bucket.

1840

"sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence

1841

# classes in this bucket.

1842

"bucketSize": "A String", # Total number of equivalence classes in this bucket.

1843

"bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.

1844

},

1845

],

1846

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1847

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1848

"name": "A String", # The server-assigned name.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1849

"errors": [ # A stream of errors encountered running the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1850

{ # Details information about an error encountered during job execution or

1851

# the results of an unsuccessful activation of the JobTrigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1852

"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]

1853

# different programming environments, including REST APIs and RPC APIs. It is

1854

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

1855

# three pieces of data: error code, error message, and error details.

1856

#

1857

# You can find out more about this error model and how to work with it in the

1858

# [API Design Guide](https://cloud.google.com/apis/design/errors).

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1859

"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]

1860

# user-facing error message should be localized and sent in the

1861

# google.rpc.Status.details field, or localized by the client.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1862

"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]

1863

# message types for APIs to use.

1864

{

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1865

"a_key": "", # Properties of the object. Contains field @type with type URL.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1866

},

1867

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1868

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1869

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1870

"timestamps": [ # The times the error occurred.

1871

"A String",

1872

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1873

},

1874

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

}</pre>

</div>

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1879

<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]

1880

<pre>Creates a job trigger to run DLP actions such as scanning storage for

1881

sensitive information on a set schedule.

1882

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

1883

1884

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1885

parent: string, Required. The parent resource name, for example projects/my-project-id. (required)

1886

body: object, The request body.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1887

The object takes the form of:

1888

1889

{ # Request message for CreateJobTrigger.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1890

"locationId": "A String", # The geographic location to store the job trigger. Reserved for

1891

# future extensions.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1892

"jobTrigger": { # Contains a configuration to make dlp api calls on a repeating basis. # Required. The JobTrigger to create.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1893

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1894

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

1895

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

1896

# triggeredJob is created, for example

1897

# `projects/dlp-test-project/jobTriggers/53234423`.

1898

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

1899

# errors may result in the JobTrigger automatically being paused.

1900

# Will return the last 100 errors. Whenever the JobTrigger is modified

1901

# this list will be cleared.

1902

{ # Details information about an error encountered during job execution or

1903

# the results of an unsuccessful activation of the JobTrigger.

1904

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

1905

# different programming environments, including REST APIs and RPC APIs. It is

1906

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

1907

# three pieces of data: error code, error message, and error details.

1908

#

1909

# You can find out more about this error model and how to work with it in the

1910

# [API Design Guide](https://cloud.google.com/apis/design/errors).

1911

"message": "A String", # A developer-facing error message, which should be in English. Any

1912

# user-facing error message should be localized and sent in the

1913

# google.rpc.Status.details field, or localized by the client.

1914

"details": [ # A list of messages that carry the error details. There is a common set of

1915

# message types for APIs to use.

1916

{

1917

"a_key": "", # Properties of the object. Contains field @type with type URL.

1918

},

1919

],

1920

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

1921

},

1922

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1928

"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1929

# needs to trigger for a job to be started. The list may contain only

1930

# a single Schedule trigger and must have at least one object.

1931

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1932

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

1933

"recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1934

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1935

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1936

# A scheduled start time will be skipped if the previous

1937

# execution has not ended when its scheduled time occurs.

1938

#

1939

# This value must be set to a time duration greater than or equal

1940

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1941

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1942

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1943

# Early access feature is in a pre-release state and might change or have

1944

# limited support. For more information, see

1945

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1946

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1947

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1948

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1949

],

1950

"displayName": "A String", # Display name (max 100 chars)

1951

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

1952

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

1953

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

1954

"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]

1955

# When used with redactContent only info_types and min_likelihood are currently

1956

# used.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1957

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

1958

# POSSIBLE.

1959

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

1960

"contentOptions": [ # List of options defining data content to scan.

1961

# If empty, text, images, and other content will be included.

1962

"A String",

1963

],

1964

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

1965

# InfoType values returned by ListInfoTypes or listed at

1966

# https://cloud.google.com/dlp/docs/infotypes-reference.

1967

#

1968

# When no InfoTypes or CustomInfoTypes are specified in a request, the

1969

# system may automatically choose what detectors to run. By default this may

1970

# be all types, but may change over time as detectors are updated.

1971

#

1972

# If you need precise control and predictability as to what detectors are

1973

# run you should specify specific InfoTypes listed in the reference,

1974

# otherwise a default list will be used, which may change over time.

1975

{ # Type of information detected by the API.

1976

"name": "A String", # Name of the information type. Either a name of your choosing when

1977

# creating a CustomInfoType, or one of the names listed

1978

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1979

# a built-in type. InfoType names should conform to the pattern

1980

# `[a-zA-Z0-9_]{1,64}`.

1981

},

1982

],

1983

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

1984

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

1985

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

1986

{ # Custom information type provided by the user. Used to find domain-specific

1987

# sensitive information configurable to the data in question.

1988

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

1989

# support reversing.

1990

# such as

1991

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

1992

# These types of transformations are

1993

# those that perform pseudonymization, thereby producing a "surrogate" as

1994

# output. This should be used in conjunction with a field on the

1995

# transformation such as `surrogate_info_type`. This CustomInfoType does

1996

# not support the use of `detection_rules`.

1997

},

1998

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

1999

# altered by a detection rule if the finding meets the criteria specified by

2000

# the rule. Defaults to `VERY_LIKELY` if not specified.

2001

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

2002

# infoType, when the name matches one of existing infoTypes and that infoType

2003

# is specified in `InspectContent.info_types` field. Specifying the latter

2004

# adds findings to the one detected by the system. If built-in info type is

2005

# not specified in `InspectContent.info_types` list then the name is treated

2006

# as a custom info type.

2007

"name": "A String", # Name of the information type. Either a name of your choosing when

2008

# creating a CustomInfoType, or one of the names listed

2009

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2010

# a built-in type. InfoType names should conform to the pattern

2011

# `[a-zA-Z0-9_]{1,64}`.

2012

},

2013

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

2014

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2015

# specified, the entire match is returned. No more than 3 may be included.

2016

42,

2017

],

2018

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2019

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2020

# google/re2 repository on GitHub.

2021

},

2022

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

2023

# Rules are applied in order that they are specified. Not supported for the

2024

# `surrogate_type` CustomInfoType.

2025

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

2026

# `CustomInfoType` to alter behavior under certain circumstances, depending

2027

# on the specific details of the rule. Not supported for the `surrogate_type`

2028

# custom infoType.

2029

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

2030

# proximity of hotwords.

2031

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

2032

# part of a detection rule.

2033

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

2034

# levels. For example, if a finding would be `POSSIBLE` without the

2035

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2036

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2037

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2038

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2039

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2040

# a final likelihood of `LIKELY`.

2041

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

2042

},

2043

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2044

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2045

# specified, the entire match is returned. No more than 3 may be included.

2046

42,

2047

],

2048

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2049

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2050

# google/re2 repository on GitHub.

2051

},

2052

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2053

# The total length of the window cannot exceed 1000 characters. Note that

2054

# the finding itself will be included in the window, so that hotwords may

2055

# be used to match substrings of the finding itself. For example, the

2056

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

2057

# adjusted upwards if the area code is known to be the local area code of

2058

# a company office using the hotword regex "\(xxx\)", where "xxx"

2059

# is the area code in question.

2060

# rule.

2061

"windowBefore": 42, # Number of characters before the finding to consider.

2062

"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

2068

# to be returned. It still can be used for rules matching.

2069

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

2070

# be used to match sensitive information specific to the data, such as a list

2071

# of employee IDs or job titles.

2072

#

2073

# Dictionary words are case-insensitive and all characters other than letters

2074

# and digits in the unicode [Basic Multilingual

2075

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2076

# will be replaced with whitespace when scanning for matches, so the

2077

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2078

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

2079

# surrounding any match must be of a different type than the adjacent

2080

# characters within the word, so letters must be next to non-letters and

2081

# digits next to non-digits. For example, the dictionary word "jen" will

2082

# match the first three letters of the text "jen123" but will return no

2083

# matches for "jennifer".

2084

#

2085

# Dictionary words containing a large number of characters that are not

2086

# letters or digits may result in unexpected findings because such characters

2087

# are treated as whitespace. The

2088

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2089

# the size limits of dictionaries. For dictionaries that do not fit within

2090

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2091

# `StoredInfoType` API.

2092

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2093

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

2094

# at least one phrase and every phrase must contain at least 2 characters

2095

# 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

2100

# is accepted.

2101

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

2102

# Example: gs://[BUCKET_NAME]/dictionary.txt

2103

},

2104

},

2105

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

2106

# `InspectDataSource`. Not currently supported in `InspectContent`.

2107

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

2108

# `organizations/433245324/storedInfoTypes/432452342` or

2109

# `projects/project-id/storedInfoTypes/432452342`.

2110

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

2111

# inspection was created. Output-only field, populated by the system.

2112

},

2113

},

2114

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2115

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

2116

# included in the response; see Finding.quote.

2117

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

2118

# Exclusion rules, contained in the set are executed in the end, other

2119

# rules are executed in the order they are specified for each info type.

2120

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

2121

# circumstances, depending on the specific details of the rules within the set.

2122

"infoTypes": [ # List of infoTypes this rule set is applied to.

2123

{ # Type of information detected by the API.

2124

"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]

2125

# creating a CustomInfoType, or one of the names listed

2126

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2127

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2128

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2129

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2130

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2131

"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]

2132

{ # A single inspection rule to be applied to infoTypes, specified in

2133

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2134

"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]

2135

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2136

"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]

2137

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2138

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2139

# levels. For example, if a finding would be `POSSIBLE` without the

2140

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2141

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2142

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2143

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2144

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2145

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2146

"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]

2147

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2148

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2149

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2150

# specified, the entire match is returned. No more than 3 may be included.

2151

42,

2152

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2153

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2154

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2155

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2156

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2157

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2158

# The total length of the window cannot exceed 1000 characters. Note that

2159

# the finding itself will be included in the window, so that hotwords may

2160

# be used to match substrings of the finding itself. For example, the

2161

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

2162

# adjusted upwards if the area code is known to be the local area code of

2163

# a company office using the hotword regex "\(xxx\)", where "xxx"

2164

# is the area code in question.

2165

# rule.

2166

"windowBefore": 42, # Number of characters before the finding to consider.

2167

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2168

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2169

},

2170

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

2171

# `InspectionRuleSet` are removed from results.

2172

"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]

2173

# be used to match sensitive information specific to the data, such as a list

2174

# of employee IDs or job titles.

2175

#

2176

# Dictionary words are case-insensitive and all characters other than letters

2177

# and digits in the unicode [Basic Multilingual

2178

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2179

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2180

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2181

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2182

# surrounding any match must be of a different type than the adjacent

2183

# 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]

2184

# digits next to non-digits. For example, the dictionary word "jen" will

2185

# match the first three letters of the text "jen123" but will return no

2186

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2187

#

2188

# Dictionary words containing a large number of characters that are not

2189

# letters or digits may result in unexpected findings because such characters

2190

# are treated as whitespace. The

2191

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2192

# the size limits of dictionaries. For dictionaries that do not fit within

2193

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2194

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2195

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2196

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2197

# at least one phrase and every phrase must contain at least 2 characters

2198

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2199

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2200

],

2201

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2202

"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]

2203

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2204

"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]

2205

# Example: gs://[BUCKET_NAME]/dictionary.txt

2206

},

2207

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2208

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

2209

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2210

# specified, the entire match is returned. No more than 3 may be included.

2211

42,

2212

],

2213

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2214

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2215

# google/re2 repository on GitHub.

2216

},

2217

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

2218

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

2219

# contained within with a finding of an infoType from this list. For

2220

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

2221

# `exclusion_rule` containing `exclude_info_types.info_types` with

2222

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

2223

# with EMAIL_ADDRESS finding.

2224

# That leads to "555-222-2222@example.org" to generate only a single

2225

# finding, namely email address.

2226

{ # Type of information detected by the API.

2227

"name": "A String", # Name of the information type. Either a name of your choosing when

2228

# creating a CustomInfoType, or one of the names listed

2229

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2230

# a built-in type. InfoType names should conform to the pattern

2231

# `[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]

2236

},

2237

},

2238

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2239

},

2240

],

2241

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

2242

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

2243

# When set within `InspectJobConfig`,

2244

# the maximum returned is 2000 regardless if this is set higher.

2245

# When set within `InspectContentRequest`, this field is ignored.

2246

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

2247

{ # Max findings configuration per infoType, per content item or long

2248

# running DlpJob.

2249

"maxFindings": 42, # Max findings limit for the given infoType.

2250

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

2251

# info_type should be provided. If InfoTypeLimit does not have an

2252

# info_type, the DLP API applies the limit against all info_types that

2253

# are found but not specified in another InfoTypeLimit.

2254

"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]

2255

# creating a CustomInfoType, or one of the names listed

2256

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2257

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2258

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2259

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2260

},

2261

],

2262

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

2263

# When set within `InspectContentRequest`, the maximum returned is 2000

2264

# regardless if this is set higher.

2265

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2266

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2267

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2268

{ # A task to execute on the completion of a job.

2269

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2270

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

2271

# Command Center (CSCC Alpha).

2272

# This action is only available for projects which are parts of

2273

# an organization and whitelisted for the alpha Cloud Security Command

2274

# Center.

2275

# The action will publish count of finding instances and their info types.

2276

# The summary of findings will be persisted in CSCC and are governed by CSCC

2277

# service-specific policy, see https://cloud.google.com/terms/service-terms

2278

# Only a single instance of this action can be specified.

2279

# Compatible with: Inspect

2280

},

2281

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

2282

# completion/failure.

2283

# completion/failure.

2284

},

2285

"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]

2286

# OutputStorageConfig. Only a single instance of this action can be

2287

# specified.

2288

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2289

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2290

"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]

2291

# dataset. If table_id is not set a new one will be generated

2292

# for you with the following format:

2293

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

2294

# generating the date details.

2295

#

2296

# For Inspect, each column in an existing output table must have the same

2297

# name, type, and mode of a field in the `Finding` object.

2298

#

2299

# For Risk, an existing output table should be the output of a previous

2300

# Risk analysis job run on the same source table, with the same privacy

2301

# metric and quasi-identifiers. Risk jobs that analyze the same table but

2302

# compute a different privacy metric, or use different sets of

2303

# quasi-identifiers, cannot store their results in the same table.

2304

# identified by its project_id, dataset_id, and table_name. Within a query

2305

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2306

# `<project_id>:<dataset_id>.<table_id>` or

2307

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2308

"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]

2309

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2310

"datasetId": "A String", # Dataset ID of the table.

2311

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2312

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2313

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

2314

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

2315

# from the `Finding` object. If appending to an existing table, any columns

2316

# from the predefined schema that are missing will be added. No columns in

2317

# the existing table will be deleted.

2318

#

2319

# If unspecified, then all available columns will be used for a new table or

2320

# an (existing) table with no schema, and no changes will be made to an

2321

# existing table that has a schema.

2322

# Only for use with external storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2323

},

2324

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2325

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

2326

# message contains a single field, `DlpJobName`, which is equal to the

2327

# finished job's

2328

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

2329

# Compatible with: Inspect, Risk

2330

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

2331

# publishing access rights to the DLP API service account executing

2332

# the long running DlpJob sending the notifications.

2333

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2334

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2335

"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]

2336

# results of the DlpJob will be applied to the entry for the resource scanned

2337

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

2338

# be deleted. InfoType naming patterns are strictly enforced when using this

2339

# feature. Note that the findings will be persisted in Cloud Data Catalog

2340

# storage and are governed by Data Catalog service-specific policy, see

2341

# https://cloud.google.com/terms/service-terms

2342

# Only a single instance of this action can be specified and only allowed if

2343

# all resources being scanned are BigQuery tables.

2344

# Compatible with: Inspect

2345

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2346

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

2347

# will publish a metric to stack driver on each infotype requested and

2348

# how many findings were found for it. CustomDetectors will be bucketed

2349

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2350

},

2351

},

2352

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2353

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2354

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

2355

# Early access feature is in a pre-release state and might change or have

2356

# limited support. For more information, see

2357

# https://cloud.google.com/products#product-launch-stages.

2358

# of Google Cloud Platform.

2359

"labels": { # To organize findings, these labels will be added to each finding.

2360

#

2361

# Label keys must be between 1 and 63 characters long and must conform

2362

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

2363

#

2364

# Label values must be between 0 and 63 characters long and must conform

2365

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

2366

#

2367

# No more than 10 labels can be associated with a given finding.

2368

#

2369

# Examples:

2370

# * `"environment" : "production"`

2371

# * `"pipeline" : "etl"`

2372

"a_key": "A String",

2373

},

2374

"description": "A String", # A short description of where the data is coming from. Will be stored once

2375

# in the job. 256 max length.

2376

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

2377

# meaningful such as the columns that are primary keys.

2378

"identifyingFields": [ # The columns that are the primary keys for table objects included in

2379

# ContentItem. A copy of this cell's value will stored alongside alongside

2380

# each finding so that the finding can be traced to the specific row it came

2381

# from. No more than 3 may be provided.

2382

{ # General identifier of a data field in a storage service.

2383

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

2388

# 'finding_labels' map. Request may contain others, but any missing one of

2389

# these will be rejected.

2390

#

2391

# Label keys must be between 1 and 63 characters long and must conform

2392

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

2393

#

2394

# No more than 10 keys can be required.

2395

"A String",

2396

],

2397

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2398

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

2399

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

2400

# by project and namespace, however the namespace ID may be empty.

2401

# A partition ID identifies a grouping of entities. The grouping is always

2402

# by project and namespace, however the namespace ID may be empty.

2403

#

2404

# A partition ID contains several dimensions:

2405

# project ID and namespace ID.

2406

"projectId": "A String", # The ID of the project to which the entities belong.

2407

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

2408

},

2409

"kind": { # A representation of a Datastore kind. # The kind to process.

2410

"name": "A String", # The name of the kind.

2411

},

2412

},

2413

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

2414

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

2415

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

2416

# Used for data sources like Datastore and BigQuery.

2417

#

2418

# For BigQuery:

2419

# Required to filter out rows based on the given start and

2420

# end times. If not specified and the table was modified between the given

2421

# start and end times, the entire table will be scanned.

2422

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

2423

# `TIMESTAMP`, or `DATETIME` BigQuery column.

2424

#

2425

# For Datastore.

2426

# Valid data types of the timestamp field are: `TIMESTAMP`.

2427

# Datastore entity will be scanned if the timestamp property does not

2428

# exist or its value is empty or invalid.

2429

"name": "A String", # Name describing the field.

2430

},

2431

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

2432

# a valid start_time to avoid scanning files that have not been modified

2433

# since the last time the JobTrigger executed. This will be based on the

2434

# time of the execution of the last run of the JobTrigger.

2435

"endTime": "A String", # Exclude files or rows newer than this value.

2436

# If set to zero, no upper time limit is applied.

2437

"startTime": "A String", # Exclude files or rows older than this value.

2438

},

2439

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

2440

# bucket.

2441

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

2442

# than this value then the rest of the bytes are omitted. Only one

2443

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

2444

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

2445

"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

2446

# `regex_file_set` must be set.

2447

# expressions are used to allow fine-grained control over which files in the

2448

# bucket to include.

2449

#

2450

# Included files are those that match at least one item in `include_regex` and

2451

# do not match any items in `exclude_regex`. Note that a file that matches

2452

# items from both lists will _not_ be included. For a match to occur, the

2453

# entire file path (i.e., everything in the url after the bucket name) must

2454

# match the regular expression.

2455

#

2456

# For example, given the input `{bucket_name: "mybucket", include_regex:

2457

# ["directory1/.*"], exclude_regex:

2458

# ["directory1/excluded.*"]}`:

2459

#

2460

# * `gs://mybucket/directory1/myfile` will be included

2461

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

2462

# across `/`)

2463

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

2464

# full path doesn't match any items in `include_regex`)

2465

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

2466

# matches an item in `exclude_regex`)

2467

#

2468

# If `include_regex` is left empty, it will match all files by default

2469

# (this is equivalent to setting `include_regex: [".*"]`).

2470

#

2471

# Some other common use cases:

2472

#

2473

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

2474

# files in `mybucket` except for .pdf files

2475

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

2476

# include all files directly under `gs://mybucket/directory/`, without matching

2477

# across `/`

2478

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

2479

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

2480

# the bucket that match at least one of these regular expressions will be

2481

# included in the set of files, except for those that also match an item in

2482

# `exclude_regex`. Leaving this field empty will match all files by default

2483

# (this is equivalent to including `.*` in the list).

2484

#

2485

# Regular expressions use RE2

2486

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

2487

# under the google/re2 repository on GitHub.

2488

"A String",

2489

],

2490

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

2491

# the bucket that match at least one of these regular expressions will be

2492

# excluded from the scan.

2493

#

2494

# Regular expressions use RE2

2495

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

2496

# 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

2501

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

2502

#

2503

# If the url ends in a trailing slash, the bucket or directory represented

2504

# by the url will be scanned non-recursively (content in sub-directories

2505

# will not be scanned). This means that `gs://mybucket/` is equivalent to

2506

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

2507

# `gs://mybucket/directory/*`.

2508

#

2509

# Exactly one of `url` or `regex_file_set` must be set.

2510

},

2511

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

2512

# Number of files scanned is rounded down. Must be between 0 and 100,

2513

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

2514

"fileTypes": [ # List of file type groups to include in the scan.

2515

# If empty, all files are scanned and available data format processors

2516

# are applied. In addition, the binary content of the selected files

2517

# is always scanned as well.

2518

# Images are scanned only as binary if the specified region

2519

# does not support image inspection and no file_types were specified.

2520

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

2521

"A String",

2522

],

2523

"sampleMethod": "A String",

2524

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

2525

# number of bytes scanned is rounded down. Must be between 0 and 100,

2526

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

2527

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

2528

},

2529

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

2530

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

2531

# identified by its project_id, dataset_id, and table_name. Within a query

2532

# a table is often referenced with a string in the format of:

2533

# `<project_id>:<dataset_id>.<table_id>` or

2534

# `<project_id>.<dataset_id>.<table_id>`.

2535

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

2536

# If omitted, project ID is inferred from the API call.

2537

"datasetId": "A String", # Dataset ID of the table.

2538

"tableId": "A String", # Name of the table.

2539

},

2540

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

2541

# `actions.saveFindings.outputConfig.table` is specified, the values of

2542

# columns specified here are available in the output table under

2543

# `location.content_locations.record_location.record_key.id_values`. Nested

2544

# fields such as `person.birthdate.year` are allowed.

2545

{ # General identifier of a data field in a storage service.

2546

"name": "A String", # Name describing the field.

2547

},

2548

],

2549

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

2550

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

2551

# 100 means no limit. Defaults to 0. Only one of rows_limit and

2552

# rows_limit_percent can be specified. Cannot be used in conjunction with

2553

# TimespanConfig.

2554

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

2555

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

2556

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

2557

# Cannot be used in conjunction with TimespanConfig.

2558

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

2559

# inspection of entire columns which you know have no findings.

2560

{ # General identifier of a data field in a storage service.

2561

"name": "A String", # Name describing the field.

2562

},

2563

],

2564

"sampleMethod": "A String",

2565

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2566

},

2567

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

2568

# `inspect_config` will be merged into the values persisted as part of the

2569

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2570

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2571

"status": "A String", # Required. A status for this trigger.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2572

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2573

"triggerId": "A String", # The trigger id can contain uppercase and lowercase letters,

2574

# numbers, and hyphens; that is, it must match the regular

2575

# expression: `[a-zA-Z\\d-_]+`. The maximum length is 100

2576

# characters. Can be empty to allow the system to generate one.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2577

}

2578

2579

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

2586

2587

{ # Contains a configuration to make dlp api calls on a repeating basis.

2588

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2589

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

2590

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

2591

# triggeredJob is created, for example

2592

# `projects/dlp-test-project/jobTriggers/53234423`.

2593

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

2594

# errors may result in the JobTrigger automatically being paused.

2595

# Will return the last 100 errors. Whenever the JobTrigger is modified

2596

# this list will be cleared.

2597

{ # Details information about an error encountered during job execution or

2598

# the results of an unsuccessful activation of the JobTrigger.

2599

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

2600

# different programming environments, including REST APIs and RPC APIs. It is

2601

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

2602

# three pieces of data: error code, error message, and error details.

2603

#

2604

# You can find out more about this error model and how to work with it in the

2605

# [API Design Guide](https://cloud.google.com/apis/design/errors).

2606

"message": "A String", # A developer-facing error message, which should be in English. Any

2607

# user-facing error message should be localized and sent in the

2608

# google.rpc.Status.details field, or localized by the client.

2609

"details": [ # A list of messages that carry the error details. There is a common set of

2610

# message types for APIs to use.

2611

{

2612

"a_key": "", # Properties of the object. Contains field @type with type URL.

2613

},

2614

],

2615

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

2616

},

2617

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2623

"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2624

# needs to trigger for a job to be started. The list may contain only

2625

# a single Schedule trigger and must have at least one object.

2626

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2627

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

2628

"recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2629

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2630

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2631

# A scheduled start time will be skipped if the previous

2632

# execution has not ended when its scheduled time occurs.

2633

#

2634

# This value must be set to a time duration greater than or equal

2635

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2636

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2637

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2638

# Early access feature is in a pre-release state and might change or have

2639

# limited support. For more information, see

2640

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2641

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2642

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2643

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2644

],

2645

"displayName": "A String", # Display name (max 100 chars)

2646

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

2647

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

2648

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

2649

"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]

2650

# When used with redactContent only info_types and min_likelihood are currently

2651

# used.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2652

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

2653

# POSSIBLE.

2654

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

2655

"contentOptions": [ # List of options defining data content to scan.

2656

# If empty, text, images, and other content will be included.

2657

"A String",

2658

],

2659

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

2660

# InfoType values returned by ListInfoTypes or listed at

2661

# https://cloud.google.com/dlp/docs/infotypes-reference.

2662

#

2663

# When no InfoTypes or CustomInfoTypes are specified in a request, the

2664

# system may automatically choose what detectors to run. By default this may

2665

# be all types, but may change over time as detectors are updated.

2666

#

2667

# If you need precise control and predictability as to what detectors are

2668

# run you should specify specific InfoTypes listed in the reference,

2669

# otherwise a default list will be used, which may change over time.

2670

{ # Type of information detected by the API.

2671

"name": "A String", # Name of the information type. Either a name of your choosing when

2672

# creating a CustomInfoType, or one of the names listed

2673

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2674

# a built-in type. InfoType names should conform to the pattern

2675

# `[a-zA-Z0-9_]{1,64}`.

2676

},

2677

],

2678

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

2679

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

2680

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

2681

{ # Custom information type provided by the user. Used to find domain-specific

2682

# sensitive information configurable to the data in question.

2683

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

2684

# support reversing.

2685

# such as

2686

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

2687

# These types of transformations are

2688

# those that perform pseudonymization, thereby producing a "surrogate" as

2689

# output. This should be used in conjunction with a field on the

2690

# transformation such as `surrogate_info_type`. This CustomInfoType does

2691

# not support the use of `detection_rules`.

2692

},

2693

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

2694

# altered by a detection rule if the finding meets the criteria specified by

2695

# the rule. Defaults to `VERY_LIKELY` if not specified.

2696

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

2697

# infoType, when the name matches one of existing infoTypes and that infoType

2698

# is specified in `InspectContent.info_types` field. Specifying the latter

2699

# adds findings to the one detected by the system. If built-in info type is

2700

# not specified in `InspectContent.info_types` list then the name is treated

2701

# as a custom info type.

2702

"name": "A String", # Name of the information type. Either a name of your choosing when

2703

# creating a CustomInfoType, or one of the names listed

2704

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2705

# a built-in type. InfoType names should conform to the pattern

2706

# `[a-zA-Z0-9_]{1,64}`.

2707

},

2708

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

2709

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2710

# specified, the entire match is returned. No more than 3 may be included.

2711

42,

2712

],

2713

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2714

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2715

# google/re2 repository on GitHub.

2716

},

2717

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

2718

# Rules are applied in order that they are specified. Not supported for the

2719

# `surrogate_type` CustomInfoType.

2720

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

2721

# `CustomInfoType` to alter behavior under certain circumstances, depending

2722

# on the specific details of the rule. Not supported for the `surrogate_type`

2723

# custom infoType.

2724

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

2725

# proximity of hotwords.

2726

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

2727

# part of a detection rule.

2728

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

2729

# levels. For example, if a finding would be `POSSIBLE` without the

2730

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2731

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2732

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2733

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2734

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2735

# a final likelihood of `LIKELY`.

2736

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

2737

},

2738

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2739

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2740

# specified, the entire match is returned. No more than 3 may be included.

2741

42,

2742

],

2743

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2744

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2745

# google/re2 repository on GitHub.

2746

},

2747

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2748

# The total length of the window cannot exceed 1000 characters. Note that

2749

# the finding itself will be included in the window, so that hotwords may

2750

# be used to match substrings of the finding itself. For example, the

2751

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

2752

# adjusted upwards if the area code is known to be the local area code of

2753

# a company office using the hotword regex "\(xxx\)", where "xxx"

2754

# is the area code in question.

2755

# rule.

2756

"windowBefore": 42, # Number of characters before the finding to consider.

2757

"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

2763

# to be returned. It still can be used for rules matching.

2764

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

2765

# be used to match sensitive information specific to the data, such as a list

2766

# of employee IDs or job titles.

2767

#

2768

# Dictionary words are case-insensitive and all characters other than letters

2769

# and digits in the unicode [Basic Multilingual

2770

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2771

# will be replaced with whitespace when scanning for matches, so the

2772

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2773

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

2774

# surrounding any match must be of a different type than the adjacent

2775

# characters within the word, so letters must be next to non-letters and

2776

# digits next to non-digits. For example, the dictionary word "jen" will

2777

# match the first three letters of the text "jen123" but will return no

2778

# matches for "jennifer".

2779

#

2780

# Dictionary words containing a large number of characters that are not

2781

# letters or digits may result in unexpected findings because such characters

2782

# are treated as whitespace. The

2783

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2784

# the size limits of dictionaries. For dictionaries that do not fit within

2785

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2786

# `StoredInfoType` API.

2787

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2788

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

2789

# at least one phrase and every phrase must contain at least 2 characters

2790

# 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

2795

# is accepted.

2796

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

2797

# Example: gs://[BUCKET_NAME]/dictionary.txt

2798

},

2799

},

2800

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

2801

# `InspectDataSource`. Not currently supported in `InspectContent`.

2802

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

2803

# `organizations/433245324/storedInfoTypes/432452342` or

2804

# `projects/project-id/storedInfoTypes/432452342`.

2805

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

2806

# inspection was created. Output-only field, populated by the system.

2807

},

2808

},

2809

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2810

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

2811

# included in the response; see Finding.quote.

2812

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

2813

# Exclusion rules, contained in the set are executed in the end, other

2814

# rules are executed in the order they are specified for each info type.

2815

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

2816

# circumstances, depending on the specific details of the rules within the set.

2817

"infoTypes": [ # List of infoTypes this rule set is applied to.

2818

{ # Type of information detected by the API.

2819

"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]

2820

# creating a CustomInfoType, or one of the names listed

2821

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2822

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2823

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2824

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2825

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2826

"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]

2827

{ # A single inspection rule to be applied to infoTypes, specified in

2828

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2829

"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]

2830

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2831

"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]

2832

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2833

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2834

# levels. For example, if a finding would be `POSSIBLE` without the

2835

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2836

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2837

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2838

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2839

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2840

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2841

"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]

2842

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2843

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2844

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2845

# specified, the entire match is returned. No more than 3 may be included.

2846

42,

2847

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2848

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2849

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2850

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2851

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2852

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2853

# The total length of the window cannot exceed 1000 characters. Note that

2854

# the finding itself will be included in the window, so that hotwords may

2855

# be used to match substrings of the finding itself. For example, the

2856

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

2857

# adjusted upwards if the area code is known to be the local area code of

2858

# a company office using the hotword regex "\(xxx\)", where "xxx"

2859

# is the area code in question.

2860

# rule.

2861

"windowBefore": 42, # Number of characters before the finding to consider.

2862

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2863

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2864

},

2865

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

2866

# `InspectionRuleSet` are removed from results.

2867

"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]

2868

# be used to match sensitive information specific to the data, such as a list

2869

# of employee IDs or job titles.

2870

#

2871

# Dictionary words are case-insensitive and all characters other than letters

2872

# and digits in the unicode [Basic Multilingual

2873

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2874

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2875

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2876

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2877

# surrounding any match must be of a different type than the adjacent

2878

# 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]

2879

# digits next to non-digits. For example, the dictionary word "jen" will

2880

# match the first three letters of the text "jen123" but will return no

2881

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2882

#

2883

# Dictionary words containing a large number of characters that are not

2884

# letters or digits may result in unexpected findings because such characters

2885

# are treated as whitespace. The

2886

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2887

# the size limits of dictionaries. For dictionaries that do not fit within

2888

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2889

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2890

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2891

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2892

# at least one phrase and every phrase must contain at least 2 characters

2893

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2894

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2895

],

2896

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2897

"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]

2898

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2899

"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]

2900

# Example: gs://[BUCKET_NAME]/dictionary.txt

2901

},

2902

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2903

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

2904

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2905

# specified, the entire match is returned. No more than 3 may be included.

2906

42,

2907

],

2908

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2909

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2910

# google/re2 repository on GitHub.

2911

},

2912

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

2913

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

2914

# contained within with a finding of an infoType from this list. For

2915

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

2916

# `exclusion_rule` containing `exclude_info_types.info_types` with

2917

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

2918

# with EMAIL_ADDRESS finding.

2919

# That leads to "555-222-2222@example.org" to generate only a single

2920

# finding, namely email address.

2921

{ # Type of information detected by the API.

2922

"name": "A String", # Name of the information type. Either a name of your choosing when

2923

# creating a CustomInfoType, or one of the names listed

2924

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2925

# a built-in type. InfoType names should conform to the pattern

2926

# `[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]

2931

},

2932

},

2933

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2934

},

2935

],

2936

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

2937

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

2938

# When set within `InspectJobConfig`,

2939

# the maximum returned is 2000 regardless if this is set higher.

2940

# When set within `InspectContentRequest`, this field is ignored.

2941

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

2942

{ # Max findings configuration per infoType, per content item or long

2943

# running DlpJob.

2944

"maxFindings": 42, # Max findings limit for the given infoType.

2945

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

2946

# info_type should be provided. If InfoTypeLimit does not have an

2947

# info_type, the DLP API applies the limit against all info_types that

2948

# are found but not specified in another InfoTypeLimit.

2949

"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]

2950

# creating a CustomInfoType, or one of the names listed

2951

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2952

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2953

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2954

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2955

},

2956

],

2957

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

2958

# When set within `InspectContentRequest`, the maximum returned is 2000

2959

# regardless if this is set higher.

2960

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2961

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2962

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2963

{ # A task to execute on the completion of a job.

2964

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2965

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

2966

# Command Center (CSCC Alpha).

2967

# This action is only available for projects which are parts of

2968

# an organization and whitelisted for the alpha Cloud Security Command

2969

# Center.

2970

# The action will publish count of finding instances and their info types.

2971

# The summary of findings will be persisted in CSCC and are governed by CSCC

2972

# service-specific policy, see https://cloud.google.com/terms/service-terms

2973

# Only a single instance of this action can be specified.

2974

# Compatible with: Inspect

2975

},

2976

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

2977

# completion/failure.

2978

# completion/failure.

2979

},

2980

"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]

2981

# OutputStorageConfig. Only a single instance of this action can be

2982

# specified.

2983

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2984

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2985

"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]

2986

# dataset. If table_id is not set a new one will be generated

2987

# for you with the following format:

2988

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

2989

# generating the date details.

2990

#

2991

# For Inspect, each column in an existing output table must have the same

2992

# name, type, and mode of a field in the `Finding` object.

2993

#

2994

# For Risk, an existing output table should be the output of a previous

2995

# Risk analysis job run on the same source table, with the same privacy

2996

# metric and quasi-identifiers. Risk jobs that analyze the same table but

2997

# compute a different privacy metric, or use different sets of

2998

# quasi-identifiers, cannot store their results in the same table.

2999

# identified by its project_id, dataset_id, and table_name. Within a query

3000

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3001

# `<project_id>:<dataset_id>.<table_id>` or

3002

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3003

"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]

3004

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3005

"datasetId": "A String", # Dataset ID of the table.

3006

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3007

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3008

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

3009

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

3010

# from the `Finding` object. If appending to an existing table, any columns

3011

# from the predefined schema that are missing will be added. No columns in

3012

# the existing table will be deleted.

3013

#

3014

# If unspecified, then all available columns will be used for a new table or

3015

# an (existing) table with no schema, and no changes will be made to an

3016

# existing table that has a schema.

3017

# Only for use with external storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3018

},

3019

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3020

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

3021

# message contains a single field, `DlpJobName`, which is equal to the

3022

# finished job's

3023

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

3024

# Compatible with: Inspect, Risk

3025

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

3026

# publishing access rights to the DLP API service account executing

3027

# the long running DlpJob sending the notifications.

3028

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3029

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3030

"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]

3031

# results of the DlpJob will be applied to the entry for the resource scanned

3032

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

3033

# be deleted. InfoType naming patterns are strictly enforced when using this

3034

# feature. Note that the findings will be persisted in Cloud Data Catalog

3035

# storage and are governed by Data Catalog service-specific policy, see

3036

# https://cloud.google.com/terms/service-terms

3037

# Only a single instance of this action can be specified and only allowed if

3038

# all resources being scanned are BigQuery tables.

3039

# Compatible with: Inspect

3040

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3041

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

3042

# will publish a metric to stack driver on each infotype requested and

3043

# how many findings were found for it. CustomDetectors will be bucketed

3044

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3045

},

3046

},

3047

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3048

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3049

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

3050

# Early access feature is in a pre-release state and might change or have

3051

# limited support. For more information, see

3052

# https://cloud.google.com/products#product-launch-stages.

3053

# of Google Cloud Platform.

3054

"labels": { # To organize findings, these labels will be added to each finding.

3055

#

3056

# Label keys must be between 1 and 63 characters long and must conform

3057

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

3058

#

3059

# Label values must be between 0 and 63 characters long and must conform

3060

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

3061

#

3062

# No more than 10 labels can be associated with a given finding.

3063

#

3064

# Examples:

3065

# * `"environment" : "production"`

3066

# * `"pipeline" : "etl"`

3067

"a_key": "A String",

3068

},

3069

"description": "A String", # A short description of where the data is coming from. Will be stored once

3070

# in the job. 256 max length.

3071

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

3072

# meaningful such as the columns that are primary keys.

3073

"identifyingFields": [ # The columns that are the primary keys for table objects included in

3074

# ContentItem. A copy of this cell's value will stored alongside alongside

3075

# each finding so that the finding can be traced to the specific row it came

3076

# from. No more than 3 may be provided.

3077

{ # General identifier of a data field in a storage service.

3078

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

3083

# 'finding_labels' map. Request may contain others, but any missing one of

3084

# these will be rejected.

3085

#

3086

# Label keys must be between 1 and 63 characters long and must conform

3087

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

3088

#

3089

# No more than 10 keys can be required.

3090

"A String",

3091

],

3092

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3093

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

3094

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

3095

# by project and namespace, however the namespace ID may be empty.

3096

# A partition ID identifies a grouping of entities. The grouping is always

3097

# by project and namespace, however the namespace ID may be empty.

3098

#

3099

# A partition ID contains several dimensions:

3100

# project ID and namespace ID.

3101

"projectId": "A String", # The ID of the project to which the entities belong.

3102

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

3103

},

3104

"kind": { # A representation of a Datastore kind. # The kind to process.

3105

"name": "A String", # The name of the kind.

3106

},

3107

},

3108

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

3109

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

3110

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

3111

# Used for data sources like Datastore and BigQuery.

3112

#

3113

# For BigQuery:

3114

# Required to filter out rows based on the given start and

3115

# end times. If not specified and the table was modified between the given

3116

# start and end times, the entire table will be scanned.

3117

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

3118

# `TIMESTAMP`, or `DATETIME` BigQuery column.

3119

#

3120

# For Datastore.

3121

# Valid data types of the timestamp field are: `TIMESTAMP`.

3122

# Datastore entity will be scanned if the timestamp property does not

3123

# exist or its value is empty or invalid.

3124

"name": "A String", # Name describing the field.

3125

},

3126

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

3127

# a valid start_time to avoid scanning files that have not been modified

3128

# since the last time the JobTrigger executed. This will be based on the

3129

# time of the execution of the last run of the JobTrigger.

3130

"endTime": "A String", # Exclude files or rows newer than this value.

3131

# If set to zero, no upper time limit is applied.

3132

"startTime": "A String", # Exclude files or rows older than this value.

3133

},

3134

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

3135

# bucket.

3136

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

3137

# than this value then the rest of the bytes are omitted. Only one

3138

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

3139

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

3140

"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

3141

# `regex_file_set` must be set.

3142

# expressions are used to allow fine-grained control over which files in the

3143

# bucket to include.

3144

#

3145

# Included files are those that match at least one item in `include_regex` and

3146

# do not match any items in `exclude_regex`. Note that a file that matches

3147

# items from both lists will _not_ be included. For a match to occur, the

3148

# entire file path (i.e., everything in the url after the bucket name) must

3149

# match the regular expression.

3150

#

3151

# For example, given the input `{bucket_name: "mybucket", include_regex:

3152

# ["directory1/.*"], exclude_regex:

3153

# ["directory1/excluded.*"]}`:

3154

#

3155

# * `gs://mybucket/directory1/myfile` will be included

3156

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

3157

# across `/`)

3158

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

3159

# full path doesn't match any items in `include_regex`)

3160

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

3161

# matches an item in `exclude_regex`)

3162

#

3163

# If `include_regex` is left empty, it will match all files by default

3164

# (this is equivalent to setting `include_regex: [".*"]`).

3165

#

3166

# Some other common use cases:

3167

#

3168

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

3169

# files in `mybucket` except for .pdf files

3170

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

3171

# include all files directly under `gs://mybucket/directory/`, without matching

3172

# across `/`

3173

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

3174

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

3175

# the bucket that match at least one of these regular expressions will be

3176

# included in the set of files, except for those that also match an item in

3177

# `exclude_regex`. Leaving this field empty will match all files by default

3178

# (this is equivalent to including `.*` in the list).

3179

#

3180

# Regular expressions use RE2

3181

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

3182

# under the google/re2 repository on GitHub.

3183

"A String",

3184

],

3185

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

3186

# the bucket that match at least one of these regular expressions will be

3187

# excluded from the scan.

3188

#

3189

# Regular expressions use RE2

3190

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

3191

# 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

3196

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

3197

#

3198

# If the url ends in a trailing slash, the bucket or directory represented

3199

# by the url will be scanned non-recursively (content in sub-directories

3200

# will not be scanned). This means that `gs://mybucket/` is equivalent to

3201

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

3202

# `gs://mybucket/directory/*`.

3203

#

3204

# Exactly one of `url` or `regex_file_set` must be set.

3205

},

3206

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

3207

# Number of files scanned is rounded down. Must be between 0 and 100,

3208

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

3209

"fileTypes": [ # List of file type groups to include in the scan.

3210

# If empty, all files are scanned and available data format processors

3211

# are applied. In addition, the binary content of the selected files

3212

# is always scanned as well.

3213

# Images are scanned only as binary if the specified region

3214

# does not support image inspection and no file_types were specified.

3215

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

3216

"A String",

3217

],

3218

"sampleMethod": "A String",

3219

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

3220

# number of bytes scanned is rounded down. Must be between 0 and 100,

3221

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

3222

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

3223

},

3224

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

3225

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

3226

# identified by its project_id, dataset_id, and table_name. Within a query

3227

# a table is often referenced with a string in the format of:

3228

# `<project_id>:<dataset_id>.<table_id>` or

3229

# `<project_id>.<dataset_id>.<table_id>`.

3230

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

3231

# If omitted, project ID is inferred from the API call.

3232

"datasetId": "A String", # Dataset ID of the table.

3233

"tableId": "A String", # Name of the table.

3234

},

3235

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

3236

# `actions.saveFindings.outputConfig.table` is specified, the values of

3237

# columns specified here are available in the output table under

3238

# `location.content_locations.record_location.record_key.id_values`. Nested

3239

# fields such as `person.birthdate.year` are allowed.

3240

{ # General identifier of a data field in a storage service.

3241

"name": "A String", # Name describing the field.

3242

},

3243

],

3244

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

3245

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

3246

# 100 means no limit. Defaults to 0. Only one of rows_limit and

3247

# rows_limit_percent can be specified. Cannot be used in conjunction with

3248

# TimespanConfig.

3249

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

3250

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

3251

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

3252

# Cannot be used in conjunction with TimespanConfig.

3253

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

3254

# inspection of entire columns which you know have no findings.

3255

{ # General identifier of a data field in a storage service.

3256

"name": "A String", # Name describing the field.

3257

},

3258

],

3259

"sampleMethod": "A String",

3260

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3261

},

3262

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

3263

# `inspect_config` will be merged into the values persisted as part of the

3264

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3265

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3266

"status": "A String", # Required. A status for this trigger.

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>

3272

<pre>Deletes a job trigger.

3273

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

3274

3275

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3276

name: string, Required. Resource name of the project and the triggeredJob, for example

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3277

`projects/dlp-test-project/jobTriggers/53234423`. (required)

3278

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

3285

3286

{ # A generic empty message that you can re-use to avoid defining duplicated

3287

# empty messages in your APIs. A typical example is to use it as the request

3288

# or the response type of an API method. For instance:

3289

#

3290

# service Foo {

3291

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

3292

# }

3293

#

3294

# The JSON representation for `Empty` is empty JSON object `{}`.

}</pre>

</div>

<code class="details" id="get">get(name, x__xgafv=None)</code>

3300

<pre>Gets a job trigger.

3301

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

3302

3303

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3304

name: string, Required. Resource name of the project and the triggeredJob, for example

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3305

`projects/dlp-test-project/jobTriggers/53234423`. (required)

3306

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

3313

3314

{ # Contains a configuration to make dlp api calls on a repeating basis.

3315

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3316

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

3317

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

3318

# triggeredJob is created, for example

3319

# `projects/dlp-test-project/jobTriggers/53234423`.

3320

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

3321

# errors may result in the JobTrigger automatically being paused.

3322

# Will return the last 100 errors. Whenever the JobTrigger is modified

3323

# this list will be cleared.

3324

{ # Details information about an error encountered during job execution or

3325

# the results of an unsuccessful activation of the JobTrigger.

3326

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

3327

# different programming environments, including REST APIs and RPC APIs. It is

3328

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

3329

# three pieces of data: error code, error message, and error details.

3330

#

3331

# You can find out more about this error model and how to work with it in the

3332

# [API Design Guide](https://cloud.google.com/apis/design/errors).

3333

"message": "A String", # A developer-facing error message, which should be in English. Any

3334

# user-facing error message should be localized and sent in the

3335

# google.rpc.Status.details field, or localized by the client.

3336

"details": [ # A list of messages that carry the error details. There is a common set of

3337

# message types for APIs to use.

3338

{

3339

"a_key": "", # Properties of the object. Contains field @type with type URL.

3340

},

3341

],

3342

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

3343

},

3344

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3350

"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3351

# needs to trigger for a job to be started. The list may contain only

3352

# a single Schedule trigger and must have at least one object.

3353

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3354

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

3355

"recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3356

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3357

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3358

# A scheduled start time will be skipped if the previous

3359

# execution has not ended when its scheduled time occurs.

3360

#

3361

# This value must be set to a time duration greater than or equal

3362

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3363

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3364

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3365

# Early access feature is in a pre-release state and might change or have

3366

# limited support. For more information, see

3367

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3368

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3369

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3370

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3371

],

3372

"displayName": "A String", # Display name (max 100 chars)

3373

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

3374

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

3375

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

3376

"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]

3377

# When used with redactContent only info_types and min_likelihood are currently

3378

# used.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3379

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

3380

# POSSIBLE.

3381

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

3382

"contentOptions": [ # List of options defining data content to scan.

3383

# If empty, text, images, and other content will be included.

3384

"A String",

3385

],

3386

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

3387

# InfoType values returned by ListInfoTypes or listed at

3388

# https://cloud.google.com/dlp/docs/infotypes-reference.

3389

#

3390

# When no InfoTypes or CustomInfoTypes are specified in a request, the

3391

# system may automatically choose what detectors to run. By default this may

3392

# be all types, but may change over time as detectors are updated.

3393

#

3394

# If you need precise control and predictability as to what detectors are

3395

# run you should specify specific InfoTypes listed in the reference,

3396

# otherwise a default list will be used, which may change over time.

3397

{ # Type of information detected by the API.

3398

"name": "A String", # Name of the information type. Either a name of your choosing when

3399

# creating a CustomInfoType, or one of the names listed

3400

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3401

# a built-in type. InfoType names should conform to the pattern

3402

# `[a-zA-Z0-9_]{1,64}`.

3403

},

3404

],

3405

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

3406

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

3407

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

3408

{ # Custom information type provided by the user. Used to find domain-specific

3409

# sensitive information configurable to the data in question.

3410

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

3411

# support reversing.

3412

# such as

3413

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

3414

# These types of transformations are

3415

# those that perform pseudonymization, thereby producing a "surrogate" as

3416

# output. This should be used in conjunction with a field on the

3417

# transformation such as `surrogate_info_type`. This CustomInfoType does

3418

# not support the use of `detection_rules`.

3419

},

3420

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

3421

# altered by a detection rule if the finding meets the criteria specified by

3422

# the rule. Defaults to `VERY_LIKELY` if not specified.

3423

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

3424

# infoType, when the name matches one of existing infoTypes and that infoType

3425

# is specified in `InspectContent.info_types` field. Specifying the latter

3426

# adds findings to the one detected by the system. If built-in info type is

3427

# not specified in `InspectContent.info_types` list then the name is treated

3428

# as a custom info type.

3429

"name": "A String", # Name of the information type. Either a name of your choosing when

3430

# creating a CustomInfoType, or one of the names listed

3431

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3432

# a built-in type. InfoType names should conform to the pattern

3433

# `[a-zA-Z0-9_]{1,64}`.

3434

},

3435

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

3436

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3437

# specified, the entire match is returned. No more than 3 may be included.

3438

42,

3439

],

3440

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3441

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3442

# google/re2 repository on GitHub.

3443

},

3444

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

3445

# Rules are applied in order that they are specified. Not supported for the

3446

# `surrogate_type` CustomInfoType.

3447

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

3448

# `CustomInfoType` to alter behavior under certain circumstances, depending

3449

# on the specific details of the rule. Not supported for the `surrogate_type`

3450

# custom infoType.

3451

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

3452

# proximity of hotwords.

3453

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

3454

# part of a detection rule.

3455

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

3456

# levels. For example, if a finding would be `POSSIBLE` without the

3457

# detection rule and `relative_likelihood` is 1, then it is upgraded to

3458

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

3459

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

3460

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

3461

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

3462

# a final likelihood of `LIKELY`.

3463

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

3464

},

3465

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

3466

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3467

# specified, the entire match is returned. No more than 3 may be included.

3468

42,

3469

],

3470

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3471

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3472

# google/re2 repository on GitHub.

3473

},

3474

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

3475

# The total length of the window cannot exceed 1000 characters. Note that

3476

# the finding itself will be included in the window, so that hotwords may

3477

# be used to match substrings of the finding itself. For example, the

3478

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

3479

# adjusted upwards if the area code is known to be the local area code of

3480

# a company office using the hotword regex "\(xxx\)", where "xxx"

3481

# is the area code in question.

3482

# rule.

3483

"windowBefore": 42, # Number of characters before the finding to consider.

3484

"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

3490

# to be returned. It still can be used for rules matching.

3491

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

3492

# be used to match sensitive information specific to the data, such as a list

3493

# of employee IDs or job titles.

3494

#

3495

# Dictionary words are case-insensitive and all characters other than letters

3496

# and digits in the unicode [Basic Multilingual

3497

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

3498

# will be replaced with whitespace when scanning for matches, so the

3499

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

3500

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

3501

# surrounding any match must be of a different type than the adjacent

3502

# characters within the word, so letters must be next to non-letters and

3503

# digits next to non-digits. For example, the dictionary word "jen" will

3504

# match the first three letters of the text "jen123" but will return no

3505

# matches for "jennifer".

3506

#

3507

# Dictionary words containing a large number of characters that are not

3508

# letters or digits may result in unexpected findings because such characters

3509

# are treated as whitespace. The

3510

# [limits](https://cloud.google.com/dlp/limits) page contains details about

3511

# the size limits of dictionaries. For dictionaries that do not fit within

3512

# these constraints, consider using `LargeCustomDictionaryConfig` in the

3513

# `StoredInfoType` API.

3514

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

3515

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

3516

# at least one phrase and every phrase must contain at least 2 characters

3517

# 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

3522

# is accepted.

3523

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

3524

# Example: gs://[BUCKET_NAME]/dictionary.txt

3525

},

3526

},

3527

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

3528

# `InspectDataSource`. Not currently supported in `InspectContent`.

3529

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

3530

# `organizations/433245324/storedInfoTypes/432452342` or

3531

# `projects/project-id/storedInfoTypes/432452342`.

3532

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

3533

# inspection was created. Output-only field, populated by the system.

3534

},

3535

},

3536

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3537

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

3538

# included in the response; see Finding.quote.

3539

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

3540

# Exclusion rules, contained in the set are executed in the end, other

3541

# rules are executed in the order they are specified for each info type.

3542

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

3543

# circumstances, depending on the specific details of the rules within the set.

3544

"infoTypes": [ # List of infoTypes this rule set is applied to.

3545

{ # Type of information detected by the API.

3546

"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]

3547

# creating a CustomInfoType, or one of the names listed

3548

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3549

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3550

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3551

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3552

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3553

"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]

3554

{ # A single inspection rule to be applied to infoTypes, specified in

3555

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3556

"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]

3557

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3558

"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]

3559

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3560

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3561

# levels. For example, if a finding would be `POSSIBLE` without the

3562

# detection rule and `relative_likelihood` is 1, then it is upgraded to

3563

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

3564

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

3565

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

3566

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

3567

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3568

"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]

3569

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3570

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

3571

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3572

# specified, the entire match is returned. No more than 3 may be included.

3573

42,

3574

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3575

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3576

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3577

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3578

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3579

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

3580

# The total length of the window cannot exceed 1000 characters. Note that

3581

# the finding itself will be included in the window, so that hotwords may

3582

# be used to match substrings of the finding itself. For example, the

3583

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

3584

# adjusted upwards if the area code is known to be the local area code of

3585

# a company office using the hotword regex "\(xxx\)", where "xxx"

3586

# is the area code in question.

3587

# rule.

3588

"windowBefore": 42, # Number of characters before the finding to consider.

3589

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3590

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3591

},

3592

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

3593

# `InspectionRuleSet` are removed from results.

3594

"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]

3595

# be used to match sensitive information specific to the data, such as a list

3596

# of employee IDs or job titles.

3597

#

3598

# Dictionary words are case-insensitive and all characters other than letters

3599

# and digits in the unicode [Basic Multilingual

3600

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

3601

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3602

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

3603

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3604

# surrounding any match must be of a different type than the adjacent

3605

# 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]

3606

# digits next to non-digits. For example, the dictionary word "jen" will

3607

# match the first three letters of the text "jen123" but will return no

3608

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3609

#

3610

# Dictionary words containing a large number of characters that are not

3611

# letters or digits may result in unexpected findings because such characters

3612

# are treated as whitespace. The

3613

# [limits](https://cloud.google.com/dlp/limits) page contains details about

3614

# the size limits of dictionaries. For dictionaries that do not fit within

3615

# these constraints, consider using `LargeCustomDictionaryConfig` in the

3616

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3617

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

3618

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3619

# at least one phrase and every phrase must contain at least 2 characters

3620

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3621

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3622

],

3623

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3624

"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]

3625

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3626

"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]

3627

# Example: gs://[BUCKET_NAME]/dictionary.txt

3628

},

3629

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3630

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

3631

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3632

# specified, the entire match is returned. No more than 3 may be included.

3633

42,

3634

],

3635

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3636

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3637

# google/re2 repository on GitHub.

3638

},

3639

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

3640

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

3641

# contained within with a finding of an infoType from this list. For

3642

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

3643

# `exclusion_rule` containing `exclude_info_types.info_types` with

3644

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

3645

# with EMAIL_ADDRESS finding.

3646

# That leads to "555-222-2222@example.org" to generate only a single

3647

# finding, namely email address.

3648

{ # Type of information detected by the API.

3649

"name": "A String", # Name of the information type. Either a name of your choosing when

3650

# creating a CustomInfoType, or one of the names listed

3651

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3652

# a built-in type. InfoType names should conform to the pattern

3653

# `[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]

3658

},

3659

},

3660

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3661

},

3662

],

3663

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

3664

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

3665

# When set within `InspectJobConfig`,

3666

# the maximum returned is 2000 regardless if this is set higher.

3667

# When set within `InspectContentRequest`, this field is ignored.

3668

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

3669

{ # Max findings configuration per infoType, per content item or long

3670

# running DlpJob.

3671

"maxFindings": 42, # Max findings limit for the given infoType.

3672

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

3673

# info_type should be provided. If InfoTypeLimit does not have an

3674

# info_type, the DLP API applies the limit against all info_types that

3675

# are found but not specified in another InfoTypeLimit.

3676

"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]

3677

# creating a CustomInfoType, or one of the names listed

3678

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3679

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3680

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3681

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3682

},

3683

],

3684

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

3685

# When set within `InspectContentRequest`, the maximum returned is 2000

3686

# regardless if this is set higher.

3687

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3688

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3689

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3690

{ # A task to execute on the completion of a job.

3691

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3692

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

3693

# Command Center (CSCC Alpha).

3694

# This action is only available for projects which are parts of

3695

# an organization and whitelisted for the alpha Cloud Security Command

3696

# Center.

3697

# The action will publish count of finding instances and their info types.

3698

# The summary of findings will be persisted in CSCC and are governed by CSCC

3699

# service-specific policy, see https://cloud.google.com/terms/service-terms

3700

# Only a single instance of this action can be specified.

3701

# Compatible with: Inspect

3702

},

3703

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

3704

# completion/failure.

3705

# completion/failure.

3706

},

3707

"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]

3708

# OutputStorageConfig. Only a single instance of this action can be

3709

# specified.

3710

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3711

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3712

"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]

3713

# dataset. If table_id is not set a new one will be generated

3714

# for you with the following format:

3715

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

3716

# generating the date details.

3717

#

3718

# For Inspect, each column in an existing output table must have the same

3719

# name, type, and mode of a field in the `Finding` object.

3720

#

3721

# For Risk, an existing output table should be the output of a previous

3722

# Risk analysis job run on the same source table, with the same privacy

3723

# metric and quasi-identifiers. Risk jobs that analyze the same table but

3724

# compute a different privacy metric, or use different sets of

3725

# quasi-identifiers, cannot store their results in the same table.

3726

# identified by its project_id, dataset_id, and table_name. Within a query

3727

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3728

# `<project_id>:<dataset_id>.<table_id>` or

3729

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3730

"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]

3731

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3732

"datasetId": "A String", # Dataset ID of the table.

3733

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3734

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3735

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

3736

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

3737

# from the `Finding` object. If appending to an existing table, any columns

3738

# from the predefined schema that are missing will be added. No columns in

3739

# the existing table will be deleted.

3740

#

3741

# If unspecified, then all available columns will be used for a new table or

3742

# an (existing) table with no schema, and no changes will be made to an

3743

# existing table that has a schema.

3744

# Only for use with external storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3745

},

3746

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3747

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

3748

# message contains a single field, `DlpJobName`, which is equal to the

3749

# finished job's

3750

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

3751

# Compatible with: Inspect, Risk

3752

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

3753

# publishing access rights to the DLP API service account executing

3754

# the long running DlpJob sending the notifications.

3755

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3756

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3757

"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]

3758

# results of the DlpJob will be applied to the entry for the resource scanned

3759

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

3760

# be deleted. InfoType naming patterns are strictly enforced when using this

3761

# feature. Note that the findings will be persisted in Cloud Data Catalog

3762

# storage and are governed by Data Catalog service-specific policy, see

3763

# https://cloud.google.com/terms/service-terms

3764

# Only a single instance of this action can be specified and only allowed if

3765

# all resources being scanned are BigQuery tables.

3766

# Compatible with: Inspect

3767

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3768

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

3769

# will publish a metric to stack driver on each infotype requested and

3770

# how many findings were found for it. CustomDetectors will be bucketed

3771

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3772

},

3773

},

3774

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3775

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3776

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

3777

# Early access feature is in a pre-release state and might change or have

3778

# limited support. For more information, see

3779

# https://cloud.google.com/products#product-launch-stages.

3780

# of Google Cloud Platform.

3781

"labels": { # To organize findings, these labels will be added to each finding.

3782

#

3783

# Label keys must be between 1 and 63 characters long and must conform

3784

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

3785

#

3786

# Label values must be between 0 and 63 characters long and must conform

3787

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

3788

#

3789

# No more than 10 labels can be associated with a given finding.

3790

#

3791

# Examples:

3792

# * `"environment" : "production"`

3793

# * `"pipeline" : "etl"`

3794

"a_key": "A String",

3795

},

3796

"description": "A String", # A short description of where the data is coming from. Will be stored once

3797

# in the job. 256 max length.

3798

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

3799

# meaningful such as the columns that are primary keys.

3800

"identifyingFields": [ # The columns that are the primary keys for table objects included in

3801

# ContentItem. A copy of this cell's value will stored alongside alongside

3802

# each finding so that the finding can be traced to the specific row it came

3803

# from. No more than 3 may be provided.

3804

{ # General identifier of a data field in a storage service.

3805

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

3810

# 'finding_labels' map. Request may contain others, but any missing one of

3811

# these will be rejected.

3812

#

3813

# Label keys must be between 1 and 63 characters long and must conform

3814

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

3815

#

3816

# No more than 10 keys can be required.

3817

"A String",

3818

],

3819

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3820

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

3821

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

3822

# by project and namespace, however the namespace ID may be empty.

3823

# A partition ID identifies a grouping of entities. The grouping is always

3824

# by project and namespace, however the namespace ID may be empty.

3825

#

3826

# A partition ID contains several dimensions:

3827

# project ID and namespace ID.

3828

"projectId": "A String", # The ID of the project to which the entities belong.

3829

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

3830

},

3831

"kind": { # A representation of a Datastore kind. # The kind to process.

3832

"name": "A String", # The name of the kind.

3833

},

3834

},

3835

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

3836

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

3837

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

3838

# Used for data sources like Datastore and BigQuery.

3839

#

3840

# For BigQuery:

3841

# Required to filter out rows based on the given start and

3842

# end times. If not specified and the table was modified between the given

3843

# start and end times, the entire table will be scanned.

3844

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

3845

# `TIMESTAMP`, or `DATETIME` BigQuery column.

3846

#

3847

# For Datastore.

3848

# Valid data types of the timestamp field are: `TIMESTAMP`.

3849

# Datastore entity will be scanned if the timestamp property does not

3850

# exist or its value is empty or invalid.

3851

"name": "A String", # Name describing the field.

3852

},

3853

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

3854

# a valid start_time to avoid scanning files that have not been modified

3855

# since the last time the JobTrigger executed. This will be based on the

3856

# time of the execution of the last run of the JobTrigger.

3857

"endTime": "A String", # Exclude files or rows newer than this value.

3858

# If set to zero, no upper time limit is applied.

3859

"startTime": "A String", # Exclude files or rows older than this value.

3860

},

3861

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

3862

# bucket.

3863

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

3864

# than this value then the rest of the bytes are omitted. Only one

3865

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

3866

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

3867

"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

3868

# `regex_file_set` must be set.

3869

# expressions are used to allow fine-grained control over which files in the

3870

# bucket to include.

3871

#

3872

# Included files are those that match at least one item in `include_regex` and

3873

# do not match any items in `exclude_regex`. Note that a file that matches

3874

# items from both lists will _not_ be included. For a match to occur, the

3875

# entire file path (i.e., everything in the url after the bucket name) must

3876

# match the regular expression.

3877

#

3878

# For example, given the input `{bucket_name: "mybucket", include_regex:

3879

# ["directory1/.*"], exclude_regex:

3880

# ["directory1/excluded.*"]}`:

3881

#

3882

# * `gs://mybucket/directory1/myfile` will be included

3883

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

3884

# across `/`)

3885

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

3886

# full path doesn't match any items in `include_regex`)

3887

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

3888

# matches an item in `exclude_regex`)

3889

#

3890

# If `include_regex` is left empty, it will match all files by default

3891

# (this is equivalent to setting `include_regex: [".*"]`).

3892

#

3893

# Some other common use cases:

3894

#

3895

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

3896

# files in `mybucket` except for .pdf files

3897

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

3898

# include all files directly under `gs://mybucket/directory/`, without matching

3899

# across `/`

3900

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

3901

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

3902

# the bucket that match at least one of these regular expressions will be

3903

# included in the set of files, except for those that also match an item in

3904

# `exclude_regex`. Leaving this field empty will match all files by default

3905

# (this is equivalent to including `.*` in the list).

3906

#

3907

# Regular expressions use RE2

3908

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

3909

# under the google/re2 repository on GitHub.

3910

"A String",

3911

],

3912

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

3913

# the bucket that match at least one of these regular expressions will be

3914

# excluded from the scan.

3915

#

3916

# Regular expressions use RE2

3917

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

3918

# 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

3923

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

3924

#

3925

# If the url ends in a trailing slash, the bucket or directory represented

3926

# by the url will be scanned non-recursively (content in sub-directories

3927

# will not be scanned). This means that `gs://mybucket/` is equivalent to

3928

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

3929

# `gs://mybucket/directory/*`.

3930

#

3931

# Exactly one of `url` or `regex_file_set` must be set.

3932

},

3933

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

3934

# Number of files scanned is rounded down. Must be between 0 and 100,

3935

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

3936

"fileTypes": [ # List of file type groups to include in the scan.

3937

# If empty, all files are scanned and available data format processors

3938

# are applied. In addition, the binary content of the selected files

3939

# is always scanned as well.

3940

# Images are scanned only as binary if the specified region

3941

# does not support image inspection and no file_types were specified.

3942

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

3943

"A String",

3944

],

3945

"sampleMethod": "A String",

3946

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

3947

# number of bytes scanned is rounded down. Must be between 0 and 100,

3948

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

3949

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

3950

},

3951

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

3952

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

3953

# identified by its project_id, dataset_id, and table_name. Within a query

3954

# a table is often referenced with a string in the format of:

3955

# `<project_id>:<dataset_id>.<table_id>` or

3956

# `<project_id>.<dataset_id>.<table_id>`.

3957

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

3958

# If omitted, project ID is inferred from the API call.

3959

"datasetId": "A String", # Dataset ID of the table.

3960

"tableId": "A String", # Name of the table.

3961

},

3962

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

3963

# `actions.saveFindings.outputConfig.table` is specified, the values of

3964

# columns specified here are available in the output table under

3965

# `location.content_locations.record_location.record_key.id_values`. Nested

3966

# fields such as `person.birthdate.year` are allowed.

3967

{ # General identifier of a data field in a storage service.

3968

"name": "A String", # Name describing the field.

3969

},

3970

],

3971

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

3972

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

3973

# 100 means no limit. Defaults to 0. Only one of rows_limit and

3974

# rows_limit_percent can be specified. Cannot be used in conjunction with

3975

# TimespanConfig.

3976

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

3977

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

3978

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

3979

# Cannot be used in conjunction with TimespanConfig.

3980

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

3981

# inspection of entire columns which you know have no findings.

3982

{ # General identifier of a data field in a storage service.

3983

"name": "A String", # Name describing the field.

3984

},

3985

],

3986

"sampleMethod": "A String",

3987

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3988

},

3989

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

3990

# `inspect_config` will be merged into the values persisted as part of the

3991

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3992

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3993

"status": "A String", # Required. A status for this trigger.

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]

3998

<code class="details" id="list">list(parent, pageToken=None, locationId=None, pageSize=None, filter=None, orderBy=None, x__xgafv=None)</code>

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3999

<pre>Lists job triggers.

4000

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

4001

4002

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4003

parent: string, Required. The parent resource name, for example `projects/my-project-id`. (required)

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4004

pageToken: string, Page token to continue retrieval. Comes from previous call

4005

to ListJobTriggers. `order_by` field must not

4006

change for subsequent calls.

4007

locationId: string, The geographic location where job triggers will be retrieved from.

4008

Use `-` for all locations. Reserved for future extensions.

4009

pageSize: integer, Size of the page, can be limited by a server.

4010

filter: string, Allows filtering.

Supported syntax:

* Filter expressions are made up of one or more restrictions.

4015

* Restrictions can be combined by `AND` or `OR` logical operators. A

4016

sequence of restrictions implicitly uses `AND`.

4017

* A restriction has the form of `{field} {operator} {value}`.

4018

* Supported fields/values for inspect jobs:

4019

- `status` - HEALTHY|PAUSED|CANCELLED

4020

- `inspected_storage` - DATASTORE|CLOUD_STORAGE|BIGQUERY

4021

- 'last_run_time` - RFC 3339 formatted timestamp, surrounded by

4022

quotation marks. Nanoseconds are ignored.

4023

- 'error_count' - Number of errors that have occurred while running.

4024

* The operator must be `=` or `!=` for status and inspected_storage.

Examples:

* inspected_storage = cloud_storage AND status = HEALTHY

4029

* inspected_storage = cloud_storage OR inspected_storage = bigquery

4030

* inspected_storage = cloud_storage AND (state = PAUSED OR state = HEALTHY)

4031

* last_run_time > \"2017-12-12T00:00:00+00:00\"

4032

4033

The length of this field should be no more than 500 characters.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4034

orderBy: string, Comma separated list of triggeredJob fields to order by,

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4035

followed by `asc` or `desc` postfix. This list is case-insensitive,

4036

default sorting order is ascending, redundant space characters are

4037

insignificant.

4038

4039

Example: `name asc,update_time, create_time desc`

4040

4041

Supported fields are:

4042

4043

- `create_time`: corresponds to time the JobTrigger was created.

4044

- `update_time`: corresponds to time the JobTrigger was last updated.

4045

- `last_run_time`: corresponds to the last time the JobTrigger ran.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4046

- `name`: corresponds to JobTrigger's name.

4047

- `display_name`: corresponds to JobTrigger's display name.

4048

- `status`: corresponds to JobTrigger's status.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4049

x__xgafv: string, V1 error format.

4050

Allowed values

4051

1 - v1 error format

4052

2 - v2 error format

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4053

4054

Returns:

4055

An object of the form:

4056

4057

{ # Response message for ListJobTriggers.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4058

"jobTriggers": [ # List of triggeredJobs, up to page_size in ListJobTriggersRequest.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4059

{ # Contains a configuration to make dlp api calls on a repeating basis.

4060

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4061

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

4062

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

4063

# triggeredJob is created, for example

4064

# `projects/dlp-test-project/jobTriggers/53234423`.

4065

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

4066

# errors may result in the JobTrigger automatically being paused.

4067

# Will return the last 100 errors. Whenever the JobTrigger is modified

4068

# this list will be cleared.

4069

{ # Details information about an error encountered during job execution or

4070

# the results of an unsuccessful activation of the JobTrigger.

4071

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

4072

# different programming environments, including REST APIs and RPC APIs. It is

4073

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

4074

# three pieces of data: error code, error message, and error details.

4075

#

4076

# You can find out more about this error model and how to work with it in the

4077

# [API Design Guide](https://cloud.google.com/apis/design/errors).

4078

"message": "A String", # A developer-facing error message, which should be in English. Any

4079

# user-facing error message should be localized and sent in the

4080

# google.rpc.Status.details field, or localized by the client.

4081

"details": [ # A list of messages that carry the error details. There is a common set of

4082

# message types for APIs to use.

4083

{

4084

"a_key": "", # Properties of the object. Contains field @type with type URL.

4085

},

4086

],

4087

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

4088

},

4089

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4095

"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4096

# needs to trigger for a job to be started. The list may contain only

4097

# a single Schedule trigger and must have at least one object.

4098

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4099

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

4100

"recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4101

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4102

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4103

# A scheduled start time will be skipped if the previous

4104

# execution has not ended when its scheduled time occurs.

4105

#

4106

# This value must be set to a time duration greater than or equal

4107

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4108

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4109

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4110

# Early access feature is in a pre-release state and might change or have

4111

# limited support. For more information, see

4112

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4113

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4114

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4115

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4116

],

4117

"displayName": "A String", # Display name (max 100 chars)

4118

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

4119

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

4120

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

4121

"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]

4122

# When used with redactContent only info_types and min_likelihood are currently

4123

# used.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4124

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

4125

# POSSIBLE.

4126

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

4127

"contentOptions": [ # List of options defining data content to scan.

4128

# If empty, text, images, and other content will be included.

4129

"A String",

4130

],

4131

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

4132

# InfoType values returned by ListInfoTypes or listed at

4133

# https://cloud.google.com/dlp/docs/infotypes-reference.

4134

#

4135

# When no InfoTypes or CustomInfoTypes are specified in a request, the

4136

# system may automatically choose what detectors to run. By default this may

4137

# be all types, but may change over time as detectors are updated.

4138

#

4139

# If you need precise control and predictability as to what detectors are

4140

# run you should specify specific InfoTypes listed in the reference,

4141

# otherwise a default list will be used, which may change over time.

4142

{ # Type of information detected by the API.

4143

"name": "A String", # Name of the information type. Either a name of your choosing when

4144

# creating a CustomInfoType, or one of the names listed

4145

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4146

# a built-in type. InfoType names should conform to the pattern

4147

# `[a-zA-Z0-9_]{1,64}`.

4148

},

4149

],

4150

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

4151

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

4152

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

4153

{ # Custom information type provided by the user. Used to find domain-specific

4154

# sensitive information configurable to the data in question.

4155

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

4156

# support reversing.

4157

# such as

4158

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

4159

# These types of transformations are

4160

# those that perform pseudonymization, thereby producing a "surrogate" as

4161

# output. This should be used in conjunction with a field on the

4162

# transformation such as `surrogate_info_type`. This CustomInfoType does

4163

# not support the use of `detection_rules`.

4164

},

4165

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

4166

# altered by a detection rule if the finding meets the criteria specified by

4167

# the rule. Defaults to `VERY_LIKELY` if not specified.

4168

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

4169

# infoType, when the name matches one of existing infoTypes and that infoType

4170

# is specified in `InspectContent.info_types` field. Specifying the latter

4171

# adds findings to the one detected by the system. If built-in info type is

4172

# not specified in `InspectContent.info_types` list then the name is treated

4173

# as a custom info type.

4174

"name": "A String", # Name of the information type. Either a name of your choosing when

4175

# creating a CustomInfoType, or one of the names listed

4176

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4177

# a built-in type. InfoType names should conform to the pattern

4178

# `[a-zA-Z0-9_]{1,64}`.

4179

},

4180

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

4181

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4182

# specified, the entire match is returned. No more than 3 may be included.

4183

42,

4184

],

4185

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4186

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4187

# google/re2 repository on GitHub.

4188

},

4189

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

4190

# Rules are applied in order that they are specified. Not supported for the

4191

# `surrogate_type` CustomInfoType.

4192

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

4193

# `CustomInfoType` to alter behavior under certain circumstances, depending

4194

# on the specific details of the rule. Not supported for the `surrogate_type`

4195

# custom infoType.

4196

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

4197

# proximity of hotwords.

4198

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

4199

# part of a detection rule.

4200

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

4201

# levels. For example, if a finding would be `POSSIBLE` without the

4202

# detection rule and `relative_likelihood` is 1, then it is upgraded to

4203

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

4204

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

4205

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

4206

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

4207

# a final likelihood of `LIKELY`.

4208

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

4209

},

4210

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

4211

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4212

# specified, the entire match is returned. No more than 3 may be included.

4213

42,

4214

],

4215

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4216

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4217

# google/re2 repository on GitHub.

4218

},

4219

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

4220

# The total length of the window cannot exceed 1000 characters. Note that

4221

# the finding itself will be included in the window, so that hotwords may

4222

# be used to match substrings of the finding itself. For example, the

4223

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

4224

# adjusted upwards if the area code is known to be the local area code of

4225

# a company office using the hotword regex "\(xxx\)", where "xxx"

4226

# is the area code in question.

4227

# rule.

4228

"windowBefore": 42, # Number of characters before the finding to consider.

4229

"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

4235

# to be returned. It still can be used for rules matching.

4236

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

4237

# be used to match sensitive information specific to the data, such as a list

4238

# of employee IDs or job titles.

4239

#

4240

# Dictionary words are case-insensitive and all characters other than letters

4241

# and digits in the unicode [Basic Multilingual

4242

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

4243

# will be replaced with whitespace when scanning for matches, so the

4244

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

4245

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

4246

# surrounding any match must be of a different type than the adjacent

4247

# characters within the word, so letters must be next to non-letters and

4248

# digits next to non-digits. For example, the dictionary word "jen" will

4249

# match the first three letters of the text "jen123" but will return no

4250

# matches for "jennifer".

4251

#

4252

# Dictionary words containing a large number of characters that are not

4253

# letters or digits may result in unexpected findings because such characters

4254

# are treated as whitespace. The

4255

# [limits](https://cloud.google.com/dlp/limits) page contains details about

4256

# the size limits of dictionaries. For dictionaries that do not fit within

4257

# these constraints, consider using `LargeCustomDictionaryConfig` in the

4258

# `StoredInfoType` API.

4259

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

4260

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

4261

# at least one phrase and every phrase must contain at least 2 characters

4262

# 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

4267

# is accepted.

4268

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

4269

# Example: gs://[BUCKET_NAME]/dictionary.txt

4270

},

4271

},

4272

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

4273

# `InspectDataSource`. Not currently supported in `InspectContent`.

4274

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

4275

# `organizations/433245324/storedInfoTypes/432452342` or

4276

# `projects/project-id/storedInfoTypes/432452342`.

4277

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

4278

# inspection was created. Output-only field, populated by the system.

4279

},

4280

},

4281

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4282

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

4283

# included in the response; see Finding.quote.

4284

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

4285

# Exclusion rules, contained in the set are executed in the end, other

4286

# rules are executed in the order they are specified for each info type.

4287

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

4288

# circumstances, depending on the specific details of the rules within the set.

4289

"infoTypes": [ # List of infoTypes this rule set is applied to.

4290

{ # Type of information detected by the API.

4291

"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]

4292

# creating a CustomInfoType, or one of the names listed

4293

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4294

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4295

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4296

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4297

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4298

"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]

4299

{ # A single inspection rule to be applied to infoTypes, specified in

4300

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4301

"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]

4302

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4303

"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]

4304

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4305

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4306

# levels. For example, if a finding would be `POSSIBLE` without the

4307

# detection rule and `relative_likelihood` is 1, then it is upgraded to

4308

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

4309

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

4310

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

4311

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

4312

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4313

"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]

4314

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4315

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

4316

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4317

# specified, the entire match is returned. No more than 3 may be included.

4318

42,

4319

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4320

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4321

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4322

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4323

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4324

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

4325

# The total length of the window cannot exceed 1000 characters. Note that

4326

# the finding itself will be included in the window, so that hotwords may

4327

# be used to match substrings of the finding itself. For example, the

4328

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

4329

# adjusted upwards if the area code is known to be the local area code of

4330

# a company office using the hotword regex "\(xxx\)", where "xxx"

4331

# is the area code in question.

4332

# rule.

4333

"windowBefore": 42, # Number of characters before the finding to consider.

4334

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4335

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4336

},

4337

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

4338

# `InspectionRuleSet` are removed from results.

4339

"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]

4340

# be used to match sensitive information specific to the data, such as a list

4341

# of employee IDs or job titles.

4342

#

4343

# Dictionary words are case-insensitive and all characters other than letters

4344

# and digits in the unicode [Basic Multilingual

4345

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

4346

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4347

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

4348

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4349

# surrounding any match must be of a different type than the adjacent

4350

# 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]

4351

# digits next to non-digits. For example, the dictionary word "jen" will

4352

# match the first three letters of the text "jen123" but will return no

4353

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4354

#

4355

# Dictionary words containing a large number of characters that are not

4356

# letters or digits may result in unexpected findings because such characters

4357

# are treated as whitespace. The

4358

# [limits](https://cloud.google.com/dlp/limits) page contains details about

4359

# the size limits of dictionaries. For dictionaries that do not fit within

4360

# these constraints, consider using `LargeCustomDictionaryConfig` in the

4361

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4362

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

4363

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4364

# at least one phrase and every phrase must contain at least 2 characters

4365

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4366

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4367

],

4368

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4369

"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]

4370

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4371

"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]

4372

# Example: gs://[BUCKET_NAME]/dictionary.txt

4373

},

4374

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4375

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

4376

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4377

# specified, the entire match is returned. No more than 3 may be included.

4378

42,

4379

],

4380

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4381

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4382

# google/re2 repository on GitHub.

4383

},

4384

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

4385

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

4386

# contained within with a finding of an infoType from this list. For

4387

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

4388

# `exclusion_rule` containing `exclude_info_types.info_types` with

4389

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

4390

# with EMAIL_ADDRESS finding.

4391

# That leads to "555-222-2222@example.org" to generate only a single

4392

# finding, namely email address.

4393

{ # Type of information detected by the API.

4394

"name": "A String", # Name of the information type. Either a name of your choosing when

4395

# creating a CustomInfoType, or one of the names listed

4396

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4397

# a built-in type. InfoType names should conform to the pattern

4398

# `[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]

4403

},

4404

},

4405

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4406

},

4407

],

4408

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

4409

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

4410

# When set within `InspectJobConfig`,

4411

# the maximum returned is 2000 regardless if this is set higher.

4412

# When set within `InspectContentRequest`, this field is ignored.

4413

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

4414

{ # Max findings configuration per infoType, per content item or long

4415

# running DlpJob.

4416

"maxFindings": 42, # Max findings limit for the given infoType.

4417

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

4418

# info_type should be provided. If InfoTypeLimit does not have an

4419

# info_type, the DLP API applies the limit against all info_types that

4420

# are found but not specified in another InfoTypeLimit.

4421

"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]

4422

# creating a CustomInfoType, or one of the names listed

4423

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4424

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4425

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4426

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4427

},

4428

],

4429

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

4430

# When set within `InspectContentRequest`, the maximum returned is 2000

4431

# regardless if this is set higher.

4432

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4433

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4434

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4435

{ # A task to execute on the completion of a job.

4436

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4437

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

4438

# Command Center (CSCC Alpha).

4439

# This action is only available for projects which are parts of

4440

# an organization and whitelisted for the alpha Cloud Security Command

4441

# Center.

4442

# The action will publish count of finding instances and their info types.

4443

# The summary of findings will be persisted in CSCC and are governed by CSCC

4444

# service-specific policy, see https://cloud.google.com/terms/service-terms

4445

# Only a single instance of this action can be specified.

4446

# Compatible with: Inspect

4447

},

4448

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

4449

# completion/failure.

4450

# completion/failure.

4451

},

4452

"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]

4453

# OutputStorageConfig. Only a single instance of this action can be

4454

# specified.

4455

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4456

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4457

"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]

4458

# dataset. If table_id is not set a new one will be generated

4459

# for you with the following format:

4460

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

4461

# generating the date details.

4462

#

4463

# For Inspect, each column in an existing output table must have the same

4464

# name, type, and mode of a field in the `Finding` object.

4465

#

4466

# For Risk, an existing output table should be the output of a previous

4467

# Risk analysis job run on the same source table, with the same privacy

4468

# metric and quasi-identifiers. Risk jobs that analyze the same table but

4469

# compute a different privacy metric, or use different sets of

4470

# quasi-identifiers, cannot store their results in the same table.

4471

# identified by its project_id, dataset_id, and table_name. Within a query

4472

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4473

# `<project_id>:<dataset_id>.<table_id>` or

4474

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4475

"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]

4476

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4477

"datasetId": "A String", # Dataset ID of the table.

4478

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4479

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4480

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

4481

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

4482

# from the `Finding` object. If appending to an existing table, any columns

4483

# from the predefined schema that are missing will be added. No columns in

4484

# the existing table will be deleted.

4485

#

4486

# If unspecified, then all available columns will be used for a new table or

4487

# an (existing) table with no schema, and no changes will be made to an

4488

# existing table that has a schema.

4489

# Only for use with external storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4490

},

4491

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4492

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

4493

# message contains a single field, `DlpJobName`, which is equal to the

4494

# finished job's

4495

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

4496

# Compatible with: Inspect, Risk

4497

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

4498

# publishing access rights to the DLP API service account executing

4499

# the long running DlpJob sending the notifications.

4500

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4501

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4502

"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]

4503

# results of the DlpJob will be applied to the entry for the resource scanned

4504

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

4505

# be deleted. InfoType naming patterns are strictly enforced when using this

4506

# feature. Note that the findings will be persisted in Cloud Data Catalog

4507

# storage and are governed by Data Catalog service-specific policy, see

4508

# https://cloud.google.com/terms/service-terms

4509

# Only a single instance of this action can be specified and only allowed if

4510

# all resources being scanned are BigQuery tables.

4511

# Compatible with: Inspect

4512

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4513

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

4514

# will publish a metric to stack driver on each infotype requested and

4515

# how many findings were found for it. CustomDetectors will be bucketed

4516

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4517

},

4518

},

4519

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4520

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4521

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

4522

# Early access feature is in a pre-release state and might change or have

4523

# limited support. For more information, see

4524

# https://cloud.google.com/products#product-launch-stages.

4525

# of Google Cloud Platform.

4526

"labels": { # To organize findings, these labels will be added to each finding.

4527

#

4528

# Label keys must be between 1 and 63 characters long and must conform

4529

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

4530

#

4531

# Label values must be between 0 and 63 characters long and must conform

4532

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

4533

#

4534

# No more than 10 labels can be associated with a given finding.

4535

#

4536

# Examples:

4537

# * `"environment" : "production"`

4538

# * `"pipeline" : "etl"`

4539

"a_key": "A String",

4540

},

4541

"description": "A String", # A short description of where the data is coming from. Will be stored once

4542

# in the job. 256 max length.

4543

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

4544

# meaningful such as the columns that are primary keys.

4545

"identifyingFields": [ # The columns that are the primary keys for table objects included in

4546

# ContentItem. A copy of this cell's value will stored alongside alongside

4547

# each finding so that the finding can be traced to the specific row it came

4548

# from. No more than 3 may be provided.

4549

{ # General identifier of a data field in a storage service.

4550

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

4555

# 'finding_labels' map. Request may contain others, but any missing one of

4556

# these will be rejected.

4557

#

4558

# Label keys must be between 1 and 63 characters long and must conform

4559

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

4560

#

4561

# No more than 10 keys can be required.

4562

"A String",

4563

],

4564

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4565

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

4566

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

4567

# by project and namespace, however the namespace ID may be empty.

4568

# A partition ID identifies a grouping of entities. The grouping is always

4569

# by project and namespace, however the namespace ID may be empty.

4570

#

4571

# A partition ID contains several dimensions:

4572

# project ID and namespace ID.

4573

"projectId": "A String", # The ID of the project to which the entities belong.

4574

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

4575

},

4576

"kind": { # A representation of a Datastore kind. # The kind to process.

4577

"name": "A String", # The name of the kind.

4578

},

4579

},

4580

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

4581

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

4582

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

4583

# Used for data sources like Datastore and BigQuery.

4584

#

4585

# For BigQuery:

4586

# Required to filter out rows based on the given start and

4587

# end times. If not specified and the table was modified between the given

4588

# start and end times, the entire table will be scanned.

4589

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

4590

# `TIMESTAMP`, or `DATETIME` BigQuery column.

4591

#

4592

# For Datastore.

4593

# Valid data types of the timestamp field are: `TIMESTAMP`.

4594

# Datastore entity will be scanned if the timestamp property does not

4595

# exist or its value is empty or invalid.

4596

"name": "A String", # Name describing the field.

4597

},

4598

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

4599

# a valid start_time to avoid scanning files that have not been modified

4600

# since the last time the JobTrigger executed. This will be based on the

4601

# time of the execution of the last run of the JobTrigger.

4602

"endTime": "A String", # Exclude files or rows newer than this value.

4603

# If set to zero, no upper time limit is applied.

4604

"startTime": "A String", # Exclude files or rows older than this value.

4605

},

4606

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

4607

# bucket.

4608

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

4609

# than this value then the rest of the bytes are omitted. Only one

4610

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

4611

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

4612

"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

4613

# `regex_file_set` must be set.

4614

# expressions are used to allow fine-grained control over which files in the

4615

# bucket to include.

4616

#

4617

# Included files are those that match at least one item in `include_regex` and

4618

# do not match any items in `exclude_regex`. Note that a file that matches

4619

# items from both lists will _not_ be included. For a match to occur, the

4620

# entire file path (i.e., everything in the url after the bucket name) must

4621

# match the regular expression.

4622

#

4623

# For example, given the input `{bucket_name: "mybucket", include_regex:

4624

# ["directory1/.*"], exclude_regex:

4625

# ["directory1/excluded.*"]}`:

4626

#

4627

# * `gs://mybucket/directory1/myfile` will be included

4628

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

4629

# across `/`)

4630

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

4631

# full path doesn't match any items in `include_regex`)

4632

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

4633

# matches an item in `exclude_regex`)

4634

#

4635

# If `include_regex` is left empty, it will match all files by default

4636

# (this is equivalent to setting `include_regex: [".*"]`).

4637

#

4638

# Some other common use cases:

4639

#

4640

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

4641

# files in `mybucket` except for .pdf files

4642

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

4643

# include all files directly under `gs://mybucket/directory/`, without matching

4644

# across `/`

4645

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

4646

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

4647

# the bucket that match at least one of these regular expressions will be

4648

# included in the set of files, except for those that also match an item in

4649

# `exclude_regex`. Leaving this field empty will match all files by default

4650

# (this is equivalent to including `.*` in the list).

4651

#

4652

# Regular expressions use RE2

4653

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

4654

# under the google/re2 repository on GitHub.

4655

"A String",

4656

],

4657

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

4658

# the bucket that match at least one of these regular expressions will be

4659

# excluded from the scan.

4660

#

4661

# Regular expressions use RE2

4662

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

4663

# 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

4668

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

4669

#

4670

# If the url ends in a trailing slash, the bucket or directory represented

4671

# by the url will be scanned non-recursively (content in sub-directories

4672

# will not be scanned). This means that `gs://mybucket/` is equivalent to

4673

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

4674

# `gs://mybucket/directory/*`.

4675

#

4676

# Exactly one of `url` or `regex_file_set` must be set.

4677

},

4678

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

4679

# Number of files scanned is rounded down. Must be between 0 and 100,

4680

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

4681

"fileTypes": [ # List of file type groups to include in the scan.

4682

# If empty, all files are scanned and available data format processors

4683

# are applied. In addition, the binary content of the selected files

4684

# is always scanned as well.

4685

# Images are scanned only as binary if the specified region

4686

# does not support image inspection and no file_types were specified.

4687

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

4688

"A String",

4689

],

4690

"sampleMethod": "A String",

4691

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

4692

# number of bytes scanned is rounded down. Must be between 0 and 100,

4693

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

4694

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

4695

},

4696

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

4697

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

4698

# identified by its project_id, dataset_id, and table_name. Within a query

4699

# a table is often referenced with a string in the format of:

4700

# `<project_id>:<dataset_id>.<table_id>` or

4701

# `<project_id>.<dataset_id>.<table_id>`.

4702

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

4703

# If omitted, project ID is inferred from the API call.

4704

"datasetId": "A String", # Dataset ID of the table.

4705

"tableId": "A String", # Name of the table.

4706

},

4707

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

4708

# `actions.saveFindings.outputConfig.table` is specified, the values of

4709

# columns specified here are available in the output table under

4710

# `location.content_locations.record_location.record_key.id_values`. Nested

4711

# fields such as `person.birthdate.year` are allowed.

4712

{ # General identifier of a data field in a storage service.

4713

"name": "A String", # Name describing the field.

4714

},

4715

],

4716

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

4717

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

4718

# 100 means no limit. Defaults to 0. Only one of rows_limit and

4719

# rows_limit_percent can be specified. Cannot be used in conjunction with

4720

# TimespanConfig.

4721

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

4722

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

4723

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

4724

# Cannot be used in conjunction with TimespanConfig.

4725

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

4726

# inspection of entire columns which you know have no findings.

4727

{ # General identifier of a data field in a storage service.

4728

"name": "A String", # Name describing the field.

4729

},

4730

],

4731

"sampleMethod": "A String",

4732

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4733

},

4734

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

4735

# `inspect_config` will be merged into the values persisted as part of the

4736

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4737

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4738

"status": "A String", # Required. A status for this trigger.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4739

},

4740

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4741

"nextPageToken": "A String", # If the next page is available then the next page token to be used

4742

# in following ListJobTriggers request.

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>

4748

<pre>Retrieves the next page of results.

4749

4750

Args:

4751

previous_request: The request for the previous page. (required)

4752

previous_response: The response from the request for the previous page. (required)

4753

4754

Returns:

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4755

A request object that you can call 'execute()' on to request the next

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4756

page. Returns None if there are no more items in the collection.

</pre>

</div>

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4761

<code class="details" id="patch">patch(name, body=None, x__xgafv=None)</code>

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4762

<pre>Updates a job trigger.

4763

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

4764

4765

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4766

name: string, Required. Resource name of the project and the triggeredJob, for example

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4767

`projects/dlp-test-project/jobTriggers/53234423`. (required)

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4768

body: object, The request body.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4769

The object takes the form of:

4770

4771

{ # Request message for UpdateJobTrigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4772

"jobTrigger": { # Contains a configuration to make dlp api calls on a repeating basis. # New JobTrigger value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4773

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4774

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

4775

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

4776

# triggeredJob is created, for example

4777

# `projects/dlp-test-project/jobTriggers/53234423`.

4778

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

4779

# errors may result in the JobTrigger automatically being paused.

4780

# Will return the last 100 errors. Whenever the JobTrigger is modified

4781

# this list will be cleared.

4782

{ # Details information about an error encountered during job execution or

4783

# the results of an unsuccessful activation of the JobTrigger.

4784

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

4785

# different programming environments, including REST APIs and RPC APIs. It is

4786

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

4787

# three pieces of data: error code, error message, and error details.

4788

#

4789

# You can find out more about this error model and how to work with it in the

4790

# [API Design Guide](https://cloud.google.com/apis/design/errors).

4791

"message": "A String", # A developer-facing error message, which should be in English. Any

4792

# user-facing error message should be localized and sent in the

4793

# google.rpc.Status.details field, or localized by the client.

4794

"details": [ # A list of messages that carry the error details. There is a common set of

4795

# message types for APIs to use.

4796

{

4797

"a_key": "", # Properties of the object. Contains field @type with type URL.

4798

},

4799

],

4800

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

4801

},

4802

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4808

"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4809

# needs to trigger for a job to be started. The list may contain only

4810

# a single Schedule trigger and must have at least one object.

4811

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4812

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

4813

"recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4814

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4815

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4816

# A scheduled start time will be skipped if the previous

4817

# execution has not ended when its scheduled time occurs.

4818

#

4819

# This value must be set to a time duration greater than or equal

4820

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4821

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4822

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4823

# Early access feature is in a pre-release state and might change or have

4824

# limited support. For more information, see

4825

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4826

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4827

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4828

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4829

],

4830

"displayName": "A String", # Display name (max 100 chars)

4831

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

4832

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

4833

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

4834

"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]

4835

# When used with redactContent only info_types and min_likelihood are currently

4836

# used.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4837

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

4838

# POSSIBLE.

4839

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

4840

"contentOptions": [ # List of options defining data content to scan.

4841

# If empty, text, images, and other content will be included.

4842

"A String",

4843

],

4844

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

4845

# InfoType values returned by ListInfoTypes or listed at

4846

# https://cloud.google.com/dlp/docs/infotypes-reference.

4847

#

4848

# When no InfoTypes or CustomInfoTypes are specified in a request, the

4849

# system may automatically choose what detectors to run. By default this may

4850

# be all types, but may change over time as detectors are updated.

4851

#

4852

# If you need precise control and predictability as to what detectors are

4853

# run you should specify specific InfoTypes listed in the reference,

4854

# otherwise a default list will be used, which may change over time.

4855

{ # Type of information detected by the API.

4856

"name": "A String", # Name of the information type. Either a name of your choosing when

4857

# creating a CustomInfoType, or one of the names listed

4858

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4859

# a built-in type. InfoType names should conform to the pattern

4860

# `[a-zA-Z0-9_]{1,64}`.

4861

},

4862

],

4863

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

4864

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

4865

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

4866

{ # Custom information type provided by the user. Used to find domain-specific

4867

# sensitive information configurable to the data in question.

4868

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

4869

# support reversing.

4870

# such as

4871

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

4872

# These types of transformations are

4873

# those that perform pseudonymization, thereby producing a "surrogate" as

4874

# output. This should be used in conjunction with a field on the

4875

# transformation such as `surrogate_info_type`. This CustomInfoType does

4876

# not support the use of `detection_rules`.

4877

},

4878

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

4879

# altered by a detection rule if the finding meets the criteria specified by

4880

# the rule. Defaults to `VERY_LIKELY` if not specified.

4881

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

4882

# infoType, when the name matches one of existing infoTypes and that infoType

4883

# is specified in `InspectContent.info_types` field. Specifying the latter

4884

# adds findings to the one detected by the system. If built-in info type is

4885

# not specified in `InspectContent.info_types` list then the name is treated

4886

# as a custom info type.

4887

"name": "A String", # Name of the information type. Either a name of your choosing when

4888

# creating a CustomInfoType, or one of the names listed

4889

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4890

# a built-in type. InfoType names should conform to the pattern

4891

# `[a-zA-Z0-9_]{1,64}`.

4892

},

4893

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

4894

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4895

# specified, the entire match is returned. No more than 3 may be included.

4896

42,

4897

],

4898

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4899

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4900

# google/re2 repository on GitHub.

4901

},

4902

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

4903

# Rules are applied in order that they are specified. Not supported for the

4904

# `surrogate_type` CustomInfoType.

4905

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

4906

# `CustomInfoType` to alter behavior under certain circumstances, depending

4907

# on the specific details of the rule. Not supported for the `surrogate_type`

4908

# custom infoType.

4909

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

4910

# proximity of hotwords.

4911

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

4912

# part of a detection rule.

4913

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

4914

# levels. For example, if a finding would be `POSSIBLE` without the

4915

# detection rule and `relative_likelihood` is 1, then it is upgraded to

4916

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

4917

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

4918

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

4919

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

4920

# a final likelihood of `LIKELY`.

4921

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

4922

},

4923

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

4924

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4925

# specified, the entire match is returned. No more than 3 may be included.

4926

42,

4927

],

4928

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4929

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4930

# google/re2 repository on GitHub.

4931

},

4932

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

4933

# The total length of the window cannot exceed 1000 characters. Note that

4934

# the finding itself will be included in the window, so that hotwords may

4935

# be used to match substrings of the finding itself. For example, the

4936

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

4937

# adjusted upwards if the area code is known to be the local area code of

4938

# a company office using the hotword regex "\(xxx\)", where "xxx"

4939

# is the area code in question.

4940

# rule.

4941

"windowBefore": 42, # Number of characters before the finding to consider.

4942

"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

4948

# to be returned. It still can be used for rules matching.

4949

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

4950

# be used to match sensitive information specific to the data, such as a list

4951

# of employee IDs or job titles.

4952

#

4953

# Dictionary words are case-insensitive and all characters other than letters

4954

# and digits in the unicode [Basic Multilingual

4955

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

4956

# will be replaced with whitespace when scanning for matches, so the

4957

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

4958

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

4959

# surrounding any match must be of a different type than the adjacent

4960

# characters within the word, so letters must be next to non-letters and

4961

# digits next to non-digits. For example, the dictionary word "jen" will

4962

# match the first three letters of the text "jen123" but will return no

4963

# matches for "jennifer".

4964

#

4965

# Dictionary words containing a large number of characters that are not

4966

# letters or digits may result in unexpected findings because such characters

4967

# are treated as whitespace. The

4968

# [limits](https://cloud.google.com/dlp/limits) page contains details about

4969

# the size limits of dictionaries. For dictionaries that do not fit within

4970

# these constraints, consider using `LargeCustomDictionaryConfig` in the

4971

# `StoredInfoType` API.

4972

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

4973

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

4974

# at least one phrase and every phrase must contain at least 2 characters

4975

# 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

4980

# is accepted.

4981

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

4982

# Example: gs://[BUCKET_NAME]/dictionary.txt

4983

},

4984

},

4985

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

4986

# `InspectDataSource`. Not currently supported in `InspectContent`.

4987

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

4988

# `organizations/433245324/storedInfoTypes/432452342` or

4989

# `projects/project-id/storedInfoTypes/432452342`.

4990

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

4991

# inspection was created. Output-only field, populated by the system.

4992

},

4993

},

4994

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4995

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

4996

# included in the response; see Finding.quote.

4997

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

4998

# Exclusion rules, contained in the set are executed in the end, other

4999

# rules are executed in the order they are specified for each info type.

5000

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

5001

# circumstances, depending on the specific details of the rules within the set.

5002

"infoTypes": [ # List of infoTypes this rule set is applied to.

5003

{ # Type of information detected by the API.

5004

"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]

5005

# creating a CustomInfoType, or one of the names listed

5006

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5007

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5008

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5009

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5010

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5011

"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]

5012

{ # A single inspection rule to be applied to infoTypes, specified in

5013

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5014

"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]

5015

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5016

"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]

5017

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5018

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5019

# levels. For example, if a finding would be `POSSIBLE` without the

5020

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5021

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5022

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5023

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5024

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5025

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5026

"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]

5027

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5028

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5029

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5030

# specified, the entire match is returned. No more than 3 may be included.

5031

42,

5032

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5033

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5034

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5035

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5036

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5037

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5038

# The total length of the window cannot exceed 1000 characters. Note that

5039

# the finding itself will be included in the window, so that hotwords may

5040

# be used to match substrings of the finding itself. For example, the

5041

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

5042

# adjusted upwards if the area code is known to be the local area code of

5043

# a company office using the hotword regex "\(xxx\)", where "xxx"

5044

# is the area code in question.

5045

# rule.

5046

"windowBefore": 42, # Number of characters before the finding to consider.

5047

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5048

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5049

},

5050

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

5051

# `InspectionRuleSet` are removed from results.

5052

"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]

5053

# be used to match sensitive information specific to the data, such as a list

5054

# of employee IDs or job titles.

5055

#

5056

# Dictionary words are case-insensitive and all characters other than letters

5057

# and digits in the unicode [Basic Multilingual

5058

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5059

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5060

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5061

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5062

# surrounding any match must be of a different type than the adjacent

5063

# 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]

5064

# digits next to non-digits. For example, the dictionary word "jen" will

5065

# match the first three letters of the text "jen123" but will return no

5066

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5067

#

5068

# Dictionary words containing a large number of characters that are not

5069

# letters or digits may result in unexpected findings because such characters

5070

# are treated as whitespace. The

5071

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5072

# the size limits of dictionaries. For dictionaries that do not fit within

5073

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5074

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5075

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5076

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5077

# at least one phrase and every phrase must contain at least 2 characters

5078

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5079

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5080

],

5081

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5082

"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]

5083

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5084

"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]

5085

# Example: gs://[BUCKET_NAME]/dictionary.txt

5086

},

5087

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5088

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

5089

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5090

# specified, the entire match is returned. No more than 3 may be included.

5091

42,

5092

],

5093

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5094

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5095

# google/re2 repository on GitHub.

5096

},

5097

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

5098

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

5099

# contained within with a finding of an infoType from this list. For

5100

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

5101

# `exclusion_rule` containing `exclude_info_types.info_types` with

5102

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

5103

# with EMAIL_ADDRESS finding.

5104

# That leads to "555-222-2222@example.org" to generate only a single

5105

# finding, namely email address.

5106

{ # Type of information detected by the API.

5107

"name": "A String", # Name of the information type. Either a name of your choosing when

5108

# creating a CustomInfoType, or one of the names listed

5109

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5110

# a built-in type. InfoType names should conform to the pattern

5111

# `[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]

5116

},

5117

},

5118

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5119

},

5120

],

5121

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

5122

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

5123

# When set within `InspectJobConfig`,

5124

# the maximum returned is 2000 regardless if this is set higher.

5125

# When set within `InspectContentRequest`, this field is ignored.

5126

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

5127

{ # Max findings configuration per infoType, per content item or long

5128

# running DlpJob.

5129

"maxFindings": 42, # Max findings limit for the given infoType.

5130

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

5131

# info_type should be provided. If InfoTypeLimit does not have an

5132

# info_type, the DLP API applies the limit against all info_types that

5133

# are found but not specified in another InfoTypeLimit.

5134

"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]

5135

# creating a CustomInfoType, or one of the names listed

5136

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5137

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5138

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5139

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5140

},

5141

],

5142

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

5143

# When set within `InspectContentRequest`, the maximum returned is 2000

5144

# regardless if this is set higher.

5145

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5146

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5147

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5148

{ # A task to execute on the completion of a job.

5149

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5150

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

5151

# Command Center (CSCC Alpha).

5152

# This action is only available for projects which are parts of

5153

# an organization and whitelisted for the alpha Cloud Security Command

5154

# Center.

5155

# The action will publish count of finding instances and their info types.

5156

# The summary of findings will be persisted in CSCC and are governed by CSCC

5157

# service-specific policy, see https://cloud.google.com/terms/service-terms

5158

# Only a single instance of this action can be specified.

5159

# Compatible with: Inspect

5160

},

5161

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

5162

# completion/failure.

5163

# completion/failure.

5164

},

5165

"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]

5166

# OutputStorageConfig. Only a single instance of this action can be

5167

# specified.

5168

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5169

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5170

"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]

5171

# dataset. If table_id is not set a new one will be generated

5172

# for you with the following format:

5173

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

5174

# generating the date details.

5175

#

5176

# For Inspect, each column in an existing output table must have the same

5177

# name, type, and mode of a field in the `Finding` object.

5178

#

5179

# For Risk, an existing output table should be the output of a previous

5180

# Risk analysis job run on the same source table, with the same privacy

5181

# metric and quasi-identifiers. Risk jobs that analyze the same table but

5182

# compute a different privacy metric, or use different sets of

5183

# quasi-identifiers, cannot store their results in the same table.

5184

# identified by its project_id, dataset_id, and table_name. Within a query

5185

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5186

# `<project_id>:<dataset_id>.<table_id>` or

5187

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5188

"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]

5189

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5190

"datasetId": "A String", # Dataset ID of the table.

5191

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5192

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5193

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

5194

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

5195

# from the `Finding` object. If appending to an existing table, any columns

5196

# from the predefined schema that are missing will be added. No columns in

5197

# the existing table will be deleted.

5198

#

5199

# If unspecified, then all available columns will be used for a new table or

5200

# an (existing) table with no schema, and no changes will be made to an

5201

# existing table that has a schema.

5202

# Only for use with external storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5203

},

5204

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5205

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

5206

# message contains a single field, `DlpJobName`, which is equal to the

5207

# finished job's

5208

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

5209

# Compatible with: Inspect, Risk

5210

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

5211

# publishing access rights to the DLP API service account executing

5212

# the long running DlpJob sending the notifications.

5213

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5214

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5215

"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]

5216

# results of the DlpJob will be applied to the entry for the resource scanned

5217

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

5218

# be deleted. InfoType naming patterns are strictly enforced when using this

5219

# feature. Note that the findings will be persisted in Cloud Data Catalog

5220

# storage and are governed by Data Catalog service-specific policy, see

5221

# https://cloud.google.com/terms/service-terms

5222

# Only a single instance of this action can be specified and only allowed if

5223

# all resources being scanned are BigQuery tables.

5224

# Compatible with: Inspect

5225

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5226

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

5227

# will publish a metric to stack driver on each infotype requested and

5228

# how many findings were found for it. CustomDetectors will be bucketed

5229

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5230

},

5231

},

5232

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5233

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5234

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

5235

# Early access feature is in a pre-release state and might change or have

5236

# limited support. For more information, see

5237

# https://cloud.google.com/products#product-launch-stages.

5238

# of Google Cloud Platform.

5239

"labels": { # To organize findings, these labels will be added to each finding.

5240

#

5241

# Label keys must be between 1 and 63 characters long and must conform

5242

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

5243

#

5244

# Label values must be between 0 and 63 characters long and must conform

5245

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

5246

#

5247

# No more than 10 labels can be associated with a given finding.

5248

#

5249

# Examples:

5250

# * `"environment" : "production"`

5251

# * `"pipeline" : "etl"`

5252

"a_key": "A String",

5253

},

5254

"description": "A String", # A short description of where the data is coming from. Will be stored once

5255

# in the job. 256 max length.

5256

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

5257

# meaningful such as the columns that are primary keys.

5258

"identifyingFields": [ # The columns that are the primary keys for table objects included in

5259

# ContentItem. A copy of this cell's value will stored alongside alongside

5260

# each finding so that the finding can be traced to the specific row it came

5261

# from. No more than 3 may be provided.

5262

{ # General identifier of a data field in a storage service.

5263

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

5268

# 'finding_labels' map. Request may contain others, but any missing one of

5269

# these will be rejected.

5270

#

5271

# Label keys must be between 1 and 63 characters long and must conform

5272

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

5273

#

5274

# No more than 10 keys can be required.

5275

"A String",

5276

],

5277

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5278

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

5279

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

5280

# by project and namespace, however the namespace ID may be empty.

5281

# A partition ID identifies a grouping of entities. The grouping is always

5282

# by project and namespace, however the namespace ID may be empty.

5283

#

5284

# A partition ID contains several dimensions:

5285

# project ID and namespace ID.

5286

"projectId": "A String", # The ID of the project to which the entities belong.

5287

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

5288

},

5289

"kind": { # A representation of a Datastore kind. # The kind to process.

5290

"name": "A String", # The name of the kind.

5291

},

5292

},

5293

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

5294

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

5295

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

5296

# Used for data sources like Datastore and BigQuery.

5297

#

5298

# For BigQuery:

5299

# Required to filter out rows based on the given start and

5300

# end times. If not specified and the table was modified between the given

5301

# start and end times, the entire table will be scanned.

5302

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

5303

# `TIMESTAMP`, or `DATETIME` BigQuery column.

5304

#

5305

# For Datastore.

5306

# Valid data types of the timestamp field are: `TIMESTAMP`.

5307

# Datastore entity will be scanned if the timestamp property does not

5308

# exist or its value is empty or invalid.

5309

"name": "A String", # Name describing the field.

5310

},

5311

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

5312

# a valid start_time to avoid scanning files that have not been modified

5313

# since the last time the JobTrigger executed. This will be based on the

5314

# time of the execution of the last run of the JobTrigger.

5315

"endTime": "A String", # Exclude files or rows newer than this value.

5316

# If set to zero, no upper time limit is applied.

5317

"startTime": "A String", # Exclude files or rows older than this value.

5318

},

5319

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

5320

# bucket.

5321

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

5322

# than this value then the rest of the bytes are omitted. Only one

5323

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

5324

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

5325

"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

5326

# `regex_file_set` must be set.

5327

# expressions are used to allow fine-grained control over which files in the

5328

# bucket to include.

5329

#

5330

# Included files are those that match at least one item in `include_regex` and

5331

# do not match any items in `exclude_regex`. Note that a file that matches

5332

# items from both lists will _not_ be included. For a match to occur, the

5333

# entire file path (i.e., everything in the url after the bucket name) must

5334

# match the regular expression.

5335

#

5336

# For example, given the input `{bucket_name: "mybucket", include_regex:

5337

# ["directory1/.*"], exclude_regex:

5338

# ["directory1/excluded.*"]}`:

5339

#

5340

# * `gs://mybucket/directory1/myfile` will be included

5341

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

5342

# across `/`)

5343

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

5344

# full path doesn't match any items in `include_regex`)

5345

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

5346

# matches an item in `exclude_regex`)

5347

#

5348

# If `include_regex` is left empty, it will match all files by default

5349

# (this is equivalent to setting `include_regex: [".*"]`).

5350

#

5351

# Some other common use cases:

5352

#

5353

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

5354

# files in `mybucket` except for .pdf files

5355

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

5356

# include all files directly under `gs://mybucket/directory/`, without matching

5357

# across `/`

5358

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

5359

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

5360

# the bucket that match at least one of these regular expressions will be

5361

# included in the set of files, except for those that also match an item in

5362

# `exclude_regex`. Leaving this field empty will match all files by default

5363

# (this is equivalent to including `.*` in the list).

5364

#

5365

# Regular expressions use RE2

5366

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

5367

# under the google/re2 repository on GitHub.

5368

"A String",

5369

],

5370

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

5371

# the bucket that match at least one of these regular expressions will be

5372

# excluded from the scan.

5373

#

5374

# Regular expressions use RE2

5375

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

5376

# 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

5381

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

5382

#

5383

# If the url ends in a trailing slash, the bucket or directory represented

5384

# by the url will be scanned non-recursively (content in sub-directories

5385

# will not be scanned). This means that `gs://mybucket/` is equivalent to

5386

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

5387

# `gs://mybucket/directory/*`.

5388

#

5389

# Exactly one of `url` or `regex_file_set` must be set.

5390

},

5391

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

5392

# Number of files scanned is rounded down. Must be between 0 and 100,

5393

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

5394

"fileTypes": [ # List of file type groups to include in the scan.

5395

# If empty, all files are scanned and available data format processors

5396

# are applied. In addition, the binary content of the selected files

5397

# is always scanned as well.

5398

# Images are scanned only as binary if the specified region

5399

# does not support image inspection and no file_types were specified.

5400

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

5401

"A String",

5402

],

5403

"sampleMethod": "A String",

5404

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

5405

# number of bytes scanned is rounded down. Must be between 0 and 100,

5406

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

5407

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

5408

},

5409

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

5410

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

5411

# identified by its project_id, dataset_id, and table_name. Within a query

5412

# a table is often referenced with a string in the format of:

5413

# `<project_id>:<dataset_id>.<table_id>` or

5414

# `<project_id>.<dataset_id>.<table_id>`.

5415

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

5416

# If omitted, project ID is inferred from the API call.

5417

"datasetId": "A String", # Dataset ID of the table.

5418

"tableId": "A String", # Name of the table.

5419

},

5420

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

5421

# `actions.saveFindings.outputConfig.table` is specified, the values of

5422

# columns specified here are available in the output table under

5423

# `location.content_locations.record_location.record_key.id_values`. Nested

5424

# fields such as `person.birthdate.year` are allowed.

5425

{ # General identifier of a data field in a storage service.

5426

"name": "A String", # Name describing the field.

5427

},

5428

],

5429

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

5430

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

5431

# 100 means no limit. Defaults to 0. Only one of rows_limit and

5432

# rows_limit_percent can be specified. Cannot be used in conjunction with

5433

# TimespanConfig.

5434

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

5435

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

5436

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

5437

# Cannot be used in conjunction with TimespanConfig.

5438

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

5439

# inspection of entire columns which you know have no findings.

5440

{ # General identifier of a data field in a storage service.

5441

"name": "A String", # Name describing the field.

5442

},

5443

],

5444

"sampleMethod": "A String",

5445

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5446

},

5447

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

5448

# `inspect_config` will be merged into the values persisted as part of the

5449

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5450

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5451

"status": "A String", # Required. A status for this trigger.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5452

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5453

"updateMask": "A String", # Mask to control which fields get updated.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5454

}

5455

5456

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

5463

5464

{ # Contains a configuration to make dlp api calls on a repeating basis.

5465

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5466

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

5467

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

5468

# triggeredJob is created, for example

5469

# `projects/dlp-test-project/jobTriggers/53234423`.

5470

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

5471

# errors may result in the JobTrigger automatically being paused.

5472

# Will return the last 100 errors. Whenever the JobTrigger is modified

5473

# this list will be cleared.

5474

{ # Details information about an error encountered during job execution or

5475

# the results of an unsuccessful activation of the JobTrigger.

5476

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

5477

# different programming environments, including REST APIs and RPC APIs. It is

5478

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

5479

# three pieces of data: error code, error message, and error details.

5480

#

5481

# You can find out more about this error model and how to work with it in the

5482

# [API Design Guide](https://cloud.google.com/apis/design/errors).

5483

"message": "A String", # A developer-facing error message, which should be in English. Any

5484

# user-facing error message should be localized and sent in the

5485

# google.rpc.Status.details field, or localized by the client.

5486

"details": [ # A list of messages that carry the error details. There is a common set of

5487

# message types for APIs to use.

5488

{

5489

"a_key": "", # Properties of the object. Contains field @type with type URL.

5490

},

5491

],

5492

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

5493

},

5494

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5500

"triggers": [ # A list of triggers which will be OR'ed together. Only one in the list

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5501

# needs to trigger for a job to be started. The list may contain only

5502

# a single Schedule trigger and must have at least one object.

5503

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5504

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

5505

"recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5506

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5507

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5508

# A scheduled start time will be skipped if the previous

5509

# execution has not ended when its scheduled time occurs.

5510

#

5511

# This value must be set to a time duration greater than or equal

5512

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5513

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5514

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5515

# Early access feature is in a pre-release state and might change or have

5516

# limited support. For more information, see

5517

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5518

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5519

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5520

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5521

],

5522

"displayName": "A String", # Display name (max 100 chars)

5523

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

5524

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

5525

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

5526

"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]

5527

# When used with redactContent only info_types and min_likelihood are currently

5528

# used.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5529

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

5530

# POSSIBLE.

5531

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

5532

"contentOptions": [ # List of options defining data content to scan.

5533

# If empty, text, images, and other content will be included.

5534

"A String",

5535

],

5536

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

5537

# InfoType values returned by ListInfoTypes or listed at

5538

# https://cloud.google.com/dlp/docs/infotypes-reference.

5539

#

5540

# When no InfoTypes or CustomInfoTypes are specified in a request, the

5541

# system may automatically choose what detectors to run. By default this may

5542

# be all types, but may change over time as detectors are updated.

5543

#

5544

# If you need precise control and predictability as to what detectors are

5545

# run you should specify specific InfoTypes listed in the reference,

5546

# otherwise a default list will be used, which may change over time.

5547

{ # Type of information detected by the API.

5548

"name": "A String", # Name of the information type. Either a name of your choosing when

5549

# creating a CustomInfoType, or one of the names listed

5550

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5551

# a built-in type. InfoType names should conform to the pattern

5552

# `[a-zA-Z0-9_]{1,64}`.

5553

},

5554

],

5555

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

5556

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

5557

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

5558

{ # Custom information type provided by the user. Used to find domain-specific

5559

# sensitive information configurable to the data in question.

5560

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

5561

# support reversing.

5562

# such as

5563

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

5564

# These types of transformations are

5565

# those that perform pseudonymization, thereby producing a "surrogate" as

5566

# output. This should be used in conjunction with a field on the

5567

# transformation such as `surrogate_info_type`. This CustomInfoType does

5568

# not support the use of `detection_rules`.

5569

},

5570

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

5571

# altered by a detection rule if the finding meets the criteria specified by

5572

# the rule. Defaults to `VERY_LIKELY` if not specified.

5573

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

5574

# infoType, when the name matches one of existing infoTypes and that infoType

5575

# is specified in `InspectContent.info_types` field. Specifying the latter

5576

# adds findings to the one detected by the system. If built-in info type is

5577

# not specified in `InspectContent.info_types` list then the name is treated

5578

# as a custom info type.

5579

"name": "A String", # Name of the information type. Either a name of your choosing when

5580

# creating a CustomInfoType, or one of the names listed

5581

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5582

# a built-in type. InfoType names should conform to the pattern

5583

# `[a-zA-Z0-9_]{1,64}`.

5584

},

5585

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

5586

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5587

# specified, the entire match is returned. No more than 3 may be included.

5588

42,

5589

],

5590

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5591

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5592

# google/re2 repository on GitHub.

5593

},

5594

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

5595

# Rules are applied in order that they are specified. Not supported for the

5596

# `surrogate_type` CustomInfoType.

5597

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

5598

# `CustomInfoType` to alter behavior under certain circumstances, depending

5599

# on the specific details of the rule. Not supported for the `surrogate_type`

5600

# custom infoType.

5601

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

5602

# proximity of hotwords.

5603

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

5604

# part of a detection rule.

5605

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

5606

# levels. For example, if a finding would be `POSSIBLE` without the

5607

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5608

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5609

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5610

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5611

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5612

# a final likelihood of `LIKELY`.

5613

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

5614

},

5615

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5616

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5617

# specified, the entire match is returned. No more than 3 may be included.

5618

42,

5619

],

5620

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5621

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5622

# google/re2 repository on GitHub.

5623

},

5624

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5625

# The total length of the window cannot exceed 1000 characters. Note that

5626

# the finding itself will be included in the window, so that hotwords may

5627

# be used to match substrings of the finding itself. For example, the

5628

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

5629

# adjusted upwards if the area code is known to be the local area code of

5630

# a company office using the hotword regex "\(xxx\)", where "xxx"

5631

# is the area code in question.

5632

# rule.

5633

"windowBefore": 42, # Number of characters before the finding to consider.

5634

"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

5640

# to be returned. It still can be used for rules matching.

5641

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

5642

# be used to match sensitive information specific to the data, such as a list

5643

# of employee IDs or job titles.

5644

#

5645

# Dictionary words are case-insensitive and all characters other than letters

5646

# and digits in the unicode [Basic Multilingual

5647

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5648

# will be replaced with whitespace when scanning for matches, so the

5649

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5650

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

5651

# surrounding any match must be of a different type than the adjacent

5652

# characters within the word, so letters must be next to non-letters and

5653

# digits next to non-digits. For example, the dictionary word "jen" will

5654

# match the first three letters of the text "jen123" but will return no

5655

# matches for "jennifer".

5656

#

5657

# Dictionary words containing a large number of characters that are not

5658

# letters or digits may result in unexpected findings because such characters

5659

# are treated as whitespace. The

5660

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5661

# the size limits of dictionaries. For dictionaries that do not fit within

5662

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5663

# `StoredInfoType` API.

5664

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5665

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

5666

# at least one phrase and every phrase must contain at least 2 characters

5667

# 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

5672

# is accepted.

5673

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

5674

# Example: gs://[BUCKET_NAME]/dictionary.txt

5675

},

5676

},

5677

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

5678

# `InspectDataSource`. Not currently supported in `InspectContent`.

5679

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

5680

# `organizations/433245324/storedInfoTypes/432452342` or

5681

# `projects/project-id/storedInfoTypes/432452342`.

5682

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

5683

# inspection was created. Output-only field, populated by the system.

5684

},

5685

},

5686

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5687

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

5688

# included in the response; see Finding.quote.

5689

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

5690

# Exclusion rules, contained in the set are executed in the end, other

5691

# rules are executed in the order they are specified for each info type.

5692

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

5693

# circumstances, depending on the specific details of the rules within the set.

5694

"infoTypes": [ # List of infoTypes this rule set is applied to.

5695

{ # Type of information detected by the API.

5696

"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]

5697

# creating a CustomInfoType, or one of the names listed

5698

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5699

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5700

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5701

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5702

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5703

"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]

5704

{ # A single inspection rule to be applied to infoTypes, specified in

5705

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5706

"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]

5707

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5708

"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]

5709

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5710

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5711

# levels. For example, if a finding would be `POSSIBLE` without the

5712

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5713

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5714

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5715

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5716

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5717

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5718

"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]

5719

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5720

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5721

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5722

# specified, the entire match is returned. No more than 3 may be included.

5723

42,

5724

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5725

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5726

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5727

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5728

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5729

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5730

# The total length of the window cannot exceed 1000 characters. Note that

5731

# the finding itself will be included in the window, so that hotwords may

5732

# be used to match substrings of the finding itself. For example, the

5733

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

5734

# adjusted upwards if the area code is known to be the local area code of

5735

# a company office using the hotword regex "\(xxx\)", where "xxx"

5736

# is the area code in question.

5737

# rule.

5738

"windowBefore": 42, # Number of characters before the finding to consider.

5739

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5740

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5741

},

5742

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

5743

# `InspectionRuleSet` are removed from results.

5744

"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]

5745

# be used to match sensitive information specific to the data, such as a list

5746

# of employee IDs or job titles.

5747

#

5748

# Dictionary words are case-insensitive and all characters other than letters

5749

# and digits in the unicode [Basic Multilingual

5750

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5751

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5752

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5753

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5754

# surrounding any match must be of a different type than the adjacent

5755

# 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]

5756

# digits next to non-digits. For example, the dictionary word "jen" will

5757

# match the first three letters of the text "jen123" but will return no

5758

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5759

#

5760

# Dictionary words containing a large number of characters that are not

5761

# letters or digits may result in unexpected findings because such characters

5762

# are treated as whitespace. The

5763

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5764

# the size limits of dictionaries. For dictionaries that do not fit within

5765

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5766

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5767

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5768

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5769

# at least one phrase and every phrase must contain at least 2 characters

5770

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5771

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5772

],

5773

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5774

"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]

5775

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5776

"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]

5777

# Example: gs://[BUCKET_NAME]/dictionary.txt

5778

},

5779

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5780

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

5781

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5782

# specified, the entire match is returned. No more than 3 may be included.

5783

42,

5784

],

5785

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5786

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5787

# google/re2 repository on GitHub.

5788

},

5789

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

5790

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

5791

# contained within with a finding of an infoType from this list. For

5792

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

5793

# `exclusion_rule` containing `exclude_info_types.info_types` with

5794

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

5795

# with EMAIL_ADDRESS finding.

5796

# That leads to "555-222-2222@example.org" to generate only a single

5797

# finding, namely email address.

5798

{ # Type of information detected by the API.

5799

"name": "A String", # Name of the information type. Either a name of your choosing when

5800

# creating a CustomInfoType, or one of the names listed

5801

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5802

# a built-in type. InfoType names should conform to the pattern

5803

# `[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]

5808

},

5809

},

5810

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5811

},

5812

],

5813

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

5814

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

5815

# When set within `InspectJobConfig`,

5816

# the maximum returned is 2000 regardless if this is set higher.

5817

# When set within `InspectContentRequest`, this field is ignored.

5818

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

5819

{ # Max findings configuration per infoType, per content item or long

5820

# running DlpJob.

5821

"maxFindings": 42, # Max findings limit for the given infoType.

5822

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

5823

# info_type should be provided. If InfoTypeLimit does not have an

5824

# info_type, the DLP API applies the limit against all info_types that

5825

# are found but not specified in another InfoTypeLimit.

5826

"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]

5827

# creating a CustomInfoType, or one of the names listed

5828

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5829

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5830

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5831

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5832

},

5833

],

5834

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

5835

# When set within `InspectContentRequest`, the maximum returned is 2000

5836

# regardless if this is set higher.

5837

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5838

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5839

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5840

{ # A task to execute on the completion of a job.

5841

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5842

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

5843

# Command Center (CSCC Alpha).

5844

# This action is only available for projects which are parts of

5845

# an organization and whitelisted for the alpha Cloud Security Command

5846

# Center.

5847

# The action will publish count of finding instances and their info types.

5848

# The summary of findings will be persisted in CSCC and are governed by CSCC

5849

# service-specific policy, see https://cloud.google.com/terms/service-terms

5850

# Only a single instance of this action can be specified.

5851

# Compatible with: Inspect

5852

},

5853

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

5854

# completion/failure.

5855

# completion/failure.

5856

},

5857

"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]

5858

# OutputStorageConfig. Only a single instance of this action can be

5859

# specified.

5860

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5861

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5862

"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]

5863

# dataset. If table_id is not set a new one will be generated

5864

# for you with the following format:

5865

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

5866

# generating the date details.

5867

#

5868

# For Inspect, each column in an existing output table must have the same

5869

# name, type, and mode of a field in the `Finding` object.

5870

#

5871

# For Risk, an existing output table should be the output of a previous

5872

# Risk analysis job run on the same source table, with the same privacy

5873

# metric and quasi-identifiers. Risk jobs that analyze the same table but

5874

# compute a different privacy metric, or use different sets of

5875

# quasi-identifiers, cannot store their results in the same table.

5876

# identified by its project_id, dataset_id, and table_name. Within a query

5877

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5878

# `<project_id>:<dataset_id>.<table_id>` or

5879

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5880

"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]

5881

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5882

"datasetId": "A String", # Dataset ID of the table.

5883

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5884

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5885

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

5886

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

5887

# from the `Finding` object. If appending to an existing table, any columns

5888

# from the predefined schema that are missing will be added. No columns in

5889

# the existing table will be deleted.

5890

#

5891

# If unspecified, then all available columns will be used for a new table or

5892

# an (existing) table with no schema, and no changes will be made to an

5893

# existing table that has a schema.

5894

# Only for use with external storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5895

},

5896

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5897

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

5898

# message contains a single field, `DlpJobName`, which is equal to the

5899

# finished job's

5900

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

5901

# Compatible with: Inspect, Risk

5902

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

5903

# publishing access rights to the DLP API service account executing

5904

# the long running DlpJob sending the notifications.

5905

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5906

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5907

"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]

5908

# results of the DlpJob will be applied to the entry for the resource scanned

5909

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

5910

# be deleted. InfoType naming patterns are strictly enforced when using this

5911

# feature. Note that the findings will be persisted in Cloud Data Catalog

5912

# storage and are governed by Data Catalog service-specific policy, see

5913

# https://cloud.google.com/terms/service-terms

5914

# Only a single instance of this action can be specified and only allowed if

5915

# all resources being scanned are BigQuery tables.

5916

# Compatible with: Inspect

5917

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5918

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

5919

# will publish a metric to stack driver on each infotype requested and

5920

# how many findings were found for it. CustomDetectors will be bucketed

5921

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5922

},

5923

},

5924

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5925

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5926

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

5927

# Early access feature is in a pre-release state and might change or have

5928

# limited support. For more information, see

5929

# https://cloud.google.com/products#product-launch-stages.

5930

# of Google Cloud Platform.

5931

"labels": { # To organize findings, these labels will be added to each finding.

5932

#

5933

# Label keys must be between 1 and 63 characters long and must conform

5934

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

5935

#

5936

# Label values must be between 0 and 63 characters long and must conform

5937

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

5938

#

5939

# No more than 10 labels can be associated with a given finding.

5940

#

5941

# Examples:

5942

# * `"environment" : "production"`

5943

# * `"pipeline" : "etl"`

5944

"a_key": "A String",

5945

},

5946

"description": "A String", # A short description of where the data is coming from. Will be stored once

5947

# in the job. 256 max length.

5948

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

5949

# meaningful such as the columns that are primary keys.

5950

"identifyingFields": [ # The columns that are the primary keys for table objects included in

5951

# ContentItem. A copy of this cell's value will stored alongside alongside

5952

# each finding so that the finding can be traced to the specific row it came

5953

# from. No more than 3 may be provided.

5954

{ # General identifier of a data field in a storage service.

5955

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

5960

# 'finding_labels' map. Request may contain others, but any missing one of

5961

# these will be rejected.

5962

#

5963

# Label keys must be between 1 and 63 characters long and must conform

5964

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

5965

#

5966

# No more than 10 keys can be required.

5967

"A String",

5968

],

5969

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5970

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

5971

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

5972

# by project and namespace, however the namespace ID may be empty.

5973

# A partition ID identifies a grouping of entities. The grouping is always

5974

# by project and namespace, however the namespace ID may be empty.

5975

#

5976

# A partition ID contains several dimensions:

5977

# project ID and namespace ID.

5978

"projectId": "A String", # The ID of the project to which the entities belong.

5979

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

5980

},

5981

"kind": { # A representation of a Datastore kind. # The kind to process.

5982

"name": "A String", # The name of the kind.

5983

},

5984

},

5985

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

5986

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

5987

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

5988

# Used for data sources like Datastore and BigQuery.

5989

#

5990

# For BigQuery:

5991

# Required to filter out rows based on the given start and

5992

# end times. If not specified and the table was modified between the given

5993

# start and end times, the entire table will be scanned.

5994

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

5995

# `TIMESTAMP`, or `DATETIME` BigQuery column.

5996

#

5997

# For Datastore.

5998

# Valid data types of the timestamp field are: `TIMESTAMP`.

5999

# Datastore entity will be scanned if the timestamp property does not

6000

# exist or its value is empty or invalid.

6001

"name": "A String", # Name describing the field.

6002

},

6003

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

6004

# a valid start_time to avoid scanning files that have not been modified

6005

# since the last time the JobTrigger executed. This will be based on the

6006

# time of the execution of the last run of the JobTrigger.

6007

"endTime": "A String", # Exclude files or rows newer than this value.

6008

# If set to zero, no upper time limit is applied.

6009

"startTime": "A String", # Exclude files or rows older than this value.

6010

},

6011

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

6012

# bucket.

6013

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

6014

# than this value then the rest of the bytes are omitted. Only one

6015

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

6016

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

6017

"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

6018

# `regex_file_set` must be set.

6019

# expressions are used to allow fine-grained control over which files in the

6020

# bucket to include.

6021

#

6022

# Included files are those that match at least one item in `include_regex` and

6023

# do not match any items in `exclude_regex`. Note that a file that matches

6024

# items from both lists will _not_ be included. For a match to occur, the

6025

# entire file path (i.e., everything in the url after the bucket name) must

6026

# match the regular expression.

6027

#

6028

# For example, given the input `{bucket_name: "mybucket", include_regex:

6029

# ["directory1/.*"], exclude_regex:

6030

# ["directory1/excluded.*"]}`:

6031

#

6032

# * `gs://mybucket/directory1/myfile` will be included

6033

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

6034

# across `/`)

6035

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

6036

# full path doesn't match any items in `include_regex`)

6037

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

6038

# matches an item in `exclude_regex`)

6039

#

6040

# If `include_regex` is left empty, it will match all files by default

6041

# (this is equivalent to setting `include_regex: [".*"]`).

6042

#

6043

# Some other common use cases:

6044

#

6045

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

6046

# files in `mybucket` except for .pdf files

6047

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

6048

# include all files directly under `gs://mybucket/directory/`, without matching

6049

# across `/`

6050

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

6051

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

6052

# the bucket that match at least one of these regular expressions will be

6053

# included in the set of files, except for those that also match an item in

6054

# `exclude_regex`. Leaving this field empty will match all files by default

6055

# (this is equivalent to including `.*` in the list).

6056

#

6057

# Regular expressions use RE2

6058

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

6059

# under the google/re2 repository on GitHub.

6060

"A String",

6061

],

6062

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

6063

# the bucket that match at least one of these regular expressions will be

6064

# excluded from the scan.

6065

#

6066

# Regular expressions use RE2

6067

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

6068

# 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

6073

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

6074

#

6075

# If the url ends in a trailing slash, the bucket or directory represented

6076

# by the url will be scanned non-recursively (content in sub-directories

6077

# will not be scanned). This means that `gs://mybucket/` is equivalent to

6078

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

6079

# `gs://mybucket/directory/*`.

6080

#

6081

# Exactly one of `url` or `regex_file_set` must be set.

6082

},

6083

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

6084

# Number of files scanned is rounded down. Must be between 0 and 100,

6085

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

6086

"fileTypes": [ # List of file type groups to include in the scan.

6087

# If empty, all files are scanned and available data format processors

6088

# are applied. In addition, the binary content of the selected files

6089

# is always scanned as well.

6090

# Images are scanned only as binary if the specified region

6091

# does not support image inspection and no file_types were specified.

6092

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

6093

"A String",

6094

],

6095

"sampleMethod": "A String",

6096

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

6097

# number of bytes scanned is rounded down. Must be between 0 and 100,

6098

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

6099

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

6100

},

6101

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

6102

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

6103

# identified by its project_id, dataset_id, and table_name. Within a query

6104

# a table is often referenced with a string in the format of:

6105

# `<project_id>:<dataset_id>.<table_id>` or

6106

# `<project_id>.<dataset_id>.<table_id>`.

6107

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

6108

# If omitted, project ID is inferred from the API call.

6109

"datasetId": "A String", # Dataset ID of the table.

6110

"tableId": "A String", # Name of the table.

6111

},

6112

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

6113

# `actions.saveFindings.outputConfig.table` is specified, the values of

6114

# columns specified here are available in the output table under

6115

# `location.content_locations.record_location.record_key.id_values`. Nested

6116

# fields such as `person.birthdate.year` are allowed.

6117

{ # General identifier of a data field in a storage service.

6118

"name": "A String", # Name describing the field.

6119

},

6120

],

6121

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

6122

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

6123

# 100 means no limit. Defaults to 0. Only one of rows_limit and

6124

# rows_limit_percent can be specified. Cannot be used in conjunction with

6125

# TimespanConfig.

6126

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

6127

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

6128

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

6129

# Cannot be used in conjunction with TimespanConfig.

6130

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

6131

# inspection of entire columns which you know have no findings.

6132

{ # General identifier of a data field in a storage service.

6133

"name": "A String", # Name describing the field.

6134

},

6135

],

6136

"sampleMethod": "A String",

6137

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6138

},

6139

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

6140

# `inspect_config` will be merged into the values persisted as part of the

6141

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6142

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6143

"status": "A String", # Required. A status for this trigger.

Bu Sun Kim