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

2020-07-22 17:02:09 -0700

[diff] [blame]

90

<code><a href="#list">list(parent, filter=None, locationId=None, pageSize=None, pageToken=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

2020-07-22 17:02:09 -0700

[diff] [blame]

122

"errors": [ # A stream of errors encountered running the job.

123

{ # Details information about an error encountered during job execution or

124

# the results of an unsuccessful activation of the JobTrigger.

125

"timestamps": [ # The times the error occurred.

126

"A String",

127

],

128

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

129

# different programming environments, including REST APIs and RPC APIs. It is

130

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

131

# three pieces of data: error code, error message, and error details.

132

#

133

# You can find out more about this error model and how to work with it in the

134

# [API Design Guide](https://cloud.google.com/apis/design/errors).

135

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

136

"details": [ # A list of messages that carry the error details. There is a common set of

137

# message types for APIs to use.

138

{

139

"a_key": "", # Properties of the object. Contains field @type with type URL.

Bu Sun Kim

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

[diff] [blame]

140

},

141

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

142

"message": "A String", # A developer-facing error message, which should be in English. Any

143

# user-facing error message should be localized and sent in the

144

# google.rpc.Status.details field, or localized by the client.

},

},

],

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

149

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

150

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

151

"kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an # K-map result

152

# estimation, not exact values.

153

"kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value

154

# doesn't correspond to any such interval, the associated frequency is

155

# zero. For example, the following records:

156

# {min_anonymity: 1, max_anonymity: 1, frequency: 17}

157

# {min_anonymity: 2, max_anonymity: 3, frequency: 42}

158

# {min_anonymity: 5, max_anonymity: 10, frequency: 99}

159

# mean that there are no record with an estimated anonymity of 4, 5, or

160

# larger than 10.

161

{ # 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

166

# to 3, 4 or 5 people in the overlying population. An important particular

167

# case is when min_anonymity = max_anonymity = 1: the frequency field then

168

# corresponds to the number of uniquely identifiable records.

169

"maxAnonymity": "A String", # Always greater than or equal to min_anonymity.

170

"bucketSize": "A String", # Number of records within these anonymity bounds.

171

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

172

"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total

173

# number of classes returned per bucket is capped at 20.

174

{ # A tuple of values for the quasi-identifier columns.

175

"estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values.

176

"quasiIdsValues": [ # The quasi-identifier values.

177

{ # Set of primitive values supported by the system.

178

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

179

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

180

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

181

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

182

# int64 only holds up to 8 bytes of data.

183

"integerValue": "A String", # integer

184

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

185

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

186

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

187

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

188

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

189

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

190

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

191

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

192

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

193

},

194

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

195

"floatValue": 3.14, # float

196

"stringValue": "A String", # string

197

"timestampValue": "A String", # timestamp

198

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

199

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

200

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

201

#

202

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

203

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

204

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

205

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

206

#

207

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

208

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

209

# month and day.

210

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

211

# a year.

212

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

213

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

214

# significant.

215

},

216

"booleanValue": True or False, # boolean

Bu Sun Kim

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

[diff] [blame]

217

},

218

],

219

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

220

],

221

"minAnonymity": "A String", # Always positive.

Bu Sun Kim

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

[diff] [blame]

222

},

223

],

224

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

225

"deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an # Delta-presence result

226

# estimation, not exact values.

227

"deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a

228

# value doesn't correspond to any such interval, the associated frequency

229

# is zero. For example, the following records:

230

# {min_probability: 0, max_probability: 0.1, frequency: 17}

231

# {min_probability: 0.2, max_probability: 0.3, frequency: 42}

232

# {min_probability: 0.3, max_probability: 0.4, frequency: 99}

233

# mean that there are no record with an estimated probability in [0.1, 0.2)

234

# nor larger or equal to 0.4.

235

{ # A DeltaPresenceEstimationHistogramBucket message with the following

236

# values:

237

# min_probability: 0.1

238

# max_probability: 0.2

239

# frequency: 42

240

# means that there are 42 records for which δ is in [0.1, 0.2). An

241

# important particular case is when min_probability = max_probability = 1:

242

# then, every individual who shares this quasi-identifier combination is in

243

# the dataset.

244

"maxProbability": 3.14, # Always greater than or equal to min_probability.

245

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

246

"bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total

247

# number of classes returned per bucket is capped at 20.

248

{ # A tuple of values for the quasi-identifier columns.

249

"estimatedProbability": 3.14, # The estimated probability that a given individual sharing these

250

# quasi-identifier values is in the dataset. This value, typically called

251

# δ, is the ratio between the number of records in the dataset with these

252

# quasi-identifier values, and the total number of individuals (inside

253

# *and* outside the dataset) with these quasi-identifier values.

254

# For example, if there are 15 individuals in the dataset who share the

255

# same quasi-identifier values, and an estimated 100 people in the entire

256

# population with these values, then δ is 0.15.

257

"quasiIdsValues": [ # The quasi-identifier values.

258

{ # Set of primitive values supported by the system.

259

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

260

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

261

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

262

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

263

# int64 only holds up to 8 bytes of data.

264

"integerValue": "A String", # integer

265

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

266

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

267

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

268

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

269

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

270

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

271

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

272

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

273

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

274

},

275

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

276

"floatValue": 3.14, # float

277

"stringValue": "A String", # string

278

"timestampValue": "A String", # timestamp

279

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

280

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

281

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

282

#

283

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

284

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

285

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

286

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

287

#

288

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

289

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

290

# month and day.

291

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

292

# a year.

293

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

294

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

295

# significant.

296

},

297

"booleanValue": True or False, # boolean

},

],

},

],

"minProbability": 3.14, # Between 0 and 1.

303

"bucketSize": "A String", # Number of records within these probability bounds.

},

],

},

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

308

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

309

{ # Histogram of value frequencies in the column.

310

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

311

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

312

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

313

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

314

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

315

# values returned per bucket is capped at 20.

316

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

317

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

318

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

319

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

320

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

321

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

322

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

323

# int64 only holds up to 8 bytes of data.

324

"integerValue": "A String", # integer

325

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

326

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

327

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

328

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

329

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

330

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

331

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

332

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

333

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

334

},

335

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

336

"floatValue": 3.14, # float

337

"stringValue": "A String", # string

338

"timestampValue": "A String", # timestamp

339

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

340

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

341

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

342

#

343

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

344

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

345

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

346

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

347

#

348

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

349

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

350

# month and day.

351

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

352

# a year.

353

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

354

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

355

# significant.

356

},

357

"booleanValue": True or False, # boolean

},

},

],

},

],

},

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

365

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

366

# sized buckets.

367

{ # Set of primitive values supported by the system.

368

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

369

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

370

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

371

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

372

# int64 only holds up to 8 bytes of data.

373

"integerValue": "A String", # integer

374

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

375

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

376

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

377

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

378

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

379

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

380

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

381

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

382

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

383

},

384

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

385

"floatValue": 3.14, # float

386

"stringValue": "A String", # string

387

"timestampValue": "A String", # timestamp

388

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

389

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

390

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

391

#

392

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

393

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

394

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

395

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

396

#

397

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

398

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

399

# month and day.

400

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

401

# a year.

402

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

403

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

404

# significant.

405

},

406

"booleanValue": True or False, # boolean

407

},

408

],

409

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

410

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

411

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

412

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

413

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

414

# int64 only holds up to 8 bytes of data.

415

"integerValue": "A String", # integer

416

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

417

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

418

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

419

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

420

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

421

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

422

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

423

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

424

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

425

},

426

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

427

"floatValue": 3.14, # float

428

"stringValue": "A String", # string

429

"timestampValue": "A String", # timestamp

430

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

431

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

432

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

433

#

434

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

435

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

436

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

437

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

438

#

439

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

440

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

441

# month and day.

442

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

443

# a year.

444

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

445

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

446

# significant.

447

},

448

"booleanValue": True or False, # boolean

449

},

450

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

451

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

452

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

453

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

454

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

455

# int64 only holds up to 8 bytes of data.

456

"integerValue": "A String", # integer

457

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

458

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

459

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

460

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

461

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

462

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

463

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

464

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

465

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

466

},

467

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

468

"floatValue": 3.14, # float

469

"stringValue": "A String", # string

470

"timestampValue": "A String", # timestamp

471

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

472

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

473

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

474

#

475

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

476

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

477

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

478

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

479

#

480

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

481

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

482

# month and day.

483

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

484

# a year.

485

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

486

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

487

# significant.

488

},

489

"booleanValue": True or False, # boolean

490

},

491

},

492

"kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result

493

"equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.

494

{ # Histogram of k-anonymity equivalence classes.

495

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

496

# classes returned per bucket is capped at 20.

497

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

498

"quasiIdsValues": [ # Set of values defining the equivalence class. One value per

499

# quasi-identifier column in the original KAnonymity metric message.

500

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

501

{ # Set of primitive values supported by the system.

502

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

503

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

504

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

505

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

506

# int64 only holds up to 8 bytes of data.

507

"integerValue": "A String", # integer

508

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

509

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

510

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

511

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

512

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

513

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

514

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

515

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

516

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

517

},

518

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

519

"floatValue": 3.14, # float

520

"stringValue": "A String", # string

521

"timestampValue": "A String", # timestamp

522

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

523

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

524

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

525

#

526

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

527

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

528

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

529

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

530

#

531

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

532

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

533

# month and day.

534

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

535

# a year.

536

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

537

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

538

# significant.

539

},

540

"booleanValue": True or False, # boolean

541

},

542

],

543

"equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the

544

# above set of values.

545

},

546

],

547

"equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket.

548

"equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket.

549

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

550

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

551

},

552

],

553

},

Bu Sun Kim

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

[diff] [blame]

554

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

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

555

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

556

# number of distinct values and value count distribution.

557

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

558

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

559

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

560

# depending on the data.

561

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

562

},

563

},

564

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

565

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

566

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

567

},

568

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

569

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

570

# specified, they are considered a single composite key.

571

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

572

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

},

],

},

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

577

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

578

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

579

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

580

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

581

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

Bu Sun Kim

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

[diff] [blame]

582

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

583

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

584

# US_ZIP_5) or a region code.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

585

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

586

# same tag.

587

{ # A column with a semantic tag attached.

588

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

589

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

590

},

591

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

592

# indicate an auxiliary table that contains statistical information on

593

# the possible values of this column (below).

594

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

595

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

596

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

597

# To programmatically obtain the list of supported InfoTypes, use

598

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

599

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

600

# creating a CustomInfoType, or one of the names listed

601

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

602

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

603

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

604

},

605

"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

606

# the distribution of values in the input data

607

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

608

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

609

#

610

# service Foo {

611

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

612

# }

613

#

614

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

615

},

616

},

617

],

Bu Sun Kim

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

[diff] [blame]

618

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

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

619

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

620

# of one auxiliary table.

621

{ # An auxiliary table contains statistical information on the relative

Bu Sun Kim

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

[diff] [blame]

622

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

623

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

624

# frequency of each quasi-identifier tuple.

625

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

626

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

627

# tuple is highly reidentifiable).

Bu Sun Kim

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

[diff] [blame]

628

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

629

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

630

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

631

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

632

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

633

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

634

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

635

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

636

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

637

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

638

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

639

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

640

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

641

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

642

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

643

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

644

},

645

},

646

],

Bu Sun Kim

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

[diff] [blame]

647

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

648

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

649

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

650

},

651

},

652

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

653

},

654

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

655

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

656

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

657

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

Bu Sun Kim

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

[diff] [blame]

658

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

659

# same tag.

660

{ # A column with a semantic tag attached.

661

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

662

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

663

},

664

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

665

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

666

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

667

# To programmatically obtain the list of supported InfoTypes, use

668

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

669

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

670

# creating a CustomInfoType, or one of the names listed

671

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

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

672

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

673

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

Bu Sun Kim

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

[diff] [blame]

674

},

675

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

676

# indicate an auxiliary table that contains statistical information on

677

# the possible values of this column (below).

678

"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

679

# the distribution of values in the input data

680

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

681

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

682

#

683

# service Foo {

684

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

685

# }

686

#

687

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

688

},

689

},

690

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

691

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

692

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

693

# field of one auxiliary table.

694

{ # An auxiliary table containing statistical information on the relative

695

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

696

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

697

# frequency of each quasi-identifier tuple.

698

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

699

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

700

# tuple is highly reidentifiable).

701

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

702

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

703

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

704

},

705

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

706

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

707

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

708

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

709

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

710

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

711

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

712

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

713

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

714

},

715

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

716

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

717

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

718

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

719

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

720

},

721

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

722

# indicate an auxiliary table that contains statistical information on

723

# the possible values of this column (below).

},

],

},

],

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

729

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

730

# US_ZIP_5) or a region code.

Bu Sun Kim

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

[diff] [blame]

731

},

732

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

Bu Sun Kim

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

[diff] [blame]

733

"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

734

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

735

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

736

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

737

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

738

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

739

#

740

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

741

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

742

# might be ignored.

743

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

744

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

745

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

746

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

747

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

748

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

749

},

750

},

Bu Sun Kim

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

[diff] [blame]

751

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

752

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

753

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

754

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

755

# a repeated field.

756

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

757

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

758

},

759

],

Bu Sun Kim

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

[diff] [blame]

760

},

761

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

762

# min, max, and quantiles.

763

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

764

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

765

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

766

},

767

},

Bu Sun Kim

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

[diff] [blame]

768

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

769

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

770

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

771

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

772

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

Bu Sun Kim

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

[diff] [blame]

773

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

774

# classes returned per bucket is capped at 20.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

775

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

776

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

777

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

Bu Sun Kim

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

[diff] [blame]

778

{ # Set of primitive values supported by the system.

779

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

780

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

781

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

782

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

783

# int64 only holds up to 8 bytes of data.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

784

"integerValue": "A String", # integer

785

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

786

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

787

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

788

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

789

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

790

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

791

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

792

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

793

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

794

},

795

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

796

"floatValue": 3.14, # float

797

"stringValue": "A String", # string

Bu Sun Kim

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

[diff] [blame]

798

"timestampValue": "A String", # timestamp

799

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

800

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

801

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

802

#

803

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

804

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

805

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

806

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

807

#

808

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

Bu Sun Kim

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

[diff] [blame]

809

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

810

# month and day.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

811

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

812

# a year.

Bu Sun Kim

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

[diff] [blame]

813

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

814

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

815

# significant.

816

},

Bu Sun Kim

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

[diff] [blame]

817

"booleanValue": True or False, # boolean

Bu Sun Kim

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

[diff] [blame]

818

},

819

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

820

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

821

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

822

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

823

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

824

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

825

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

826

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

827

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

828

# int64 only holds up to 8 bytes of data.

829

"integerValue": "A String", # integer

830

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

831

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

832

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

833

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

834

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

835

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

836

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

837

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

838

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

839

},

840

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

841

"floatValue": 3.14, # float

842

"stringValue": "A String", # string

843

"timestampValue": "A String", # timestamp

844

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

845

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

846

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

847

#

848

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

849

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

850

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

851

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

852

#

853

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

854

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

855

# month and day.

856

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

857

# a year.

858

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

859

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

860

# significant.

861

},

862

"booleanValue": True or False, # boolean

},

},

],

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

867

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

Bu Sun Kim

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

[diff] [blame]

868

},

869

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

870

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

871

# classes in this bucket.

Bu Sun Kim

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

[diff] [blame]

872

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

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

873

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

874

# classes in this bucket.

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.

879

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

880

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

881

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

882

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

883

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

884

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

885

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

886

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

887

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

888

},

889

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

890

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

891

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

892

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

893

# instantiated the job.

894

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

895

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

896

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

897

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

898

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

899

# template.

900

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

901

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

902

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

903

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

904

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

905

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

906

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

907

},

908

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

909

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

910

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

911

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

912

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

913

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

914

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

915

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

916

# all resources being scanned are BigQuery tables.

917

# Compatible with: Inspect

918

},

919

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

920

# completion/failure.

921

# completion/failure.

922

},

923

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

924

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

925

# finished job's

926

# [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

927

# Compatible with: Inspect, Risk

928

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

929

# publishing access rights to the DLP API service account executing

930

# the long running DlpJob sending the notifications.

931

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

932

},

933

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

934

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

935

# specified.

936

# Compatible with: Inspect, Risk

937

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

938

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

939

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

940

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

941

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

942

# the existing table will be deleted.

943

#

944

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

945

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

946

# existing table that has a schema.

947

# Only for use with external storage.

948

"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

949

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

950

# for you with the following format:

951

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

952

# generating the date details.

953

#

954

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

955

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

956

#

957

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

958

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

959

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

960

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

961

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

962

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

963

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

964

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

965

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

966

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

967

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

968

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

969

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

},

},

},

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

974

# Command Center (CSCC Alpha).

975

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

976

# an organization and whitelisted for the alpha Cloud Security Command

977

# Center.

978

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

979

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

980

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

981

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

982

# Compatible with: Inspect

983

},

Bu Sun Kim

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

[diff] [blame]

984

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

985

],

986

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

987

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

988

# bucket.

989

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

990

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

991

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

992

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

993

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

994

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

995

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

996

# is always scanned as well.

997

# Images are scanned only as binary if the specified region

998

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

999

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

1000

"A String",

1001

],

1002

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

1003

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

1004

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

1005

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

1006

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

1007

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

1008

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

1009

"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

1010

# `regex_file_set` must be set.

1011

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

1012

# bucket to include.

1013

#

1014

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

1015

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

1016

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

1017

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

1018

# match the regular expression.

1019

#

1020

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

1021

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

1022

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

1023

#

1024

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

1025

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

1026

# across `/`)

1027

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

1028

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

1029

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

1030

# matches an item in `exclude_regex`)

1031

#

1032

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

1033

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

1034

#

1035

# Some other common use cases:

1036

#

1037

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

1038

# files in `mybucket` except for .pdf files

1039

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

1040

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

1041

# across `/`

1042

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

1043

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

1044

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

1045

# excluded from the scan.

1046

#

1047

# Regular expressions use RE2

1048

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

1049

# under the google/re2 repository on GitHub.

1050

"A String",

1051

],

1052

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

1053

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

1054

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

1055

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

1056

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

1057

#

1058

# Regular expressions use RE2

1059

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

1060

# 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

1065

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

1066

#

1067

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

1068

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

1069

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

1070

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

1071

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

1072

#

1073

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

1074

},

1075

"sampleMethod": "A String",

Bu Sun Kim

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

[diff] [blame]

1076

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1077

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

1078

"sampleMethod": "A String",

1079

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

1080

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

1081

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

1082

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

1083

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

1084

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

1085

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

1086

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

1087

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

1088

},

1089

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

1090

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

1091

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

1092

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

1093

# TimespanConfig.

1094

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

1095

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

1096

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

1097

# Cannot be used in conjunction with TimespanConfig.

1098

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

1099

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

1100

# columns specified here are available in the output table under

1101

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

1102

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

1103

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

1104

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

1105

},

1106

],

1107

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

1108

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

1109

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

1110

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

},

],

},

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

1115

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

1116

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

1117

# Used for data sources like Datastore and BigQuery.

1118

#

1119

# For BigQuery:

1120

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

1121

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

1122

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

1123

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

1124

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

1125

#

1126

# For Datastore.

1127

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

1128

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

1129

# exist or its value is empty or invalid.

1130

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

1131

},

1132

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

1133

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

1134

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

1135

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

1136

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

1137

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

1138

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

1139

},

1140

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

1141

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

1142

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

1143

},

1144

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

1145

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

1146

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

1147

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

1148

#

1149

# A partition ID contains several dimensions:

1150

# project ID and namespace ID.

1151

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

1152

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

1153

},

1154

},

1155

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

1156

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

1157

# limited support. For more information, see

1158

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

1159

# of Google Cloud Platform.

1160

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

1161

# meaningful such as the columns that are primary keys.

1162

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

1163

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

1164

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

1165

# from. No more than 3 may be provided.

1166

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

1167

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

},

],

},

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

1172

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

1173

# these will be rejected.

1174

#

1175

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

1176

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

1177

#

1178

# No more than 10 keys can be required.

1179

"A String",

1180

],

1181

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

1182

#

1183

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

1184

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

1185

#

1186

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

1187

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

1188

#

1189

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

1190

#

1191

# Examples:

1192

# * `"environment" : "production"`

1193

# * `"pipeline" : "etl"`

1194

"a_key": "A String",

1195

},

1196

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

1197

# in the job. 256 max length.

1198

},

Bu Sun Kim

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

[diff] [blame]

1199

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1200

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

1201

# When used with redactContent only info_types and min_likelihood are currently

1202

# used.

1203

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

1204

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

1205

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

1206

# sensitive information configurable to the data in question.

1207

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

1208

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

1209

# of employee IDs or job titles.

1210

#

1211

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

1212

# and digits in the unicode [Basic Multilingual

1213

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

1214

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

1215

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

1216

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

1217

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

1218

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

1219

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

1220

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

1221

# matches for "jennifer".

1222

#

1223

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

1224

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

1225

# are treated as whitespace. The

1226

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

1227

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

1228

# these constraints, consider using `LargeCustomDictionaryConfig` in the

1229

# `StoredInfoType` API.

1230

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

1231

# is accepted.

1232

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

1233

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

1234

},

1235

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

1236

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

1237

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

1238

# that are letters or digits. [required]

"A String",

],

},

},

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

1244

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

1245

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

1246

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

1247

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

1248

# as a custom info type.

1249

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

1250

# creating a CustomInfoType, or one of the names listed

1251

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

1252

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

1253

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

1254

},

1255

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

1256

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

1257

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

1258

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

1259

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

1260

# `surrogate_type` CustomInfoType.

1261

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

1262

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

1263

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

1264

# custom infoType.

1265

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

1266

# proximity of hotwords.

1267

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

1268

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

1269

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

1270

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

1271

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

1272

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

1273

# a company office using the hotword regex "$xxx$", where "xxx"

1274

# is the area code in question.

1275

# rule.

1276

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

1277

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

Bu Sun Kim

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

[diff] [blame]

1278

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1279

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

1280

# part of a detection rule.

1281

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

1282

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

1283

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

1284

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

1285

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

1286

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

1287

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

1288

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

1289

# a final likelihood of `LIKELY`.

Bu Sun Kim

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

[diff] [blame]

1290

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1291

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

1292

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

1293

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

1294

42,

1295

],

1296

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

1297

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

1298

# google/re2 repository on GitHub.

1299

},

Bu Sun Kim

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

[diff] [blame]

1300

},

1301

},

1302

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1303

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

1304

# support reversing.

1305

# such as

1306

# [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

1307

# These types of transformations are

1308

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

1309

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

1310

# transformation such as `surrogate_info_type`. This CustomInfoType does

1311

# not support the use of `detection_rules`.

1312

},

1313

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

1314

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

1315

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

1316

42,

1317

],

1318

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

1319

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

1320

# google/re2 repository on GitHub.

1321

},

1322

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

1323

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

1324

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

1325

# `organizations/433245324/storedInfoTypes/432452342` or

1326

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

1327

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

1328

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

1329

},

1330

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

1331

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

Bu Sun Kim

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

[diff] [blame]

1332

},

1333

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1334

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

1335

# POSSIBLE.

1336

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

1337

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

1338

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

1339

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

1340

# regardless if this is set higher.

1341

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

1342

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

1343

# running DlpJob.

1344

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

1345

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

1346

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

1347

# are found but not specified in another InfoTypeLimit.

1348

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

1349

# creating a CustomInfoType, or one of the names listed

1350

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

1351

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

1352

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

1353

},

1354

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

1355

},

1356

],

1357

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

1358

# When set within `InspectJobConfig`,

1359

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

1360

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

1361

},

1362

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

1363

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

1364

# included in the response; see Finding.quote.

1365

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

1366

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

1367

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

1368

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

1369

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

1370

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

1371

{ # Type of information detected by the API.

1372

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

1373

# creating a CustomInfoType, or one of the names listed

1374

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

1375

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

1376

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

1377

},

1378

],

1379

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

1380

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

1381

# `InspectionRuleSet`.

1382

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

1383

# proximity of hotwords.

1384

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

1385

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

1386

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

1387

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

1388

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

1389

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

1390

# a company office using the hotword regex "$xxx$", where "xxx"

1391

# is the area code in question.

1392

# rule.

1393

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

1394

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

1395

},

1396

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

1397

# part of a detection rule.

1398

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

1399

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

1400

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

1401

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

1402

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

1403

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

1404

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

1405

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

1406

# a final likelihood of `LIKELY`.

1407

},

1408

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

1409

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

1410

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

1411

42,

1412

],

1413

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

1414

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

1415

# google/re2 repository on GitHub.

1416

},

1417

},

1418

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

1419

# `InspectionRuleSet` are removed from results.

1420

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

1421

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

1422

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

1423

# of employee IDs or job titles.

1424

#

1425

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

1426

# and digits in the unicode [Basic Multilingual

1427

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

1428

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

1429

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

1430

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

1431

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

1432

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

1433

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

1434

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

1435

# matches for "jennifer".

1436

#

1437

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

1438

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

1439

# are treated as whitespace. The

1440

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

1441

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

1442

# these constraints, consider using `LargeCustomDictionaryConfig` in the

1443

# `StoredInfoType` API.

1444

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

1445

# is accepted.

1446

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

1447

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

1448

},

1449

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

1450

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

1451

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

1452

# that are letters or digits. [required]

"A String",

],

},

},

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

1458

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

1459

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

1460

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

1461

# `exclusion_rule` containing `exclude_info_types.info_types` with

1462

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

1463

# with EMAIL_ADDRESS finding.

1464

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

1465

# finding, namely email address.

1466

{ # Type of information detected by the API.

1467

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

1468

# creating a CustomInfoType, or one of the names listed

1469

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

1470

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

1471

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

},

],

},

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

1476

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

1477

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

1478

42,

1479

],

1480

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

1481

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

1482

# google/re2 repository on GitHub.

},

},

},

],

},

],

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

1490

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

1491

"A String",

1492

],

1493

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

1494

# InfoType values returned by ListInfoTypes or listed at

1495

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

1496

#

1497

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

1498

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

1499

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

1500

#

1501

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

1502

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

1503

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

1504

{ # Type of information detected by the API.

1505

"name": "A String", # Name of the information type. Either a name of your choosing when

1506

# creating a CustomInfoType, or one of the names listed

1507

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1508

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

1509

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

},

],

},

},

"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

1515

# this run.

1516

# to be detected) to be used anywhere you otherwise would normally specify

1517

# InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates

1518

# to learn more.

1519

"description": "A String", # Short description (max 256 chars).

1520

"displayName": "A String", # Display name (max 256 chars).

1521

"createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.

1522

"updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.

1523

"name": "A String", # Output only. The template name.

1524

#

1525

# The template will have one of the following formats:

1526

# `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR

1527

# `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`;

1528

"inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process.

1529

# When used with redactContent only info_types and min_likelihood are currently

1530

# used.

1531

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

1532

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

1533

{ # Custom information type provided by the user. Used to find domain-specific

1534

# sensitive information configurable to the data in question.

1535

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

1536

# be used to match sensitive information specific to the data, such as a list

1537

# of employee IDs or job titles.

1538

#

1539

# Dictionary words are case-insensitive and all characters other than letters

1540

# and digits in the unicode [Basic Multilingual

1541

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

1542

# will be replaced with whitespace when scanning for matches, so the

1543

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

1544

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

1545

# surrounding any match must be of a different type than the adjacent

1546

# characters within the word, so letters must be next to non-letters and

1547

# digits next to non-digits. For example, the dictionary word "jen" will

1548

# match the first three letters of the text "jen123" but will return no

1549

# matches for "jennifer".

1550

#

1551

# Dictionary words containing a large number of characters that are not

1552

# letters or digits may result in unexpected findings because such characters

1553

# are treated as whitespace. The

1554

# [limits](https://cloud.google.com/dlp/limits) page contains details about

1555

# the size limits of dictionaries. For dictionaries that do not fit within

1556

# these constraints, consider using `LargeCustomDictionaryConfig` in the

1557

# `StoredInfoType` API.

1558

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

1559

# is accepted.

1560

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

1561

# Example: gs://[BUCKET_NAME]/dictionary.txt

1562

},

1563

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

1564

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

1565

# at least one phrase and every phrase must contain at least 2 characters

1566

# that are letters or digits. [required]

"A String",

],

},

},

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

1572

# infoType, when the name matches one of existing infoTypes and that infoType

1573

# is specified in `InspectContent.info_types` field. Specifying the latter

1574

# adds findings to the one detected by the system. If built-in info type is

1575

# not specified in `InspectContent.info_types` list then the name is treated

1576

# as a custom info type.

1577

"name": "A String", # Name of the information type. Either a name of your choosing when

1578

# creating a CustomInfoType, or one of the names listed

1579

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1580

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

1581

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

1582

},

1583

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

1584

# altered by a detection rule if the finding meets the criteria specified by

1585

# the rule. Defaults to `VERY_LIKELY` if not specified.

1586

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

1587

# Rules are applied in order that they are specified. Not supported for the

1588

# `surrogate_type` CustomInfoType.

1589

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

1590

# `CustomInfoType` to alter behavior under certain circumstances, depending

1591

# on the specific details of the rule. Not supported for the `surrogate_type`

1592

# custom infoType.

1593

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

1594

# proximity of hotwords.

1595

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

1596

# The total length of the window cannot exceed 1000 characters. Note that

1597

# the finding itself will be included in the window, so that hotwords may

1598

# be used to match substrings of the finding itself. For example, the

1599

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

1600

# adjusted upwards if the area code is known to be the local area code of

1601

# a company office using the hotword regex "$xxx$", where "xxx"

1602

# is the area code in question.

1603

# rule.

1604

"windowAfter": 42, # Number of characters after the finding to consider.

1605

"windowBefore": 42, # Number of characters before the finding to consider.

1606

},

1607

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

1608

# part of a detection rule.

1609

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

1610

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

1611

# levels. For example, if a finding would be `POSSIBLE` without the

1612

# detection rule and `relative_likelihood` is 1, then it is upgraded to

1613

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

1614

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

1615

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

1616

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

1617

# a final likelihood of `LIKELY`.

1618

},

1619

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

1620

"groupIndexes": [ # The index of the submatch to extract as findings. When not

1621

# specified, the entire match is returned. No more than 3 may be included.

1622

42,

1623

],

1624

"pattern": "A String", # Pattern defining the regular expression. Its syntax

1625

# (https://github.com/google/re2/wiki/Syntax) can be found under the

1626

# google/re2 repository on GitHub.

},

},

},

],

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

1632

# support reversing.

1633

# such as

1634

# [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

1635

# These types of transformations are

1636

# those that perform pseudonymization, thereby producing a "surrogate" as

1637

# output. This should be used in conjunction with a field on the

1638

# transformation such as `surrogate_info_type`. This CustomInfoType does

1639

# not support the use of `detection_rules`.

1640

},

1641

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

1642

"groupIndexes": [ # The index of the submatch to extract as findings. When not

1643

# specified, the entire match is returned. No more than 3 may be included.

1644

42,

1645

],

1646

"pattern": "A String", # Pattern defining the regular expression. Its syntax

1647

# (https://github.com/google/re2/wiki/Syntax) can be found under the

1648

# google/re2 repository on GitHub.

1649

},

1650

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

1651

# `InspectDataSource`. Not currently supported in `InspectContent`.

1652

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

1653

# `organizations/433245324/storedInfoTypes/432452342` or

1654

# `projects/project-id/storedInfoTypes/432452342`.

1655

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

1656

# inspection was created. Output-only field, populated by the system.

1657

},

1658

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

1659

# to be returned. It still can be used for rules matching.

1660

},

1661

],

1662

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

1663

# POSSIBLE.

1664

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

1665

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

1666

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

1667

# When set within `InspectContentRequest`, the maximum returned is 2000

1668

# regardless if this is set higher.

1669

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

1670

{ # Max findings configuration per infoType, per content item or long

1671

# running DlpJob.

1672

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

1673

# info_type should be provided. If InfoTypeLimit does not have an

1674

# info_type, the DLP API applies the limit against all info_types that

1675

# are found but not specified in another InfoTypeLimit.

1676

"name": "A String", # Name of the information type. Either a name of your choosing when

1677

# creating a CustomInfoType, or one of the names listed

1678

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1679

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

1680

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

1681

},

1682

"maxFindings": 42, # Max findings limit for the given infoType.

1683

},

1684

],

1685

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

1686

# When set within `InspectJobConfig`,

1687

# the maximum returned is 2000 regardless if this is set higher.

1688

# When set within `InspectContentRequest`, this field is ignored.

1689

},

1690

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

1691

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

1692

# included in the response; see Finding.quote.

1693

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

1694

# Exclusion rules, contained in the set are executed in the end, other

1695

# rules are executed in the order they are specified for each info type.

1696

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

1697

# circumstances, depending on the specific details of the rules within the set.

1698

"infoTypes": [ # List of infoTypes this rule set is applied to.

1699

{ # Type of information detected by the API.

1700

"name": "A String", # Name of the information type. Either a name of your choosing when

1701

# creating a CustomInfoType, or one of the names listed

1702

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1703

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

1704

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

1705

},

1706

],

1707

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

1708

{ # A single inspection rule to be applied to infoTypes, specified in

1709

# `InspectionRuleSet`.

1710

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

1711

# proximity of hotwords.

1712

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

1713

# The total length of the window cannot exceed 1000 characters. Note that

1714

# the finding itself will be included in the window, so that hotwords may

1715

# be used to match substrings of the finding itself. For example, the

1716

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

1717

# adjusted upwards if the area code is known to be the local area code of

1718

# a company office using the hotword regex "$xxx$", where "xxx"

1719

# is the area code in question.

1720

# rule.

1721

"windowAfter": 42, # Number of characters after the finding to consider.

1722

"windowBefore": 42, # Number of characters before the finding to consider.

1723

},

1724

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

1725

# part of a detection rule.

1726

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

1727

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

1728

# levels. For example, if a finding would be `POSSIBLE` without the

1729

# detection rule and `relative_likelihood` is 1, then it is upgraded to

1730

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

1731

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

1732

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

1733

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

1734

# a final likelihood of `LIKELY`.

1735

},

1736

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

1737

"groupIndexes": [ # The index of the submatch to extract as findings. When not

1738

# specified, the entire match is returned. No more than 3 may be included.

1739

42,

1740

],

1741

"pattern": "A String", # Pattern defining the regular expression. Its syntax

1742

# (https://github.com/google/re2/wiki/Syntax) can be found under the

1743

# google/re2 repository on GitHub.

1744

},

1745

},

1746

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

1747

# `InspectionRuleSet` are removed from results.

1748

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

1749

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

1750

# be used to match sensitive information specific to the data, such as a list

1751

# of employee IDs or job titles.

1752

#

1753

# Dictionary words are case-insensitive and all characters other than letters

1754

# and digits in the unicode [Basic Multilingual

1755

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

1756

# will be replaced with whitespace when scanning for matches, so the

1757

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

1758

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

1759

# surrounding any match must be of a different type than the adjacent

1760

# characters within the word, so letters must be next to non-letters and

1761

# digits next to non-digits. For example, the dictionary word "jen" will

1762

# match the first three letters of the text "jen123" but will return no

1763

# matches for "jennifer".

1764

#

1765

# Dictionary words containing a large number of characters that are not

1766

# letters or digits may result in unexpected findings because such characters

1767

# are treated as whitespace. The

1768

# [limits](https://cloud.google.com/dlp/limits) page contains details about

1769

# the size limits of dictionaries. For dictionaries that do not fit within

1770

# these constraints, consider using `LargeCustomDictionaryConfig` in the

1771

# `StoredInfoType` API.

1772

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

1773

# is accepted.

1774

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

1775

# Example: gs://[BUCKET_NAME]/dictionary.txt

1776

},

1777

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

1778

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

1779

# at least one phrase and every phrase must contain at least 2 characters

1780

# that are letters or digits. [required]

"A String",

],

},

},

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

1786

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

1787

# contained within with a finding of an infoType from this list. For

1788

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

1789

# `exclusion_rule` containing `exclude_info_types.info_types` with

1790

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

1791

# with EMAIL_ADDRESS finding.

1792

# That leads to "555-222-2222@example.org" to generate only a single

1793

# finding, namely email address.

1794

{ # Type of information detected by the API.

1795

"name": "A String", # Name of the information type. Either a name of your choosing when

1796

# creating a CustomInfoType, or one of the names listed

1797

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1798

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

1799

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

},

],

},

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

1804

"groupIndexes": [ # The index of the submatch to extract as findings. When not

1805

# specified, the entire match is returned. No more than 3 may be included.

1806

42,

1807

],

1808

"pattern": "A String", # Pattern defining the regular expression. Its syntax

1809

# (https://github.com/google/re2/wiki/Syntax) can be found under the

1810

# google/re2 repository on GitHub.

},

},

},

],

},

],

"contentOptions": [ # List of options defining data content to scan.

1818

# If empty, text, images, and other content will be included.

1819

"A String",

1820

],

1821

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

1822

# InfoType values returned by ListInfoTypes or listed at

1823

# https://cloud.google.com/dlp/docs/infotypes-reference.

1824

#

1825

# When no InfoTypes or CustomInfoTypes are specified in a request, the

1826

# system may automatically choose what detectors to run. By default this may

1827

# be all types, but may change over time as detectors are updated.

1828

#

1829

# If you need precise control and predictability as to what detectors are

1830

# run you should specify specific InfoTypes listed in the reference,

1831

# otherwise a default list will be used, which may change over time.

1832

{ # Type of information detected by the API.

1833

"name": "A String", # Name of the information type. Either a name of your choosing when

1834

# creating a CustomInfoType, or one of the names listed

1835

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1836

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

1837

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

},

],

},

},

},

"result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspect job.

1844

"hybridStats": { # Statistics related to processing hybrid inspect requests. # Statistics related to the processing of hybrid inspect.

1845

# Early access feature is in a pre-release state and might change or have

1846

# limited support. For more information, see

1847

# https://cloud.google.com/products#product-launch-stages.

1848

"processedCount": "A String", # The number of hybrid inspection requests processed within this job.

1849

"abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran

1850

# out of quota or was ended before they could be processed.

1851

"pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated

1852

# when called via method `getDlpJob`.

1853

# A burst of traffic may cause hybrid inspect requests to be enqueued.

1854

# Processing will take place as quickly as possible, but resource limitations

1855

# may impact how long a request is enqueued for.

1856

},

1857

"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.

1858

"infoTypeStats": [ # Statistics of how many instances of each info type were found during

1859

# inspect job.

1860

{ # Statistics regarding a specific InfoType.

1861

"infoType": { # Type of information detected by the API. # The type of finding this stat is for.

1862

"name": "A String", # Name of the information type. Either a name of your choosing when

1863

# creating a CustomInfoType, or one of the names listed

1864

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1865

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

1866

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

1867

},

1868

"count": "A String", # Number of findings for this infoType.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1869

},

1870

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1871

"processedBytes": "A String", # Total size in bytes that were processed.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1872

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1873

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

1874

"name": "A String", # The server-assigned name.

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:

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1885

parent: string, Required. Parent resource name.

1886

- Format:projects/[PROJECT-ID]

1887

- Format:projects/[PROJECT-ID]/locations/[LOCATION-ID] (required)

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1888

body: object, The request body.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1889

The object takes the form of:

1890

1891

{ # Request message for CreateJobTrigger.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1892

"locationId": "A String", # Deprecated. This field has no effect.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1893

"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]

1894

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1895

"status": "A String", # Required. A status for this trigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1896

"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]

1897

# needs to trigger for a job to be started. The list may contain only

1898

# a single Schedule trigger and must have at least one object.

1899

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1900

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

1901

# Early access feature is in a pre-release state and might change or have

1902

# limited support. For more information, see

1903

# https://cloud.google.com/products#product-launch-stages.

1904

# and finished.

1905

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1906

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

1907

"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]

1908

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1909

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1910

# A scheduled start time will be skipped if the previous

1911

# execution has not ended when its scheduled time occurs.

1912

#

1913

# This value must be set to a time duration greater than or equal

1914

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1915

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1916

},

1917

],

1918

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

1919

# errors may result in the JobTrigger automatically being paused.

1920

# Will return the last 100 errors. Whenever the JobTrigger is modified

1921

# this list will be cleared.

1922

{ # Details information about an error encountered during job execution or

1923

# the results of an unsuccessful activation of the JobTrigger.

1924

"timestamps": [ # The times the error occurred.

1925

"A String",

1926

],

1927

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

1928

# different programming environments, including REST APIs and RPC APIs. It is

1929

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

1930

# three pieces of data: error code, error message, and error details.

1931

#

1932

# You can find out more about this error model and how to work with it in the

1933

# [API Design Guide](https://cloud.google.com/apis/design/errors).

1934

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

1935

"details": [ # A list of messages that carry the error details. There is a common set of

1936

# message types for APIs to use.

1937

{

1938

"a_key": "", # Properties of the object. Contains field @type with type URL.

1939

},

1940

],

1941

"message": "A String", # A developer-facing error message, which should be in English. Any

1942

# user-facing error message should be localized and sent in the

1943

# google.rpc.Status.details field, or localized by the client.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1944

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1945

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1946

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1947

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

1948

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1949

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

1950

# `inspect_config` will be merged into the values persisted as part of the

1951

# template.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1952

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1953

{ # A task to execute on the completion of a job.

1954

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1955

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

1956

# will publish a metric to stack driver on each infotype requested and

1957

# how many findings were found for it. CustomDetectors will be bucketed

1958

# as 'Custom' under the Stackdriver label 'info_type'.

1959

},

1960

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

1961

# results of the DlpJob will be applied to the entry for the resource scanned

1962

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

1963

# be deleted. InfoType naming patterns are strictly enforced when using this

1964

# feature. Note that the findings will be persisted in Cloud Data Catalog

1965

# storage and are governed by Data Catalog service-specific policy, see

1966

# https://cloud.google.com/terms/service-terms

1967

# Only a single instance of this action can be specified and only allowed if

1968

# all resources being scanned are BigQuery tables.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1969

# Compatible with: Inspect

1970

},

1971

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

1972

# completion/failure.

1973

# completion/failure.

1974

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1975

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

1976

# message contains a single field, `DlpJobName`, which is equal to the

1977

# finished job's

1978

# [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

1979

# Compatible with: Inspect, Risk

1980

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

1981

# publishing access rights to the DLP API service account executing

1982

# the long running DlpJob sending the notifications.

1983

# Format is projects/{project}/topics/{topic}.

1984

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1985

"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]

1986

# OutputStorageConfig. Only a single instance of this action can be

1987

# specified.

1988

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1989

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

1990

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

1991

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

1992

# from the `Finding` object. If appending to an existing table, any columns

1993

# from the predefined schema that are missing will be added. No columns in

1994

# the existing table will be deleted.

1995

#

1996

# If unspecified, then all available columns will be used for a new table or

1997

# an (existing) table with no schema, and no changes will be made to an

1998

# existing table that has a schema.

1999

# Only for use with external storage.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2000

"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]

2001

# dataset. If table_id is not set a new one will be generated

2002

# for you with the following format:

2003

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

2004

# generating the date details.

2005

#

2006

# For Inspect, each column in an existing output table must have the same

2007

# name, type, and mode of a field in the `Finding` object.

2008

#

2009

# For Risk, an existing output table should be the output of a previous

2010

# Risk analysis job run on the same source table, with the same privacy

2011

# metric and quasi-identifiers. Risk jobs that analyze the same table but

2012

# compute a different privacy metric, or use different sets of

2013

# quasi-identifiers, cannot store their results in the same table.

2014

# identified by its project_id, dataset_id, and table_name. Within a query

2015

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2016

# `<project_id>:<dataset_id>.<table_id>` or

2017

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2018

"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]

2019

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2020

"datasetId": "A String", # Dataset ID of the table.

2021

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2022

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2023

},

2024

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2025

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

2026

# Command Center (CSCC Alpha).

2027

# This action is only available for projects which are parts of

2028

# an organization and whitelisted for the alpha Cloud Security Command

2029

# Center.

2030

# The action will publish count of finding instances and their info types.

2031

# The summary of findings will be persisted in CSCC and are governed by CSCC

2032

# service-specific policy, see https://cloud.google.com/terms/service-terms

2033

# Only a single instance of this action can be specified.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2034

# Compatible with: Inspect

2035

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2036

},

2037

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2038

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2039

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

2040

# bucket.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2041

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

2042

# number of bytes scanned is rounded down. Must be between 0 and 100,

2043

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

2044

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

2045

"fileTypes": [ # List of file type groups to include in the scan.

2046

# If empty, all files are scanned and available data format processors

2047

# are applied. In addition, the binary content of the selected files

2048

# is always scanned as well.

2049

# Images are scanned only as binary if the specified region

2050

# does not support image inspection and no file_types were specified.

2051

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

2052

"A String",

2053

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2054

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

2055

# than this value then the rest of the bytes are omitted. Only one

2056

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2057

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

2058

# Number of files scanned is rounded down. Must be between 0 and 100,

2059

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2060

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

2061

"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

2062

# `regex_file_set` must be set.

2063

# expressions are used to allow fine-grained control over which files in the

2064

# bucket to include.

2065

#

2066

# Included files are those that match at least one item in `include_regex` and

2067

# do not match any items in `exclude_regex`. Note that a file that matches

2068

# items from both lists will _not_ be included. For a match to occur, the

2069

# entire file path (i.e., everything in the url after the bucket name) must

2070

# match the regular expression.

2071

#

2072

# For example, given the input `{bucket_name: "mybucket", include_regex:

2073

# ["directory1/.*"], exclude_regex:

2074

# ["directory1/excluded.*"]}`:

2075

#

2076

# * `gs://mybucket/directory1/myfile` will be included

2077

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

2078

# across `/`)

2079

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

2080

# full path doesn't match any items in `include_regex`)

2081

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

2082

# matches an item in `exclude_regex`)

2083

#

2084

# If `include_regex` is left empty, it will match all files by default

2085

# (this is equivalent to setting `include_regex: [".*"]`).

2086

#

2087

# Some other common use cases:

2088

#

2089

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

2090

# files in `mybucket` except for .pdf files

2091

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

2092

# include all files directly under `gs://mybucket/directory/`, without matching

2093

# across `/`

2094

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2095

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2096

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2097

# excluded from the scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2098

#

2099

# Regular expressions use RE2

2100

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

2101

# under the google/re2 repository on GitHub.

2102

"A String",

2103

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2104

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2105

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2106

# included in the set of files, except for those that also match an item in

2107

# `exclude_regex`. Leaving this field empty will match all files by default

2108

# (this is equivalent to including `.*` in the list).

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2109

#

2110

# Regular expressions use RE2

2111

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

2112

# 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

2117

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

2118

#

2119

# If the url ends in a trailing slash, the bucket or directory represented

2120

# by the url will be scanned non-recursively (content in sub-directories

2121

# will not be scanned). This means that `gs://mybucket/` is equivalent to

2122

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

2123

# `gs://mybucket/directory/*`.

2124

#

2125

# Exactly one of `url` or `regex_file_set` must be set.

2126

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2127

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2128

},

2129

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2130

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2131

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

2132

# identified by its project_id, dataset_id, and table_name. Within a query

2133

# a table is often referenced with a string in the format of:

2134

# `<project_id>:<dataset_id>.<table_id>` or

2135

# `<project_id>.<dataset_id>.<table_id>`.

2136

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

2137

# If omitted, project ID is inferred from the API call.

2138

"datasetId": "A String", # Dataset ID of the table.

2139

"tableId": "A String", # Name of the table.

2140

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2141

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

2142

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

2143

# 100 means no limit. Defaults to 0. Only one of rows_limit and

2144

# rows_limit_percent can be specified. Cannot be used in conjunction with

2145

# TimespanConfig.

2146

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

2147

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

2148

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

2149

# Cannot be used in conjunction with TimespanConfig.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2150

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

2151

# `actions.saveFindings.outputConfig.table` is specified, the values of

2152

# columns specified here are available in the output table under

2153

# `location.content_locations.record_location.record_key.id_values`. Nested

2154

# fields such as `person.birthdate.year` are allowed.

2155

{ # General identifier of a data field in a storage service.

2156

"name": "A String", # Name describing the field.

2157

},

2158

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2159

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

2160

# inspection of entire columns which you know have no findings.

2161

{ # General identifier of a data field in a storage service.

2162

"name": "A String", # Name describing the field.

2163

},

2164

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2165

},

2166

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

2167

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

2168

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

2169

# Used for data sources like Datastore and BigQuery.

2170

#

2171

# For BigQuery:

2172

# Required to filter out rows based on the given start and

2173

# end times. If not specified and the table was modified between the given

2174

# start and end times, the entire table will be scanned.

2175

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

2176

# `TIMESTAMP`, or `DATETIME` BigQuery column.

2177

#

2178

# For Datastore.

2179

# Valid data types of the timestamp field are: `TIMESTAMP`.

2180

# Datastore entity will be scanned if the timestamp property does not

2181

# exist or its value is empty or invalid.

2182

"name": "A String", # Name describing the field.

2183

},

2184

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

2185

# a valid start_time to avoid scanning files that have not been modified

2186

# since the last time the JobTrigger executed. This will be based on the

2187

# time of the execution of the last run of the JobTrigger.

2188

"startTime": "A String", # Exclude files or rows older than this value.

2189

"endTime": "A String", # Exclude files or rows newer than this value.

2190

# If set to zero, no upper time limit is applied.

2191

},

2192

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

2193

"kind": { # A representation of a Datastore kind. # The kind to process.

2194

"name": "A String", # The name of the kind.

2195

},

2196

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

2197

# by project and namespace, however the namespace ID may be empty.

2198

# A partition ID identifies a grouping of entities. The grouping is always

2199

# by project and namespace, however the namespace ID may be empty.

2200

#

2201

# A partition ID contains several dimensions:

2202

# project ID and namespace ID.

2203

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

2204

"projectId": "A String", # The ID of the project to which the entities belong.

2205

},

2206

},

2207

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

2208

# Early access feature is in a pre-release state and might change or have

2209

# limited support. For more information, see

2210

# https://cloud.google.com/products#product-launch-stages.

2211

# of Google Cloud Platform.

2212

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

2213

# meaningful such as the columns that are primary keys.

2214

"identifyingFields": [ # The columns that are the primary keys for table objects included in

2215

# ContentItem. A copy of this cell's value will stored alongside alongside

2216

# each finding so that the finding can be traced to the specific row it came

2217

# from. No more than 3 may be provided.

2218

{ # General identifier of a data field in a storage service.

2219

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

2224

# 'finding_labels' map. Request may contain others, but any missing one of

2225

# these will be rejected.

2226

#

2227

# Label keys must be between 1 and 63 characters long and must conform

2228

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

2229

#

2230

# No more than 10 keys can be required.

2231

"A String",

2232

],

2233

"labels": { # To organize findings, these labels will be added to each finding.

2234

#

2235

# Label keys must be between 1 and 63 characters long and must conform

2236

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

2237

#

2238

# Label values must be between 0 and 63 characters long and must conform

2239

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

2240

#

2241

# No more than 10 labels can be associated with a given finding.

2242

#

2243

# Examples:

2244

# * `"environment" : "production"`

2245

# * `"pipeline" : "etl"`

2246

"a_key": "A String",

2247

},

2248

"description": "A String", # A short description of where the data is coming from. Will be stored once

2249

# in the job. 256 max length.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2250

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2251

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2252

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

2253

# When used with redactContent only info_types and min_likelihood are currently

2254

# used.

2255

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

2256

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

2257

{ # Custom information type provided by the user. Used to find domain-specific

2258

# sensitive information configurable to the data in question.

2259

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

2260

# be used to match sensitive information specific to the data, such as a list

2261

# of employee IDs or job titles.

2262

#

2263

# Dictionary words are case-insensitive and all characters other than letters

2264

# and digits in the unicode [Basic Multilingual

2265

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2266

# will be replaced with whitespace when scanning for matches, so the

2267

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2268

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

2269

# surrounding any match must be of a different type than the adjacent

2270

# characters within the word, so letters must be next to non-letters and

2271

# digits next to non-digits. For example, the dictionary word "jen" will

2272

# match the first three letters of the text "jen123" but will return no

2273

# matches for "jennifer".

2274

#

2275

# Dictionary words containing a large number of characters that are not

2276

# letters or digits may result in unexpected findings because such characters

2277

# are treated as whitespace. The

2278

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2279

# the size limits of dictionaries. For dictionaries that do not fit within

2280

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2281

# `StoredInfoType` API.

2282

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

2283

# is accepted.

2284

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

2285

# Example: gs://[BUCKET_NAME]/dictionary.txt

2286

},

2287

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2288

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

2289

# at least one phrase and every phrase must contain at least 2 characters

2290

# that are letters or digits. [required]

"A String",

],

},

},

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

2296

# infoType, when the name matches one of existing infoTypes and that infoType

2297

# is specified in `InspectContent.info_types` field. Specifying the latter

2298

# adds findings to the one detected by the system. If built-in info type is

2299

# not specified in `InspectContent.info_types` list then the name is treated

2300

# as a custom info type.

2301

"name": "A String", # Name of the information type. Either a name of your choosing when

2302

# creating a CustomInfoType, or one of the names listed

2303

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2304

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

2305

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

2306

},

2307

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

2308

# altered by a detection rule if the finding meets the criteria specified by

2309

# the rule. Defaults to `VERY_LIKELY` if not specified.

2310

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

2311

# Rules are applied in order that they are specified. Not supported for the

2312

# `surrogate_type` CustomInfoType.

2313

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

2314

# `CustomInfoType` to alter behavior under certain circumstances, depending

2315

# on the specific details of the rule. Not supported for the `surrogate_type`

2316

# custom infoType.

2317

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

2318

# proximity of hotwords.

2319

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2320

# The total length of the window cannot exceed 1000 characters. Note that

2321

# the finding itself will be included in the window, so that hotwords may

2322

# be used to match substrings of the finding itself. For example, the

2323

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

2324

# adjusted upwards if the area code is known to be the local area code of

2325

# a company office using the hotword regex "$xxx$", where "xxx"

2326

# is the area code in question.

2327

# rule.

2328

"windowAfter": 42, # Number of characters after the finding to consider.

2329

"windowBefore": 42, # Number of characters before the finding to consider.

2330

},

2331

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

2332

# part of a detection rule.

2333

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

2334

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

2335

# levels. For example, if a finding would be `POSSIBLE` without the

2336

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2337

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2338

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2339

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2340

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2341

# a final likelihood of `LIKELY`.

2342

},

2343

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2344

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2345

# specified, the entire match is returned. No more than 3 may be included.

2346

42,

2347

],

2348

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2349

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2350

# google/re2 repository on GitHub.

},

},

},

],

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

2356

# support reversing.

2357

# such as

2358

# [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

2359

# These types of transformations are

2360

# those that perform pseudonymization, thereby producing a "surrogate" as

2361

# output. This should be used in conjunction with a field on the

2362

# transformation such as `surrogate_info_type`. This CustomInfoType does

2363

# not support the use of `detection_rules`.

2364

},

2365

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

2366

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2367

# specified, the entire match is returned. No more than 3 may be included.

2368

42,

2369

],

2370

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2371

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2372

# google/re2 repository on GitHub.

2373

},

2374

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

2375

# `InspectDataSource`. Not currently supported in `InspectContent`.

2376

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

2377

# `organizations/433245324/storedInfoTypes/432452342` or

2378

# `projects/project-id/storedInfoTypes/432452342`.

2379

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

2380

# inspection was created. Output-only field, populated by the system.

2381

},

2382

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

2383

# to be returned. It still can be used for rules matching.

2384

},

2385

],

2386

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

2387

# POSSIBLE.

2388

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

2389

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

2390

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

2391

# When set within `InspectContentRequest`, the maximum returned is 2000

2392

# regardless if this is set higher.

2393

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

2394

{ # Max findings configuration per infoType, per content item or long

2395

# running DlpJob.

2396

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

2397

# info_type should be provided. If InfoTypeLimit does not have an

2398

# info_type, the DLP API applies the limit against all info_types that

2399

# are found but not specified in another InfoTypeLimit.

2400

"name": "A String", # Name of the information type. Either a name of your choosing when

2401

# creating a CustomInfoType, or one of the names listed

2402

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2403

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

2404

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

2405

},

2406

"maxFindings": 42, # Max findings limit for the given infoType.

2407

},

2408

],

2409

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

2410

# When set within `InspectJobConfig`,

2411

# the maximum returned is 2000 regardless if this is set higher.

2412

# When set within `InspectContentRequest`, this field is ignored.

2413

},

2414

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

2415

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

2416

# included in the response; see Finding.quote.

2417

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

2418

# Exclusion rules, contained in the set are executed in the end, other

2419

# rules are executed in the order they are specified for each info type.

2420

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

2421

# circumstances, depending on the specific details of the rules within the set.

2422

"infoTypes": [ # List of infoTypes this rule set is applied to.

2423

{ # Type of information detected by the API.

2424

"name": "A String", # Name of the information type. Either a name of your choosing when

2425

# creating a CustomInfoType, or one of the names listed

2426

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2427

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

2428

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

2429

},

2430

],

2431

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

2432

{ # A single inspection rule to be applied to infoTypes, specified in

2433

# `InspectionRuleSet`.

2434

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

2435

# proximity of hotwords.

2436

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2437

# The total length of the window cannot exceed 1000 characters. Note that

2438

# the finding itself will be included in the window, so that hotwords may

2439

# be used to match substrings of the finding itself. For example, the

2440

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

2441

# adjusted upwards if the area code is known to be the local area code of

2442

# a company office using the hotword regex "$xxx$", where "xxx"

2443

# is the area code in question.

2444

# rule.

2445

"windowAfter": 42, # Number of characters after the finding to consider.

2446

"windowBefore": 42, # Number of characters before the finding to consider.

2447

},

2448

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

2449

# part of a detection rule.

2450

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

2451

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

2452

# levels. For example, if a finding would be `POSSIBLE` without the

2453

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2454

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2455

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2456

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2457

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2458

# a final likelihood of `LIKELY`.

2459

},

2460

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2461

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2462

# specified, the entire match is returned. No more than 3 may be included.

2463

42,

2464

],

2465

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2466

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2467

# google/re2 repository on GitHub.

2468

},

2469

},

2470

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

2471

# `InspectionRuleSet` are removed from results.

2472

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

2473

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

2474

# be used to match sensitive information specific to the data, such as a list

2475

# of employee IDs or job titles.

2476

#

2477

# Dictionary words are case-insensitive and all characters other than letters

2478

# and digits in the unicode [Basic Multilingual

2479

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2480

# will be replaced with whitespace when scanning for matches, so the

2481

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2482

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

2483

# surrounding any match must be of a different type than the adjacent

2484

# characters within the word, so letters must be next to non-letters and

2485

# digits next to non-digits. For example, the dictionary word "jen" will

2486

# match the first three letters of the text "jen123" but will return no

2487

# matches for "jennifer".

2488

#

2489

# Dictionary words containing a large number of characters that are not

2490

# letters or digits may result in unexpected findings because such characters

2491

# are treated as whitespace. The

2492

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2493

# the size limits of dictionaries. For dictionaries that do not fit within

2494

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2495

# `StoredInfoType` API.

2496

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

2497

# is accepted.

2498

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

2499

# Example: gs://[BUCKET_NAME]/dictionary.txt

2500

},

2501

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2502

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

2503

# at least one phrase and every phrase must contain at least 2 characters

2504

# that are letters or digits. [required]

"A String",

],

},

},

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

2510

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

2511

# contained within with a finding of an infoType from this list. For

2512

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

2513

# `exclusion_rule` containing `exclude_info_types.info_types` with

2514

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

2515

# with EMAIL_ADDRESS finding.

2516

# That leads to "555-222-2222@example.org" to generate only a single

2517

# finding, namely email address.

2518

{ # Type of information detected by the API.

2519

"name": "A String", # Name of the information type. Either a name of your choosing when

2520

# creating a CustomInfoType, or one of the names listed

2521

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2522

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

2523

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

},

],

},

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

2528

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2529

# specified, the entire match is returned. No more than 3 may be included.

2530

42,

2531

],

2532

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2533

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2534

# google/re2 repository on GitHub.

},

},

},

],

},

],

"contentOptions": [ # List of options defining data content to scan.

2542

# If empty, text, images, and other content will be included.

2543

"A String",

2544

],

2545

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

2546

# InfoType values returned by ListInfoTypes or listed at

2547

# https://cloud.google.com/dlp/docs/infotypes-reference.

2548

#

2549

# When no InfoTypes or CustomInfoTypes are specified in a request, the

2550

# system may automatically choose what detectors to run. By default this may

2551

# be all types, but may change over time as detectors are updated.

2552

#

2553

# If you need precise control and predictability as to what detectors are

2554

# run you should specify specific InfoTypes listed in the reference,

2555

# otherwise a default list will be used, which may change over time.

2556

{ # Type of information detected by the API.

2557

"name": "A String", # Name of the information type. Either a name of your choosing when

2558

# creating a CustomInfoType, or one of the names listed

2559

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2560

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

2561

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

2562

},

2563

],

2564

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2565

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2566

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

2567

# triggeredJob is created, for example

2568

# `projects/dlp-test-project/jobTriggers/53234423`.

2569

"displayName": "A String", # Display name (max 100 chars)

2570

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

2571

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

2572

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2573

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2574

"triggerId": "A String", # The trigger id can contain uppercase and lowercase letters,

2575

# numbers, and hyphens; that is, it must match the regular

2576

# expression: `[a-zA-Z\\d-_]+`. The maximum length is 100

2577

# characters. Can be empty to allow the system to generate one.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2578

}

2579

2580

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

2587

2588

{ # Contains a configuration to make dlp api calls on a repeating basis.

2589

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2590

"status": "A String", # Required. A status for this trigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2591

"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]

2592

# needs to trigger for a job to be started. The list may contain only

2593

# a single Schedule trigger and must have at least one object.

2594

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2595

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

2596

# Early access feature is in a pre-release state and might change or have

2597

# limited support. For more information, see

2598

# https://cloud.google.com/products#product-launch-stages.

2599

# and finished.

2600

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2601

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

2602

"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]

2603

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2604

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2605

# A scheduled start time will be skipped if the previous

2606

# execution has not ended when its scheduled time occurs.

2607

#

2608

# This value must be set to a time duration greater than or equal

2609

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2610

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2611

},

2612

],

2613

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

2614

# errors may result in the JobTrigger automatically being paused.

2615

# Will return the last 100 errors. Whenever the JobTrigger is modified

2616

# this list will be cleared.

2617

{ # Details information about an error encountered during job execution or

2618

# the results of an unsuccessful activation of the JobTrigger.

2619

"timestamps": [ # The times the error occurred.

2620

"A String",

2621

],

2622

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

2623

# different programming environments, including REST APIs and RPC APIs. It is

2624

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

2625

# three pieces of data: error code, error message, and error details.

2626

#

2627

# You can find out more about this error model and how to work with it in the

2628

# [API Design Guide](https://cloud.google.com/apis/design/errors).

2629

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

2630

"details": [ # A list of messages that carry the error details. There is a common set of

2631

# message types for APIs to use.

2632

{

2633

"a_key": "", # Properties of the object. Contains field @type with type URL.

2634

},

2635

],

2636

"message": "A String", # A developer-facing error message, which should be in English. Any

2637

# user-facing error message should be localized and sent in the

2638

# google.rpc.Status.details field, or localized by the client.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2639

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2640

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2641

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2642

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

2643

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2644

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

2645

# `inspect_config` will be merged into the values persisted as part of the

2646

# template.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2647

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2648

{ # A task to execute on the completion of a job.

2649

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2650

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

2651

# will publish a metric to stack driver on each infotype requested and

2652

# how many findings were found for it. CustomDetectors will be bucketed

2653

# as 'Custom' under the Stackdriver label 'info_type'.

2654

},

2655

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

2656

# results of the DlpJob will be applied to the entry for the resource scanned

2657

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

2658

# be deleted. InfoType naming patterns are strictly enforced when using this

2659

# feature. Note that the findings will be persisted in Cloud Data Catalog

2660

# storage and are governed by Data Catalog service-specific policy, see

2661

# https://cloud.google.com/terms/service-terms

2662

# Only a single instance of this action can be specified and only allowed if

2663

# all resources being scanned are BigQuery tables.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2664

# Compatible with: Inspect

2665

},

2666

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

2667

# completion/failure.

2668

# completion/failure.

2669

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2670

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

2671

# message contains a single field, `DlpJobName`, which is equal to the

2672

# finished job's

2673

# [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

2674

# Compatible with: Inspect, Risk

2675

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

2676

# publishing access rights to the DLP API service account executing

2677

# the long running DlpJob sending the notifications.

2678

# Format is projects/{project}/topics/{topic}.

2679

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2680

"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]

2681

# OutputStorageConfig. Only a single instance of this action can be

2682

# specified.

2683

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2684

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2685

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

2686

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

2687

# from the `Finding` object. If appending to an existing table, any columns

2688

# from the predefined schema that are missing will be added. No columns in

2689

# the existing table will be deleted.

2690

#

2691

# If unspecified, then all available columns will be used for a new table or

2692

# an (existing) table with no schema, and no changes will be made to an

2693

# existing table that has a schema.

2694

# Only for use with external storage.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2695

"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]

2696

# dataset. If table_id is not set a new one will be generated

2697

# for you with the following format:

2698

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

2699

# generating the date details.

2700

#

2701

# For Inspect, each column in an existing output table must have the same

2702

# name, type, and mode of a field in the `Finding` object.

2703

#

2704

# For Risk, an existing output table should be the output of a previous

2705

# Risk analysis job run on the same source table, with the same privacy

2706

# metric and quasi-identifiers. Risk jobs that analyze the same table but

2707

# compute a different privacy metric, or use different sets of

2708

# quasi-identifiers, cannot store their results in the same table.

2709

# identified by its project_id, dataset_id, and table_name. Within a query

2710

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2711

# `<project_id>:<dataset_id>.<table_id>` or

2712

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2713

"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]

2714

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2715

"datasetId": "A String", # Dataset ID of the table.

2716

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2717

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2718

},

2719

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2720

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

2721

# Command Center (CSCC Alpha).

2722

# This action is only available for projects which are parts of

2723

# an organization and whitelisted for the alpha Cloud Security Command

2724

# Center.

2725

# The action will publish count of finding instances and their info types.

2726

# The summary of findings will be persisted in CSCC and are governed by CSCC

2727

# service-specific policy, see https://cloud.google.com/terms/service-terms

2728

# Only a single instance of this action can be specified.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2729

# Compatible with: Inspect

2730

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2731

},

2732

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2733

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2734

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

2735

# bucket.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2736

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

2737

# number of bytes scanned is rounded down. Must be between 0 and 100,

2738

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

2739

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

2740

"fileTypes": [ # List of file type groups to include in the scan.

2741

# If empty, all files are scanned and available data format processors

2742

# are applied. In addition, the binary content of the selected files

2743

# is always scanned as well.

2744

# Images are scanned only as binary if the specified region

2745

# does not support image inspection and no file_types were specified.

2746

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

2747

"A String",

2748

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2749

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

2750

# than this value then the rest of the bytes are omitted. Only one

2751

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2752

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

2753

# Number of files scanned is rounded down. Must be between 0 and 100,

2754

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2755

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

2756

"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

2757

# `regex_file_set` must be set.

2758

# expressions are used to allow fine-grained control over which files in the

2759

# bucket to include.

2760

#

2761

# Included files are those that match at least one item in `include_regex` and

2762

# do not match any items in `exclude_regex`. Note that a file that matches

2763

# items from both lists will _not_ be included. For a match to occur, the

2764

# entire file path (i.e., everything in the url after the bucket name) must

2765

# match the regular expression.

2766

#

2767

# For example, given the input `{bucket_name: "mybucket", include_regex:

2768

# ["directory1/.*"], exclude_regex:

2769

# ["directory1/excluded.*"]}`:

2770

#

2771

# * `gs://mybucket/directory1/myfile` will be included

2772

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

2773

# across `/`)

2774

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

2775

# full path doesn't match any items in `include_regex`)

2776

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

2777

# matches an item in `exclude_regex`)

2778

#

2779

# If `include_regex` is left empty, it will match all files by default

2780

# (this is equivalent to setting `include_regex: [".*"]`).

2781

#

2782

# Some other common use cases:

2783

#

2784

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

2785

# files in `mybucket` except for .pdf files

2786

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

2787

# include all files directly under `gs://mybucket/directory/`, without matching

2788

# across `/`

2789

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2790

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2791

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2792

# excluded from the scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2793

#

2794

# Regular expressions use RE2

2795

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

2796

# under the google/re2 repository on GitHub.

2797

"A String",

2798

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2799

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2800

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2801

# included in the set of files, except for those that also match an item in

2802

# `exclude_regex`. Leaving this field empty will match all files by default

2803

# (this is equivalent to including `.*` in the list).

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2804

#

2805

# Regular expressions use RE2

2806

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

2807

# 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

2812

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

2813

#

2814

# If the url ends in a trailing slash, the bucket or directory represented

2815

# by the url will be scanned non-recursively (content in sub-directories

2816

# will not be scanned). This means that `gs://mybucket/` is equivalent to

2817

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

2818

# `gs://mybucket/directory/*`.

2819

#

2820

# Exactly one of `url` or `regex_file_set` must be set.

2821

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2822

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2823

},

2824

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2825

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2826

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

2827

# identified by its project_id, dataset_id, and table_name. Within a query

2828

# a table is often referenced with a string in the format of:

2829

# `<project_id>:<dataset_id>.<table_id>` or

2830

# `<project_id>.<dataset_id>.<table_id>`.

2831

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

2832

# If omitted, project ID is inferred from the API call.

2833

"datasetId": "A String", # Dataset ID of the table.

2834

"tableId": "A String", # Name of the table.

2835

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2836

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

2837

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

2838

# 100 means no limit. Defaults to 0. Only one of rows_limit and

2839

# rows_limit_percent can be specified. Cannot be used in conjunction with

2840

# TimespanConfig.

2841

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

2842

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

2843

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

2844

# Cannot be used in conjunction with TimespanConfig.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2845

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

2846

# `actions.saveFindings.outputConfig.table` is specified, the values of

2847

# columns specified here are available in the output table under

2848

# `location.content_locations.record_location.record_key.id_values`. Nested

2849

# fields such as `person.birthdate.year` are allowed.

2850

{ # General identifier of a data field in a storage service.

2851

"name": "A String", # Name describing the field.

2852

},

2853

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2854

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

2855

# inspection of entire columns which you know have no findings.

2856

{ # General identifier of a data field in a storage service.

2857

"name": "A String", # Name describing the field.

2858

},

2859

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2860

},

2861

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

2862

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

2863

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

2864

# Used for data sources like Datastore and BigQuery.

2865

#

2866

# For BigQuery:

2867

# Required to filter out rows based on the given start and

2868

# end times. If not specified and the table was modified between the given

2869

# start and end times, the entire table will be scanned.

2870

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

2871

# `TIMESTAMP`, or `DATETIME` BigQuery column.

2872

#

2873

# For Datastore.

2874

# Valid data types of the timestamp field are: `TIMESTAMP`.

2875

# Datastore entity will be scanned if the timestamp property does not

2876

# exist or its value is empty or invalid.

2877

"name": "A String", # Name describing the field.

2878

},

2879

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

2880

# a valid start_time to avoid scanning files that have not been modified

2881

# since the last time the JobTrigger executed. This will be based on the

2882

# time of the execution of the last run of the JobTrigger.

2883

"startTime": "A String", # Exclude files or rows older than this value.

2884

"endTime": "A String", # Exclude files or rows newer than this value.

2885

# If set to zero, no upper time limit is applied.

2886

},

2887

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

2888

"kind": { # A representation of a Datastore kind. # The kind to process.

2889

"name": "A String", # The name of the kind.

2890

},

2891

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

2892

# by project and namespace, however the namespace ID may be empty.

2893

# A partition ID identifies a grouping of entities. The grouping is always

2894

# by project and namespace, however the namespace ID may be empty.

2895

#

2896

# A partition ID contains several dimensions:

2897

# project ID and namespace ID.

2898

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

2899

"projectId": "A String", # The ID of the project to which the entities belong.

2900

},

2901

},

2902

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

2903

# Early access feature is in a pre-release state and might change or have

2904

# limited support. For more information, see

2905

# https://cloud.google.com/products#product-launch-stages.

2906

# of Google Cloud Platform.

2907

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

2908

# meaningful such as the columns that are primary keys.

2909

"identifyingFields": [ # The columns that are the primary keys for table objects included in

2910

# ContentItem. A copy of this cell's value will stored alongside alongside

2911

# each finding so that the finding can be traced to the specific row it came

2912

# from. No more than 3 may be provided.

2913

{ # General identifier of a data field in a storage service.

2914

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

2919

# 'finding_labels' map. Request may contain others, but any missing one of

2920

# these will be rejected.

2921

#

2922

# Label keys must be between 1 and 63 characters long and must conform

2923

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

2924

#

2925

# No more than 10 keys can be required.

2926

"A String",

2927

],

2928

"labels": { # To organize findings, these labels will be added to each finding.

2929

#

2930

# Label keys must be between 1 and 63 characters long and must conform

2931

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

2932

#

2933

# Label values must be between 0 and 63 characters long and must conform

2934

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

2935

#

2936

# No more than 10 labels can be associated with a given finding.

2937

#

2938

# Examples:

2939

# * `"environment" : "production"`

2940

# * `"pipeline" : "etl"`

2941

"a_key": "A String",

2942

},

2943

"description": "A String", # A short description of where the data is coming from. Will be stored once

2944

# in the job. 256 max length.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

2945

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2946

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

2947

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

2948

# When used with redactContent only info_types and min_likelihood are currently

2949

# used.

2950

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

2951

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

2952

{ # Custom information type provided by the user. Used to find domain-specific

2953

# sensitive information configurable to the data in question.

2954

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

2955

# be used to match sensitive information specific to the data, such as a list

2956

# of employee IDs or job titles.

2957

#

2958

# Dictionary words are case-insensitive and all characters other than letters

2959

# and digits in the unicode [Basic Multilingual

2960

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2961

# will be replaced with whitespace when scanning for matches, so the

2962

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2963

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

2964

# surrounding any match must be of a different type than the adjacent

2965

# characters within the word, so letters must be next to non-letters and

2966

# digits next to non-digits. For example, the dictionary word "jen" will

2967

# match the first three letters of the text "jen123" but will return no

2968

# matches for "jennifer".

2969

#

2970

# Dictionary words containing a large number of characters that are not

2971

# letters or digits may result in unexpected findings because such characters

2972

# are treated as whitespace. The

2973

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2974

# the size limits of dictionaries. For dictionaries that do not fit within

2975

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2976

# `StoredInfoType` API.

2977

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

2978

# is accepted.

2979

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

2980

# Example: gs://[BUCKET_NAME]/dictionary.txt

2981

},

2982

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2983

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

2984

# at least one phrase and every phrase must contain at least 2 characters

2985

# that are letters or digits. [required]

"A String",

],

},

},

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

2991

# infoType, when the name matches one of existing infoTypes and that infoType

2992

# is specified in `InspectContent.info_types` field. Specifying the latter

2993

# adds findings to the one detected by the system. If built-in info type is

2994

# not specified in `InspectContent.info_types` list then the name is treated

2995

# as a custom info type.

2996

"name": "A String", # Name of the information type. Either a name of your choosing when

2997

# creating a CustomInfoType, or one of the names listed

2998

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2999

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

3000

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

3001

},

3002

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

3003

# altered by a detection rule if the finding meets the criteria specified by

3004

# the rule. Defaults to `VERY_LIKELY` if not specified.

3005

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

3006

# Rules are applied in order that they are specified. Not supported for the

3007

# `surrogate_type` CustomInfoType.

3008

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

3009

# `CustomInfoType` to alter behavior under certain circumstances, depending

3010

# on the specific details of the rule. Not supported for the `surrogate_type`

3011

# custom infoType.

3012

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

3013

# proximity of hotwords.

3014

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

3015

# The total length of the window cannot exceed 1000 characters. Note that

3016

# the finding itself will be included in the window, so that hotwords may

3017

# be used to match substrings of the finding itself. For example, the

3018

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

3019

# adjusted upwards if the area code is known to be the local area code of

3020

# a company office using the hotword regex "$xxx$", where "xxx"

3021

# is the area code in question.

3022

# rule.

3023

"windowAfter": 42, # Number of characters after the finding to consider.

3024

"windowBefore": 42, # Number of characters before the finding to consider.

3025

},

3026

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

3027

# part of a detection rule.

3028

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

3029

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

3030

# levels. For example, if a finding would be `POSSIBLE` without the

3031

# detection rule and `relative_likelihood` is 1, then it is upgraded to

3032

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

3033

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

3034

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

3035

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

3036

# a final likelihood of `LIKELY`.

3037

},

3038

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

3039

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3040

# specified, the entire match is returned. No more than 3 may be included.

3041

42,

3042

],

3043

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3044

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3045

# google/re2 repository on GitHub.

},

},

},

],

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

3051

# support reversing.

3052

# such as

3053

# [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

3054

# These types of transformations are

3055

# those that perform pseudonymization, thereby producing a "surrogate" as

3056

# output. This should be used in conjunction with a field on the

3057

# transformation such as `surrogate_info_type`. This CustomInfoType does

3058

# not support the use of `detection_rules`.

3059

},

3060

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

3061

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3062

# specified, the entire match is returned. No more than 3 may be included.

3063

42,

3064

],

3065

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3066

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3067

# google/re2 repository on GitHub.

3068

},

3069

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

3070

# `InspectDataSource`. Not currently supported in `InspectContent`.

3071

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

3072

# `organizations/433245324/storedInfoTypes/432452342` or

3073

# `projects/project-id/storedInfoTypes/432452342`.

3074

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

3075

# inspection was created. Output-only field, populated by the system.

3076

},

3077

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

3078

# to be returned. It still can be used for rules matching.

3079

},

3080

],

3081

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

3082

# POSSIBLE.

3083

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

3084

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

3085

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

3086

# When set within `InspectContentRequest`, the maximum returned is 2000

3087

# regardless if this is set higher.

3088

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

3089

{ # Max findings configuration per infoType, per content item or long

3090

# running DlpJob.

3091

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

3092

# info_type should be provided. If InfoTypeLimit does not have an

3093

# info_type, the DLP API applies the limit against all info_types that

3094

# are found but not specified in another InfoTypeLimit.

3095

"name": "A String", # Name of the information type. Either a name of your choosing when

3096

# creating a CustomInfoType, or one of the names listed

3097

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3098

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

3099

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

3100

},

3101

"maxFindings": 42, # Max findings limit for the given infoType.

3102

},

3103

],

3104

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

3105

# When set within `InspectJobConfig`,

3106

# the maximum returned is 2000 regardless if this is set higher.

3107

# When set within `InspectContentRequest`, this field is ignored.

3108

},

3109

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

3110

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

3111

# included in the response; see Finding.quote.

3112

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

3113

# Exclusion rules, contained in the set are executed in the end, other

3114

# rules are executed in the order they are specified for each info type.

3115

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

3116

# circumstances, depending on the specific details of the rules within the set.

3117

"infoTypes": [ # List of infoTypes this rule set is applied to.

3118

{ # Type of information detected by the API.

3119

"name": "A String", # Name of the information type. Either a name of your choosing when

3120

# creating a CustomInfoType, or one of the names listed

3121

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3122

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

3123

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

3124

},

3125

],

3126

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

3127

{ # A single inspection rule to be applied to infoTypes, specified in

3128

# `InspectionRuleSet`.

3129

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

3130

# proximity of hotwords.

3131

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

3132

# The total length of the window cannot exceed 1000 characters. Note that

3133

# the finding itself will be included in the window, so that hotwords may

3134

# be used to match substrings of the finding itself. For example, the

3135

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

3136

# adjusted upwards if the area code is known to be the local area code of

3137

# a company office using the hotword regex "$xxx$", where "xxx"

3138

# is the area code in question.

3139

# rule.

3140

"windowAfter": 42, # Number of characters after the finding to consider.

3141

"windowBefore": 42, # Number of characters before the finding to consider.

3142

},

3143

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

3144

# part of a detection rule.

3145

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

3146

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

3147

# levels. For example, if a finding would be `POSSIBLE` without the

3148

# detection rule and `relative_likelihood` is 1, then it is upgraded to

3149

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

3150

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

3151

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

3152

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

3153

# a final likelihood of `LIKELY`.

3154

},

3155

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

3156

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3157

# specified, the entire match is returned. No more than 3 may be included.

3158

42,

3159

],

3160

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3161

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3162

# google/re2 repository on GitHub.

3163

},

3164

},

3165

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

3166

# `InspectionRuleSet` are removed from results.

3167

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

3168

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

3169

# be used to match sensitive information specific to the data, such as a list

3170

# of employee IDs or job titles.

3171

#

3172

# Dictionary words are case-insensitive and all characters other than letters

3173

# and digits in the unicode [Basic Multilingual

3174

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

3175

# will be replaced with whitespace when scanning for matches, so the

3176

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

3177

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

3178

# surrounding any match must be of a different type than the adjacent

3179

# characters within the word, so letters must be next to non-letters and

3180

# digits next to non-digits. For example, the dictionary word "jen" will

3181

# match the first three letters of the text "jen123" but will return no

3182

# matches for "jennifer".

3183

#

3184

# Dictionary words containing a large number of characters that are not

3185

# letters or digits may result in unexpected findings because such characters

3186

# are treated as whitespace. The

3187

# [limits](https://cloud.google.com/dlp/limits) page contains details about

3188

# the size limits of dictionaries. For dictionaries that do not fit within

3189

# these constraints, consider using `LargeCustomDictionaryConfig` in the

3190

# `StoredInfoType` API.

3191

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

3192

# is accepted.

3193

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

3194

# Example: gs://[BUCKET_NAME]/dictionary.txt

3195

},

3196

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

3197

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

3198

# at least one phrase and every phrase must contain at least 2 characters

3199

# that are letters or digits. [required]

"A String",

],

},

},

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

3205

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

3206

# contained within with a finding of an infoType from this list. For

3207

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

3208

# `exclusion_rule` containing `exclude_info_types.info_types` with

3209

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

3210

# with EMAIL_ADDRESS finding.

3211

# That leads to "555-222-2222@example.org" to generate only a single

3212

# finding, namely email address.

3213

{ # Type of information detected by the API.

3214

"name": "A String", # Name of the information type. Either a name of your choosing when

3215

# creating a CustomInfoType, or one of the names listed

3216

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3217

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

3218

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

},

],

},

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

3223

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3224

# specified, the entire match is returned. No more than 3 may be included.

3225

42,

3226

],

3227

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3228

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3229

# google/re2 repository on GitHub.

},

},

},

],

},

],

"contentOptions": [ # List of options defining data content to scan.

3237

# If empty, text, images, and other content will be included.

3238

"A String",

3239

],

3240

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

3241

# InfoType values returned by ListInfoTypes or listed at

3242

# https://cloud.google.com/dlp/docs/infotypes-reference.

3243

#

3244

# When no InfoTypes or CustomInfoTypes are specified in a request, the

3245

# system may automatically choose what detectors to run. By default this may

3246

# be all types, but may change over time as detectors are updated.

3247

#

3248

# If you need precise control and predictability as to what detectors are

3249

# run you should specify specific InfoTypes listed in the reference,

3250

# otherwise a default list will be used, which may change over time.

3251

{ # Type of information detected by the API.

3252

"name": "A String", # Name of the information type. Either a name of your choosing when

3253

# creating a CustomInfoType, or one of the names listed

3254

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3255

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

3256

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

3257

},

3258

],

3259

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3260

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3261

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

3262

# triggeredJob is created, for example

3263

# `projects/dlp-test-project/jobTriggers/53234423`.

3264

"displayName": "A String", # Display name (max 100 chars)

3265

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

3266

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

3267

"description": "A String", # User provided description (max 256 chars)

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>

3273

<pre>Deletes a job trigger.

3274

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

3275

3276

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3277

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]

3278

`projects/dlp-test-project/jobTriggers/53234423`. (required)

3279

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

3286

3287

{ # A generic empty message that you can re-use to avoid defining duplicated

3288

# empty messages in your APIs. A typical example is to use it as the request

3289

# or the response type of an API method. For instance:

3290

#

3291

# service Foo {

3292

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

3293

# }

3294

#

3295

# The JSON representation for `Empty` is empty JSON object `{}`.

}</pre>

</div>

<code class="details" id="get">get(name, x__xgafv=None)</code>

3301

<pre>Gets a job trigger.

3302

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

3303

3304

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3305

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]

3306

`projects/dlp-test-project/jobTriggers/53234423`. (required)

3307

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

3314

3315

{ # Contains a configuration to make dlp api calls on a repeating basis.

3316

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3317

"status": "A String", # Required. A status for this trigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3318

"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]

3319

# needs to trigger for a job to be started. The list may contain only

3320

# a single Schedule trigger and must have at least one object.

3321

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3322

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

3323

# Early access feature is in a pre-release state and might change or have

3324

# limited support. For more information, see

3325

# https://cloud.google.com/products#product-launch-stages.

3326

# and finished.

3327

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3328

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

3329

"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]

3330

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3331

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3332

# A scheduled start time will be skipped if the previous

3333

# execution has not ended when its scheduled time occurs.

3334

#

3335

# This value must be set to a time duration greater than or equal

3336

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3337

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3338

},

3339

],

3340

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

3341

# errors may result in the JobTrigger automatically being paused.

3342

# Will return the last 100 errors. Whenever the JobTrigger is modified

3343

# this list will be cleared.

3344

{ # Details information about an error encountered during job execution or

3345

# the results of an unsuccessful activation of the JobTrigger.

3346

"timestamps": [ # The times the error occurred.

3347

"A String",

3348

],

3349

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

3350

# different programming environments, including REST APIs and RPC APIs. It is

3351

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

3352

# three pieces of data: error code, error message, and error details.

3353

#

3354

# You can find out more about this error model and how to work with it in the

3355

# [API Design Guide](https://cloud.google.com/apis/design/errors).

3356

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

3357

"details": [ # A list of messages that carry the error details. There is a common set of

3358

# message types for APIs to use.

3359

{

3360

"a_key": "", # Properties of the object. Contains field @type with type URL.

3361

},

3362

],

3363

"message": "A String", # A developer-facing error message, which should be in English. Any

3364

# user-facing error message should be localized and sent in the

3365

# google.rpc.Status.details field, or localized by the client.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3366

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3367

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3368

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3369

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

3370

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3371

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

3372

# `inspect_config` will be merged into the values persisted as part of the

3373

# template.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3374

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3375

{ # A task to execute on the completion of a job.

3376

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3377

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

3378

# will publish a metric to stack driver on each infotype requested and

3379

# how many findings were found for it. CustomDetectors will be bucketed

3380

# as 'Custom' under the Stackdriver label 'info_type'.

3381

},

3382

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

3383

# results of the DlpJob will be applied to the entry for the resource scanned

3384

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

3385

# be deleted. InfoType naming patterns are strictly enforced when using this

3386

# feature. Note that the findings will be persisted in Cloud Data Catalog

3387

# storage and are governed by Data Catalog service-specific policy, see

3388

# https://cloud.google.com/terms/service-terms

3389

# Only a single instance of this action can be specified and only allowed if

3390

# all resources being scanned are BigQuery tables.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3391

# Compatible with: Inspect

3392

},

3393

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

3394

# completion/failure.

3395

# completion/failure.

3396

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3397

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

3398

# message contains a single field, `DlpJobName`, which is equal to the

3399

# finished job's

3400

# [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

3401

# Compatible with: Inspect, Risk

3402

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

3403

# publishing access rights to the DLP API service account executing

3404

# the long running DlpJob sending the notifications.

3405

# Format is projects/{project}/topics/{topic}.

3406

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3407

"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]

3408

# OutputStorageConfig. Only a single instance of this action can be

3409

# specified.

3410

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3411

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3412

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

3413

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

3414

# from the `Finding` object. If appending to an existing table, any columns

3415

# from the predefined schema that are missing will be added. No columns in

3416

# the existing table will be deleted.

3417

#

3418

# If unspecified, then all available columns will be used for a new table or

3419

# an (existing) table with no schema, and no changes will be made to an

3420

# existing table that has a schema.

3421

# Only for use with external storage.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3422

"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]

3423

# dataset. If table_id is not set a new one will be generated

3424

# for you with the following format:

3425

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

3426

# generating the date details.

3427

#

3428

# For Inspect, each column in an existing output table must have the same

3429

# name, type, and mode of a field in the `Finding` object.

3430

#

3431

# For Risk, an existing output table should be the output of a previous

3432

# Risk analysis job run on the same source table, with the same privacy

3433

# metric and quasi-identifiers. Risk jobs that analyze the same table but

3434

# compute a different privacy metric, or use different sets of

3435

# quasi-identifiers, cannot store their results in the same table.

3436

# identified by its project_id, dataset_id, and table_name. Within a query

3437

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3438

# `<project_id>:<dataset_id>.<table_id>` or

3439

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3440

"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]

3441

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3442

"datasetId": "A String", # Dataset ID of the table.

3443

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3444

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3445

},

3446

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3447

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

3448

# Command Center (CSCC Alpha).

3449

# This action is only available for projects which are parts of

3450

# an organization and whitelisted for the alpha Cloud Security Command

3451

# Center.

3452

# The action will publish count of finding instances and their info types.

3453

# The summary of findings will be persisted in CSCC and are governed by CSCC

3454

# service-specific policy, see https://cloud.google.com/terms/service-terms

3455

# Only a single instance of this action can be specified.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3456

# Compatible with: Inspect

3457

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3458

},

3459

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3460

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3461

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

3462

# bucket.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3463

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

3464

# number of bytes scanned is rounded down. Must be between 0 and 100,

3465

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

3466

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

3467

"fileTypes": [ # List of file type groups to include in the scan.

3468

# If empty, all files are scanned and available data format processors

3469

# are applied. In addition, the binary content of the selected files

3470

# is always scanned as well.

3471

# Images are scanned only as binary if the specified region

3472

# does not support image inspection and no file_types were specified.

3473

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

3474

"A String",

3475

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3476

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

3477

# than this value then the rest of the bytes are omitted. Only one

3478

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3479

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

3480

# Number of files scanned is rounded down. Must be between 0 and 100,

3481

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3482

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

3483

"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

3484

# `regex_file_set` must be set.

3485

# expressions are used to allow fine-grained control over which files in the

3486

# bucket to include.

3487

#

3488

# Included files are those that match at least one item in `include_regex` and

3489

# do not match any items in `exclude_regex`. Note that a file that matches

3490

# items from both lists will _not_ be included. For a match to occur, the

3491

# entire file path (i.e., everything in the url after the bucket name) must

3492

# match the regular expression.

3493

#

3494

# For example, given the input `{bucket_name: "mybucket", include_regex:

3495

# ["directory1/.*"], exclude_regex:

3496

# ["directory1/excluded.*"]}`:

3497

#

3498

# * `gs://mybucket/directory1/myfile` will be included

3499

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

3500

# across `/`)

3501

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

3502

# full path doesn't match any items in `include_regex`)

3503

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

3504

# matches an item in `exclude_regex`)

3505

#

3506

# If `include_regex` is left empty, it will match all files by default

3507

# (this is equivalent to setting `include_regex: [".*"]`).

3508

#

3509

# Some other common use cases:

3510

#

3511

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

3512

# files in `mybucket` except for .pdf files

3513

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

3514

# include all files directly under `gs://mybucket/directory/`, without matching

3515

# across `/`

3516

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3517

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3518

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3519

# excluded from the scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3520

#

3521

# Regular expressions use RE2

3522

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

3523

# under the google/re2 repository on GitHub.

3524

"A String",

3525

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3526

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3527

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3528

# included in the set of files, except for those that also match an item in

3529

# `exclude_regex`. Leaving this field empty will match all files by default

3530

# (this is equivalent to including `.*` in the list).

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3531

#

3532

# Regular expressions use RE2

3533

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

3534

# 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

3539

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

3540

#

3541

# If the url ends in a trailing slash, the bucket or directory represented

3542

# by the url will be scanned non-recursively (content in sub-directories

3543

# will not be scanned). This means that `gs://mybucket/` is equivalent to

3544

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

3545

# `gs://mybucket/directory/*`.

3546

#

3547

# Exactly one of `url` or `regex_file_set` must be set.

3548

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3549

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3550

},

3551

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3552

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3553

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

3554

# identified by its project_id, dataset_id, and table_name. Within a query

3555

# a table is often referenced with a string in the format of:

3556

# `<project_id>:<dataset_id>.<table_id>` or

3557

# `<project_id>.<dataset_id>.<table_id>`.

3558

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

3559

# If omitted, project ID is inferred from the API call.

3560

"datasetId": "A String", # Dataset ID of the table.

3561

"tableId": "A String", # Name of the table.

3562

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3563

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

3564

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

3565

# 100 means no limit. Defaults to 0. Only one of rows_limit and

3566

# rows_limit_percent can be specified. Cannot be used in conjunction with

3567

# TimespanConfig.

3568

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

3569

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

3570

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

3571

# Cannot be used in conjunction with TimespanConfig.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3572

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

3573

# `actions.saveFindings.outputConfig.table` is specified, the values of

3574

# columns specified here are available in the output table under

3575

# `location.content_locations.record_location.record_key.id_values`. Nested

3576

# fields such as `person.birthdate.year` are allowed.

3577

{ # General identifier of a data field in a storage service.

3578

"name": "A String", # Name describing the field.

3579

},

3580

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3581

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

3582

# inspection of entire columns which you know have no findings.

3583

{ # General identifier of a data field in a storage service.

3584

"name": "A String", # Name describing the field.

3585

},

3586

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3587

},

3588

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

3589

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

3590

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

3591

# Used for data sources like Datastore and BigQuery.

3592

#

3593

# For BigQuery:

3594

# Required to filter out rows based on the given start and

3595

# end times. If not specified and the table was modified between the given

3596

# start and end times, the entire table will be scanned.

3597

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

3598

# `TIMESTAMP`, or `DATETIME` BigQuery column.

3599

#

3600

# For Datastore.

3601

# Valid data types of the timestamp field are: `TIMESTAMP`.

3602

# Datastore entity will be scanned if the timestamp property does not

3603

# exist or its value is empty or invalid.

3604

"name": "A String", # Name describing the field.

3605

},

3606

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

3607

# a valid start_time to avoid scanning files that have not been modified

3608

# since the last time the JobTrigger executed. This will be based on the

3609

# time of the execution of the last run of the JobTrigger.

3610

"startTime": "A String", # Exclude files or rows older than this value.

3611

"endTime": "A String", # Exclude files or rows newer than this value.

3612

# If set to zero, no upper time limit is applied.

3613

},

3614

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

3615

"kind": { # A representation of a Datastore kind. # The kind to process.

3616

"name": "A String", # The name of the kind.

3617

},

3618

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

3619

# by project and namespace, however the namespace ID may be empty.

3620

# A partition ID identifies a grouping of entities. The grouping is always

3621

# by project and namespace, however the namespace ID may be empty.

3622

#

3623

# A partition ID contains several dimensions:

3624

# project ID and namespace ID.

3625

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

3626

"projectId": "A String", # The ID of the project to which the entities belong.

3627

},

3628

},

3629

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

3630

# Early access feature is in a pre-release state and might change or have

3631

# limited support. For more information, see

3632

# https://cloud.google.com/products#product-launch-stages.

3633

# of Google Cloud Platform.

3634

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

3635

# meaningful such as the columns that are primary keys.

3636

"identifyingFields": [ # The columns that are the primary keys for table objects included in

3637

# ContentItem. A copy of this cell's value will stored alongside alongside

3638

# each finding so that the finding can be traced to the specific row it came

3639

# from. No more than 3 may be provided.

3640

{ # General identifier of a data field in a storage service.

3641

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

3646

# 'finding_labels' map. Request may contain others, but any missing one of

3647

# these will be rejected.

3648

#

3649

# Label keys must be between 1 and 63 characters long and must conform

3650

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

3651

#

3652

# No more than 10 keys can be required.

3653

"A String",

3654

],

3655

"labels": { # To organize findings, these labels will be added to each finding.

3656

#

3657

# Label keys must be between 1 and 63 characters long and must conform

3658

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

3659

#

3660

# Label values must be between 0 and 63 characters long and must conform

3661

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

3662

#

3663

# No more than 10 labels can be associated with a given finding.

3664

#

3665

# Examples:

3666

# * `"environment" : "production"`

3667

# * `"pipeline" : "etl"`

3668

"a_key": "A String",

3669

},

3670

"description": "A String", # A short description of where the data is coming from. Will be stored once

3671

# in the job. 256 max length.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

3672

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3673

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3674

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

3675

# When used with redactContent only info_types and min_likelihood are currently

3676

# used.

3677

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

3678

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

3679

{ # Custom information type provided by the user. Used to find domain-specific

3680

# sensitive information configurable to the data in question.

3681

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

3682

# be used to match sensitive information specific to the data, such as a list

3683

# of employee IDs or job titles.

3684

#

3685

# Dictionary words are case-insensitive and all characters other than letters

3686

# and digits in the unicode [Basic Multilingual

3687

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

3688

# will be replaced with whitespace when scanning for matches, so the

3689

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

3690

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

3691

# surrounding any match must be of a different type than the adjacent

3692

# characters within the word, so letters must be next to non-letters and

3693

# digits next to non-digits. For example, the dictionary word "jen" will

3694

# match the first three letters of the text "jen123" but will return no

3695

# matches for "jennifer".

3696

#

3697

# Dictionary words containing a large number of characters that are not

3698

# letters or digits may result in unexpected findings because such characters

3699

# are treated as whitespace. The

3700

# [limits](https://cloud.google.com/dlp/limits) page contains details about

3701

# the size limits of dictionaries. For dictionaries that do not fit within

3702

# these constraints, consider using `LargeCustomDictionaryConfig` in the

3703

# `StoredInfoType` API.

3704

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

3705

# is accepted.

3706

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

3707

# Example: gs://[BUCKET_NAME]/dictionary.txt

3708

},

3709

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

3710

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

3711

# at least one phrase and every phrase must contain at least 2 characters

3712

# that are letters or digits. [required]

"A String",

],

},

},

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

3718

# infoType, when the name matches one of existing infoTypes and that infoType

3719

# is specified in `InspectContent.info_types` field. Specifying the latter

3720

# adds findings to the one detected by the system. If built-in info type is

3721

# not specified in `InspectContent.info_types` list then the name is treated

3722

# as a custom info type.

3723

"name": "A String", # Name of the information type. Either a name of your choosing when

3724

# creating a CustomInfoType, or one of the names listed

3725

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3726

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

3727

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

3728

},

3729

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

3730

# altered by a detection rule if the finding meets the criteria specified by

3731

# the rule. Defaults to `VERY_LIKELY` if not specified.

3732

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

3733

# Rules are applied in order that they are specified. Not supported for the

3734

# `surrogate_type` CustomInfoType.

3735

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

3736

# `CustomInfoType` to alter behavior under certain circumstances, depending

3737

# on the specific details of the rule. Not supported for the `surrogate_type`

3738

# custom infoType.

3739

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

3740

# proximity of hotwords.

3741

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

3742

# The total length of the window cannot exceed 1000 characters. Note that

3743

# the finding itself will be included in the window, so that hotwords may

3744

# be used to match substrings of the finding itself. For example, the

3745

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

3746

# adjusted upwards if the area code is known to be the local area code of

3747

# a company office using the hotword regex "$xxx$", where "xxx"

3748

# is the area code in question.

3749

# rule.

3750

"windowAfter": 42, # Number of characters after the finding to consider.

3751

"windowBefore": 42, # Number of characters before the finding to consider.

3752

},

3753

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

3754

# part of a detection rule.

3755

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

3756

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

3757

# levels. For example, if a finding would be `POSSIBLE` without the

3758

# detection rule and `relative_likelihood` is 1, then it is upgraded to

3759

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

3760

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

3761

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

3762

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

3763

# a final likelihood of `LIKELY`.

3764

},

3765

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

3766

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3767

# specified, the entire match is returned. No more than 3 may be included.

3768

42,

3769

],

3770

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3771

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3772

# google/re2 repository on GitHub.

},

},

},

],

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

3778

# support reversing.

3779

# such as

3780

# [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

3781

# These types of transformations are

3782

# those that perform pseudonymization, thereby producing a "surrogate" as

3783

# output. This should be used in conjunction with a field on the

3784

# transformation such as `surrogate_info_type`. This CustomInfoType does

3785

# not support the use of `detection_rules`.

3786

},

3787

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

3788

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3789

# specified, the entire match is returned. No more than 3 may be included.

3790

42,

3791

],

3792

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3793

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3794

# google/re2 repository on GitHub.

3795

},

3796

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

3797

# `InspectDataSource`. Not currently supported in `InspectContent`.

3798

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

3799

# `organizations/433245324/storedInfoTypes/432452342` or

3800

# `projects/project-id/storedInfoTypes/432452342`.

3801

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

3802

# inspection was created. Output-only field, populated by the system.

3803

},

3804

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

3805

# to be returned. It still can be used for rules matching.

3806

},

3807

],

3808

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

3809

# POSSIBLE.

3810

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

3811

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

3812

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

3813

# When set within `InspectContentRequest`, the maximum returned is 2000

3814

# regardless if this is set higher.

3815

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

3816

{ # Max findings configuration per infoType, per content item or long

3817

# running DlpJob.

3818

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

3819

# info_type should be provided. If InfoTypeLimit does not have an

3820

# info_type, the DLP API applies the limit against all info_types that

3821

# are found but not specified in another InfoTypeLimit.

3822

"name": "A String", # Name of the information type. Either a name of your choosing when

3823

# creating a CustomInfoType, or one of the names listed

3824

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3825

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

3826

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

3827

},

3828

"maxFindings": 42, # Max findings limit for the given infoType.

3829

},

3830

],

3831

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

3832

# When set within `InspectJobConfig`,

3833

# the maximum returned is 2000 regardless if this is set higher.

3834

# When set within `InspectContentRequest`, this field is ignored.

3835

},

3836

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

3837

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

3838

# included in the response; see Finding.quote.

3839

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

3840

# Exclusion rules, contained in the set are executed in the end, other

3841

# rules are executed in the order they are specified for each info type.

3842

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

3843

# circumstances, depending on the specific details of the rules within the set.

3844

"infoTypes": [ # List of infoTypes this rule set is applied to.

3845

{ # Type of information detected by the API.

3846

"name": "A String", # Name of the information type. Either a name of your choosing when

3847

# creating a CustomInfoType, or one of the names listed

3848

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3849

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

3850

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

3851

},

3852

],

3853

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

3854

{ # A single inspection rule to be applied to infoTypes, specified in

3855

# `InspectionRuleSet`.

3856

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

3857

# proximity of hotwords.

3858

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

3859

# The total length of the window cannot exceed 1000 characters. Note that

3860

# the finding itself will be included in the window, so that hotwords may

3861

# be used to match substrings of the finding itself. For example, the

3862

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

3863

# adjusted upwards if the area code is known to be the local area code of

3864

# a company office using the hotword regex "$xxx$", where "xxx"

3865

# is the area code in question.

3866

# rule.

3867

"windowAfter": 42, # Number of characters after the finding to consider.

3868

"windowBefore": 42, # Number of characters before the finding to consider.

3869

},

3870

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

3871

# part of a detection rule.

3872

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

3873

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

3874

# levels. For example, if a finding would be `POSSIBLE` without the

3875

# detection rule and `relative_likelihood` is 1, then it is upgraded to

3876

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

3877

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

3878

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

3879

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

3880

# a final likelihood of `LIKELY`.

3881

},

3882

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

3883

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3884

# specified, the entire match is returned. No more than 3 may be included.

3885

42,

3886

],

3887

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3888

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3889

# google/re2 repository on GitHub.

3890

},

3891

},

3892

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

3893

# `InspectionRuleSet` are removed from results.

3894

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

3895

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

3896

# be used to match sensitive information specific to the data, such as a list

3897

# of employee IDs or job titles.

3898

#

3899

# Dictionary words are case-insensitive and all characters other than letters

3900

# and digits in the unicode [Basic Multilingual

3901

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

3902

# will be replaced with whitespace when scanning for matches, so the

3903

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

3904

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

3905

# surrounding any match must be of a different type than the adjacent

3906

# characters within the word, so letters must be next to non-letters and

3907

# digits next to non-digits. For example, the dictionary word "jen" will

3908

# match the first three letters of the text "jen123" but will return no

3909

# matches for "jennifer".

3910

#

3911

# Dictionary words containing a large number of characters that are not

3912

# letters or digits may result in unexpected findings because such characters

3913

# are treated as whitespace. The

3914

# [limits](https://cloud.google.com/dlp/limits) page contains details about

3915

# the size limits of dictionaries. For dictionaries that do not fit within

3916

# these constraints, consider using `LargeCustomDictionaryConfig` in the

3917

# `StoredInfoType` API.

3918

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

3919

# is accepted.

3920

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

3921

# Example: gs://[BUCKET_NAME]/dictionary.txt

3922

},

3923

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

3924

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

3925

# at least one phrase and every phrase must contain at least 2 characters

3926

# that are letters or digits. [required]

"A String",

],

},

},

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

3932

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

3933

# contained within with a finding of an infoType from this list. For

3934

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

3935

# `exclusion_rule` containing `exclude_info_types.info_types` with

3936

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

3937

# with EMAIL_ADDRESS finding.

3938

# That leads to "555-222-2222@example.org" to generate only a single

3939

# finding, namely email address.

3940

{ # Type of information detected by the API.

3941

"name": "A String", # Name of the information type. Either a name of your choosing when

3942

# creating a CustomInfoType, or one of the names listed

3943

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3944

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

3945

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

},

],

},

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

3950

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3951

# specified, the entire match is returned. No more than 3 may be included.

3952

42,

3953

],

3954

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3955

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3956

# google/re2 repository on GitHub.

},

},

},

],

},

],

"contentOptions": [ # List of options defining data content to scan.

3964

# If empty, text, images, and other content will be included.

3965

"A String",

3966

],

3967

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

3968

# InfoType values returned by ListInfoTypes or listed at

3969

# https://cloud.google.com/dlp/docs/infotypes-reference.

3970

#

3971

# When no InfoTypes or CustomInfoTypes are specified in a request, the

3972

# system may automatically choose what detectors to run. By default this may

3973

# be all types, but may change over time as detectors are updated.

3974

#

3975

# If you need precise control and predictability as to what detectors are

3976

# run you should specify specific InfoTypes listed in the reference,

3977

# otherwise a default list will be used, which may change over time.

3978

{ # Type of information detected by the API.

3979

"name": "A String", # Name of the information type. Either a name of your choosing when

3980

# creating a CustomInfoType, or one of the names listed

3981

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3982

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

3983

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

3984

},

3985

],

3986

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3987

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3988

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

3989

# triggeredJob is created, for example

3990

# `projects/dlp-test-project/jobTriggers/53234423`.

3991

"displayName": "A String", # Display name (max 100 chars)

3992

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

3993

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

3994

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

}</pre>

</div>

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

3999

<code class="details" id="list">list(parent, filter=None, locationId=None, pageSize=None, pageToken=None, orderBy=None, x__xgafv=None)</code>

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4000

<pre>Lists job triggers.

4001

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

4002

4003

Args:

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4004

parent: string, Required. Parent resource name.

4005

- Format:projects/[PROJECT-ID]

4006

- Format:projects/[PROJECT-ID]/locations/[LOCATION-ID] (required)

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4007

filter: string, Allows filtering.

Supported syntax:

* Filter expressions are made up of one or more restrictions.

4012

* Restrictions can be combined by `AND` or `OR` logical operators. A

4013

sequence of restrictions implicitly uses `AND`.

4014

* A restriction has the form of `{field} {operator} {value}`.

4015

* Supported fields/values for inspect jobs:

4016

- `status` - HEALTHY|PAUSED|CANCELLED

4017

- `inspected_storage` - DATASTORE|CLOUD_STORAGE|BIGQUERY

4018

- 'last_run_time` - RFC 3339 formatted timestamp, surrounded by

4019

quotation marks. Nanoseconds are ignored.

4020

- 'error_count' - Number of errors that have occurred while running.

4021

* The operator must be `=` or `!=` for status and inspected_storage.

Examples:

* inspected_storage = cloud_storage AND status = HEALTHY

4026

* inspected_storage = cloud_storage OR inspected_storage = bigquery

4027

* inspected_storage = cloud_storage AND (state = PAUSED OR state = HEALTHY)

4028

* last_run_time > \"2017-12-12T00:00:00+00:00\"

4029

4030

The length of this field should be no more than 500 characters.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4031

locationId: string, Deprecated. This field has no effect.

4032

pageSize: integer, Size of the page, can be limited by a server.

4033

pageToken: string, Page token to continue retrieval. Comes from previous call

4034

to ListJobTriggers. `order_by` field must not

4035

change for subsequent calls.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4036

orderBy: string, Comma separated list of triggeredJob fields to order by,

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4037

followed by `asc` or `desc` postfix. This list is case-insensitive,

4038

default sorting order is ascending, redundant space characters are

4039

insignificant.

4040

4041

Example: `name asc,update_time, create_time desc`

4042

4043

Supported fields are:

4044

4045

- `create_time`: corresponds to time the JobTrigger was created.

4046

- `update_time`: corresponds to time the JobTrigger was last updated.

4047

- `last_run_time`: corresponds to the last time the JobTrigger ran.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4048

- `name`: corresponds to JobTrigger's name.

4049

- `display_name`: corresponds to JobTrigger's display name.

4050

- `status`: corresponds to JobTrigger's status.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4051

x__xgafv: string, V1 error format.

4052

Allowed values

4053

1 - v1 error format

4054

2 - v2 error format

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4055

4056

Returns:

4057

An object of the form:

4058

4059

{ # Response message for ListJobTriggers.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4060

"jobTriggers": [ # List of triggeredJobs, up to page_size in ListJobTriggersRequest.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4061

{ # Contains a configuration to make dlp api calls on a repeating basis.

4062

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4063

"status": "A String", # Required. A status for this trigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4064

"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]

4065

# needs to trigger for a job to be started. The list may contain only

4066

# a single Schedule trigger and must have at least one object.

4067

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4068

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

4069

# Early access feature is in a pre-release state and might change or have

4070

# limited support. For more information, see

4071

# https://cloud.google.com/products#product-launch-stages.

4072

# and finished.

4073

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4074

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

4075

"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]

4076

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4077

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4078

# A scheduled start time will be skipped if the previous

4079

# execution has not ended when its scheduled time occurs.

4080

#

4081

# This value must be set to a time duration greater than or equal

4082

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4083

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4084

},

4085

],

4086

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

4087

# errors may result in the JobTrigger automatically being paused.

4088

# Will return the last 100 errors. Whenever the JobTrigger is modified

4089

# this list will be cleared.

4090

{ # Details information about an error encountered during job execution or

4091

# the results of an unsuccessful activation of the JobTrigger.

4092

"timestamps": [ # The times the error occurred.

4093

"A String",

4094

],

4095

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

4096

# different programming environments, including REST APIs and RPC APIs. It is

4097

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

4098

# three pieces of data: error code, error message, and error details.

4099

#

4100

# You can find out more about this error model and how to work with it in the

4101

# [API Design Guide](https://cloud.google.com/apis/design/errors).

4102

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

4103

"details": [ # A list of messages that carry the error details. There is a common set of

4104

# message types for APIs to use.

4105

{

4106

"a_key": "", # Properties of the object. Contains field @type with type URL.

4107

},

4108

],

4109

"message": "A String", # A developer-facing error message, which should be in English. Any

4110

# user-facing error message should be localized and sent in the

4111

# google.rpc.Status.details field, or localized by the client.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4112

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4113

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4114

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4115

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

4116

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4117

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

4118

# `inspect_config` will be merged into the values persisted as part of the

4119

# template.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4120

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4121

{ # A task to execute on the completion of a job.

4122

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4123

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

4124

# will publish a metric to stack driver on each infotype requested and

4125

# how many findings were found for it. CustomDetectors will be bucketed

4126

# as 'Custom' under the Stackdriver label 'info_type'.

4127

},

4128

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

4129

# results of the DlpJob will be applied to the entry for the resource scanned

4130

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

4131

# be deleted. InfoType naming patterns are strictly enforced when using this

4132

# feature. Note that the findings will be persisted in Cloud Data Catalog

4133

# storage and are governed by Data Catalog service-specific policy, see

4134

# https://cloud.google.com/terms/service-terms

4135

# Only a single instance of this action can be specified and only allowed if

4136

# all resources being scanned are BigQuery tables.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4137

# Compatible with: Inspect

4138

},

4139

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

4140

# completion/failure.

4141

# completion/failure.

4142

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4143

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

4144

# message contains a single field, `DlpJobName`, which is equal to the

4145

# finished job's

4146

# [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

4147

# Compatible with: Inspect, Risk

4148

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

4149

# publishing access rights to the DLP API service account executing

4150

# the long running DlpJob sending the notifications.

4151

# Format is projects/{project}/topics/{topic}.

4152

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4153

"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]

4154

# OutputStorageConfig. Only a single instance of this action can be

4155

# specified.

4156

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4157

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4158

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

4159

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

4160

# from the `Finding` object. If appending to an existing table, any columns

4161

# from the predefined schema that are missing will be added. No columns in

4162

# the existing table will be deleted.

4163

#

4164

# If unspecified, then all available columns will be used for a new table or

4165

# an (existing) table with no schema, and no changes will be made to an

4166

# existing table that has a schema.

4167

# Only for use with external storage.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4168

"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]

4169

# dataset. If table_id is not set a new one will be generated

4170

# for you with the following format:

4171

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

4172

# generating the date details.

4173

#

4174

# For Inspect, each column in an existing output table must have the same

4175

# name, type, and mode of a field in the `Finding` object.

4176

#

4177

# For Risk, an existing output table should be the output of a previous

4178

# Risk analysis job run on the same source table, with the same privacy

4179

# metric and quasi-identifiers. Risk jobs that analyze the same table but

4180

# compute a different privacy metric, or use different sets of

4181

# quasi-identifiers, cannot store their results in the same table.

4182

# identified by its project_id, dataset_id, and table_name. Within a query

4183

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4184

# `<project_id>:<dataset_id>.<table_id>` or

4185

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4186

"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]

4187

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4188

"datasetId": "A String", # Dataset ID of the table.

4189

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4190

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4191

},

4192

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4193

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

4194

# Command Center (CSCC Alpha).

4195

# This action is only available for projects which are parts of

4196

# an organization and whitelisted for the alpha Cloud Security Command

4197

# Center.

4198

# The action will publish count of finding instances and their info types.

4199

# The summary of findings will be persisted in CSCC and are governed by CSCC

4200

# service-specific policy, see https://cloud.google.com/terms/service-terms

4201

# Only a single instance of this action can be specified.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4202

# Compatible with: Inspect

4203

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4204

},

4205

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4206

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4207

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

4208

# bucket.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4209

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

4210

# number of bytes scanned is rounded down. Must be between 0 and 100,

4211

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

4212

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

4213

"fileTypes": [ # List of file type groups to include in the scan.

4214

# If empty, all files are scanned and available data format processors

4215

# are applied. In addition, the binary content of the selected files

4216

# is always scanned as well.

4217

# Images are scanned only as binary if the specified region

4218

# does not support image inspection and no file_types were specified.

4219

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

4220

"A String",

4221

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4222

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

4223

# than this value then the rest of the bytes are omitted. Only one

4224

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4225

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

4226

# Number of files scanned is rounded down. Must be between 0 and 100,

4227

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4228

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

4229

"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

4230

# `regex_file_set` must be set.

4231

# expressions are used to allow fine-grained control over which files in the

4232

# bucket to include.

4233

#

4234

# Included files are those that match at least one item in `include_regex` and

4235

# do not match any items in `exclude_regex`. Note that a file that matches

4236

# items from both lists will _not_ be included. For a match to occur, the

4237

# entire file path (i.e., everything in the url after the bucket name) must

4238

# match the regular expression.

4239

#

4240

# For example, given the input `{bucket_name: "mybucket", include_regex:

4241

# ["directory1/.*"], exclude_regex:

4242

# ["directory1/excluded.*"]}`:

4243

#

4244

# * `gs://mybucket/directory1/myfile` will be included

4245

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

4246

# across `/`)

4247

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

4248

# full path doesn't match any items in `include_regex`)

4249

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

4250

# matches an item in `exclude_regex`)

4251

#

4252

# If `include_regex` is left empty, it will match all files by default

4253

# (this is equivalent to setting `include_regex: [".*"]`).

4254

#

4255

# Some other common use cases:

4256

#

4257

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

4258

# files in `mybucket` except for .pdf files

4259

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

4260

# include all files directly under `gs://mybucket/directory/`, without matching

4261

# across `/`

4262

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4263

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4264

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4265

# excluded from the scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4266

#

4267

# Regular expressions use RE2

4268

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

4269

# under the google/re2 repository on GitHub.

4270

"A String",

4271

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4272

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4273

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4274

# included in the set of files, except for those that also match an item in

4275

# `exclude_regex`. Leaving this field empty will match all files by default

4276

# (this is equivalent to including `.*` in the list).

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4277

#

4278

# Regular expressions use RE2

4279

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

4280

# 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

4285

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

4286

#

4287

# If the url ends in a trailing slash, the bucket or directory represented

4288

# by the url will be scanned non-recursively (content in sub-directories

4289

# will not be scanned). This means that `gs://mybucket/` is equivalent to

4290

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

4291

# `gs://mybucket/directory/*`.

4292

#

4293

# Exactly one of `url` or `regex_file_set` must be set.

4294

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4295

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4296

},

4297

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4298

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4299

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

4300

# identified by its project_id, dataset_id, and table_name. Within a query

4301

# a table is often referenced with a string in the format of:

4302

# `<project_id>:<dataset_id>.<table_id>` or

4303

# `<project_id>.<dataset_id>.<table_id>`.

4304

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

4305

# If omitted, project ID is inferred from the API call.

4306

"datasetId": "A String", # Dataset ID of the table.

4307

"tableId": "A String", # Name of the table.

4308

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4309

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

4310

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

4311

# 100 means no limit. Defaults to 0. Only one of rows_limit and

4312

# rows_limit_percent can be specified. Cannot be used in conjunction with

4313

# TimespanConfig.

4314

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

4315

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

4316

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

4317

# Cannot be used in conjunction with TimespanConfig.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4318

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

4319

# `actions.saveFindings.outputConfig.table` is specified, the values of

4320

# columns specified here are available in the output table under

4321

# `location.content_locations.record_location.record_key.id_values`. Nested

4322

# fields such as `person.birthdate.year` are allowed.

4323

{ # General identifier of a data field in a storage service.

4324

"name": "A String", # Name describing the field.

4325

},

4326

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4327

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

4328

# inspection of entire columns which you know have no findings.

4329

{ # General identifier of a data field in a storage service.

4330

"name": "A String", # Name describing the field.

4331

},

4332

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4333

},

4334

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

4335

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

4336

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

4337

# Used for data sources like Datastore and BigQuery.

4338

#

4339

# For BigQuery:

4340

# Required to filter out rows based on the given start and

4341

# end times. If not specified and the table was modified between the given

4342

# start and end times, the entire table will be scanned.

4343

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

4344

# `TIMESTAMP`, or `DATETIME` BigQuery column.

4345

#

4346

# For Datastore.

4347

# Valid data types of the timestamp field are: `TIMESTAMP`.

4348

# Datastore entity will be scanned if the timestamp property does not

4349

# exist or its value is empty or invalid.

4350

"name": "A String", # Name describing the field.

4351

},

4352

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

4353

# a valid start_time to avoid scanning files that have not been modified

4354

# since the last time the JobTrigger executed. This will be based on the

4355

# time of the execution of the last run of the JobTrigger.

4356

"startTime": "A String", # Exclude files or rows older than this value.

4357

"endTime": "A String", # Exclude files or rows newer than this value.

4358

# If set to zero, no upper time limit is applied.

4359

},

4360

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

4361

"kind": { # A representation of a Datastore kind. # The kind to process.

4362

"name": "A String", # The name of the kind.

4363

},

4364

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

4365

# by project and namespace, however the namespace ID may be empty.

4366

# A partition ID identifies a grouping of entities. The grouping is always

4367

# by project and namespace, however the namespace ID may be empty.

4368

#

4369

# A partition ID contains several dimensions:

4370

# project ID and namespace ID.

4371

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

4372

"projectId": "A String", # The ID of the project to which the entities belong.

4373

},

4374

},

4375

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

4376

# Early access feature is in a pre-release state and might change or have

4377

# limited support. For more information, see

4378

# https://cloud.google.com/products#product-launch-stages.

4379

# of Google Cloud Platform.

4380

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

4381

# meaningful such as the columns that are primary keys.

4382

"identifyingFields": [ # The columns that are the primary keys for table objects included in

4383

# ContentItem. A copy of this cell's value will stored alongside alongside

4384

# each finding so that the finding can be traced to the specific row it came

4385

# from. No more than 3 may be provided.

4386

{ # General identifier of a data field in a storage service.

4387

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

4392

# 'finding_labels' map. Request may contain others, but any missing one of

4393

# these will be rejected.

4394

#

4395

# Label keys must be between 1 and 63 characters long and must conform

4396

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

4397

#

4398

# No more than 10 keys can be required.

4399

"A String",

4400

],

4401

"labels": { # To organize findings, these labels will be added to each finding.

4402

#

4403

# Label keys must be between 1 and 63 characters long and must conform

4404

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

4405

#

4406

# Label values must be between 0 and 63 characters long and must conform

4407

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

4408

#

4409

# No more than 10 labels can be associated with a given finding.

4410

#

4411

# Examples:

4412

# * `"environment" : "production"`

4413

# * `"pipeline" : "etl"`

4414

"a_key": "A String",

4415

},

4416

"description": "A String", # A short description of where the data is coming from. Will be stored once

4417

# in the job. 256 max length.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4418

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4419

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4420

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

4421

# When used with redactContent only info_types and min_likelihood are currently

4422

# used.

4423

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

4424

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

4425

{ # Custom information type provided by the user. Used to find domain-specific

4426

# sensitive information configurable to the data in question.

4427

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

4428

# be used to match sensitive information specific to the data, such as a list

4429

# of employee IDs or job titles.

4430

#

4431

# Dictionary words are case-insensitive and all characters other than letters

4432

# and digits in the unicode [Basic Multilingual

4433

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

4434

# will be replaced with whitespace when scanning for matches, so the

4435

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

4436

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

4437

# surrounding any match must be of a different type than the adjacent

4438

# characters within the word, so letters must be next to non-letters and

4439

# digits next to non-digits. For example, the dictionary word "jen" will

4440

# match the first three letters of the text "jen123" but will return no

4441

# matches for "jennifer".

4442

#

4443

# Dictionary words containing a large number of characters that are not

4444

# letters or digits may result in unexpected findings because such characters

4445

# are treated as whitespace. The

4446

# [limits](https://cloud.google.com/dlp/limits) page contains details about

4447

# the size limits of dictionaries. For dictionaries that do not fit within

4448

# these constraints, consider using `LargeCustomDictionaryConfig` in the

4449

# `StoredInfoType` API.

4450

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

4451

# is accepted.

4452

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

4453

# Example: gs://[BUCKET_NAME]/dictionary.txt

4454

},

4455

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

4456

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

4457

# at least one phrase and every phrase must contain at least 2 characters

4458

# that are letters or digits. [required]

"A String",

],

},

},

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

4464

# infoType, when the name matches one of existing infoTypes and that infoType

4465

# is specified in `InspectContent.info_types` field. Specifying the latter

4466

# adds findings to the one detected by the system. If built-in info type is

4467

# not specified in `InspectContent.info_types` list then the name is treated

4468

# as a custom info type.

4469

"name": "A String", # Name of the information type. Either a name of your choosing when

4470

# creating a CustomInfoType, or one of the names listed

4471

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4472

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

4473

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

4474

},

4475

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

4476

# altered by a detection rule if the finding meets the criteria specified by

4477

# the rule. Defaults to `VERY_LIKELY` if not specified.

4478

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

4479

# Rules are applied in order that they are specified. Not supported for the

4480

# `surrogate_type` CustomInfoType.

4481

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

4482

# `CustomInfoType` to alter behavior under certain circumstances, depending

4483

# on the specific details of the rule. Not supported for the `surrogate_type`

4484

# custom infoType.

4485

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

4486

# proximity of hotwords.

4487

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

4488

# The total length of the window cannot exceed 1000 characters. Note that

4489

# the finding itself will be included in the window, so that hotwords may

4490

# be used to match substrings of the finding itself. For example, the

4491

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

4492

# adjusted upwards if the area code is known to be the local area code of

4493

# a company office using the hotword regex "$xxx$", where "xxx"

4494

# is the area code in question.

4495

# rule.

4496

"windowAfter": 42, # Number of characters after the finding to consider.

4497

"windowBefore": 42, # Number of characters before the finding to consider.

4498

},

4499

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

4500

# part of a detection rule.

4501

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

4502

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

4503

# levels. For example, if a finding would be `POSSIBLE` without the

4504

# detection rule and `relative_likelihood` is 1, then it is upgraded to

4505

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

4506

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

4507

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

4508

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

4509

# a final likelihood of `LIKELY`.

4510

},

4511

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

4512

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4513

# specified, the entire match is returned. No more than 3 may be included.

4514

42,

4515

],

4516

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4517

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4518

# google/re2 repository on GitHub.

},

},

},

],

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

4524

# support reversing.

4525

# such as

4526

# [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

4527

# These types of transformations are

4528

# those that perform pseudonymization, thereby producing a "surrogate" as

4529

# output. This should be used in conjunction with a field on the

4530

# transformation such as `surrogate_info_type`. This CustomInfoType does

4531

# not support the use of `detection_rules`.

4532

},

4533

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

4534

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4535

# specified, the entire match is returned. No more than 3 may be included.

4536

42,

4537

],

4538

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4539

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4540

# google/re2 repository on GitHub.

4541

},

4542

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

4543

# `InspectDataSource`. Not currently supported in `InspectContent`.

4544

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

4545

# `organizations/433245324/storedInfoTypes/432452342` or

4546

# `projects/project-id/storedInfoTypes/432452342`.

4547

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

4548

# inspection was created. Output-only field, populated by the system.

4549

},

4550

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

4551

# to be returned. It still can be used for rules matching.

4552

},

4553

],

4554

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

4555

# POSSIBLE.

4556

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

4557

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

4558

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

4559

# When set within `InspectContentRequest`, the maximum returned is 2000

4560

# regardless if this is set higher.

4561

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

4562

{ # Max findings configuration per infoType, per content item or long

4563

# running DlpJob.

4564

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

4565

# info_type should be provided. If InfoTypeLimit does not have an

4566

# info_type, the DLP API applies the limit against all info_types that

4567

# are found but not specified in another InfoTypeLimit.

4568

"name": "A String", # Name of the information type. Either a name of your choosing when

4569

# creating a CustomInfoType, or one of the names listed

4570

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4571

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

4572

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

4573

},

4574

"maxFindings": 42, # Max findings limit for the given infoType.

4575

},

4576

],

4577

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

4578

# When set within `InspectJobConfig`,

4579

# the maximum returned is 2000 regardless if this is set higher.

4580

# When set within `InspectContentRequest`, this field is ignored.

4581

},

4582

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

4583

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

4584

# included in the response; see Finding.quote.

4585

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

4586

# Exclusion rules, contained in the set are executed in the end, other

4587

# rules are executed in the order they are specified for each info type.

4588

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

4589

# circumstances, depending on the specific details of the rules within the set.

4590

"infoTypes": [ # List of infoTypes this rule set is applied to.

4591

{ # Type of information detected by the API.

4592

"name": "A String", # Name of the information type. Either a name of your choosing when

4593

# creating a CustomInfoType, or one of the names listed

4594

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4595

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

4596

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

4597

},

4598

],

4599

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

4600

{ # A single inspection rule to be applied to infoTypes, specified in

4601

# `InspectionRuleSet`.

4602

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

4603

# proximity of hotwords.

4604

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

4605

# The total length of the window cannot exceed 1000 characters. Note that

4606

# the finding itself will be included in the window, so that hotwords may

4607

# be used to match substrings of the finding itself. For example, the

4608

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

4609

# adjusted upwards if the area code is known to be the local area code of

4610

# a company office using the hotword regex "$xxx$", where "xxx"

4611

# is the area code in question.

4612

# rule.

4613

"windowAfter": 42, # Number of characters after the finding to consider.

4614

"windowBefore": 42, # Number of characters before the finding to consider.

4615

},

4616

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

4617

# part of a detection rule.

4618

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

4619

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

4620

# levels. For example, if a finding would be `POSSIBLE` without the

4621

# detection rule and `relative_likelihood` is 1, then it is upgraded to

4622

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

4623

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

4624

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

4625

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

4626

# a final likelihood of `LIKELY`.

4627

},

4628

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

4629

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4630

# specified, the entire match is returned. No more than 3 may be included.

4631

42,

4632

],

4633

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4634

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4635

# google/re2 repository on GitHub.

4636

},

4637

},

4638

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

4639

# `InspectionRuleSet` are removed from results.

4640

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

4641

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

4642

# be used to match sensitive information specific to the data, such as a list

4643

# of employee IDs or job titles.

4644

#

4645

# Dictionary words are case-insensitive and all characters other than letters

4646

# and digits in the unicode [Basic Multilingual

4647

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

4648

# will be replaced with whitespace when scanning for matches, so the

4649

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

4650

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

4651

# surrounding any match must be of a different type than the adjacent

4652

# characters within the word, so letters must be next to non-letters and

4653

# digits next to non-digits. For example, the dictionary word "jen" will

4654

# match the first three letters of the text "jen123" but will return no

4655

# matches for "jennifer".

4656

#

4657

# Dictionary words containing a large number of characters that are not

4658

# letters or digits may result in unexpected findings because such characters

4659

# are treated as whitespace. The

4660

# [limits](https://cloud.google.com/dlp/limits) page contains details about

4661

# the size limits of dictionaries. For dictionaries that do not fit within

4662

# these constraints, consider using `LargeCustomDictionaryConfig` in the

4663

# `StoredInfoType` API.

4664

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

4665

# is accepted.

4666

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

4667

# Example: gs://[BUCKET_NAME]/dictionary.txt

4668

},

4669

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

4670

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

4671

# at least one phrase and every phrase must contain at least 2 characters

4672

# that are letters or digits. [required]

"A String",

],

},

},

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

4678

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

4679

# contained within with a finding of an infoType from this list. For

4680

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

4681

# `exclusion_rule` containing `exclude_info_types.info_types` with

4682

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

4683

# with EMAIL_ADDRESS finding.

4684

# That leads to "555-222-2222@example.org" to generate only a single

4685

# finding, namely email address.

4686

{ # Type of information detected by the API.

4687

"name": "A String", # Name of the information type. Either a name of your choosing when

4688

# creating a CustomInfoType, or one of the names listed

4689

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4690

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

4691

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

},

],

},

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

4696

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4697

# specified, the entire match is returned. No more than 3 may be included.

4698

42,

4699

],

4700

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4701

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4702

# google/re2 repository on GitHub.

},

},

},

],

},

],

"contentOptions": [ # List of options defining data content to scan.

4710

# If empty, text, images, and other content will be included.

4711

"A String",

4712

],

4713

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

4714

# InfoType values returned by ListInfoTypes or listed at

4715

# https://cloud.google.com/dlp/docs/infotypes-reference.

4716

#

4717

# When no InfoTypes or CustomInfoTypes are specified in a request, the

4718

# system may automatically choose what detectors to run. By default this may

4719

# be all types, but may change over time as detectors are updated.

4720

#

4721

# If you need precise control and predictability as to what detectors are

4722

# run you should specify specific InfoTypes listed in the reference,

4723

# otherwise a default list will be used, which may change over time.

4724

{ # Type of information detected by the API.

4725

"name": "A String", # Name of the information type. Either a name of your choosing when

4726

# creating a CustomInfoType, or one of the names listed

4727

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4728

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

4729

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

4730

},

4731

],

4732

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4733

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4734

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

4735

# triggeredJob is created, for example

4736

# `projects/dlp-test-project/jobTriggers/53234423`.

4737

"displayName": "A String", # Display name (max 100 chars)

4738

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

4739

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

4740

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4741

},

4742

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4743

"nextPageToken": "A String", # If the next page is available then the next page token to be used

4744

# 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>

4750

<pre>Retrieves the next page of results.

4751

4752

Args:

4753

previous_request: The request for the previous page. (required)

4754

previous_response: The response from the request for the previous page. (required)

4755

4756

Returns:

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4757

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]

4758

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]

4763

<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]

4764

<pre>Updates a job trigger.

4765

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

4766

4767

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4768

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]

4769

`projects/dlp-test-project/jobTriggers/53234423`. (required)

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4770

body: object, The request body.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4771

The object takes the form of:

4772

4773

{ # Request message for UpdateJobTrigger.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4774

"updateMask": "A String", # Mask to control which fields get updated.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4775

"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]

4776

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4777

"status": "A String", # Required. A status for this trigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4778

"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]

4779

# needs to trigger for a job to be started. The list may contain only

4780

# a single Schedule trigger and must have at least one object.

4781

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4782

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

4783

# Early access feature is in a pre-release state and might change or have

4784

# limited support. For more information, see

4785

# https://cloud.google.com/products#product-launch-stages.

4786

# and finished.

4787

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4788

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

4789

"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]

4790

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4791

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4792

# A scheduled start time will be skipped if the previous

4793

# execution has not ended when its scheduled time occurs.

4794

#

4795

# This value must be set to a time duration greater than or equal

4796

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4797

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4798

},

4799

],

4800

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

4801

# errors may result in the JobTrigger automatically being paused.

4802

# Will return the last 100 errors. Whenever the JobTrigger is modified

4803

# this list will be cleared.

4804

{ # Details information about an error encountered during job execution or

4805

# the results of an unsuccessful activation of the JobTrigger.

4806

"timestamps": [ # The times the error occurred.

4807

"A String",

4808

],

4809

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

4810

# different programming environments, including REST APIs and RPC APIs. It is

4811

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

4812

# three pieces of data: error code, error message, and error details.

4813

#

4814

# You can find out more about this error model and how to work with it in the

4815

# [API Design Guide](https://cloud.google.com/apis/design/errors).

4816

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

4817

"details": [ # A list of messages that carry the error details. There is a common set of

4818

# message types for APIs to use.

4819

{

4820

"a_key": "", # Properties of the object. Contains field @type with type URL.

4821

},

4822

],

4823

"message": "A String", # A developer-facing error message, which should be in English. Any

4824

# user-facing error message should be localized and sent in the

4825

# google.rpc.Status.details field, or localized by the client.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4826

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4827

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4828

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4829

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

4830

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4831

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

4832

# `inspect_config` will be merged into the values persisted as part of the

4833

# template.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4834

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4835

{ # A task to execute on the completion of a job.

4836

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4837

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

4838

# will publish a metric to stack driver on each infotype requested and

4839

# how many findings were found for it. CustomDetectors will be bucketed

4840

# as 'Custom' under the Stackdriver label 'info_type'.

4841

},

4842

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

4843

# results of the DlpJob will be applied to the entry for the resource scanned

4844

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

4845

# be deleted. InfoType naming patterns are strictly enforced when using this

4846

# feature. Note that the findings will be persisted in Cloud Data Catalog

4847

# storage and are governed by Data Catalog service-specific policy, see

4848

# https://cloud.google.com/terms/service-terms

4849

# Only a single instance of this action can be specified and only allowed if

4850

# all resources being scanned are BigQuery tables.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4851

# Compatible with: Inspect

4852

},

4853

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

4854

# completion/failure.

4855

# completion/failure.

4856

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4857

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

4858

# message contains a single field, `DlpJobName`, which is equal to the

4859

# finished job's

4860

# [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

4861

# Compatible with: Inspect, Risk

4862

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

4863

# publishing access rights to the DLP API service account executing

4864

# the long running DlpJob sending the notifications.

4865

# Format is projects/{project}/topics/{topic}.

4866

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4867

"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]

4868

# OutputStorageConfig. Only a single instance of this action can be

4869

# specified.

4870

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4871

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4872

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

4873

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

4874

# from the `Finding` object. If appending to an existing table, any columns

4875

# from the predefined schema that are missing will be added. No columns in

4876

# the existing table will be deleted.

4877

#

4878

# If unspecified, then all available columns will be used for a new table or

4879

# an (existing) table with no schema, and no changes will be made to an

4880

# existing table that has a schema.

4881

# Only for use with external storage.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4882

"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]

4883

# dataset. If table_id is not set a new one will be generated

4884

# for you with the following format:

4885

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

4886

# generating the date details.

4887

#

4888

# For Inspect, each column in an existing output table must have the same

4889

# name, type, and mode of a field in the `Finding` object.

4890

#

4891

# For Risk, an existing output table should be the output of a previous

4892

# Risk analysis job run on the same source table, with the same privacy

4893

# metric and quasi-identifiers. Risk jobs that analyze the same table but

4894

# compute a different privacy metric, or use different sets of

4895

# quasi-identifiers, cannot store their results in the same table.

4896

# identified by its project_id, dataset_id, and table_name. Within a query

4897

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4898

# `<project_id>:<dataset_id>.<table_id>` or

4899

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4900

"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]

4901

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4902

"datasetId": "A String", # Dataset ID of the table.

4903

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4904

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4905

},

4906

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4907

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

4908

# Command Center (CSCC Alpha).

4909

# This action is only available for projects which are parts of

4910

# an organization and whitelisted for the alpha Cloud Security Command

4911

# Center.

4912

# The action will publish count of finding instances and their info types.

4913

# The summary of findings will be persisted in CSCC and are governed by CSCC

4914

# service-specific policy, see https://cloud.google.com/terms/service-terms

4915

# Only a single instance of this action can be specified.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4916

# Compatible with: Inspect

4917

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4918

},

4919

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4920

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4921

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

4922

# bucket.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4923

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

4924

# number of bytes scanned is rounded down. Must be between 0 and 100,

4925

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

4926

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

4927

"fileTypes": [ # List of file type groups to include in the scan.

4928

# If empty, all files are scanned and available data format processors

4929

# are applied. In addition, the binary content of the selected files

4930

# is always scanned as well.

4931

# Images are scanned only as binary if the specified region

4932

# does not support image inspection and no file_types were specified.

4933

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

4934

"A String",

4935

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4936

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

4937

# than this value then the rest of the bytes are omitted. Only one

4938

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4939

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

4940

# Number of files scanned is rounded down. Must be between 0 and 100,

4941

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4942

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

4943

"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

4944

# `regex_file_set` must be set.

4945

# expressions are used to allow fine-grained control over which files in the

4946

# bucket to include.

4947

#

4948

# Included files are those that match at least one item in `include_regex` and

4949

# do not match any items in `exclude_regex`. Note that a file that matches

4950

# items from both lists will _not_ be included. For a match to occur, the

4951

# entire file path (i.e., everything in the url after the bucket name) must

4952

# match the regular expression.

4953

#

4954

# For example, given the input `{bucket_name: "mybucket", include_regex:

4955

# ["directory1/.*"], exclude_regex:

4956

# ["directory1/excluded.*"]}`:

4957

#

4958

# * `gs://mybucket/directory1/myfile` will be included

4959

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

4960

# across `/`)

4961

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

4962

# full path doesn't match any items in `include_regex`)

4963

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

4964

# matches an item in `exclude_regex`)

4965

#

4966

# If `include_regex` is left empty, it will match all files by default

4967

# (this is equivalent to setting `include_regex: [".*"]`).

4968

#

4969

# Some other common use cases:

4970

#

4971

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

4972

# files in `mybucket` except for .pdf files

4973

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

4974

# include all files directly under `gs://mybucket/directory/`, without matching

4975

# across `/`

4976

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4977

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4978

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4979

# excluded from the scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4980

#

4981

# Regular expressions use RE2

4982

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

4983

# under the google/re2 repository on GitHub.

4984

"A String",

4985

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4986

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4987

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

4988

# included in the set of files, except for those that also match an item in

4989

# `exclude_regex`. Leaving this field empty will match all files by default

4990

# (this is equivalent to including `.*` in the list).

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

4991

#

4992

# Regular expressions use RE2

4993

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

4994

# 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

4999

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

5000

#

5001

# If the url ends in a trailing slash, the bucket or directory represented

5002

# by the url will be scanned non-recursively (content in sub-directories

5003

# will not be scanned). This means that `gs://mybucket/` is equivalent to

5004

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

5005

# `gs://mybucket/directory/*`.

5006

#

5007

# Exactly one of `url` or `regex_file_set` must be set.

5008

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5009

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5010

},

5011

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5012

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5013

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

5014

# identified by its project_id, dataset_id, and table_name. Within a query

5015

# a table is often referenced with a string in the format of:

5016

# `<project_id>:<dataset_id>.<table_id>` or

5017

# `<project_id>.<dataset_id>.<table_id>`.

5018

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

5019

# If omitted, project ID is inferred from the API call.

5020

"datasetId": "A String", # Dataset ID of the table.

5021

"tableId": "A String", # Name of the table.

5022

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5023

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

5024

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

5025

# 100 means no limit. Defaults to 0. Only one of rows_limit and

5026

# rows_limit_percent can be specified. Cannot be used in conjunction with

5027

# TimespanConfig.

5028

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

5029

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

5030

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

5031

# Cannot be used in conjunction with TimespanConfig.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5032

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

5033

# `actions.saveFindings.outputConfig.table` is specified, the values of

5034

# columns specified here are available in the output table under

5035

# `location.content_locations.record_location.record_key.id_values`. Nested

5036

# fields such as `person.birthdate.year` are allowed.

5037

{ # General identifier of a data field in a storage service.

5038

"name": "A String", # Name describing the field.

5039

},

5040

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5041

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

5042

# inspection of entire columns which you know have no findings.

5043

{ # General identifier of a data field in a storage service.

5044

"name": "A String", # Name describing the field.

5045

},

5046

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5047

},

5048

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

5049

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

5050

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

5051

# Used for data sources like Datastore and BigQuery.

5052

#

5053

# For BigQuery:

5054

# Required to filter out rows based on the given start and

5055

# end times. If not specified and the table was modified between the given

5056

# start and end times, the entire table will be scanned.

5057

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

5058

# `TIMESTAMP`, or `DATETIME` BigQuery column.

5059

#

5060

# For Datastore.

5061

# Valid data types of the timestamp field are: `TIMESTAMP`.

5062

# Datastore entity will be scanned if the timestamp property does not

5063

# exist or its value is empty or invalid.

5064

"name": "A String", # Name describing the field.

5065

},

5066

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

5067

# a valid start_time to avoid scanning files that have not been modified

5068

# since the last time the JobTrigger executed. This will be based on the

5069

# time of the execution of the last run of the JobTrigger.

5070

"startTime": "A String", # Exclude files or rows older than this value.

5071

"endTime": "A String", # Exclude files or rows newer than this value.

5072

# If set to zero, no upper time limit is applied.

5073

},

5074

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

5075

"kind": { # A representation of a Datastore kind. # The kind to process.

5076

"name": "A String", # The name of the kind.

5077

},

5078

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

5079

# by project and namespace, however the namespace ID may be empty.

5080

# A partition ID identifies a grouping of entities. The grouping is always

5081

# by project and namespace, however the namespace ID may be empty.

5082

#

5083

# A partition ID contains several dimensions:

5084

# project ID and namespace ID.

5085

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

5086

"projectId": "A String", # The ID of the project to which the entities belong.

5087

},

5088

},

5089

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

5090

# Early access feature is in a pre-release state and might change or have

5091

# limited support. For more information, see

5092

# https://cloud.google.com/products#product-launch-stages.

5093

# of Google Cloud Platform.

5094

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

5095

# meaningful such as the columns that are primary keys.

5096

"identifyingFields": [ # The columns that are the primary keys for table objects included in

5097

# ContentItem. A copy of this cell's value will stored alongside alongside

5098

# each finding so that the finding can be traced to the specific row it came

5099

# from. No more than 3 may be provided.

5100

{ # General identifier of a data field in a storage service.

5101

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

5106

# 'finding_labels' map. Request may contain others, but any missing one of

5107

# these will be rejected.

5108

#

5109

# Label keys must be between 1 and 63 characters long and must conform

5110

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

5111

#

5112

# No more than 10 keys can be required.

5113

"A String",

5114

],

5115

"labels": { # To organize findings, these labels will be added to each finding.

5116

#

5117

# Label keys must be between 1 and 63 characters long and must conform

5118

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

5119

#

5120

# Label values must be between 0 and 63 characters long and must conform

5121

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

5122

#

5123

# No more than 10 labels can be associated with a given finding.

5124

#

5125

# Examples:

5126

# * `"environment" : "production"`

5127

# * `"pipeline" : "etl"`

5128

"a_key": "A String",

5129

},

5130

"description": "A String", # A short description of where the data is coming from. Will be stored once

5131

# in the job. 256 max length.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5132

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5133

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5134

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

5135

# When used with redactContent only info_types and min_likelihood are currently

5136

# used.

5137

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

5138

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

5139

{ # Custom information type provided by the user. Used to find domain-specific

5140

# sensitive information configurable to the data in question.

5141

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

5142

# be used to match sensitive information specific to the data, such as a list

5143

# of employee IDs or job titles.

5144

#

5145

# Dictionary words are case-insensitive and all characters other than letters

5146

# and digits in the unicode [Basic Multilingual

5147

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5148

# will be replaced with whitespace when scanning for matches, so the

5149

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5150

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

5151

# surrounding any match must be of a different type than the adjacent

5152

# characters within the word, so letters must be next to non-letters and

5153

# digits next to non-digits. For example, the dictionary word "jen" will

5154

# match the first three letters of the text "jen123" but will return no

5155

# matches for "jennifer".

5156

#

5157

# Dictionary words containing a large number of characters that are not

5158

# letters or digits may result in unexpected findings because such characters

5159

# are treated as whitespace. The

5160

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5161

# the size limits of dictionaries. For dictionaries that do not fit within

5162

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5163

# `StoredInfoType` API.

5164

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

5165

# is accepted.

5166

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

5167

# Example: gs://[BUCKET_NAME]/dictionary.txt

5168

},

5169

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5170

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

5171

# at least one phrase and every phrase must contain at least 2 characters

5172

# that are letters or digits. [required]

"A String",

],

},

},

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

5178

# infoType, when the name matches one of existing infoTypes and that infoType

5179

# is specified in `InspectContent.info_types` field. Specifying the latter

5180

# adds findings to the one detected by the system. If built-in info type is

5181

# not specified in `InspectContent.info_types` list then the name is treated

5182

# as a custom info type.

5183

"name": "A String", # Name of the information type. Either a name of your choosing when

5184

# creating a CustomInfoType, or one of the names listed

5185

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5186

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

5187

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

5188

},

5189

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

5190

# altered by a detection rule if the finding meets the criteria specified by

5191

# the rule. Defaults to `VERY_LIKELY` if not specified.

5192

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

5193

# Rules are applied in order that they are specified. Not supported for the

5194

# `surrogate_type` CustomInfoType.

5195

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

5196

# `CustomInfoType` to alter behavior under certain circumstances, depending

5197

# on the specific details of the rule. Not supported for the `surrogate_type`

5198

# custom infoType.

5199

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

5200

# proximity of hotwords.

5201

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5202

# The total length of the window cannot exceed 1000 characters. Note that

5203

# the finding itself will be included in the window, so that hotwords may

5204

# be used to match substrings of the finding itself. For example, the

5205

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

5206

# adjusted upwards if the area code is known to be the local area code of

5207

# a company office using the hotword regex "$xxx$", where "xxx"

5208

# is the area code in question.

5209

# rule.

5210

"windowAfter": 42, # Number of characters after the finding to consider.

5211

"windowBefore": 42, # Number of characters before the finding to consider.

5212

},

5213

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

5214

# part of a detection rule.

5215

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

5216

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

5217

# levels. For example, if a finding would be `POSSIBLE` without the

5218

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5219

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5220

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5221

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5222

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5223

# a final likelihood of `LIKELY`.

5224

},

5225

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5226

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5227

# specified, the entire match is returned. No more than 3 may be included.

5228

42,

5229

],

5230

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5231

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5232

# google/re2 repository on GitHub.

},

},

},

],

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

5238

# support reversing.

5239

# such as

5240

# [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

5241

# These types of transformations are

5242

# those that perform pseudonymization, thereby producing a "surrogate" as

5243

# output. This should be used in conjunction with a field on the

5244

# transformation such as `surrogate_info_type`. This CustomInfoType does

5245

# not support the use of `detection_rules`.

5246

},

5247

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

5248

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5249

# specified, the entire match is returned. No more than 3 may be included.

5250

42,

5251

],

5252

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5253

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5254

# google/re2 repository on GitHub.

5255

},

5256

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

5257

# `InspectDataSource`. Not currently supported in `InspectContent`.

5258

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

5259

# `organizations/433245324/storedInfoTypes/432452342` or

5260

# `projects/project-id/storedInfoTypes/432452342`.

5261

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

5262

# inspection was created. Output-only field, populated by the system.

5263

},

5264

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

5265

# to be returned. It still can be used for rules matching.

5266

},

5267

],

5268

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

5269

# POSSIBLE.

5270

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

5271

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

5272

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

5273

# When set within `InspectContentRequest`, the maximum returned is 2000

5274

# regardless if this is set higher.

5275

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

5276

{ # Max findings configuration per infoType, per content item or long

5277

# running DlpJob.

5278

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

5279

# info_type should be provided. If InfoTypeLimit does not have an

5280

# info_type, the DLP API applies the limit against all info_types that

5281

# are found but not specified in another InfoTypeLimit.

5282

"name": "A String", # Name of the information type. Either a name of your choosing when

5283

# creating a CustomInfoType, or one of the names listed

5284

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5285

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

5286

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

5287

},

5288

"maxFindings": 42, # Max findings limit for the given infoType.

5289

},

5290

],

5291

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

5292

# When set within `InspectJobConfig`,

5293

# the maximum returned is 2000 regardless if this is set higher.

5294

# When set within `InspectContentRequest`, this field is ignored.

5295

},

5296

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

5297

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

5298

# included in the response; see Finding.quote.

5299

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

5300

# Exclusion rules, contained in the set are executed in the end, other

5301

# rules are executed in the order they are specified for each info type.

5302

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

5303

# circumstances, depending on the specific details of the rules within the set.

5304

"infoTypes": [ # List of infoTypes this rule set is applied to.

5305

{ # Type of information detected by the API.

5306

"name": "A String", # Name of the information type. Either a name of your choosing when

5307

# creating a CustomInfoType, or one of the names listed

5308

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5309

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

5310

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

5311

},

5312

],

5313

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

5314

{ # A single inspection rule to be applied to infoTypes, specified in

5315

# `InspectionRuleSet`.

5316

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

5317

# proximity of hotwords.

5318

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5319

# The total length of the window cannot exceed 1000 characters. Note that

5320

# the finding itself will be included in the window, so that hotwords may

5321

# be used to match substrings of the finding itself. For example, the

5322

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

5323

# adjusted upwards if the area code is known to be the local area code of

5324

# a company office using the hotword regex "$xxx$", where "xxx"

5325

# is the area code in question.

5326

# rule.

5327

"windowAfter": 42, # Number of characters after the finding to consider.

5328

"windowBefore": 42, # Number of characters before the finding to consider.

5329

},

5330

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

5331

# part of a detection rule.

5332

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

5333

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

5334

# levels. For example, if a finding would be `POSSIBLE` without the

5335

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5336

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5337

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5338

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5339

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5340

# a final likelihood of `LIKELY`.

5341

},

5342

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5343

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5344

# specified, the entire match is returned. No more than 3 may be included.

5345

42,

5346

],

5347

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5348

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5349

# google/re2 repository on GitHub.

5350

},

5351

},

5352

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

5353

# `InspectionRuleSet` are removed from results.

5354

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

5355

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

5356

# be used to match sensitive information specific to the data, such as a list

5357

# of employee IDs or job titles.

5358

#

5359

# Dictionary words are case-insensitive and all characters other than letters

5360

# and digits in the unicode [Basic Multilingual

5361

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5362

# will be replaced with whitespace when scanning for matches, so the

5363

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5364

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

5365

# surrounding any match must be of a different type than the adjacent

5366

# characters within the word, so letters must be next to non-letters and

5367

# digits next to non-digits. For example, the dictionary word "jen" will

5368

# match the first three letters of the text "jen123" but will return no

5369

# matches for "jennifer".

5370

#

5371

# Dictionary words containing a large number of characters that are not

5372

# letters or digits may result in unexpected findings because such characters

5373

# are treated as whitespace. The

5374

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5375

# the size limits of dictionaries. For dictionaries that do not fit within

5376

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5377

# `StoredInfoType` API.

5378

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

5379

# is accepted.

5380

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

5381

# Example: gs://[BUCKET_NAME]/dictionary.txt

5382

},

5383

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5384

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

5385

# at least one phrase and every phrase must contain at least 2 characters

5386

# that are letters or digits. [required]

"A String",

],

},

},

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

5392

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

5393

# contained within with a finding of an infoType from this list. For

5394

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

5395

# `exclusion_rule` containing `exclude_info_types.info_types` with

5396

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

5397

# with EMAIL_ADDRESS finding.

5398

# That leads to "555-222-2222@example.org" to generate only a single

5399

# finding, namely email address.

5400

{ # Type of information detected by the API.

5401

"name": "A String", # Name of the information type. Either a name of your choosing when

5402

# creating a CustomInfoType, or one of the names listed

5403

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5404

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

5405

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

},

],

},

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

5410

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5411

# specified, the entire match is returned. No more than 3 may be included.

5412

42,

5413

],

5414

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5415

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5416

# google/re2 repository on GitHub.

},

},

},

],

},

],

"contentOptions": [ # List of options defining data content to scan.

5424

# If empty, text, images, and other content will be included.

5425

"A String",

5426

],

5427

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

5428

# InfoType values returned by ListInfoTypes or listed at

5429

# https://cloud.google.com/dlp/docs/infotypes-reference.

5430

#

5431

# When no InfoTypes or CustomInfoTypes are specified in a request, the

5432

# system may automatically choose what detectors to run. By default this may

5433

# be all types, but may change over time as detectors are updated.

5434

#

5435

# If you need precise control and predictability as to what detectors are

5436

# run you should specify specific InfoTypes listed in the reference,

5437

# otherwise a default list will be used, which may change over time.

5438

{ # Type of information detected by the API.

5439

"name": "A String", # Name of the information type. Either a name of your choosing when

5440

# creating a CustomInfoType, or one of the names listed

5441

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5442

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

5443

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

5444

},

5445

],

5446

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5447

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5448

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

5449

# triggeredJob is created, for example

5450

# `projects/dlp-test-project/jobTriggers/53234423`.

5451

"displayName": "A String", # Display name (max 100 chars)

5452

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

5453

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

5454

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5455

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5456

}

5457

5458

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

5465

5466

{ # Contains a configuration to make dlp api calls on a repeating basis.

5467

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5468

"status": "A String", # Required. A status for this trigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5469

"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]

5470

# needs to trigger for a job to be started. The list may contain only

5471

# a single Schedule trigger and must have at least one object.

5472

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5473

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

5474

# Early access feature is in a pre-release state and might change or have

5475

# limited support. For more information, see

5476

# https://cloud.google.com/products#product-launch-stages.

5477

# and finished.

5478

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5479

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

5480

"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]

5481

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5482

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5483

# A scheduled start time will be skipped if the previous

5484

# execution has not ended when its scheduled time occurs.

5485

#

5486

# This value must be set to a time duration greater than or equal

5487

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5488

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5489

},

5490

],

5491

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

5492

# errors may result in the JobTrigger automatically being paused.

5493

# Will return the last 100 errors. Whenever the JobTrigger is modified

5494

# this list will be cleared.

5495

{ # Details information about an error encountered during job execution or

5496

# the results of an unsuccessful activation of the JobTrigger.

5497

"timestamps": [ # The times the error occurred.

5498

"A String",

5499

],

5500

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

5501

# different programming environments, including REST APIs and RPC APIs. It is

5502

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

5503

# three pieces of data: error code, error message, and error details.

5504

#

5505

# You can find out more about this error model and how to work with it in the

5506

# [API Design Guide](https://cloud.google.com/apis/design/errors).

5507

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

5508

"details": [ # A list of messages that carry the error details. There is a common set of

5509

# message types for APIs to use.

5510

{

5511

"a_key": "", # Properties of the object. Contains field @type with type URL.

5512

},

5513

],

5514

"message": "A String", # A developer-facing error message, which should be in English. Any

5515

# user-facing error message should be localized and sent in the

5516

# google.rpc.Status.details field, or localized by the client.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5517

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5518

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5519

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5520

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

5521

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5522

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

5523

# `inspect_config` will be merged into the values persisted as part of the

5524

# template.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5525

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5526

{ # A task to execute on the completion of a job.

5527

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5528

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

5529

# will publish a metric to stack driver on each infotype requested and

5530

# how many findings were found for it. CustomDetectors will be bucketed

5531

# as 'Custom' under the Stackdriver label 'info_type'.

5532

},

5533

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

5534

# results of the DlpJob will be applied to the entry for the resource scanned

5535

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

5536

# be deleted. InfoType naming patterns are strictly enforced when using this

5537

# feature. Note that the findings will be persisted in Cloud Data Catalog

5538

# storage and are governed by Data Catalog service-specific policy, see

5539

# https://cloud.google.com/terms/service-terms

5540

# Only a single instance of this action can be specified and only allowed if

5541

# all resources being scanned are BigQuery tables.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5542

# Compatible with: Inspect

5543

},

5544

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

5545

# completion/failure.

5546

# completion/failure.

5547

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5548

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

5549

# message contains a single field, `DlpJobName`, which is equal to the

5550

# finished job's

5551

# [`DlpJob.name`](https://cloud.google.com/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

5552

# Compatible with: Inspect, Risk

5553

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

5554

# publishing access rights to the DLP API service account executing

5555

# the long running DlpJob sending the notifications.

5556

# Format is projects/{project}/topics/{topic}.

5557

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5558

"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]

5559

# OutputStorageConfig. Only a single instance of this action can be

5560

# specified.

5561

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5562

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5563

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

5564

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

5565

# from the `Finding` object. If appending to an existing table, any columns

5566

# from the predefined schema that are missing will be added. No columns in

5567

# the existing table will be deleted.

5568

#

5569

# If unspecified, then all available columns will be used for a new table or

5570

# an (existing) table with no schema, and no changes will be made to an

5571

# existing table that has a schema.

5572

# Only for use with external storage.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5573

"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]

5574

# dataset. If table_id is not set a new one will be generated

5575

# for you with the following format:

5576

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

5577

# generating the date details.

5578

#

5579

# For Inspect, each column in an existing output table must have the same

5580

# name, type, and mode of a field in the `Finding` object.

5581

#

5582

# For Risk, an existing output table should be the output of a previous

5583

# Risk analysis job run on the same source table, with the same privacy

5584

# metric and quasi-identifiers. Risk jobs that analyze the same table but

5585

# compute a different privacy metric, or use different sets of

5586

# quasi-identifiers, cannot store their results in the same table.

5587

# identified by its project_id, dataset_id, and table_name. Within a query

5588

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5589

# `<project_id>:<dataset_id>.<table_id>` or

5590

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5591

"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]

5592

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5593

"datasetId": "A String", # Dataset ID of the table.

5594

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5595

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5596

},

5597

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5598

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

5599

# Command Center (CSCC Alpha).

5600

# This action is only available for projects which are parts of

5601

# an organization and whitelisted for the alpha Cloud Security Command

5602

# Center.

5603

# The action will publish count of finding instances and their info types.

5604

# The summary of findings will be persisted in CSCC and are governed by CSCC

5605

# service-specific policy, see https://cloud.google.com/terms/service-terms

5606

# Only a single instance of this action can be specified.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5607

# Compatible with: Inspect

5608

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5609

},

5610

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5611

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5612

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

5613

# bucket.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5614

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

5615

# number of bytes scanned is rounded down. Must be between 0 and 100,

5616

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

5617

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

5618

"fileTypes": [ # List of file type groups to include in the scan.

5619

# If empty, all files are scanned and available data format processors

5620

# are applied. In addition, the binary content of the selected files

5621

# is always scanned as well.

5622

# Images are scanned only as binary if the specified region

5623

# does not support image inspection and no file_types were specified.

5624

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

5625

"A String",

5626

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5627

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

5628

# than this value then the rest of the bytes are omitted. Only one

5629

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5630

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

5631

# Number of files scanned is rounded down. Must be between 0 and 100,

5632

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5633

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

5634

"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

5635

# `regex_file_set` must be set.

5636

# expressions are used to allow fine-grained control over which files in the

5637

# bucket to include.

5638

#

5639

# Included files are those that match at least one item in `include_regex` and

5640

# do not match any items in `exclude_regex`. Note that a file that matches

5641

# items from both lists will _not_ be included. For a match to occur, the

5642

# entire file path (i.e., everything in the url after the bucket name) must

5643

# match the regular expression.

5644

#

5645

# For example, given the input `{bucket_name: "mybucket", include_regex:

5646

# ["directory1/.*"], exclude_regex:

5647

# ["directory1/excluded.*"]}`:

5648

#

5649

# * `gs://mybucket/directory1/myfile` will be included

5650

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

5651

# across `/`)

5652

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

5653

# full path doesn't match any items in `include_regex`)

5654

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

5655

# matches an item in `exclude_regex`)

5656

#

5657

# If `include_regex` is left empty, it will match all files by default

5658

# (this is equivalent to setting `include_regex: [".*"]`).

5659

#

5660

# Some other common use cases:

5661

#

5662

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

5663

# files in `mybucket` except for .pdf files

5664

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

5665

# include all files directly under `gs://mybucket/directory/`, without matching

5666

# across `/`

5667

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5668

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5669

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5670

# excluded from the scan.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5671

#

5672

# Regular expressions use RE2

5673

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

5674

# under the google/re2 repository on GitHub.

5675

"A String",

5676

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5677

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5678

# the bucket that match at least one of these regular expressions will be

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5679

# included in the set of files, except for those that also match an item in

5680

# `exclude_regex`. Leaving this field empty will match all files by default

5681

# (this is equivalent to including `.*` in the list).

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5682

#

5683

# Regular expressions use RE2

5684

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

5685

# 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

5690

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

5691

#

5692

# If the url ends in a trailing slash, the bucket or directory represented

5693

# by the url will be scanned non-recursively (content in sub-directories

5694

# will not be scanned). This means that `gs://mybucket/` is equivalent to

5695

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

5696

# `gs://mybucket/directory/*`.

5697

#

5698

# Exactly one of `url` or `regex_file_set` must be set.

5699

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5700

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5701

},

5702

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5703

"sampleMethod": "A String",

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5704

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

5705

# identified by its project_id, dataset_id, and table_name. Within a query

5706

# a table is often referenced with a string in the format of:

5707

# `<project_id>:<dataset_id>.<table_id>` or

5708

# `<project_id>.<dataset_id>.<table_id>`.

5709

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

5710

# If omitted, project ID is inferred from the API call.

5711

"datasetId": "A String", # Dataset ID of the table.

5712

"tableId": "A String", # Name of the table.

5713

},

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5714

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

5715

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

5716

# 100 means no limit. Defaults to 0. Only one of rows_limit and

5717

# rows_limit_percent can be specified. Cannot be used in conjunction with

5718

# TimespanConfig.

5719

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

5720

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

5721

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

5722

# Cannot be used in conjunction with TimespanConfig.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5723

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

5724

# `actions.saveFindings.outputConfig.table` is specified, the values of

5725

# columns specified here are available in the output table under

5726

# `location.content_locations.record_location.record_key.id_values`. Nested

5727

# fields such as `person.birthdate.year` are allowed.

5728

{ # General identifier of a data field in a storage service.

5729

"name": "A String", # Name describing the field.

5730

},

5731

],

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5732

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

5733

# inspection of entire columns which you know have no findings.

5734

{ # General identifier of a data field in a storage service.

5735

"name": "A String", # Name describing the field.

5736

},

5737

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5738

},

5739

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

5740

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

5741

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

5742

# Used for data sources like Datastore and BigQuery.

5743

#

5744

# For BigQuery:

5745

# Required to filter out rows based on the given start and

5746

# end times. If not specified and the table was modified between the given

5747

# start and end times, the entire table will be scanned.

5748

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

5749

# `TIMESTAMP`, or `DATETIME` BigQuery column.

5750

#

5751

# For Datastore.

5752

# Valid data types of the timestamp field are: `TIMESTAMP`.

5753

# Datastore entity will be scanned if the timestamp property does not

5754

# exist or its value is empty or invalid.

5755

"name": "A String", # Name describing the field.

5756

},

5757

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

5758

# a valid start_time to avoid scanning files that have not been modified

5759

# since the last time the JobTrigger executed. This will be based on the

5760

# time of the execution of the last run of the JobTrigger.

5761

"startTime": "A String", # Exclude files or rows older than this value.

5762

"endTime": "A String", # Exclude files or rows newer than this value.

5763

# If set to zero, no upper time limit is applied.

5764

},

5765

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

5766

"kind": { # A representation of a Datastore kind. # The kind to process.

5767

"name": "A String", # The name of the kind.

5768

},

5769

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

5770

# by project and namespace, however the namespace ID may be empty.

5771

# A partition ID identifies a grouping of entities. The grouping is always

5772

# by project and namespace, however the namespace ID may be empty.

5773

#

5774

# A partition ID contains several dimensions:

5775

# project ID and namespace ID.

5776

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

5777

"projectId": "A String", # The ID of the project to which the entities belong.

5778

},

5779

},

5780

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

5781

# Early access feature is in a pre-release state and might change or have

5782

# limited support. For more information, see

5783

# https://cloud.google.com/products#product-launch-stages.

5784

# of Google Cloud Platform.

5785

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

5786

# meaningful such as the columns that are primary keys.

5787

"identifyingFields": [ # The columns that are the primary keys for table objects included in

5788

# ContentItem. A copy of this cell's value will stored alongside alongside

5789

# each finding so that the finding can be traced to the specific row it came

5790

# from. No more than 3 may be provided.

5791

{ # General identifier of a data field in a storage service.

5792

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

5797

# 'finding_labels' map. Request may contain others, but any missing one of

5798

# these will be rejected.

5799

#

5800

# Label keys must be between 1 and 63 characters long and must conform

5801

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

5802

#

5803

# No more than 10 keys can be required.

5804

"A String",

5805

],

5806

"labels": { # To organize findings, these labels will be added to each finding.

5807

#

5808

# Label keys must be between 1 and 63 characters long and must conform

5809

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

5810

#

5811

# Label values must be between 0 and 63 characters long and must conform

5812

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

5813

#

5814

# No more than 10 labels can be associated with a given finding.

5815

#

5816

# Examples:

5817

# * `"environment" : "production"`

5818

# * `"pipeline" : "etl"`

5819

"a_key": "A String",

5820

},

5821

"description": "A String", # A short description of where the data is coming from. Will be stored once

5822

# in the job. 256 max length.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

5823

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5824

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

5825

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

5826

# When used with redactContent only info_types and min_likelihood are currently

5827

# used.

5828

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

5829

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

5830

{ # Custom information type provided by the user. Used to find domain-specific

5831

# sensitive information configurable to the data in question.

5832

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

5833

# be used to match sensitive information specific to the data, such as a list

5834

# of employee IDs or job titles.

5835

#

5836

# Dictionary words are case-insensitive and all characters other than letters

5837

# and digits in the unicode [Basic Multilingual

5838

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5839

# will be replaced with whitespace when scanning for matches, so the

5840

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5841

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

5842

# surrounding any match must be of a different type than the adjacent

5843

# characters within the word, so letters must be next to non-letters and

5844

# digits next to non-digits. For example, the dictionary word "jen" will

5845

# match the first three letters of the text "jen123" but will return no

5846

# matches for "jennifer".

5847

#

5848

# Dictionary words containing a large number of characters that are not

5849

# letters or digits may result in unexpected findings because such characters

5850

# are treated as whitespace. The

5851

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5852

# the size limits of dictionaries. For dictionaries that do not fit within

5853

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5854

# `StoredInfoType` API.

5855

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

5856

# is accepted.

5857

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

5858

# Example: gs://[BUCKET_NAME]/dictionary.txt

5859

},

5860

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5861

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

5862

# at least one phrase and every phrase must contain at least 2 characters

5863

# that are letters or digits. [required]

"A String",

],

},

},

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

5869

# infoType, when the name matches one of existing infoTypes and that infoType

5870

# is specified in `InspectContent.info_types` field. Specifying the latter

5871

# adds findings to the one detected by the system. If built-in info type is

5872

# not specified in `InspectContent.info_types` list then the name is treated

5873

# as a custom info type.

5874

"name": "A String", # Name of the information type. Either a name of your choosing when

5875

# creating a CustomInfoType, or one of the names listed

5876

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5877

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

5878

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

5879

},

5880

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

5881

# altered by a detection rule if the finding meets the criteria specified by

5882

# the rule. Defaults to `VERY_LIKELY` if not specified.

5883

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

5884

# Rules are applied in order that they are specified. Not supported for the

5885

# `surrogate_type` CustomInfoType.

5886

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

5887

# `CustomInfoType` to alter behavior under certain circumstances, depending

5888

# on the specific details of the rule. Not supported for the `surrogate_type`

5889

# custom infoType.

5890

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

5891

# proximity of hotwords.

5892

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5893

# The total length of the window cannot exceed 1000 characters. Note that

5894

# the finding itself will be included in the window, so that hotwords may

5895

# be used to match substrings of the finding itself. For example, the

5896

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

5897

# adjusted upwards if the area code is known to be the local area code of

5898

# a company office using the hotword regex "$xxx$", where "xxx"

5899

# is the area code in question.

5900

# rule.

5901

"windowAfter": 42, # Number of characters after the finding to consider.

5902

"windowBefore": 42, # Number of characters before the finding to consider.

5903

},

5904

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

5905

# part of a detection rule.

5906

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

5907

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

5908

# levels. For example, if a finding would be `POSSIBLE` without the

5909

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5910

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5911

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5912

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5913

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5914

# a final likelihood of `LIKELY`.

5915

},

5916

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5917

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5918

# specified, the entire match is returned. No more than 3 may be included.

5919

42,

5920

],

5921

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5922

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5923

# google/re2 repository on GitHub.

},

},

},

],

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

5929

# support reversing.

5930

# such as

5931

# [`CryptoReplaceFfxFpeConfig`](https://cloud.google.com/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

5932

# These types of transformations are

5933

# those that perform pseudonymization, thereby producing a "surrogate" as

5934

# output. This should be used in conjunction with a field on the

5935

# transformation such as `surrogate_info_type`. This CustomInfoType does

5936

# not support the use of `detection_rules`.

5937

},

5938

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

5939

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5940

# specified, the entire match is returned. No more than 3 may be included.

5941

42,

5942

],

5943

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5944

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5945

# google/re2 repository on GitHub.

5946

},

5947

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

5948

# `InspectDataSource`. Not currently supported in `InspectContent`.

5949

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

5950

# `organizations/433245324/storedInfoTypes/432452342` or

5951

# `projects/project-id/storedInfoTypes/432452342`.

5952

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

5953

# inspection was created. Output-only field, populated by the system.

5954

},

5955

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

5956

# to be returned. It still can be used for rules matching.

5957

},

5958

],

5959

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

5960

# POSSIBLE.

5961

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

5962

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

5963

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

5964

# When set within `InspectContentRequest`, the maximum returned is 2000

5965

# regardless if this is set higher.

5966

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

5967

{ # Max findings configuration per infoType, per content item or long

5968

# running DlpJob.

5969

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

5970

# info_type should be provided. If InfoTypeLimit does not have an

5971

# info_type, the DLP API applies the limit against all info_types that

5972

# are found but not specified in another InfoTypeLimit.

5973

"name": "A String", # Name of the information type. Either a name of your choosing when

5974

# creating a CustomInfoType, or one of the names listed

5975

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5976

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

5977

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

5978

},

5979

"maxFindings": 42, # Max findings limit for the given infoType.

5980

},

5981

],

5982

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

5983

# When set within `InspectJobConfig`,

5984

# the maximum returned is 2000 regardless if this is set higher.

5985

# When set within `InspectContentRequest`, this field is ignored.

5986

},

5987

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

5988

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

5989

# included in the response; see Finding.quote.

5990

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

5991

# Exclusion rules, contained in the set are executed in the end, other

5992

# rules are executed in the order they are specified for each info type.

5993

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

5994

# circumstances, depending on the specific details of the rules within the set.

5995

"infoTypes": [ # List of infoTypes this rule set is applied to.

5996

{ # Type of information detected by the API.

5997

"name": "A String", # Name of the information type. Either a name of your choosing when

5998

# creating a CustomInfoType, or one of the names listed

5999

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

6000

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

6001

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

6002

},

6003

],

6004

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

6005

{ # A single inspection rule to be applied to infoTypes, specified in

6006

# `InspectionRuleSet`.

6007

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

6008

# proximity of hotwords.

6009

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

6010

# The total length of the window cannot exceed 1000 characters. Note that

6011

# the finding itself will be included in the window, so that hotwords may

6012

# be used to match substrings of the finding itself. For example, the

6013

# certainty of a phone number regex "$\d{3}$ \d{3}-\d{4}" could be

6014

# adjusted upwards if the area code is known to be the local area code of

6015

# a company office using the hotword regex "$xxx$", where "xxx"

6016

# is the area code in question.

6017

# rule.

6018

"windowAfter": 42, # Number of characters after the finding to consider.

6019

"windowBefore": 42, # Number of characters before the finding to consider.

6020

},

6021

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

6022

# part of a detection rule.

6023

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

6024

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

6025

# levels. For example, if a finding would be `POSSIBLE` without the

6026

# detection rule and `relative_likelihood` is 1, then it is upgraded to

6027

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

6028

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

6029

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

6030

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

6031

# a final likelihood of `LIKELY`.

6032

},

6033

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

6034

"groupIndexes": [ # The index of the submatch to extract as findings. When not

6035

# specified, the entire match is returned. No more than 3 may be included.

6036

42,

6037

],

6038

"pattern": "A String", # Pattern defining the regular expression. Its syntax

6039

# (https://github.com/google/re2/wiki/Syntax) can be found under the

6040

# google/re2 repository on GitHub.

6041

},

6042

},

6043

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

6044

# `InspectionRuleSet` are removed from results.

6045

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

6046

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

6047

# be used to match sensitive information specific to the data, such as a list

6048

# of employee IDs or job titles.

6049

#

6050

# Dictionary words are case-insensitive and all characters other than letters

6051

# and digits in the unicode [Basic Multilingual

6052

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

6053

# will be replaced with whitespace when scanning for matches, so the

6054

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

6055

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

6056

# surrounding any match must be of a different type than the adjacent

6057

# characters within the word, so letters must be next to non-letters and

6058

# digits next to non-digits. For example, the dictionary word "jen" will

6059

# match the first three letters of the text "jen123" but will return no

6060

# matches for "jennifer".

6061

#

6062

# Dictionary words containing a large number of characters that are not

6063

# letters or digits may result in unexpected findings because such characters

6064

# are treated as whitespace. The

6065

# [limits](https://cloud.google.com/dlp/limits) page contains details about

6066

# the size limits of dictionaries. For dictionaries that do not fit within

6067

# these constraints, consider using `LargeCustomDictionaryConfig` in the

6068

# `StoredInfoType` API.

6069

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

6070

# is accepted.

6071

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

6072

# Example: gs://[BUCKET_NAME]/dictionary.txt

6073

},

6074

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

6075

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

6076

# at least one phrase and every phrase must contain at least 2 characters

6077

# that are letters or digits. [required]

"A String",

],

},

},

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

6083

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

6084

# contained within with a finding of an infoType from this list. For

6085

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

6086

# `exclusion_rule` containing `exclude_info_types.info_types` with

6087

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

6088

# with EMAIL_ADDRESS finding.

6089

# That leads to "555-222-2222@example.org" to generate only a single

6090

# finding, namely email address.

6091

{ # Type of information detected by the API.

6092

"name": "A String", # Name of the information type. Either a name of your choosing when

6093

# creating a CustomInfoType, or one of the names listed

6094

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

6095

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

6096

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

},

],

},

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

6101

"groupIndexes": [ # The index of the submatch to extract as findings. When not

6102

# specified, the entire match is returned. No more than 3 may be included.

6103

42,

6104

],

6105

"pattern": "A String", # Pattern defining the regular expression. Its syntax

6106

# (https://github.com/google/re2/wiki/Syntax) can be found under the

6107

# google/re2 repository on GitHub.

},

},

},

],

},

],

"contentOptions": [ # List of options defining data content to scan.

6115

# If empty, text, images, and other content will be included.

6116

"A String",

6117

],

6118

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

6119

# InfoType values returned by ListInfoTypes or listed at

6120

# https://cloud.google.com/dlp/docs/infotypes-reference.

6121

#

6122

# When no InfoTypes or CustomInfoTypes are specified in a request, the

6123

# system may automatically choose what detectors to run. By default this may

6124

# be all types, but may change over time as detectors are updated.

6125

#

6126

# If you need precise control and predictability as to what detectors are

6127

# run you should specify specific InfoTypes listed in the reference,

6128

# otherwise a default list will be used, which may change over time.

6129

{ # Type of information detected by the API.

6130

"name": "A String", # Name of the information type. Either a name of your choosing when

6131

# creating a CustomInfoType, or one of the names listed

6132

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

6133

# a built-in type. When sending Cloud DLP results to Data Catalog, infoType

6134

# names should conform to the pattern `[A-Za-z0-9$-_]{1,64}`.

6135

},

6136

],

6137

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6138

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

6139

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

6140

# triggeredJob is created, for example

6141

# `projects/dlp-test-project/jobTriggers/53234423`.

6142

"displayName": "A String", # Display name (max 100 chars)

6143

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

6144

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

6145

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim