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

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

[diff] [blame]

81

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

Bu Sun Kim

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

[diff] [blame]

82

<p class="firstline">Creates a job trigger to run DLP actions such as scanning storage for</p>

83

84

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

85

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

86

87

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

88

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

89

Bu Sun Kim

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

[diff] [blame]

90

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

Bu Sun Kim

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

[diff] [blame]

91

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

92

93

<code><a href="#list_next">list_next(previous_request, previous_response)</a></code></p>

94

<p class="firstline">Retrieves the next page of results.</p>

95

Dan O'Meara

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

[diff] [blame]

96

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

Bu Sun Kim

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

[diff] [blame]

97

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

98

<h3>Method Details</h3>

99

100

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

101

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

102

instead of waiting on the trigger event to occur.

103

104

Args:

Dan O'Meara

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

[diff] [blame]

105

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

Bu Sun Kim

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

[diff] [blame]

106

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

107

body: object, The request body.

108

The object takes the form of:

109

110

{ # Request message for ActivateJobTrigger.

111

}

112

113

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

120

121

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

Bu Sun Kim

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

[diff] [blame]

122

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

123

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

124

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

125

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

126

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

127

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

128

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

129

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

130

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

131

# int64 only holds up to 8 bytes of data.

132

"booleanValue": True or False, # boolean

133

"floatValue": 3.14, # float

134

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

135

"timestampValue": "A String", # timestamp

136

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

137

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

138

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

139

#

140

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

141

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

142

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

143

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

144

#

145

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

146

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

147

# a year.

148

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

149

# month and day.

150

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

151

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

152

# significant.

153

},

154

"stringValue": "A String", # string

155

"integerValue": "A String", # integer

156

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

157

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

158

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

159

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

160

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

161

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

162

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

163

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

164

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

165

},

166

},

167

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

168

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

169

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

170

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

171

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

172

# int64 only holds up to 8 bytes of data.

173

"booleanValue": True or False, # boolean

174

"floatValue": 3.14, # float

175

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

176

"timestampValue": "A String", # timestamp

177

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

178

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

179

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

180

#

181

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

182

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

183

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

184

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

185

#

186

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

187

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

188

# a year.

189

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

190

# month and day.

191

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

192

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

193

# significant.

194

},

195

"stringValue": "A String", # string

196

"integerValue": "A String", # integer

197

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

198

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

199

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

200

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

201

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

202

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

203

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

204

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

205

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

206

},

207

},

208

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

209

# sized buckets.

210

{ # Set of primitive values supported by the system.

211

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

212

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

213

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

214

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

215

# int64 only holds up to 8 bytes of data.

216

"booleanValue": True or False, # boolean

217

"floatValue": 3.14, # float

218

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

219

"timestampValue": "A String", # timestamp

220

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

221

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

222

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

223

#

224

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

225

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

226

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

227

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

228

#

229

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

230

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

231

# a year.

232

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

233

# month and day.

234

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

235

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

236

# significant.

237

},

238

"stringValue": "A String", # string

239

"integerValue": "A String", # integer

240

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

241

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

242

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

243

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

244

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

245

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

246

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

247

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

248

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

},

},

],

},

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

254

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

255

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

256

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

257

# classes in this bucket.

258

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

259

# classes in this bucket.

260

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

261

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

262

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

263

# classes returned per bucket is capped at 20.

264

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

265

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

266

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

267

{ # Set of primitive values supported by the system.

268

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

269

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

270

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

271

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

272

# int64 only holds up to 8 bytes of data.

273

"booleanValue": True or False, # boolean

274

"floatValue": 3.14, # float

275

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

276

"timestampValue": "A String", # timestamp

277

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

278

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

279

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

280

#

281

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

282

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

283

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

284

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

285

#

286

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

287

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

288

# a year.

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

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

292

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

293

# significant.

294

},

295

"stringValue": "A String", # string

296

"integerValue": "A String", # integer

297

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

298

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

299

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

300

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

301

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

302

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

303

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

304

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

305

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

},

},

],

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

310

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

311

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

312

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

313

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

314

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

315

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

316

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

317

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

318

# int64 only holds up to 8 bytes of data.

319

"booleanValue": True or False, # boolean

320

"floatValue": 3.14, # float

321

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

322

"timestampValue": "A String", # timestamp

323

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

324

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

325

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

326

#

327

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

328

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

329

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

330

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

331

#

332

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

333

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

334

# a year.

335

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

336

# month and day.

337

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

338

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

339

# significant.

340

},

341

"stringValue": "A String", # string

342

"integerValue": "A String", # integer

343

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

344

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

345

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

346

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

347

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

348

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

349

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

350

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

351

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

352

},

353

},

354

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

},

],

},

],

},

],

},

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

363

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

364

# number of distinct values and value count distribution.

365

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

366

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

367

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

368

# depending on the data.

369

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

370

},

371

},

372

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

373

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

374

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

375

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

376

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

377

# a repeated field.

378

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

379

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

380

},

381

],

382

"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

383

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

384

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

385

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

386

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

387

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

388

#

389

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

390

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

391

# might be ignored.

392

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

393

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

394

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

395

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

396

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

397

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

},

},

},

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

402

# min, max, and quantiles.

403

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

404

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

405

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

406

},

407

},

408

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

409

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

410

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

411

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

412

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

413

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

414

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

415

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

416

# US_ZIP_5) or a region code.

417

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

418

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

419

# of one auxiliary table.

420

{ # An auxiliary table contains statistical information on the relative

421

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

422

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

423

# frequency of each quasi-identifier tuple.

424

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

425

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

426

# tuple is highly reidentifiable).

427

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

428

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

429

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

430

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

431

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

432

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

433

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

434

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

435

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

436

},

437

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

438

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

439

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

440

},

441

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

442

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

443

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

444

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

445

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

446

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

},

},

],

},

],

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

453

# same tag.

454

{ # A column with a semantic tag attached.

455

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

456

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

457

},

458

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

459

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

460

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

461

# To programmatically obtain the list of supported InfoTypes, use

462

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

463

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

464

# creating a CustomInfoType, or one of the names listed

465

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

466

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

467

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

468

},

469

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

470

# indicate an auxiliary table that contains statistical information on

471

# the possible values of this column (below).

472

"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

473

# the distribution of values in the input data

474

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

475

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

476

#

477

# service Foo {

478

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

479

# }

480

#

481

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

},

},

],

},

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

487

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

488

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

489

# specified, they are considered a single composite key.

490

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

491

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

492

},

493

],

494

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

495

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

496

},

497

},

498

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

499

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

500

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

501

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

502

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

503

# same tag.

504

{ # A column with a semantic tag attached.

505

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

506

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

507

},

508

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

509

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

510

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

511

# To programmatically obtain the list of supported InfoTypes, use

512

# ListInfoTypes with the supported_by=RISK_ANALYSIS filter.

513

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

514

# creating a CustomInfoType, or one of the names listed

515

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

516

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

517

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

518

},

519

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

520

# indicate an auxiliary table that contains statistical information on

521

# the possible values of this column (below).

522

"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

523

# the distribution of values in the input data

524

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

525

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

526

#

527

# service Foo {

528

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

529

# }

530

#

531

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

},

},

],

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

536

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

537

# US_ZIP_5) or a region code.

538

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

539

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

540

# field of one auxiliary table.

541

{ # An auxiliary table containing statistical information on the relative

542

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

543

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

544

# frequency of each quasi-identifier tuple.

545

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

546

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

547

# tuple is highly reidentifiable).

548

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

549

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

550

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

551

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

552

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

553

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

554

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

555

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

556

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

557

},

558

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

559

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

560

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

561

},

562

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

563

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

564

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

565

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

566

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

567

},

568

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

569

# indicate an auxiliary table that contains statistical information on

570

# the possible values of this column (below).

},

],

},

],

},

},

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

578

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

579

{ # Histogram of value frequencies in the column.

580

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

581

# values returned per bucket is capped at 20.

582

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

583

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

584

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

585

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

586

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

587

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

588

# int64 only holds up to 8 bytes of data.

589

"booleanValue": True or False, # boolean

590

"floatValue": 3.14, # float

591

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

592

"timestampValue": "A String", # timestamp

593

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

594

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

595

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

596

#

597

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

598

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

599

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

600

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

601

#

602

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

603

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

604

# a year.

605

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

606

# month and day.

607

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

608

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

609

# significant.

610

},

611

"stringValue": "A String", # string

612

"integerValue": "A String", # integer

613

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

614

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

615

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

616

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

617

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

618

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

619

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

620

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

621

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

622

},

623

},

624

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

625

},

626

],

627

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

628

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

629

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

630

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

},

],

},

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

635

# estimation, not exact values.

636

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

637

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

638

# zero. For example, the following records:

639

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

640

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

641

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

642

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

643

# larger than 10.

644

{ # 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

649

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

650

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

651

# corresponds to the number of uniquely identifiable records.

652

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

653

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

654

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

655

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

656

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

657

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

658

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

659

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

660

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

661

{ # Set of primitive values supported by the system.

662

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

663

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

664

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

665

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

666

# int64 only holds up to 8 bytes of data.

667

"booleanValue": True or False, # boolean

668

"floatValue": 3.14, # float

669

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

670

"timestampValue": "A String", # timestamp

671

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

672

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

673

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

674

#

675

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

676

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

677

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

678

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

679

#

680

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

681

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

682

# a year.

683

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

684

# month and day.

685

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

686

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

687

# significant.

688

},

689

"stringValue": "A String", # string

690

"integerValue": "A String", # integer

691

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

692

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

693

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

694

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

695

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

696

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

697

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

698

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

699

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

},

},

],

},

],

},

],

},

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

709

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

710

{ # Histogram of k-anonymity equivalence classes.

711

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

712

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

713

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

714

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

715

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

716

# classes returned per bucket is capped at 20.

717

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

718

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

719

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

720

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

721

{ # Set of primitive values supported by the system.

722

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

723

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

724

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

725

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

726

# int64 only holds up to 8 bytes of data.

727

"booleanValue": True or False, # boolean

728

"floatValue": 3.14, # float

729

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

730

"timestampValue": "A String", # timestamp

731

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

732

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

733

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

734

#

735

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

736

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

737

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

738

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

739

#

740

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

741

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

742

# a year.

743

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

744

# month and day.

745

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

746

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

747

# significant.

748

},

749

"stringValue": "A String", # string

750

"integerValue": "A String", # integer

751

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

752

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

753

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

754

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

755

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

756

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

757

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

758

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

759

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

},

},

],

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

764

# above set of values.

},

],

},

],

},

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

771

# estimation, not exact values.

772

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

773

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

774

# is zero. For example, the following records:

775

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

776

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

777

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

778

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

779

# nor larger or equal to 0.4.

780

{ # A DeltaPresenceEstimationHistogramBucket message with the following

781

# values:

782

# min_probability: 0.1

783

# max_probability: 0.2

784

# frequency: 42

785

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

786

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

787

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

788

# the dataset.

789

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

790

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

791

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

792

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

793

{ # Set of primitive values supported by the system.

794

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

795

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

796

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

797

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

798

# int64 only holds up to 8 bytes of data.

799

"booleanValue": True or False, # boolean

800

"floatValue": 3.14, # float

801

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

802

"timestampValue": "A String", # timestamp

803

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

804

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

805

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

806

#

807

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

808

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

809

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

810

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

811

#

812

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

813

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

814

# a year.

815

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

816

# month and day.

817

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

818

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

819

# significant.

820

},

821

"stringValue": "A String", # string

822

"integerValue": "A String", # integer

823

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

824

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

825

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

826

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

827

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

828

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

829

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

830

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

831

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

},

},

],

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

836

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

837

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

838

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

839

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

840

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

841

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

842

# population with these values, then δ is 0.15.

843

},

844

],

845

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

846

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

847

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

848

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

},

],

},

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

853

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

854

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

855

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

856

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

857

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

858

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

859

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

860

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

861

},

862

},

863

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

864

# instantiated the job.

865

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

Bu Sun Kim

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

[diff] [blame]

866

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

867

# the results of an unsuccessful activation of the JobTrigger.

Bu Sun Kim

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

[diff] [blame]

868

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

Bu Sun Kim

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

[diff] [blame]

869

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

870

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

871

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

872

#

873

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

874

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

Bu Sun Kim

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

[diff] [blame]

875

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

876

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

Bu Sun Kim

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

[diff] [blame]

877

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

878

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

Bu Sun Kim

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

[diff] [blame]

879

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

Bu Sun Kim

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

[diff] [blame]

880

# message types for APIs to use.

881

{

Bu Sun Kim

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

[diff] [blame]

882

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

Bu Sun Kim

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

[diff] [blame]

883

},

884

],

885

},

Bu Sun Kim

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

[diff] [blame]

886

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

887

"A String",

888

],

Bu Sun Kim

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

[diff] [blame]

889

},

890

],

Bu Sun Kim

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

[diff] [blame]

891

"name": "A String", # The server-assigned name.

892

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

893

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

894

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

895

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

896

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

897

"snapshotInspectTemplate": { # The inspectTemplate contains a configuration (set of types of sensitive data # If run with an InspectTemplate, a snapshot of its state at the time of

Bu Sun Kim

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

[diff] [blame]

898

# this run.

899

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

900

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

901

# to learn more.

Bu Sun Kim

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

[diff] [blame]

902

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

903

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

Bu Sun Kim

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

[diff] [blame]

904

# When used with redactContent only info_types and min_likelihood are currently

905

# used.

Bu Sun Kim

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

[diff] [blame]

906

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

907

# included in the response; see Finding.quote.

908

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

909

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

910

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

911

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

912

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

913

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

914

{ # Type of information detected by the API.

915

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

Bu Sun Kim

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

[diff] [blame]

916

# creating a CustomInfoType, or one of the names listed

917

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

918

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

Dan O'Meara

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

[diff] [blame]

919

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

Bu Sun Kim

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

[diff] [blame]

920

},

Bu Sun Kim

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

[diff] [blame]

921

],

Bu Sun Kim

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

[diff] [blame]

922

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

Bu Sun Kim

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

[diff] [blame]

923

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

924

# `InspectionRuleSet`.

Bu Sun Kim

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

[diff] [blame]

925

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

Bu Sun Kim

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

[diff] [blame]

926

# proximity of hotwords.

Bu Sun Kim

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

[diff] [blame]

927

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

Bu Sun Kim

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

[diff] [blame]

928

# part of a detection rule.

Bu Sun Kim

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

[diff] [blame]

929

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

Bu Sun Kim

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

[diff] [blame]

930

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

931

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

932

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

933

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

934

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

935

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

936

# a final likelihood of `LIKELY`.

Bu Sun Kim

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

[diff] [blame]

937

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

Bu Sun Kim

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

[diff] [blame]

938

},

Bu Sun Kim

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

[diff] [blame]

939

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

940

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

Bu Sun Kim

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

[diff] [blame]

941

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

942

42,

943

],

Bu Sun Kim

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

[diff] [blame]

944

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

945

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

946

# google/re2 repository on GitHub.

Bu Sun Kim

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

[diff] [blame]

947

},

Bu Sun Kim

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

[diff] [blame]

948

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

949

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

950

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

951

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

952

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

953

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

954

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

955

# is the area code in question.

956

# rule.

957

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

958

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

Bu Sun Kim

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

[diff] [blame]

959

},

Bu Sun Kim

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

[diff] [blame]

960

},

961

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

962

# `InspectionRuleSet` are removed from results.

963

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

Bu Sun Kim

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

[diff] [blame]

964

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

965

# of employee IDs or job titles.

966

#

967

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

968

# and digits in the unicode [Basic Multilingual

969

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

970

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

Bu Sun Kim

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

[diff] [blame]

971

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

972

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

Bu Sun Kim

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

[diff] [blame]

973

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

974

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

Bu Sun Kim

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

[diff] [blame]

975

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

976

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

977

# matches for "jennifer".

Bu Sun Kim

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

[diff] [blame]

978

#

979

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

980

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

981

# are treated as whitespace. The

982

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

983

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

984

# these constraints, consider using `LargeCustomDictionaryConfig` in the

985

# `StoredInfoType` API.

Bu Sun Kim

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

[diff] [blame]

986

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

987

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

Bu Sun Kim

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

[diff] [blame]

988

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

989

# that are letters or digits. [required]

Bu Sun Kim

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

[diff] [blame]

990

"A String",

Bu Sun Kim

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

[diff] [blame]

991

],

992

},

Bu Sun Kim

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

[diff] [blame]

993

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

Bu Sun Kim

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

[diff] [blame]

994

# is accepted.

Bu Sun Kim

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

[diff] [blame]

995

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

Bu Sun Kim

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

[diff] [blame]

996

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

997

},

998

},

Bu Sun Kim

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

[diff] [blame]

999

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

1000

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

1001

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

1002

42,

1003

],

1004

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

1005

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

1006

# google/re2 repository on GitHub.

1007

},

1008

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

1009

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

1010

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

1011

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

1012

# `exclusion_rule` containing `exclude_info_types.info_types` with

1013

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

1014

# with EMAIL_ADDRESS finding.

1015

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

1016

# finding, namely email address.

1017

{ # Type of information detected by the API.

1018

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

1019

# creating a CustomInfoType, or one of the names listed

1020

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

1021

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

1022

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

},

],

},

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

Bu Sun Kim

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

[diff] [blame]

1027

},

1028

},

1029

],

Bu Sun Kim

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

[diff] [blame]

1030

},

1031

],

1032

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

1033

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

1034

# When set within `InspectJobConfig`,

1035

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

1036

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

1037

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

1038

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

1039

# running DlpJob.

1040

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

1041

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

1042

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

1043

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

1044

# are found but not specified in another InfoTypeLimit.

1045

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

Bu Sun Kim

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

[diff] [blame]

1046

# creating a CustomInfoType, or one of the names listed

1047

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

1048

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

Dan O'Meara

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

[diff] [blame]

1049

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

Bu Sun Kim

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

[diff] [blame]

1050

},

Bu Sun Kim

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

[diff] [blame]

1051

},

1052

],

1053

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

1054

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

1055

# regardless if this is set higher.

1056

},

1057

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

Bu Sun Kim

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

[diff] [blame]

1058

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

Bu Sun Kim

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

[diff] [blame]

1059

"A String",

Bu Sun Kim

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

[diff] [blame]

1060

],

Bu Sun Kim

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

[diff] [blame]

1061

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

Bu Sun Kim

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

[diff] [blame]

1062

# InfoType values returned by ListInfoTypes or listed at

1063

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

1064

#

1065

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

1066

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

1067

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

1068

#

Dan O'Meara

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

[diff] [blame]

1069

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

1070

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

1071

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

Bu Sun Kim

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

[diff] [blame]

1072

{ # Type of information detected by the API.

Bu Sun Kim

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

[diff] [blame]

1073

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

Bu Sun Kim

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

[diff] [blame]

1074

# creating a CustomInfoType, or one of the names listed

1075

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

1076

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

Dan O'Meara

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

[diff] [blame]

1077

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

Bu Sun Kim

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

[diff] [blame]

1078

},

1079

],

Bu Sun Kim

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

[diff] [blame]

1080

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

1081

# POSSIBLE.

1082

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

1083

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

1084

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

1085

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

1086

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

1087

# sensitive information configurable to the data in question.

1088

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

1089

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

1090

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

1091

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

1092

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

1093

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

1094

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

1095

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

1096

# as a custom info type.

1097

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

1098

# creating a CustomInfoType, or one of the names listed

1099

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

1100

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

1101

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

1102

},

1103

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

1104

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

1105

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

1106

42,

1107

],

1108

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

1109

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

1110

# google/re2 repository on GitHub.

1111

},

1112

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

1113

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

1114

# `surrogate_type` CustomInfoType.

1115

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

1116

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

1117

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

1118

# custom infoType.

1119

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

1120

# proximity of hotwords.

1121

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

1122

# part of a detection rule.

1123

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

1124

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

1125

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

1126

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

1127

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

1128

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

1129

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

1130

# a final likelihood of `LIKELY`.

1131

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

1132

},

1133

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

1134

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

1135

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

1136

42,

1137

],

1138

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

1139

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

1140

# google/re2 repository on GitHub.

1141

},

1142

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

1143

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

1144

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

1145

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

1146

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

1147

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

1148

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

1149

# is the area code in question.

1150

# rule.

1151

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

1152

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

},

},

},

],

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

1158

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

1159

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

1160

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

1161

# of employee IDs or job titles.

1162

#

1163

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

1164

# and digits in the unicode [Basic Multilingual

1165

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

1166

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

1167

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

1168

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

1169

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

1170

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

1171

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

1172

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

1173

# matches for "jennifer".

1174

#

1175

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

1176

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

1177

# are treated as whitespace. The

1178

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

1179

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

1180

# these constraints, consider using `LargeCustomDictionaryConfig` in the

1181

# `StoredInfoType` API.

1182

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

1183

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

1184

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

1185

# that are letters or digits. [required]

"A String",

],

},

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

1190

# is accepted.

1191

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

1192

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

1193

},

1194

},

1195

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

1196

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

1197

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

1198

# `organizations/433245324/storedInfoTypes/432452342` or

1199

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

1200

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

1201

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

1202

},

1203

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

1204

# support reversing.

1205

# such as

1206

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

1207

# These types of transformations are

1208

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

1209

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

1210

# transformation such as `surrogate_info_type`. This CustomInfoType does

1211

# not support the use of `detection_rules`.

1212

},

1213

},

1214

],

Bu Sun Kim

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

[diff] [blame]

1215

},

Bu Sun Kim

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

[diff] [blame]

1216

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

1217

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

1218

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

Bu Sun Kim

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

[diff] [blame]

1219

#

1220

# The template will have one of the following formats:

1221

# `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR

Dan O'Meara

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

[diff] [blame]

1222

# `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`;

Bu Sun Kim

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

[diff] [blame]

1223

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

Bu Sun Kim

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

[diff] [blame]

1224

},

Bu Sun Kim

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

[diff] [blame]

1225

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

1226

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

Bu Sun Kim

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

[diff] [blame]

1227

# When used with redactContent only info_types and min_likelihood are currently

1228

# used.

Bu Sun Kim

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

[diff] [blame]

1229

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

1230

# included in the response; see Finding.quote.

1231

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

1232

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

1233

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

1234

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

1235

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

1236

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

1237

{ # Type of information detected by the API.

1238

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

Bu Sun Kim

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

[diff] [blame]

1239

# creating a CustomInfoType, or one of the names listed

1240

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

1241

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

Dan O'Meara

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

[diff] [blame]

1242

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

Bu Sun Kim

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

[diff] [blame]

1243

},

Bu Sun Kim

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

[diff] [blame]

1244

],

Bu Sun Kim

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

[diff] [blame]

1245

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

Bu Sun Kim

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

[diff] [blame]

1246

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

1247

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1248

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1249

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1250

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1251

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1252

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1253

# levels. For example, if a finding would be `POSSIBLE` without the

1254

# detection rule and `relative_likelihood` is 1, then it is upgraded to

1255

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

1256

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

1257

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

1258

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

1259

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1260

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1261

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1262

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

1263

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1264

# specified, the entire match is returned. No more than 3 may be included.

1265

42,

1266

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1267

"pattern": "A String", # Pattern defining the regular expression. Its syntax

1268

# (https://github.com/google/re2/wiki/Syntax) can be found under the

1269

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1270

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1271

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

1272

# The total length of the window cannot exceed 1000 characters. Note that

1273

# the finding itself will be included in the window, so that hotwords may

1274

# be used to match substrings of the finding itself. For example, the

1275

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

1276

# adjusted upwards if the area code is known to be the local area code of

1277

# a company office using the hotword regex "\(xxx\)", where "xxx"

1278

# is the area code in question.

1279

# rule.

1280

"windowBefore": 42, # Number of characters before the finding to consider.

1281

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1282

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1283

},

1284

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

1285

# `InspectionRuleSet` are removed from results.

1286

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1287

# be used to match sensitive information specific to the data, such as a list

1288

# of employee IDs or job titles.

1289

#

1290

# Dictionary words are case-insensitive and all characters other than letters

1291

# and digits in the unicode [Basic Multilingual

1292

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

1293

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1294

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

1295

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1296

# surrounding any match must be of a different type than the adjacent

1297

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1298

# digits next to non-digits. For example, the dictionary word "jen" will

1299

# match the first three letters of the text "jen123" but will return no

1300

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1301

#

1302

# Dictionary words containing a large number of characters that are not

1303

# letters or digits may result in unexpected findings because such characters

1304

# are treated as whitespace. The

1305

# [limits](https://cloud.google.com/dlp/limits) page contains details about

1306

# the size limits of dictionaries. For dictionaries that do not fit within

1307

# these constraints, consider using `LargeCustomDictionaryConfig` in the

1308

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1309

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

1310

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1311

# at least one phrase and every phrase must contain at least 2 characters

1312

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1313

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1314

],

1315

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1316

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1317

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1318

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1319

# Example: gs://[BUCKET_NAME]/dictionary.txt

1320

},

1321

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1322

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

1323

"groupIndexes": [ # The index of the submatch to extract as findings. When not

1324

# specified, the entire match is returned. No more than 3 may be included.

1325

42,

1326

],

1327

"pattern": "A String", # Pattern defining the regular expression. Its syntax

1328

# (https://github.com/google/re2/wiki/Syntax) can be found under the

1329

# google/re2 repository on GitHub.

1330

},

1331

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

1332

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

1333

# contained within with a finding of an infoType from this list. For

1334

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

1335

# `exclusion_rule` containing `exclude_info_types.info_types` with

1336

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

1337

# with EMAIL_ADDRESS finding.

1338

# That leads to "555-222-2222@example.org" to generate only a single

1339

# finding, namely email address.

1340

{ # Type of information detected by the API.

1341

"name": "A String", # Name of the information type. Either a name of your choosing when

1342

# creating a CustomInfoType, or one of the names listed

1343

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1344

# a built-in type. InfoType names should conform to the pattern

1345

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1350

},

1351

},

1352

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1353

},

1354

],

1355

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

1356

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

1357

# When set within `InspectJobConfig`,

1358

# the maximum returned is 2000 regardless if this is set higher.

1359

# When set within `InspectContentRequest`, this field is ignored.

1360

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

1361

{ # Max findings configuration per infoType, per content item or long

1362

# running DlpJob.

1363

"maxFindings": 42, # Max findings limit for the given infoType.

1364

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

1365

# info_type should be provided. If InfoTypeLimit does not have an

1366

# info_type, the DLP API applies the limit against all info_types that

1367

# are found but not specified in another InfoTypeLimit.

1368

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1369

# creating a CustomInfoType, or one of the names listed

1370

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1371

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1372

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1373

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1374

},

1375

],

1376

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

1377

# When set within `InspectContentRequest`, the maximum returned is 2000

1378

# regardless if this is set higher.

1379

},

1380

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1381

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1382

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1383

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1384

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1385

# InfoType values returned by ListInfoTypes or listed at

1386

# https://cloud.google.com/dlp/docs/infotypes-reference.

1387

#

1388

# When no InfoTypes or CustomInfoTypes are specified in a request, the

1389

# system may automatically choose what detectors to run. By default this may

1390

# be all types, but may change over time as detectors are updated.

1391

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1392

# If you need precise control and predictability as to what detectors are

1393

# run you should specify specific InfoTypes listed in the reference,

1394

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1395

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1396

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1397

# creating a CustomInfoType, or one of the names listed

1398

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1399

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1400

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1401

},

1402

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1403

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

1404

# POSSIBLE.

1405

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

1406

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

1407

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

1408

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

1409

{ # Custom information type provided by the user. Used to find domain-specific

1410

# sensitive information configurable to the data in question.

1411

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

1412

# altered by a detection rule if the finding meets the criteria specified by

1413

# the rule. Defaults to `VERY_LIKELY` if not specified.

1414

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

1415

# infoType, when the name matches one of existing infoTypes and that infoType

1416

# is specified in `InspectContent.info_types` field. Specifying the latter

1417

# adds findings to the one detected by the system. If built-in info type is

1418

# not specified in `InspectContent.info_types` list then the name is treated

1419

# as a custom info type.

1420

"name": "A String", # Name of the information type. Either a name of your choosing when

1421

# creating a CustomInfoType, or one of the names listed

1422

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1423

# a built-in type. InfoType names should conform to the pattern

1424

# `[a-zA-Z0-9_]{1,64}`.

1425

},

1426

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

1427

"groupIndexes": [ # The index of the submatch to extract as findings. When not

1428

# specified, the entire match is returned. No more than 3 may be included.

1429

42,

1430

],

1431

"pattern": "A String", # Pattern defining the regular expression. Its syntax

1432

# (https://github.com/google/re2/wiki/Syntax) can be found under the

1433

# google/re2 repository on GitHub.

1434

},

1435

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

1436

# Rules are applied in order that they are specified. Not supported for the

1437

# `surrogate_type` CustomInfoType.

1438

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

1439

# `CustomInfoType` to alter behavior under certain circumstances, depending

1440

# on the specific details of the rule. Not supported for the `surrogate_type`

1441

# custom infoType.

1442

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

1443

# proximity of hotwords.

1444

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

1445

# part of a detection rule.

1446

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

1447

# levels. For example, if a finding would be `POSSIBLE` without the

1448

# detection rule and `relative_likelihood` is 1, then it is upgraded to

1449

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

1450

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

1451

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

1452

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

1453

# a final likelihood of `LIKELY`.

1454

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

1455

},

1456

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

1457

"groupIndexes": [ # The index of the submatch to extract as findings. When not

1458

# specified, the entire match is returned. No more than 3 may be included.

1459

42,

1460

],

1461

"pattern": "A String", # Pattern defining the regular expression. Its syntax

1462

# (https://github.com/google/re2/wiki/Syntax) can be found under the

1463

# google/re2 repository on GitHub.

1464

},

1465

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

1466

# The total length of the window cannot exceed 1000 characters. Note that

1467

# the finding itself will be included in the window, so that hotwords may

1468

# be used to match substrings of the finding itself. For example, the

1469

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

1470

# adjusted upwards if the area code is known to be the local area code of

1471

# a company office using the hotword regex "\(xxx\)", where "xxx"

1472

# is the area code in question.

1473

# rule.

1474

"windowBefore": 42, # Number of characters before the finding to consider.

1475

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

1481

# to be returned. It still can be used for rules matching.

1482

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

1483

# be used to match sensitive information specific to the data, such as a list

1484

# of employee IDs or job titles.

1485

#

1486

# Dictionary words are case-insensitive and all characters other than letters

1487

# and digits in the unicode [Basic Multilingual

1488

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

1489

# will be replaced with whitespace when scanning for matches, so the

1490

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

1491

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

1492

# surrounding any match must be of a different type than the adjacent

1493

# characters within the word, so letters must be next to non-letters and

1494

# digits next to non-digits. For example, the dictionary word "jen" will

1495

# match the first three letters of the text "jen123" but will return no

1496

# matches for "jennifer".

1497

#

1498

# Dictionary words containing a large number of characters that are not

1499

# letters or digits may result in unexpected findings because such characters

1500

# are treated as whitespace. The

1501

# [limits](https://cloud.google.com/dlp/limits) page contains details about

1502

# the size limits of dictionaries. For dictionaries that do not fit within

1503

# these constraints, consider using `LargeCustomDictionaryConfig` in the

1504

# `StoredInfoType` API.

1505

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

1506

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

1507

# at least one phrase and every phrase must contain at least 2 characters

1508

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

1513

# is accepted.

1514

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

1515

# Example: gs://[BUCKET_NAME]/dictionary.txt

1516

},

1517

},

1518

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

1519

# `InspectDataSource`. Not currently supported in `InspectContent`.

1520

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

1521

# `organizations/433245324/storedInfoTypes/432452342` or

1522

# `projects/project-id/storedInfoTypes/432452342`.

1523

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

1524

# inspection was created. Output-only field, populated by the system.

1525

},

1526

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

1527

# support reversing.

1528

# such as

1529

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

1530

# These types of transformations are

1531

# those that perform pseudonymization, thereby producing a "surrogate" as

1532

# output. This should be used in conjunction with a field on the

1533

# transformation such as `surrogate_info_type`. This CustomInfoType does

1534

# not support the use of `detection_rules`.

1535

},

1536

},

1537

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1538

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1539

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1540

{ # A task to execute on the completion of a job.

1541

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1542

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

1543

# Command Center (CSCC Alpha).

1544

# This action is only available for projects which are parts of

1545

# an organization and whitelisted for the alpha Cloud Security Command

1546

# Center.

1547

# The action will publish count of finding instances and their info types.

1548

# The summary of findings will be persisted in CSCC and are governed by CSCC

1549

# service-specific policy, see https://cloud.google.com/terms/service-terms

1550

# Only a single instance of this action can be specified.

1551

# Compatible with: Inspect

1552

},

1553

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

1554

# completion/failure.

1555

# completion/failure.

1556

},

1557

"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]

1558

# OutputStorageConfig. Only a single instance of this action can be

1559

# specified.

1560

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1561

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

1562

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

1563

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

1564

# from the `Finding` object. If appending to an existing table, any columns

1565

# from the predefined schema that are missing will be added. No columns in

1566

# the existing table will be deleted.

1567

#

1568

# If unspecified, then all available columns will be used for a new table or

1569

# an (existing) table with no schema, and no changes will be made to an

1570

# existing table that has a schema.

1571

# Only for use with external storage.

1572

"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]

1573

# dataset. If table_id is not set a new one will be generated

1574

# for you with the following format:

1575

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

1576

# generating the date details.

1577

#

1578

# For Inspect, each column in an existing output table must have the same

1579

# name, type, and mode of a field in the `Finding` object.

1580

#

1581

# For Risk, an existing output table should be the output of a previous

1582

# Risk analysis job run on the same source table, with the same privacy

1583

# metric and quasi-identifiers. Risk jobs that analyze the same table but

1584

# compute a different privacy metric, or use different sets of

1585

# quasi-identifiers, cannot store their results in the same table.

1586

# identified by its project_id, dataset_id, and table_name. Within a query

1587

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1588

# `<project_id>:<dataset_id>.<table_id>` or

1589

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1590

"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]

1591

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1592

"datasetId": "A String", # Dataset ID of the table.

1593

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1594

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1595

},

1596

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1597

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

1598

# message contains a single field, `DlpJobName`, which is equal to the

1599

# finished job's

1600

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

1601

# Compatible with: Inspect, Risk

1602

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

1603

# publishing access rights to the DLP API service account executing

1604

# the long running DlpJob sending the notifications.

1605

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1606

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1607

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1608

# results of the DlpJob will be applied to the entry for the resource scanned

1609

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

1610

# be deleted. InfoType naming patterns are strictly enforced when using this

1611

# feature. Note that the findings will be persisted in Cloud Data Catalog

1612

# storage and are governed by Data Catalog service-specific policy, see

1613

# https://cloud.google.com/terms/service-terms

1614

# Only a single instance of this action can be specified and only allowed if

1615

# all resources being scanned are BigQuery tables.

1616

# Compatible with: Inspect

1617

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1618

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

1619

# will publish a metric to stack driver on each infotype requested and

1620

# how many findings were found for it. CustomDetectors will be bucketed

1621

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1622

},

1623

},

1624

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1625

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

1626

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

1627

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

1628

# by project and namespace, however the namespace ID may be empty.

1629

# A partition ID identifies a grouping of entities. The grouping is always

1630

# by project and namespace, however the namespace ID may be empty.

1631

#

1632

# A partition ID contains several dimensions:

1633

# project ID and namespace ID.

1634

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

1635

"projectId": "A String", # The ID of the project to which the entities belong.

1636

},

1637

"kind": { # A representation of a Datastore kind. # The kind to process.

1638

"name": "A String", # The name of the kind.

1639

},

1640

},

1641

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

1642

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

1643

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

1644

# Used for data sources like Datastore and BigQuery.

1645

#

1646

# For BigQuery:

1647

# Required to filter out rows based on the given start and

1648

# end times. If not specified and the table was modified between the given

1649

# start and end times, the entire table will be scanned.

1650

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

1651

# `TIMESTAMP`, or `DATETIME` BigQuery column.

1652

#

1653

# For Datastore.

1654

# Valid data types of the timestamp field are: `TIMESTAMP`.

1655

# Datastore entity will be scanned if the timestamp property does not

1656

# exist or its value is empty or invalid.

1657

"name": "A String", # Name describing the field.

1658

},

1659

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

1660

# a valid start_time to avoid scanning files that have not been modified

1661

# since the last time the JobTrigger executed. This will be based on the

1662

# time of the execution of the last run of the JobTrigger.

1663

"endTime": "A String", # Exclude files or rows newer than this value.

1664

# If set to zero, no upper time limit is applied.

1665

"startTime": "A String", # Exclude files or rows older than this value.

1666

},

1667

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

1668

# bucket.

1669

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

1670

# Number of files scanned is rounded down. Must be between 0 and 100,

1671

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

1672

"fileTypes": [ # List of file type groups to include in the scan.

1673

# If empty, all files are scanned and available data format processors

1674

# are applied. In addition, the binary content of the selected files

1675

# is always scanned as well.

1676

# Images are scanned only as binary if the specified region

1677

# does not support image inspection and no file_types were specified.

1678

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

1679

"A String",

1680

],

1681

"sampleMethod": "A String",

1682

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

1683

# number of bytes scanned is rounded down. Must be between 0 and 100,

1684

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

1685

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

1686

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

1687

# than this value then the rest of the bytes are omitted. Only one

1688

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

1689

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

1690

"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

1691

# `regex_file_set` must be set.

1692

# expressions are used to allow fine-grained control over which files in the

1693

# bucket to include.

1694

#

1695

# Included files are those that match at least one item in `include_regex` and

1696

# do not match any items in `exclude_regex`. Note that a file that matches

1697

# items from both lists will _not_ be included. For a match to occur, the

1698

# entire file path (i.e., everything in the url after the bucket name) must

1699

# match the regular expression.

1700

#

1701

# For example, given the input `{bucket_name: "mybucket", include_regex:

1702

# ["directory1/.*"], exclude_regex:

1703

# ["directory1/excluded.*"]}`:

1704

#

1705

# * `gs://mybucket/directory1/myfile` will be included

1706

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

1707

# across `/`)

1708

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

1709

# full path doesn't match any items in `include_regex`)

1710

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

1711

# matches an item in `exclude_regex`)

1712

#

1713

# If `include_regex` is left empty, it will match all files by default

1714

# (this is equivalent to setting `include_regex: [".*"]`).

1715

#

1716

# Some other common use cases:

1717

#

1718

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

1719

# files in `mybucket` except for .pdf files

1720

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

1721

# include all files directly under `gs://mybucket/directory/`, without matching

1722

# across `/`

1723

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

1724

# the bucket that match at least one of these regular expressions will be

1725

# excluded from the scan.

1726

#

1727

# Regular expressions use RE2

1728

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

1729

# under the google/re2 repository on GitHub.

1730

"A String",

1731

],

1732

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

1733

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

1734

# the bucket that match at least one of these regular expressions will be

1735

# included in the set of files, except for those that also match an item in

1736

# `exclude_regex`. Leaving this field empty will match all files by default

1737

# (this is equivalent to including `.*` in the list).

1738

#

1739

# Regular expressions use RE2

1740

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

1741

# 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

1746

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

1747

#

1748

# If the url ends in a trailing slash, the bucket or directory represented

1749

# by the url will be scanned non-recursively (content in sub-directories

1750

# will not be scanned). This means that `gs://mybucket/` is equivalent to

1751

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

1752

# `gs://mybucket/directory/*`.

1753

#

1754

# Exactly one of `url` or `regex_file_set` must be set.

1755

},

1756

},

1757

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

1758

"sampleMethod": "A String",

1759

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

1760

# identified by its project_id, dataset_id, and table_name. Within a query

1761

# a table is often referenced with a string in the format of:

1762

# `<project_id>:<dataset_id>.<table_id>` or

1763

# `<project_id>.<dataset_id>.<table_id>`.

1764

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

1765

# If omitted, project ID is inferred from the API call.

1766

"datasetId": "A String", # Dataset ID of the table.

1767

"tableId": "A String", # Name of the table.

1768

},

1769

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

1770

# `actions.saveFindings.outputConfig.table` is specified, the values of

1771

# columns specified here are available in the output table under

1772

# `location.content_locations.record_location.record_key.id_values`. Nested

1773

# fields such as `person.birthdate.year` are allowed.

1774

{ # General identifier of a data field in a storage service.

1775

"name": "A String", # Name describing the field.

1776

},

1777

],

1778

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

1779

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

1780

# 100 means no limit. Defaults to 0. Only one of rows_limit and

1781

# rows_limit_percent can be specified. Cannot be used in conjunction with

1782

# TimespanConfig.

1783

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

1784

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

1785

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

1786

# Cannot be used in conjunction with TimespanConfig.

1787

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

1788

# inspection of entire columns which you know have no findings.

1789

{ # General identifier of a data field in a storage service.

1790

"name": "A String", # Name describing the field.

},

],

},

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

1795

# Early access feature is in a pre-release state and might change or have

1796

# limited support. For more information, see

1797

# https://cloud.google.com/products#product-launch-stages.

1798

# of Google Cloud Platform.

1799

"labels": { # To organize findings, these labels will be added to each finding.

1800

#

1801

# Label keys must be between 1 and 63 characters long and must conform

1802

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

1803

#

1804

# Label values must be between 0 and 63 characters long and must conform

1805

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

1806

#

1807

# No more than 10 labels can be associated with a given finding.

1808

#

1809

# Examples:

1810

# * `"environment" : "production"`

1811

# * `"pipeline" : "etl"`

1812

"a_key": "A String",

1813

},

1814

"description": "A String", # A short description of where the data is coming from. Will be stored once

1815

# in the job. 256 max length.

1816

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

1817

# meaningful such as the columns that are primary keys.

1818

"identifyingFields": [ # The columns that are the primary keys for table objects included in

1819

# ContentItem. A copy of this cell's value will stored alongside alongside

1820

# each finding so that the finding can be traced to the specific row it came

1821

# from. No more than 3 may be provided.

1822

{ # General identifier of a data field in a storage service.

1823

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

1828

# 'finding_labels' map. Request may contain others, but any missing one of

1829

# these will be rejected.

1830

#

1831

# Label keys must be between 1 and 63 characters long and must conform

1832

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

1833

#

1834

# No more than 10 keys can be required.

"A String",

],

},

},

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

1840

# `inspect_config` will be merged into the values persisted as part of the

1841

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1842

},

1843

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1844

"result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspect job.

1845

"hybridStats": { # Statistics related to processing hybrid inspect requests. # Statistics related to the processing of hybrid inspect.

1846

# Early access feature is in a pre-release state and might change or have

1847

# limited support. For more information, see

1848

# https://cloud.google.com/products#product-launch-stages.

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

"processedCount": "A String", # The number of hybrid inspection requests processed within this job.

1857

},

1858

"infoTypeStats": [ # Statistics of how many instances of each info type were found during

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1859

# inspect job.

1860

{ # Statistics regarding a specific InfoType.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1861

"count": "A String", # Number of findings for this infoType.

1862

"infoType": { # Type of information detected by the API. # The type of finding this stat is for.

1863

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1864

# creating a CustomInfoType, or one of the names listed

1865

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1866

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1867

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1868

},

1869

},

1870

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1871

"totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.

1872

"processedBytes": "A String", # Total size in bytes that were processed.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1873

},

1874

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

}</pre>

</div>

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1879

<code class="details" id="create">create(parent, body=None, x__xgafv=None)</code>

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1880

<pre>Creates a job trigger to run DLP actions such as scanning storage for

1881

sensitive information on a set schedule.

1882

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

1883

1884

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1885

parent: string, Required. The parent resource name, for example projects/my-project-id. (required)

1886

body: object, The request body.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1887

The object takes the form of:

1888

1889

{ # Request message for CreateJobTrigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1890

"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]

1891

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1892

"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]

1893

# needs to trigger for a job to be started. The list may contain only

1894

# a single Schedule trigger and must have at least one object.

1895

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1896

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

1897

"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]

1898

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1899

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1900

# A scheduled start time will be skipped if the previous

1901

# execution has not ended when its scheduled time occurs.

1902

#

1903

# This value must be set to a time duration greater than or equal

1904

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1905

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1906

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1907

# Early access feature is in a pre-release state and might change or have

1908

# limited support. For more information, see

1909

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1910

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1911

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1912

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1913

],

1914

"displayName": "A String", # Display name (max 100 chars)

1915

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

1916

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

1917

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

1918

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1919

# When used with redactContent only info_types and min_likelihood are currently

1920

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1921

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

1922

# included in the response; see Finding.quote.

1923

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

1924

# Exclusion rules, contained in the set are executed in the end, other

1925

# rules are executed in the order they are specified for each info type.

1926

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

1927

# circumstances, depending on the specific details of the rules within the set.

1928

"infoTypes": [ # List of infoTypes this rule set is applied to.

1929

{ # Type of information detected by the API.

1930

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1931

# creating a CustomInfoType, or one of the names listed

1932

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

1933

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

1934

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1935

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1936

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1937

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1938

{ # A single inspection rule to be applied to infoTypes, specified in

1939

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1940

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1941

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1942

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1943

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1944

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1945

# levels. For example, if a finding would be `POSSIBLE` without the

1946

# detection rule and `relative_likelihood` is 1, then it is upgraded to

1947

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

1948

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

1949

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

1950

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

1951

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1952

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1953

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1954

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

1955

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1956

# specified, the entire match is returned. No more than 3 may be included.

1957

42,

1958

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1959

"pattern": "A String", # Pattern defining the regular expression. Its syntax

1960

# (https://github.com/google/re2/wiki/Syntax) can be found under the

1961

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1962

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1963

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

1964

# The total length of the window cannot exceed 1000 characters. Note that

1965

# the finding itself will be included in the window, so that hotwords may

1966

# be used to match substrings of the finding itself. For example, the

1967

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

1968

# adjusted upwards if the area code is known to be the local area code of

1969

# a company office using the hotword regex "\(xxx\)", where "xxx"

1970

# is the area code in question.

1971

# rule.

1972

"windowBefore": 42, # Number of characters before the finding to consider.

1973

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1974

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1975

},

1976

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

1977

# `InspectionRuleSet` are removed from results.

1978

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1979

# be used to match sensitive information specific to the data, such as a list

1980

# of employee IDs or job titles.

1981

#

1982

# Dictionary words are case-insensitive and all characters other than letters

1983

# and digits in the unicode [Basic Multilingual

1984

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

1985

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1986

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

1987

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1988

# surrounding any match must be of a different type than the adjacent

1989

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

1990

# digits next to non-digits. For example, the dictionary word "jen" will

1991

# match the first three letters of the text "jen123" but will return no

1992

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

1993

#

1994

# Dictionary words containing a large number of characters that are not

1995

# letters or digits may result in unexpected findings because such characters

1996

# are treated as whitespace. The

1997

# [limits](https://cloud.google.com/dlp/limits) page contains details about

1998

# the size limits of dictionaries. For dictionaries that do not fit within

1999

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2000

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2001

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2002

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2003

# at least one phrase and every phrase must contain at least 2 characters

2004

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2005

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2006

],

2007

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2008

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2009

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2010

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2011

# Example: gs://[BUCKET_NAME]/dictionary.txt

2012

},

2013

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2014

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

2015

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2016

# specified, the entire match is returned. No more than 3 may be included.

2017

42,

2018

],

2019

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2020

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2021

# google/re2 repository on GitHub.

2022

},

2023

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

2024

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

2025

# contained within with a finding of an infoType from this list. For

2026

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

2027

# `exclusion_rule` containing `exclude_info_types.info_types` with

2028

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

2029

# with EMAIL_ADDRESS finding.

2030

# That leads to "555-222-2222@example.org" to generate only a single

2031

# finding, namely email address.

2032

{ # Type of information detected by the API.

2033

"name": "A String", # Name of the information type. Either a name of your choosing when

2034

# creating a CustomInfoType, or one of the names listed

2035

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2036

# a built-in type. InfoType names should conform to the pattern

2037

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2042

},

2043

},

2044

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2045

},

2046

],

2047

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

2048

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

2049

# When set within `InspectJobConfig`,

2050

# the maximum returned is 2000 regardless if this is set higher.

2051

# When set within `InspectContentRequest`, this field is ignored.

2052

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

2053

{ # Max findings configuration per infoType, per content item or long

2054

# running DlpJob.

2055

"maxFindings": 42, # Max findings limit for the given infoType.

2056

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

2057

# info_type should be provided. If InfoTypeLimit does not have an

2058

# info_type, the DLP API applies the limit against all info_types that

2059

# are found but not specified in another InfoTypeLimit.

2060

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2061

# creating a CustomInfoType, or one of the names listed

2062

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2063

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2064

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2065

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2066

},

2067

],

2068

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

2069

# When set within `InspectContentRequest`, the maximum returned is 2000

2070

# regardless if this is set higher.

2071

},

2072

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2073

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2074

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2075

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2076

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2077

# InfoType values returned by ListInfoTypes or listed at

2078

# https://cloud.google.com/dlp/docs/infotypes-reference.

2079

#

2080

# When no InfoTypes or CustomInfoTypes are specified in a request, the

2081

# system may automatically choose what detectors to run. By default this may

2082

# be all types, but may change over time as detectors are updated.

2083

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2084

# If you need precise control and predictability as to what detectors are

2085

# run you should specify specific InfoTypes listed in the reference,

2086

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2087

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2088

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2089

# creating a CustomInfoType, or one of the names listed

2090

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2091

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2092

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2093

},

2094

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2095

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

2096

# POSSIBLE.

2097

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

2098

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

2099

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

2100

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

2101

{ # Custom information type provided by the user. Used to find domain-specific

2102

# sensitive information configurable to the data in question.

2103

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

2104

# altered by a detection rule if the finding meets the criteria specified by

2105

# the rule. Defaults to `VERY_LIKELY` if not specified.

2106

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

2107

# infoType, when the name matches one of existing infoTypes and that infoType

2108

# is specified in `InspectContent.info_types` field. Specifying the latter

2109

# adds findings to the one detected by the system. If built-in info type is

2110

# not specified in `InspectContent.info_types` list then the name is treated

2111

# as a custom info type.

2112

"name": "A String", # Name of the information type. Either a name of your choosing when

2113

# creating a CustomInfoType, or one of the names listed

2114

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2115

# a built-in type. InfoType names should conform to the pattern

2116

# `[a-zA-Z0-9_]{1,64}`.

2117

},

2118

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

2119

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2120

# specified, the entire match is returned. No more than 3 may be included.

2121

42,

2122

],

2123

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2124

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2125

# google/re2 repository on GitHub.

2126

},

2127

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

2128

# Rules are applied in order that they are specified. Not supported for the

2129

# `surrogate_type` CustomInfoType.

2130

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

2131

# `CustomInfoType` to alter behavior under certain circumstances, depending

2132

# on the specific details of the rule. Not supported for the `surrogate_type`

2133

# custom infoType.

2134

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

2135

# proximity of hotwords.

2136

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

2137

# part of a detection rule.

2138

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

2139

# levels. For example, if a finding would be `POSSIBLE` without the

2140

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2141

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2142

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2143

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2144

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2145

# a final likelihood of `LIKELY`.

2146

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

2147

},

2148

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2149

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2150

# specified, the entire match is returned. No more than 3 may be included.

2151

42,

2152

],

2153

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2154

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2155

# google/re2 repository on GitHub.

2156

},

2157

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2158

# The total length of the window cannot exceed 1000 characters. Note that

2159

# the finding itself will be included in the window, so that hotwords may

2160

# be used to match substrings of the finding itself. For example, the

2161

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

2162

# adjusted upwards if the area code is known to be the local area code of

2163

# a company office using the hotword regex "\(xxx\)", where "xxx"

2164

# is the area code in question.

2165

# rule.

2166

"windowBefore": 42, # Number of characters before the finding to consider.

2167

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

2173

# to be returned. It still can be used for rules matching.

2174

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

2175

# be used to match sensitive information specific to the data, such as a list

2176

# of employee IDs or job titles.

2177

#

2178

# Dictionary words are case-insensitive and all characters other than letters

2179

# and digits in the unicode [Basic Multilingual

2180

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2181

# will be replaced with whitespace when scanning for matches, so the

2182

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2183

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

2184

# surrounding any match must be of a different type than the adjacent

2185

# characters within the word, so letters must be next to non-letters and

2186

# digits next to non-digits. For example, the dictionary word "jen" will

2187

# match the first three letters of the text "jen123" but will return no

2188

# matches for "jennifer".

2189

#

2190

# Dictionary words containing a large number of characters that are not

2191

# letters or digits may result in unexpected findings because such characters

2192

# are treated as whitespace. The

2193

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2194

# the size limits of dictionaries. For dictionaries that do not fit within

2195

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2196

# `StoredInfoType` API.

2197

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2198

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

2199

# at least one phrase and every phrase must contain at least 2 characters

2200

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

2205

# is accepted.

2206

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

2207

# Example: gs://[BUCKET_NAME]/dictionary.txt

2208

},

2209

},

2210

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

2211

# `InspectDataSource`. Not currently supported in `InspectContent`.

2212

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

2213

# `organizations/433245324/storedInfoTypes/432452342` or

2214

# `projects/project-id/storedInfoTypes/432452342`.

2215

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

2216

# inspection was created. Output-only field, populated by the system.

2217

},

2218

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

2219

# support reversing.

2220

# such as

2221

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

2222

# These types of transformations are

2223

# those that perform pseudonymization, thereby producing a "surrogate" as

2224

# output. This should be used in conjunction with a field on the

2225

# transformation such as `surrogate_info_type`. This CustomInfoType does

2226

# not support the use of `detection_rules`.

2227

},

2228

},

2229

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2230

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2231

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2232

{ # A task to execute on the completion of a job.

2233

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2234

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

2235

# Command Center (CSCC Alpha).

2236

# This action is only available for projects which are parts of

2237

# an organization and whitelisted for the alpha Cloud Security Command

2238

# Center.

2239

# The action will publish count of finding instances and their info types.

2240

# The summary of findings will be persisted in CSCC and are governed by CSCC

2241

# service-specific policy, see https://cloud.google.com/terms/service-terms

2242

# Only a single instance of this action can be specified.

2243

# Compatible with: Inspect

2244

},

2245

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

2246

# completion/failure.

2247

# completion/failure.

2248

},

2249

"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]

2250

# OutputStorageConfig. Only a single instance of this action can be

2251

# specified.

2252

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2253

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

2254

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

2255

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

2256

# from the `Finding` object. If appending to an existing table, any columns

2257

# from the predefined schema that are missing will be added. No columns in

2258

# the existing table will be deleted.

2259

#

2260

# If unspecified, then all available columns will be used for a new table or

2261

# an (existing) table with no schema, and no changes will be made to an

2262

# existing table that has a schema.

2263

# Only for use with external storage.

2264

"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]

2265

# dataset. If table_id is not set a new one will be generated

2266

# for you with the following format:

2267

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

2268

# generating the date details.

2269

#

2270

# For Inspect, each column in an existing output table must have the same

2271

# name, type, and mode of a field in the `Finding` object.

2272

#

2273

# For Risk, an existing output table should be the output of a previous

2274

# Risk analysis job run on the same source table, with the same privacy

2275

# metric and quasi-identifiers. Risk jobs that analyze the same table but

2276

# compute a different privacy metric, or use different sets of

2277

# quasi-identifiers, cannot store their results in the same table.

2278

# identified by its project_id, dataset_id, and table_name. Within a query

2279

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2280

# `<project_id>:<dataset_id>.<table_id>` or

2281

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2282

"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]

2283

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2284

"datasetId": "A String", # Dataset ID of the table.

2285

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2286

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2287

},

2288

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2289

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

2290

# message contains a single field, `DlpJobName`, which is equal to the

2291

# finished job's

2292

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

2293

# Compatible with: Inspect, Risk

2294

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

2295

# publishing access rights to the DLP API service account executing

2296

# the long running DlpJob sending the notifications.

2297

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2298

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2299

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2300

# results of the DlpJob will be applied to the entry for the resource scanned

2301

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

2302

# be deleted. InfoType naming patterns are strictly enforced when using this

2303

# feature. Note that the findings will be persisted in Cloud Data Catalog

2304

# storage and are governed by Data Catalog service-specific policy, see

2305

# https://cloud.google.com/terms/service-terms

2306

# Only a single instance of this action can be specified and only allowed if

2307

# all resources being scanned are BigQuery tables.

2308

# Compatible with: Inspect

2309

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2310

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

2311

# will publish a metric to stack driver on each infotype requested and

2312

# how many findings were found for it. CustomDetectors will be bucketed

2313

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2314

},

2315

},

2316

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2317

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

2318

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

2319

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

2320

# by project and namespace, however the namespace ID may be empty.

2321

# A partition ID identifies a grouping of entities. The grouping is always

2322

# by project and namespace, however the namespace ID may be empty.

2323

#

2324

# A partition ID contains several dimensions:

2325

# project ID and namespace ID.

2326

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

2327

"projectId": "A String", # The ID of the project to which the entities belong.

2328

},

2329

"kind": { # A representation of a Datastore kind. # The kind to process.

2330

"name": "A String", # The name of the kind.

2331

},

2332

},

2333

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

2334

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

2335

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

2336

# Used for data sources like Datastore and BigQuery.

2337

#

2338

# For BigQuery:

2339

# Required to filter out rows based on the given start and

2340

# end times. If not specified and the table was modified between the given

2341

# start and end times, the entire table will be scanned.

2342

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

2343

# `TIMESTAMP`, or `DATETIME` BigQuery column.

2344

#

2345

# For Datastore.

2346

# Valid data types of the timestamp field are: `TIMESTAMP`.

2347

# Datastore entity will be scanned if the timestamp property does not

2348

# exist or its value is empty or invalid.

2349

"name": "A String", # Name describing the field.

2350

},

2351

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

2352

# a valid start_time to avoid scanning files that have not been modified

2353

# since the last time the JobTrigger executed. This will be based on the

2354

# time of the execution of the last run of the JobTrigger.

2355

"endTime": "A String", # Exclude files or rows newer than this value.

2356

# If set to zero, no upper time limit is applied.

2357

"startTime": "A String", # Exclude files or rows older than this value.

2358

},

2359

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

2360

# bucket.

2361

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

2362

# Number of files scanned is rounded down. Must be between 0 and 100,

2363

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

2364

"fileTypes": [ # List of file type groups to include in the scan.

2365

# If empty, all files are scanned and available data format processors

2366

# are applied. In addition, the binary content of the selected files

2367

# is always scanned as well.

2368

# Images are scanned only as binary if the specified region

2369

# does not support image inspection and no file_types were specified.

2370

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

2371

"A String",

2372

],

2373

"sampleMethod": "A String",

2374

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

2375

# number of bytes scanned is rounded down. Must be between 0 and 100,

2376

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

2377

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

2378

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

2379

# than this value then the rest of the bytes are omitted. Only one

2380

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

2381

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

2382

"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

2383

# `regex_file_set` must be set.

2384

# expressions are used to allow fine-grained control over which files in the

2385

# bucket to include.

2386

#

2387

# Included files are those that match at least one item in `include_regex` and

2388

# do not match any items in `exclude_regex`. Note that a file that matches

2389

# items from both lists will _not_ be included. For a match to occur, the

2390

# entire file path (i.e., everything in the url after the bucket name) must

2391

# match the regular expression.

2392

#

2393

# For example, given the input `{bucket_name: "mybucket", include_regex:

2394

# ["directory1/.*"], exclude_regex:

2395

# ["directory1/excluded.*"]}`:

2396

#

2397

# * `gs://mybucket/directory1/myfile` will be included

2398

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

2399

# across `/`)

2400

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

2401

# full path doesn't match any items in `include_regex`)

2402

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

2403

# matches an item in `exclude_regex`)

2404

#

2405

# If `include_regex` is left empty, it will match all files by default

2406

# (this is equivalent to setting `include_regex: [".*"]`).

2407

#

2408

# Some other common use cases:

2409

#

2410

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

2411

# files in `mybucket` except for .pdf files

2412

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

2413

# include all files directly under `gs://mybucket/directory/`, without matching

2414

# across `/`

2415

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

2416

# the bucket that match at least one of these regular expressions will be

2417

# excluded from the scan.

2418

#

2419

# Regular expressions use RE2

2420

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

2421

# under the google/re2 repository on GitHub.

2422

"A String",

2423

],

2424

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

2425

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

2426

# the bucket that match at least one of these regular expressions will be

2427

# included in the set of files, except for those that also match an item in

2428

# `exclude_regex`. Leaving this field empty will match all files by default

2429

# (this is equivalent to including `.*` in the list).

2430

#

2431

# Regular expressions use RE2

2432

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

2433

# 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

2438

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

2439

#

2440

# If the url ends in a trailing slash, the bucket or directory represented

2441

# by the url will be scanned non-recursively (content in sub-directories

2442

# will not be scanned). This means that `gs://mybucket/` is equivalent to

2443

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

2444

# `gs://mybucket/directory/*`.

2445

#

2446

# Exactly one of `url` or `regex_file_set` must be set.

2447

},

2448

},

2449

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

2450

"sampleMethod": "A String",

2451

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

2452

# identified by its project_id, dataset_id, and table_name. Within a query

2453

# a table is often referenced with a string in the format of:

2454

# `<project_id>:<dataset_id>.<table_id>` or

2455

# `<project_id>.<dataset_id>.<table_id>`.

2456

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

2457

# If omitted, project ID is inferred from the API call.

2458

"datasetId": "A String", # Dataset ID of the table.

2459

"tableId": "A String", # Name of the table.

2460

},

2461

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

2462

# `actions.saveFindings.outputConfig.table` is specified, the values of

2463

# columns specified here are available in the output table under

2464

# `location.content_locations.record_location.record_key.id_values`. Nested

2465

# fields such as `person.birthdate.year` are allowed.

2466

{ # General identifier of a data field in a storage service.

2467

"name": "A String", # Name describing the field.

2468

},

2469

],

2470

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

2471

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

2472

# 100 means no limit. Defaults to 0. Only one of rows_limit and

2473

# rows_limit_percent can be specified. Cannot be used in conjunction with

2474

# TimespanConfig.

2475

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

2476

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

2477

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

2478

# Cannot be used in conjunction with TimespanConfig.

2479

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

2480

# inspection of entire columns which you know have no findings.

2481

{ # General identifier of a data field in a storage service.

2482

"name": "A String", # Name describing the field.

},

],

},

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

2487

# Early access feature is in a pre-release state and might change or have

2488

# limited support. For more information, see

2489

# https://cloud.google.com/products#product-launch-stages.

2490

# of Google Cloud Platform.

2491

"labels": { # To organize findings, these labels will be added to each finding.

2492

#

2493

# Label keys must be between 1 and 63 characters long and must conform

2494

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

2495

#

2496

# Label values must be between 0 and 63 characters long and must conform

2497

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

2498

#

2499

# No more than 10 labels can be associated with a given finding.

2500

#

2501

# Examples:

2502

# * `"environment" : "production"`

2503

# * `"pipeline" : "etl"`

2504

"a_key": "A String",

2505

},

2506

"description": "A String", # A short description of where the data is coming from. Will be stored once

2507

# in the job. 256 max length.

2508

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

2509

# meaningful such as the columns that are primary keys.

2510

"identifyingFields": [ # The columns that are the primary keys for table objects included in

2511

# ContentItem. A copy of this cell's value will stored alongside alongside

2512

# each finding so that the finding can be traced to the specific row it came

2513

# from. No more than 3 may be provided.

2514

{ # General identifier of a data field in a storage service.

2515

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

2520

# 'finding_labels' map. Request may contain others, but any missing one of

2521

# these will be rejected.

2522

#

2523

# Label keys must be between 1 and 63 characters long and must conform

2524

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

2525

#

2526

# No more than 10 keys can be required.

"A String",

],

},

},

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

2532

# `inspect_config` will be merged into the values persisted as part of the

2533

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2534

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2535

"status": "A String", # Required. A status for this trigger.

2536

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

2537

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2538

# triggeredJob is created, for example

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2539

# `projects/dlp-test-project/jobTriggers/53234423`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2540

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

2541

# errors may result in the JobTrigger automatically being paused.

2542

# Will return the last 100 errors. Whenever the JobTrigger is modified

2543

# this list will be cleared.

2544

{ # Details information about an error encountered during job execution or

2545

# the results of an unsuccessful activation of the JobTrigger.

2546

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

2547

# different programming environments, including REST APIs and RPC APIs. It is

2548

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

2549

# three pieces of data: error code, error message, and error details.

2550

#

2551

# You can find out more about this error model and how to work with it in the

2552

# [API Design Guide](https://cloud.google.com/apis/design/errors).

2553

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

2554

"message": "A String", # A developer-facing error message, which should be in English. Any

2555

# user-facing error message should be localized and sent in the

2556

# google.rpc.Status.details field, or localized by the client.

2557

"details": [ # A list of messages that carry the error details. There is a common set of

2558

# message types for APIs to use.

2559

{

2560

"a_key": "", # Properties of the object. Contains field @type with type URL.

},

],

},

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2570

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2571

"triggerId": "A String", # The trigger id can contain uppercase and lowercase letters,

2572

# numbers, and hyphens; that is, it must match the regular

2573

# expression: `[a-zA-Z\\d-_]+`. The maximum length is 100

2574

# characters. Can be empty to allow the system to generate one.

2575

"locationId": "A String", # The geographic location to store the job trigger. Reserved for

2576

# future extensions.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2577

}

2578

2579

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

2586

2587

{ # Contains a configuration to make dlp api calls on a repeating basis.

2588

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2589

"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]

2590

# needs to trigger for a job to be started. The list may contain only

2591

# a single Schedule trigger and must have at least one object.

2592

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2593

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

2594

"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]

2595

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2596

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2597

# A scheduled start time will be skipped if the previous

2598

# execution has not ended when its scheduled time occurs.

2599

#

2600

# This value must be set to a time duration greater than or equal

2601

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2602

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2603

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2604

# Early access feature is in a pre-release state and might change or have

2605

# limited support. For more information, see

2606

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2607

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2608

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2609

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2610

],

2611

"displayName": "A String", # Display name (max 100 chars)

2612

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

2613

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

2614

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

2615

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2616

# When used with redactContent only info_types and min_likelihood are currently

2617

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2618

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

2619

# included in the response; see Finding.quote.

2620

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

2621

# Exclusion rules, contained in the set are executed in the end, other

2622

# rules are executed in the order they are specified for each info type.

2623

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

2624

# circumstances, depending on the specific details of the rules within the set.

2625

"infoTypes": [ # List of infoTypes this rule set is applied to.

2626

{ # Type of information detected by the API.

2627

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2628

# creating a CustomInfoType, or one of the names listed

2629

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2630

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2631

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2632

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2633

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2634

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2635

{ # A single inspection rule to be applied to infoTypes, specified in

2636

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2637

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2638

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2639

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2640

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2641

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2642

# levels. For example, if a finding would be `POSSIBLE` without the

2643

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2644

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2645

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2646

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2647

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2648

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2649

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2650

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2651

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2652

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2653

# specified, the entire match is returned. No more than 3 may be included.

2654

42,

2655

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2656

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2657

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2658

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2659

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2660

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2661

# The total length of the window cannot exceed 1000 characters. Note that

2662

# the finding itself will be included in the window, so that hotwords may

2663

# be used to match substrings of the finding itself. For example, the

2664

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

2665

# adjusted upwards if the area code is known to be the local area code of

2666

# a company office using the hotword regex "\(xxx\)", where "xxx"

2667

# is the area code in question.

2668

# rule.

2669

"windowBefore": 42, # Number of characters before the finding to consider.

2670

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2671

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2672

},

2673

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

2674

# `InspectionRuleSet` are removed from results.

2675

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2676

# be used to match sensitive information specific to the data, such as a list

2677

# of employee IDs or job titles.

2678

#

2679

# Dictionary words are case-insensitive and all characters other than letters

2680

# and digits in the unicode [Basic Multilingual

2681

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2682

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2683

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2684

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2685

# surrounding any match must be of a different type than the adjacent

2686

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2687

# digits next to non-digits. For example, the dictionary word "jen" will

2688

# match the first three letters of the text "jen123" but will return no

2689

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2690

#

2691

# Dictionary words containing a large number of characters that are not

2692

# letters or digits may result in unexpected findings because such characters

2693

# are treated as whitespace. The

2694

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2695

# the size limits of dictionaries. For dictionaries that do not fit within

2696

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2697

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2698

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2699

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2700

# at least one phrase and every phrase must contain at least 2 characters

2701

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2702

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2703

],

2704

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2705

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2706

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2707

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2708

# Example: gs://[BUCKET_NAME]/dictionary.txt

2709

},

2710

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2711

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

2712

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2713

# specified, the entire match is returned. No more than 3 may be included.

2714

42,

2715

],

2716

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2717

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2718

# google/re2 repository on GitHub.

2719

},

2720

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

2721

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

2722

# contained within with a finding of an infoType from this list. For

2723

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

2724

# `exclusion_rule` containing `exclude_info_types.info_types` with

2725

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

2726

# with EMAIL_ADDRESS finding.

2727

# That leads to "555-222-2222@example.org" to generate only a single

2728

# finding, namely email address.

2729

{ # Type of information detected by the API.

2730

"name": "A String", # Name of the information type. Either a name of your choosing when

2731

# creating a CustomInfoType, or one of the names listed

2732

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2733

# a built-in type. InfoType names should conform to the pattern

2734

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2739

},

2740

},

2741

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2742

},

2743

],

2744

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

2745

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

2746

# When set within `InspectJobConfig`,

2747

# the maximum returned is 2000 regardless if this is set higher.

2748

# When set within `InspectContentRequest`, this field is ignored.

2749

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

2750

{ # Max findings configuration per infoType, per content item or long

2751

# running DlpJob.

2752

"maxFindings": 42, # Max findings limit for the given infoType.

2753

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

2754

# info_type should be provided. If InfoTypeLimit does not have an

2755

# info_type, the DLP API applies the limit against all info_types that

2756

# are found but not specified in another InfoTypeLimit.

2757

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2758

# creating a CustomInfoType, or one of the names listed

2759

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2760

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2761

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2762

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2763

},

2764

],

2765

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

2766

# When set within `InspectContentRequest`, the maximum returned is 2000

2767

# regardless if this is set higher.

2768

},

2769

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2770

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2771

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2772

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2773

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2774

# InfoType values returned by ListInfoTypes or listed at

2775

# https://cloud.google.com/dlp/docs/infotypes-reference.

2776

#

2777

# When no InfoTypes or CustomInfoTypes are specified in a request, the

2778

# system may automatically choose what detectors to run. By default this may

2779

# be all types, but may change over time as detectors are updated.

2780

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2781

# If you need precise control and predictability as to what detectors are

2782

# run you should specify specific InfoTypes listed in the reference,

2783

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2784

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2785

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2786

# creating a CustomInfoType, or one of the names listed

2787

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2788

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2789

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2790

},

2791

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2792

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

2793

# POSSIBLE.

2794

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

2795

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

2796

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

2797

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

2798

{ # Custom information type provided by the user. Used to find domain-specific

2799

# sensitive information configurable to the data in question.

2800

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

2801

# altered by a detection rule if the finding meets the criteria specified by

2802

# the rule. Defaults to `VERY_LIKELY` if not specified.

2803

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

2804

# infoType, when the name matches one of existing infoTypes and that infoType

2805

# is specified in `InspectContent.info_types` field. Specifying the latter

2806

# adds findings to the one detected by the system. If built-in info type is

2807

# not specified in `InspectContent.info_types` list then the name is treated

2808

# as a custom info type.

2809

"name": "A String", # Name of the information type. Either a name of your choosing when

2810

# creating a CustomInfoType, or one of the names listed

2811

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

2812

# a built-in type. InfoType names should conform to the pattern

2813

# `[a-zA-Z0-9_]{1,64}`.

2814

},

2815

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

2816

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2817

# specified, the entire match is returned. No more than 3 may be included.

2818

42,

2819

],

2820

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2821

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2822

# google/re2 repository on GitHub.

2823

},

2824

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

2825

# Rules are applied in order that they are specified. Not supported for the

2826

# `surrogate_type` CustomInfoType.

2827

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

2828

# `CustomInfoType` to alter behavior under certain circumstances, depending

2829

# on the specific details of the rule. Not supported for the `surrogate_type`

2830

# custom infoType.

2831

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

2832

# proximity of hotwords.

2833

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

2834

# part of a detection rule.

2835

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

2836

# levels. For example, if a finding would be `POSSIBLE` without the

2837

# detection rule and `relative_likelihood` is 1, then it is upgraded to

2838

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

2839

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

2840

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

2841

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

2842

# a final likelihood of `LIKELY`.

2843

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

2844

},

2845

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

2846

"groupIndexes": [ # The index of the submatch to extract as findings. When not

2847

# specified, the entire match is returned. No more than 3 may be included.

2848

42,

2849

],

2850

"pattern": "A String", # Pattern defining the regular expression. Its syntax

2851

# (https://github.com/google/re2/wiki/Syntax) can be found under the

2852

# google/re2 repository on GitHub.

2853

},

2854

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

2855

# The total length of the window cannot exceed 1000 characters. Note that

2856

# the finding itself will be included in the window, so that hotwords may

2857

# be used to match substrings of the finding itself. For example, the

2858

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

2859

# adjusted upwards if the area code is known to be the local area code of

2860

# a company office using the hotword regex "\(xxx\)", where "xxx"

2861

# is the area code in question.

2862

# rule.

2863

"windowBefore": 42, # Number of characters before the finding to consider.

2864

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

2870

# to be returned. It still can be used for rules matching.

2871

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

2872

# be used to match sensitive information specific to the data, such as a list

2873

# of employee IDs or job titles.

2874

#

2875

# Dictionary words are case-insensitive and all characters other than letters

2876

# and digits in the unicode [Basic Multilingual

2877

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

2878

# will be replaced with whitespace when scanning for matches, so the

2879

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

2880

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

2881

# surrounding any match must be of a different type than the adjacent

2882

# characters within the word, so letters must be next to non-letters and

2883

# digits next to non-digits. For example, the dictionary word "jen" will

2884

# match the first three letters of the text "jen123" but will return no

2885

# matches for "jennifer".

2886

#

2887

# Dictionary words containing a large number of characters that are not

2888

# letters or digits may result in unexpected findings because such characters

2889

# are treated as whitespace. The

2890

# [limits](https://cloud.google.com/dlp/limits) page contains details about

2891

# the size limits of dictionaries. For dictionaries that do not fit within

2892

# these constraints, consider using `LargeCustomDictionaryConfig` in the

2893

# `StoredInfoType` API.

2894

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

2895

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

2896

# at least one phrase and every phrase must contain at least 2 characters

2897

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

2902

# is accepted.

2903

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

2904

# Example: gs://[BUCKET_NAME]/dictionary.txt

2905

},

2906

},

2907

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

2908

# `InspectDataSource`. Not currently supported in `InspectContent`.

2909

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

2910

# `organizations/433245324/storedInfoTypes/432452342` or

2911

# `projects/project-id/storedInfoTypes/432452342`.

2912

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

2913

# inspection was created. Output-only field, populated by the system.

2914

},

2915

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

2916

# support reversing.

2917

# such as

2918

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

2919

# These types of transformations are

2920

# those that perform pseudonymization, thereby producing a "surrogate" as

2921

# output. This should be used in conjunction with a field on the

2922

# transformation such as `surrogate_info_type`. This CustomInfoType does

2923

# not support the use of `detection_rules`.

2924

},

2925

},

2926

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2927

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2928

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2929

{ # A task to execute on the completion of a job.

2930

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2931

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

2932

# Command Center (CSCC Alpha).

2933

# This action is only available for projects which are parts of

2934

# an organization and whitelisted for the alpha Cloud Security Command

2935

# Center.

2936

# The action will publish count of finding instances and their info types.

2937

# The summary of findings will be persisted in CSCC and are governed by CSCC

2938

# service-specific policy, see https://cloud.google.com/terms/service-terms

2939

# Only a single instance of this action can be specified.

2940

# Compatible with: Inspect

2941

},

2942

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

2943

# completion/failure.

2944

# completion/failure.

2945

},

2946

"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]

2947

# OutputStorageConfig. Only a single instance of this action can be

2948

# specified.

2949

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2950

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

2951

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

2952

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

2953

# from the `Finding` object. If appending to an existing table, any columns

2954

# from the predefined schema that are missing will be added. No columns in

2955

# the existing table will be deleted.

2956

#

2957

# If unspecified, then all available columns will be used for a new table or

2958

# an (existing) table with no schema, and no changes will be made to an

2959

# existing table that has a schema.

2960

# Only for use with external storage.

2961

"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]

2962

# dataset. If table_id is not set a new one will be generated

2963

# for you with the following format:

2964

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

2965

# generating the date details.

2966

#

2967

# For Inspect, each column in an existing output table must have the same

2968

# name, type, and mode of a field in the `Finding` object.

2969

#

2970

# For Risk, an existing output table should be the output of a previous

2971

# Risk analysis job run on the same source table, with the same privacy

2972

# metric and quasi-identifiers. Risk jobs that analyze the same table but

2973

# compute a different privacy metric, or use different sets of

2974

# quasi-identifiers, cannot store their results in the same table.

2975

# identified by its project_id, dataset_id, and table_name. Within a query

2976

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2977

# `<project_id>:<dataset_id>.<table_id>` or

2978

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2979

"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]

2980

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2981

"datasetId": "A String", # Dataset ID of the table.

2982

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2983

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2984

},

2985

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2986

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

2987

# message contains a single field, `DlpJobName`, which is equal to the

2988

# finished job's

2989

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

2990

# Compatible with: Inspect, Risk

2991

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

2992

# publishing access rights to the DLP API service account executing

2993

# the long running DlpJob sending the notifications.

2994

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

2995

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

2996

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

2997

# results of the DlpJob will be applied to the entry for the resource scanned

2998

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

2999

# be deleted. InfoType naming patterns are strictly enforced when using this

3000

# feature. Note that the findings will be persisted in Cloud Data Catalog

3001

# storage and are governed by Data Catalog service-specific policy, see

3002

# https://cloud.google.com/terms/service-terms

3003

# Only a single instance of this action can be specified and only allowed if

3004

# all resources being scanned are BigQuery tables.

3005

# Compatible with: Inspect

3006

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3007

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

3008

# will publish a metric to stack driver on each infotype requested and

3009

# how many findings were found for it. CustomDetectors will be bucketed

3010

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3011

},

3012

},

3013

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3014

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

3015

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

3016

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

3017

# by project and namespace, however the namespace ID may be empty.

3018

# A partition ID identifies a grouping of entities. The grouping is always

3019

# by project and namespace, however the namespace ID may be empty.

3020

#

3021

# A partition ID contains several dimensions:

3022

# project ID and namespace ID.

3023

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

3024

"projectId": "A String", # The ID of the project to which the entities belong.

3025

},

3026

"kind": { # A representation of a Datastore kind. # The kind to process.

3027

"name": "A String", # The name of the kind.

3028

},

3029

},

3030

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

3031

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

3032

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

3033

# Used for data sources like Datastore and BigQuery.

3034

#

3035

# For BigQuery:

3036

# Required to filter out rows based on the given start and

3037

# end times. If not specified and the table was modified between the given

3038

# start and end times, the entire table will be scanned.

3039

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

3040

# `TIMESTAMP`, or `DATETIME` BigQuery column.

3041

#

3042

# For Datastore.

3043

# Valid data types of the timestamp field are: `TIMESTAMP`.

3044

# Datastore entity will be scanned if the timestamp property does not

3045

# exist or its value is empty or invalid.

3046

"name": "A String", # Name describing the field.

3047

},

3048

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

3049

# a valid start_time to avoid scanning files that have not been modified

3050

# since the last time the JobTrigger executed. This will be based on the

3051

# time of the execution of the last run of the JobTrigger.

3052

"endTime": "A String", # Exclude files or rows newer than this value.

3053

# If set to zero, no upper time limit is applied.

3054

"startTime": "A String", # Exclude files or rows older than this value.

3055

},

3056

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

3057

# bucket.

3058

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

3059

# Number of files scanned is rounded down. Must be between 0 and 100,

3060

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

3061

"fileTypes": [ # List of file type groups to include in the scan.

3062

# If empty, all files are scanned and available data format processors

3063

# are applied. In addition, the binary content of the selected files

3064

# is always scanned as well.

3065

# Images are scanned only as binary if the specified region

3066

# does not support image inspection and no file_types were specified.

3067

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

3068

"A String",

3069

],

3070

"sampleMethod": "A String",

3071

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

3072

# number of bytes scanned is rounded down. Must be between 0 and 100,

3073

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

3074

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

3075

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

3076

# than this value then the rest of the bytes are omitted. Only one

3077

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

3078

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

3079

"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

3080

# `regex_file_set` must be set.

3081

# expressions are used to allow fine-grained control over which files in the

3082

# bucket to include.

3083

#

3084

# Included files are those that match at least one item in `include_regex` and

3085

# do not match any items in `exclude_regex`. Note that a file that matches

3086

# items from both lists will _not_ be included. For a match to occur, the

3087

# entire file path (i.e., everything in the url after the bucket name) must

3088

# match the regular expression.

3089

#

3090

# For example, given the input `{bucket_name: "mybucket", include_regex:

3091

# ["directory1/.*"], exclude_regex:

3092

# ["directory1/excluded.*"]}`:

3093

#

3094

# * `gs://mybucket/directory1/myfile` will be included

3095

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

3096

# across `/`)

3097

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

3098

# full path doesn't match any items in `include_regex`)

3099

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

3100

# matches an item in `exclude_regex`)

3101

#

3102

# If `include_regex` is left empty, it will match all files by default

3103

# (this is equivalent to setting `include_regex: [".*"]`).

3104

#

3105

# Some other common use cases:

3106

#

3107

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

3108

# files in `mybucket` except for .pdf files

3109

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

3110

# include all files directly under `gs://mybucket/directory/`, without matching

3111

# across `/`

3112

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

3113

# the bucket that match at least one of these regular expressions will be

3114

# excluded from the scan.

3115

#

3116

# Regular expressions use RE2

3117

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

3118

# under the google/re2 repository on GitHub.

3119

"A String",

3120

],

3121

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

3122

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

3123

# the bucket that match at least one of these regular expressions will be

3124

# included in the set of files, except for those that also match an item in

3125

# `exclude_regex`. Leaving this field empty will match all files by default

3126

# (this is equivalent to including `.*` in the list).

3127

#

3128

# Regular expressions use RE2

3129

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

3130

# 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

3135

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

3136

#

3137

# If the url ends in a trailing slash, the bucket or directory represented

3138

# by the url will be scanned non-recursively (content in sub-directories

3139

# will not be scanned). This means that `gs://mybucket/` is equivalent to

3140

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

3141

# `gs://mybucket/directory/*`.

3142

#

3143

# Exactly one of `url` or `regex_file_set` must be set.

3144

},

3145

},

3146

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

3147

"sampleMethod": "A String",

3148

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

3149

# identified by its project_id, dataset_id, and table_name. Within a query

3150

# a table is often referenced with a string in the format of:

3151

# `<project_id>:<dataset_id>.<table_id>` or

3152

# `<project_id>.<dataset_id>.<table_id>`.

3153

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

3154

# If omitted, project ID is inferred from the API call.

3155

"datasetId": "A String", # Dataset ID of the table.

3156

"tableId": "A String", # Name of the table.

3157

},

3158

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

3159

# `actions.saveFindings.outputConfig.table` is specified, the values of

3160

# columns specified here are available in the output table under

3161

# `location.content_locations.record_location.record_key.id_values`. Nested

3162

# fields such as `person.birthdate.year` are allowed.

3163

{ # General identifier of a data field in a storage service.

3164

"name": "A String", # Name describing the field.

3165

},

3166

],

3167

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

3168

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

3169

# 100 means no limit. Defaults to 0. Only one of rows_limit and

3170

# rows_limit_percent can be specified. Cannot be used in conjunction with

3171

# TimespanConfig.

3172

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

3173

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

3174

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

3175

# Cannot be used in conjunction with TimespanConfig.

3176

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

3177

# inspection of entire columns which you know have no findings.

3178

{ # General identifier of a data field in a storage service.

3179

"name": "A String", # Name describing the field.

},

],

},

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

3184

# Early access feature is in a pre-release state and might change or have

3185

# limited support. For more information, see

3186

# https://cloud.google.com/products#product-launch-stages.

3187

# of Google Cloud Platform.

3188

"labels": { # To organize findings, these labels will be added to each finding.

3189

#

3190

# Label keys must be between 1 and 63 characters long and must conform

3191

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

3192

#

3193

# Label values must be between 0 and 63 characters long and must conform

3194

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

3195

#

3196

# No more than 10 labels can be associated with a given finding.

3197

#

3198

# Examples:

3199

# * `"environment" : "production"`

3200

# * `"pipeline" : "etl"`

3201

"a_key": "A String",

3202

},

3203

"description": "A String", # A short description of where the data is coming from. Will be stored once

3204

# in the job. 256 max length.

3205

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

3206

# meaningful such as the columns that are primary keys.

3207

"identifyingFields": [ # The columns that are the primary keys for table objects included in

3208

# ContentItem. A copy of this cell's value will stored alongside alongside

3209

# each finding so that the finding can be traced to the specific row it came

3210

# from. No more than 3 may be provided.

3211

{ # General identifier of a data field in a storage service.

3212

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

3217

# 'finding_labels' map. Request may contain others, but any missing one of

3218

# these will be rejected.

3219

#

3220

# Label keys must be between 1 and 63 characters long and must conform

3221

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

3222

#

3223

# No more than 10 keys can be required.

"A String",

],

},

},

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

3229

# `inspect_config` will be merged into the values persisted as part of the

3230

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3231

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3232

"status": "A String", # Required. A status for this trigger.

3233

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

3234

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3235

# triggeredJob is created, for example

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3236

# `projects/dlp-test-project/jobTriggers/53234423`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3237

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

3238

# errors may result in the JobTrigger automatically being paused.

3239

# Will return the last 100 errors. Whenever the JobTrigger is modified

3240

# this list will be cleared.

3241

{ # Details information about an error encountered during job execution or

3242

# the results of an unsuccessful activation of the JobTrigger.

3243

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

3244

# different programming environments, including REST APIs and RPC APIs. It is

3245

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

3246

# three pieces of data: error code, error message, and error details.

3247

#

3248

# You can find out more about this error model and how to work with it in the

3249

# [API Design Guide](https://cloud.google.com/apis/design/errors).

3250

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

3251

"message": "A String", # A developer-facing error message, which should be in English. Any

3252

# user-facing error message should be localized and sent in the

3253

# google.rpc.Status.details field, or localized by the client.

3254

"details": [ # A list of messages that carry the error details. There is a common set of

3255

# message types for APIs to use.

3256

{

3257

"a_key": "", # Properties of the object. Contains field @type with type URL.

},

],

},

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"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>

3272

<pre>Deletes a job trigger.

3273

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

3274

3275

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3276

name: string, Required. Resource name of the project and the triggeredJob, for example

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3277

`projects/dlp-test-project/jobTriggers/53234423`. (required)

3278

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

3285

3286

{ # A generic empty message that you can re-use to avoid defining duplicated

3287

# empty messages in your APIs. A typical example is to use it as the request

3288

# or the response type of an API method. For instance:

3289

#

3290

# service Foo {

3291

# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);

3292

# }

3293

#

3294

# The JSON representation for `Empty` is empty JSON object `{}`.

}</pre>

</div>

<code class="details" id="get">get(name, x__xgafv=None)</code>

3300

<pre>Gets a job trigger.

3301

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

3302

3303

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3304

name: string, Required. Resource name of the project and the triggeredJob, for example

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3305

`projects/dlp-test-project/jobTriggers/53234423`. (required)

3306

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

3313

3314

{ # Contains a configuration to make dlp api calls on a repeating basis.

3315

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3316

"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]

3317

# needs to trigger for a job to be started. The list may contain only

3318

# a single Schedule trigger and must have at least one object.

3319

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3320

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

3321

"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]

3322

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3323

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3324

# A scheduled start time will be skipped if the previous

3325

# execution has not ended when its scheduled time occurs.

3326

#

3327

# This value must be set to a time duration greater than or equal

3328

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3329

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3330

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3331

# Early access feature is in a pre-release state and might change or have

3332

# limited support. For more information, see

3333

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3334

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3335

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3336

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3337

],

3338

"displayName": "A String", # Display name (max 100 chars)

3339

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

3340

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

3341

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

3342

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3343

# When used with redactContent only info_types and min_likelihood are currently

3344

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3345

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

3346

# included in the response; see Finding.quote.

3347

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

3348

# Exclusion rules, contained in the set are executed in the end, other

3349

# rules are executed in the order they are specified for each info type.

3350

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

3351

# circumstances, depending on the specific details of the rules within the set.

3352

"infoTypes": [ # List of infoTypes this rule set is applied to.

3353

{ # Type of information detected by the API.

3354

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3355

# creating a CustomInfoType, or one of the names listed

3356

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3357

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3358

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3359

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3360

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3361

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3362

{ # A single inspection rule to be applied to infoTypes, specified in

3363

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3364

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3365

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3366

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3367

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3368

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3369

# levels. For example, if a finding would be `POSSIBLE` without the

3370

# detection rule and `relative_likelihood` is 1, then it is upgraded to

3371

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

3372

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

3373

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

3374

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

3375

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3376

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3377

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3378

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

3379

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3380

# specified, the entire match is returned. No more than 3 may be included.

3381

42,

3382

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3383

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3384

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3385

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3386

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3387

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

3388

# The total length of the window cannot exceed 1000 characters. Note that

3389

# the finding itself will be included in the window, so that hotwords may

3390

# be used to match substrings of the finding itself. For example, the

3391

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

3392

# adjusted upwards if the area code is known to be the local area code of

3393

# a company office using the hotword regex "\(xxx\)", where "xxx"

3394

# is the area code in question.

3395

# rule.

3396

"windowBefore": 42, # Number of characters before the finding to consider.

3397

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3398

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3399

},

3400

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

3401

# `InspectionRuleSet` are removed from results.

3402

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3403

# be used to match sensitive information specific to the data, such as a list

3404

# of employee IDs or job titles.

3405

#

3406

# Dictionary words are case-insensitive and all characters other than letters

3407

# and digits in the unicode [Basic Multilingual

3408

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

3409

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3410

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

3411

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3412

# surrounding any match must be of a different type than the adjacent

3413

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3414

# digits next to non-digits. For example, the dictionary word "jen" will

3415

# match the first three letters of the text "jen123" but will return no

3416

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3417

#

3418

# Dictionary words containing a large number of characters that are not

3419

# letters or digits may result in unexpected findings because such characters

3420

# are treated as whitespace. The

3421

# [limits](https://cloud.google.com/dlp/limits) page contains details about

3422

# the size limits of dictionaries. For dictionaries that do not fit within

3423

# these constraints, consider using `LargeCustomDictionaryConfig` in the

3424

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3425

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

3426

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3427

# at least one phrase and every phrase must contain at least 2 characters

3428

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3429

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3430

],

3431

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3432

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3433

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3434

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3435

# Example: gs://[BUCKET_NAME]/dictionary.txt

3436

},

3437

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3438

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

3439

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3440

# specified, the entire match is returned. No more than 3 may be included.

3441

42,

3442

],

3443

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3444

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3445

# google/re2 repository on GitHub.

3446

},

3447

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

3448

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

3449

# contained within with a finding of an infoType from this list. For

3450

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

3451

# `exclusion_rule` containing `exclude_info_types.info_types` with

3452

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

3453

# with EMAIL_ADDRESS finding.

3454

# That leads to "555-222-2222@example.org" to generate only a single

3455

# finding, namely email address.

3456

{ # Type of information detected by the API.

3457

"name": "A String", # Name of the information type. Either a name of your choosing when

3458

# creating a CustomInfoType, or one of the names listed

3459

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3460

# a built-in type. InfoType names should conform to the pattern

3461

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3466

},

3467

},

3468

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3469

},

3470

],

3471

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

3472

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

3473

# When set within `InspectJobConfig`,

3474

# the maximum returned is 2000 regardless if this is set higher.

3475

# When set within `InspectContentRequest`, this field is ignored.

3476

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

3477

{ # Max findings configuration per infoType, per content item or long

3478

# running DlpJob.

3479

"maxFindings": 42, # Max findings limit for the given infoType.

3480

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

3481

# info_type should be provided. If InfoTypeLimit does not have an

3482

# info_type, the DLP API applies the limit against all info_types that

3483

# are found but not specified in another InfoTypeLimit.

3484

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3485

# creating a CustomInfoType, or one of the names listed

3486

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3487

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3488

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3489

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3490

},

3491

],

3492

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

3493

# When set within `InspectContentRequest`, the maximum returned is 2000

3494

# regardless if this is set higher.

3495

},

3496

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3497

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3498

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3499

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3500

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3501

# InfoType values returned by ListInfoTypes or listed at

3502

# https://cloud.google.com/dlp/docs/infotypes-reference.

3503

#

3504

# When no InfoTypes or CustomInfoTypes are specified in a request, the

3505

# system may automatically choose what detectors to run. By default this may

3506

# be all types, but may change over time as detectors are updated.

3507

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3508

# If you need precise control and predictability as to what detectors are

3509

# run you should specify specific InfoTypes listed in the reference,

3510

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3511

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3512

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3513

# creating a CustomInfoType, or one of the names listed

3514

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3515

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3516

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3517

},

3518

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3519

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

3520

# POSSIBLE.

3521

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

3522

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

3523

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

3524

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

3525

{ # Custom information type provided by the user. Used to find domain-specific

3526

# sensitive information configurable to the data in question.

3527

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

3528

# altered by a detection rule if the finding meets the criteria specified by

3529

# the rule. Defaults to `VERY_LIKELY` if not specified.

3530

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

3531

# infoType, when the name matches one of existing infoTypes and that infoType

3532

# is specified in `InspectContent.info_types` field. Specifying the latter

3533

# adds findings to the one detected by the system. If built-in info type is

3534

# not specified in `InspectContent.info_types` list then the name is treated

3535

# as a custom info type.

3536

"name": "A String", # Name of the information type. Either a name of your choosing when

3537

# creating a CustomInfoType, or one of the names listed

3538

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

3539

# a built-in type. InfoType names should conform to the pattern

3540

# `[a-zA-Z0-9_]{1,64}`.

3541

},

3542

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

3543

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3544

# specified, the entire match is returned. No more than 3 may be included.

3545

42,

3546

],

3547

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3548

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3549

# google/re2 repository on GitHub.

3550

},

3551

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

3552

# Rules are applied in order that they are specified. Not supported for the

3553

# `surrogate_type` CustomInfoType.

3554

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

3555

# `CustomInfoType` to alter behavior under certain circumstances, depending

3556

# on the specific details of the rule. Not supported for the `surrogate_type`

3557

# custom infoType.

3558

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

3559

# proximity of hotwords.

3560

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

3561

# part of a detection rule.

3562

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

3563

# levels. For example, if a finding would be `POSSIBLE` without the

3564

# detection rule and `relative_likelihood` is 1, then it is upgraded to

3565

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

3566

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

3567

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

3568

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

3569

# a final likelihood of `LIKELY`.

3570

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

3571

},

3572

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

3573

"groupIndexes": [ # The index of the submatch to extract as findings. When not

3574

# specified, the entire match is returned. No more than 3 may be included.

3575

42,

3576

],

3577

"pattern": "A String", # Pattern defining the regular expression. Its syntax

3578

# (https://github.com/google/re2/wiki/Syntax) can be found under the

3579

# google/re2 repository on GitHub.

3580

},

3581

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

3582

# The total length of the window cannot exceed 1000 characters. Note that

3583

# the finding itself will be included in the window, so that hotwords may

3584

# be used to match substrings of the finding itself. For example, the

3585

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

3586

# adjusted upwards if the area code is known to be the local area code of

3587

# a company office using the hotword regex "\(xxx\)", where "xxx"

3588

# is the area code in question.

3589

# rule.

3590

"windowBefore": 42, # Number of characters before the finding to consider.

3591

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

3597

# to be returned. It still can be used for rules matching.

3598

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

3599

# be used to match sensitive information specific to the data, such as a list

3600

# of employee IDs or job titles.

3601

#

3602

# Dictionary words are case-insensitive and all characters other than letters

3603

# and digits in the unicode [Basic Multilingual

3604

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

3605

# will be replaced with whitespace when scanning for matches, so the

3606

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

3607

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

3608

# surrounding any match must be of a different type than the adjacent

3609

# characters within the word, so letters must be next to non-letters and

3610

# digits next to non-digits. For example, the dictionary word "jen" will

3611

# match the first three letters of the text "jen123" but will return no

3612

# matches for "jennifer".

3613

#

3614

# Dictionary words containing a large number of characters that are not

3615

# letters or digits may result in unexpected findings because such characters

3616

# are treated as whitespace. The

3617

# [limits](https://cloud.google.com/dlp/limits) page contains details about

3618

# the size limits of dictionaries. For dictionaries that do not fit within

3619

# these constraints, consider using `LargeCustomDictionaryConfig` in the

3620

# `StoredInfoType` API.

3621

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

3622

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

3623

# at least one phrase and every phrase must contain at least 2 characters

3624

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

3629

# is accepted.

3630

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

3631

# Example: gs://[BUCKET_NAME]/dictionary.txt

3632

},

3633

},

3634

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

3635

# `InspectDataSource`. Not currently supported in `InspectContent`.

3636

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

3637

# `organizations/433245324/storedInfoTypes/432452342` or

3638

# `projects/project-id/storedInfoTypes/432452342`.

3639

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

3640

# inspection was created. Output-only field, populated by the system.

3641

},

3642

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

3643

# support reversing.

3644

# such as

3645

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

3646

# These types of transformations are

3647

# those that perform pseudonymization, thereby producing a "surrogate" as

3648

# output. This should be used in conjunction with a field on the

3649

# transformation such as `surrogate_info_type`. This CustomInfoType does

3650

# not support the use of `detection_rules`.

3651

},

3652

},

3653

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3654

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3655

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3656

{ # A task to execute on the completion of a job.

3657

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3658

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

3659

# Command Center (CSCC Alpha).

3660

# This action is only available for projects which are parts of

3661

# an organization and whitelisted for the alpha Cloud Security Command

3662

# Center.

3663

# The action will publish count of finding instances and their info types.

3664

# The summary of findings will be persisted in CSCC and are governed by CSCC

3665

# service-specific policy, see https://cloud.google.com/terms/service-terms

3666

# Only a single instance of this action can be specified.

3667

# Compatible with: Inspect

3668

},

3669

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

3670

# completion/failure.

3671

# completion/failure.

3672

},

3673

"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]

3674

# OutputStorageConfig. Only a single instance of this action can be

3675

# specified.

3676

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3677

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

3678

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

3679

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

3680

# from the `Finding` object. If appending to an existing table, any columns

3681

# from the predefined schema that are missing will be added. No columns in

3682

# the existing table will be deleted.

3683

#

3684

# If unspecified, then all available columns will be used for a new table or

3685

# an (existing) table with no schema, and no changes will be made to an

3686

# existing table that has a schema.

3687

# Only for use with external storage.

3688

"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]

3689

# dataset. If table_id is not set a new one will be generated

3690

# for you with the following format:

3691

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

3692

# generating the date details.

3693

#

3694

# For Inspect, each column in an existing output table must have the same

3695

# name, type, and mode of a field in the `Finding` object.

3696

#

3697

# For Risk, an existing output table should be the output of a previous

3698

# Risk analysis job run on the same source table, with the same privacy

3699

# metric and quasi-identifiers. Risk jobs that analyze the same table but

3700

# compute a different privacy metric, or use different sets of

3701

# quasi-identifiers, cannot store their results in the same table.

3702

# identified by its project_id, dataset_id, and table_name. Within a query

3703

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3704

# `<project_id>:<dataset_id>.<table_id>` or

3705

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3706

"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]

3707

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3708

"datasetId": "A String", # Dataset ID of the table.

3709

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3710

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3711

},

3712

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3713

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

3714

# message contains a single field, `DlpJobName`, which is equal to the

3715

# finished job's

3716

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

3717

# Compatible with: Inspect, Risk

3718

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

3719

# publishing access rights to the DLP API service account executing

3720

# the long running DlpJob sending the notifications.

3721

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3722

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3723

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3724

# results of the DlpJob will be applied to the entry for the resource scanned

3725

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

3726

# be deleted. InfoType naming patterns are strictly enforced when using this

3727

# feature. Note that the findings will be persisted in Cloud Data Catalog

3728

# storage and are governed by Data Catalog service-specific policy, see

3729

# https://cloud.google.com/terms/service-terms

3730

# Only a single instance of this action can be specified and only allowed if

3731

# all resources being scanned are BigQuery tables.

3732

# Compatible with: Inspect

3733

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3734

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

3735

# will publish a metric to stack driver on each infotype requested and

3736

# how many findings were found for it. CustomDetectors will be bucketed

3737

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3738

},

3739

},

3740

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3741

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

3742

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

3743

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

3744

# by project and namespace, however the namespace ID may be empty.

3745

# A partition ID identifies a grouping of entities. The grouping is always

3746

# by project and namespace, however the namespace ID may be empty.

3747

#

3748

# A partition ID contains several dimensions:

3749

# project ID and namespace ID.

3750

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

3751

"projectId": "A String", # The ID of the project to which the entities belong.

3752

},

3753

"kind": { # A representation of a Datastore kind. # The kind to process.

3754

"name": "A String", # The name of the kind.

3755

},

3756

},

3757

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

3758

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

3759

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

3760

# Used for data sources like Datastore and BigQuery.

3761

#

3762

# For BigQuery:

3763

# Required to filter out rows based on the given start and

3764

# end times. If not specified and the table was modified between the given

3765

# start and end times, the entire table will be scanned.

3766

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

3767

# `TIMESTAMP`, or `DATETIME` BigQuery column.

3768

#

3769

# For Datastore.

3770

# Valid data types of the timestamp field are: `TIMESTAMP`.

3771

# Datastore entity will be scanned if the timestamp property does not

3772

# exist or its value is empty or invalid.

3773

"name": "A String", # Name describing the field.

3774

},

3775

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

3776

# a valid start_time to avoid scanning files that have not been modified

3777

# since the last time the JobTrigger executed. This will be based on the

3778

# time of the execution of the last run of the JobTrigger.

3779

"endTime": "A String", # Exclude files or rows newer than this value.

3780

# If set to zero, no upper time limit is applied.

3781

"startTime": "A String", # Exclude files or rows older than this value.

3782

},

3783

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

3784

# bucket.

3785

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

3786

# Number of files scanned is rounded down. Must be between 0 and 100,

3787

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

3788

"fileTypes": [ # List of file type groups to include in the scan.

3789

# If empty, all files are scanned and available data format processors

3790

# are applied. In addition, the binary content of the selected files

3791

# is always scanned as well.

3792

# Images are scanned only as binary if the specified region

3793

# does not support image inspection and no file_types were specified.

3794

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

3795

"A String",

3796

],

3797

"sampleMethod": "A String",

3798

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

3799

# number of bytes scanned is rounded down. Must be between 0 and 100,

3800

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

3801

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

3802

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

3803

# than this value then the rest of the bytes are omitted. Only one

3804

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

3805

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

3806

"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

3807

# `regex_file_set` must be set.

3808

# expressions are used to allow fine-grained control over which files in the

3809

# bucket to include.

3810

#

3811

# Included files are those that match at least one item in `include_regex` and

3812

# do not match any items in `exclude_regex`. Note that a file that matches

3813

# items from both lists will _not_ be included. For a match to occur, the

3814

# entire file path (i.e., everything in the url after the bucket name) must

3815

# match the regular expression.

3816

#

3817

# For example, given the input `{bucket_name: "mybucket", include_regex:

3818

# ["directory1/.*"], exclude_regex:

3819

# ["directory1/excluded.*"]}`:

3820

#

3821

# * `gs://mybucket/directory1/myfile` will be included

3822

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

3823

# across `/`)

3824

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

3825

# full path doesn't match any items in `include_regex`)

3826

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

3827

# matches an item in `exclude_regex`)

3828

#

3829

# If `include_regex` is left empty, it will match all files by default

3830

# (this is equivalent to setting `include_regex: [".*"]`).

3831

#

3832

# Some other common use cases:

3833

#

3834

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

3835

# files in `mybucket` except for .pdf files

3836

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

3837

# include all files directly under `gs://mybucket/directory/`, without matching

3838

# across `/`

3839

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

3840

# the bucket that match at least one of these regular expressions will be

3841

# excluded from the scan.

3842

#

3843

# Regular expressions use RE2

3844

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

3845

# under the google/re2 repository on GitHub.

3846

"A String",

3847

],

3848

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

3849

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

3850

# the bucket that match at least one of these regular expressions will be

3851

# included in the set of files, except for those that also match an item in

3852

# `exclude_regex`. Leaving this field empty will match all files by default

3853

# (this is equivalent to including `.*` in the list).

3854

#

3855

# Regular expressions use RE2

3856

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

3857

# 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

3862

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

3863

#

3864

# If the url ends in a trailing slash, the bucket or directory represented

3865

# by the url will be scanned non-recursively (content in sub-directories

3866

# will not be scanned). This means that `gs://mybucket/` is equivalent to

3867

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

3868

# `gs://mybucket/directory/*`.

3869

#

3870

# Exactly one of `url` or `regex_file_set` must be set.

3871

},

3872

},

3873

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

3874

"sampleMethod": "A String",

3875

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

3876

# identified by its project_id, dataset_id, and table_name. Within a query

3877

# a table is often referenced with a string in the format of:

3878

# `<project_id>:<dataset_id>.<table_id>` or

3879

# `<project_id>.<dataset_id>.<table_id>`.

3880

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

3881

# If omitted, project ID is inferred from the API call.

3882

"datasetId": "A String", # Dataset ID of the table.

3883

"tableId": "A String", # Name of the table.

3884

},

3885

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

3886

# `actions.saveFindings.outputConfig.table` is specified, the values of

3887

# columns specified here are available in the output table under

3888

# `location.content_locations.record_location.record_key.id_values`. Nested

3889

# fields such as `person.birthdate.year` are allowed.

3890

{ # General identifier of a data field in a storage service.

3891

"name": "A String", # Name describing the field.

3892

},

3893

],

3894

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

3895

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

3896

# 100 means no limit. Defaults to 0. Only one of rows_limit and

3897

# rows_limit_percent can be specified. Cannot be used in conjunction with

3898

# TimespanConfig.

3899

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

3900

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

3901

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

3902

# Cannot be used in conjunction with TimespanConfig.

3903

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

3904

# inspection of entire columns which you know have no findings.

3905

{ # General identifier of a data field in a storage service.

3906

"name": "A String", # Name describing the field.

},

],

},

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

3911

# Early access feature is in a pre-release state and might change or have

3912

# limited support. For more information, see

3913

# https://cloud.google.com/products#product-launch-stages.

3914

# of Google Cloud Platform.

3915

"labels": { # To organize findings, these labels will be added to each finding.

3916

#

3917

# Label keys must be between 1 and 63 characters long and must conform

3918

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

3919

#

3920

# Label values must be between 0 and 63 characters long and must conform

3921

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

3922

#

3923

# No more than 10 labels can be associated with a given finding.

3924

#

3925

# Examples:

3926

# * `"environment" : "production"`

3927

# * `"pipeline" : "etl"`

3928

"a_key": "A String",

3929

},

3930

"description": "A String", # A short description of where the data is coming from. Will be stored once

3931

# in the job. 256 max length.

3932

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

3933

# meaningful such as the columns that are primary keys.

3934

"identifyingFields": [ # The columns that are the primary keys for table objects included in

3935

# ContentItem. A copy of this cell's value will stored alongside alongside

3936

# each finding so that the finding can be traced to the specific row it came

3937

# from. No more than 3 may be provided.

3938

{ # General identifier of a data field in a storage service.

3939

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

3944

# 'finding_labels' map. Request may contain others, but any missing one of

3945

# these will be rejected.

3946

#

3947

# Label keys must be between 1 and 63 characters long and must conform

3948

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

3949

#

3950

# No more than 10 keys can be required.

"A String",

],

},

},

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

3956

# `inspect_config` will be merged into the values persisted as part of the

3957

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3958

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3959

"status": "A String", # Required. A status for this trigger.

3960

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

3961

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3962

# triggeredJob is created, for example

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

3963

# `projects/dlp-test-project/jobTriggers/53234423`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

3964

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

3965

# errors may result in the JobTrigger automatically being paused.

3966

# Will return the last 100 errors. Whenever the JobTrigger is modified

3967

# this list will be cleared.

3968

{ # Details information about an error encountered during job execution or

3969

# the results of an unsuccessful activation of the JobTrigger.

3970

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

3971

# different programming environments, including REST APIs and RPC APIs. It is

3972

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

3973

# three pieces of data: error code, error message, and error details.

3974

#

3975

# You can find out more about this error model and how to work with it in the

3976

# [API Design Guide](https://cloud.google.com/apis/design/errors).

3977

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

3978

"message": "A String", # A developer-facing error message, which should be in English. Any

3979

# user-facing error message should be localized and sent in the

3980

# google.rpc.Status.details field, or localized by the client.

3981

"details": [ # A list of messages that carry the error details. There is a common set of

3982

# message types for APIs to use.

3983

{

3984

"a_key": "", # Properties of the object. Contains field @type with type URL.

},

],

},

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"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

2020-05-20 12:08:20 -0700

[diff] [blame]

3998

<code class="details" id="list">list(parent, pageToken=None, locationId=None, pageSize=None, filter=None, orderBy=None, x__xgafv=None)</code>

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

3999

<pre>Lists job triggers.

4000

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

4001

4002

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4003

parent: string, Required. The parent resource name, for example `projects/my-project-id`. (required)

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4004

pageToken: string, Page token to continue retrieval. Comes from previous call

4005

to ListJobTriggers. `order_by` field must not

4006

change for subsequent calls.

4007

locationId: string, The geographic location where job triggers will be retrieved from.

4008

Use `-` for all locations. Reserved for future extensions.

4009

pageSize: integer, Size of the page, can be limited by a server.

4010

filter: string, Allows filtering.

Supported syntax:

* Filter expressions are made up of one or more restrictions.

4015

* Restrictions can be combined by `AND` or `OR` logical operators. A

4016

sequence of restrictions implicitly uses `AND`.

4017

* A restriction has the form of `{field} {operator} {value}`.

4018

* Supported fields/values for inspect jobs:

4019

- `status` - HEALTHY|PAUSED|CANCELLED

4020

- `inspected_storage` - DATASTORE|CLOUD_STORAGE|BIGQUERY

4021

- 'last_run_time` - RFC 3339 formatted timestamp, surrounded by

4022

quotation marks. Nanoseconds are ignored.

4023

- 'error_count' - Number of errors that have occurred while running.

4024

* The operator must be `=` or `!=` for status and inspected_storage.

Examples:

* inspected_storage = cloud_storage AND status = HEALTHY

4029

* inspected_storage = cloud_storage OR inspected_storage = bigquery

4030

* inspected_storage = cloud_storage AND (state = PAUSED OR state = HEALTHY)

4031

* last_run_time > \"2017-12-12T00:00:00+00:00\"

4032

4033

The length of this field should be no more than 500 characters.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4034

orderBy: string, Comma separated list of triggeredJob fields to order by,

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4035

followed by `asc` or `desc` postfix. This list is case-insensitive,

4036

default sorting order is ascending, redundant space characters are

4037

insignificant.

4038

4039

Example: `name asc,update_time, create_time desc`

4040

4041

Supported fields are:

4042

4043

- `create_time`: corresponds to time the JobTrigger was created.

4044

- `update_time`: corresponds to time the JobTrigger was last updated.

4045

- `last_run_time`: corresponds to the last time the JobTrigger ran.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4046

- `name`: corresponds to JobTrigger's name.

4047

- `display_name`: corresponds to JobTrigger's display name.

4048

- `status`: corresponds to JobTrigger's status.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4049

x__xgafv: string, V1 error format.

4050

Allowed values

4051

1 - v1 error format

4052

2 - v2 error format

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4053

4054

Returns:

4055

An object of the form:

4056

4057

{ # Response message for ListJobTriggers.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4058

"jobTriggers": [ # List of triggeredJobs, up to page_size in ListJobTriggersRequest.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4059

{ # Contains a configuration to make dlp api calls on a repeating basis.

4060

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4061

"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]

4062

# needs to trigger for a job to be started. The list may contain only

4063

# a single Schedule trigger and must have at least one object.

4064

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4065

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

4066

"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]

4067

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4068

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4069

# A scheduled start time will be skipped if the previous

4070

# execution has not ended when its scheduled time occurs.

4071

#

4072

# This value must be set to a time duration greater than or equal

4073

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4074

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4075

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4076

# Early access feature is in a pre-release state and might change or have

4077

# limited support. For more information, see

4078

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4079

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4080

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4081

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4082

],

4083

"displayName": "A String", # Display name (max 100 chars)

4084

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

4085

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

4086

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

4087

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4088

# When used with redactContent only info_types and min_likelihood are currently

4089

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4090

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

4091

# included in the response; see Finding.quote.

4092

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

4093

# Exclusion rules, contained in the set are executed in the end, other

4094

# rules are executed in the order they are specified for each info type.

4095

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

4096

# circumstances, depending on the specific details of the rules within the set.

4097

"infoTypes": [ # List of infoTypes this rule set is applied to.

4098

{ # Type of information detected by the API.

4099

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4100

# creating a CustomInfoType, or one of the names listed

4101

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4102

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4103

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4104

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4105

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4106

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4107

{ # A single inspection rule to be applied to infoTypes, specified in

4108

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4109

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4110

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4111

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4112

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4113

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4114

# levels. For example, if a finding would be `POSSIBLE` without the

4115

# detection rule and `relative_likelihood` is 1, then it is upgraded to

4116

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

4117

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

4118

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

4119

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

4120

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4121

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4122

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4123

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

4124

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4125

# specified, the entire match is returned. No more than 3 may be included.

4126

42,

4127

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4128

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4129

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4130

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4131

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4132

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

4133

# The total length of the window cannot exceed 1000 characters. Note that

4134

# the finding itself will be included in the window, so that hotwords may

4135

# be used to match substrings of the finding itself. For example, the

4136

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

4137

# adjusted upwards if the area code is known to be the local area code of

4138

# a company office using the hotword regex "\(xxx\)", where "xxx"

4139

# is the area code in question.

4140

# rule.

4141

"windowBefore": 42, # Number of characters before the finding to consider.

4142

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4143

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4144

},

4145

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

4146

# `InspectionRuleSet` are removed from results.

4147

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4148

# be used to match sensitive information specific to the data, such as a list

4149

# of employee IDs or job titles.

4150

#

4151

# Dictionary words are case-insensitive and all characters other than letters

4152

# and digits in the unicode [Basic Multilingual

4153

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

4154

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4155

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

4156

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4157

# surrounding any match must be of a different type than the adjacent

4158

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4159

# digits next to non-digits. For example, the dictionary word "jen" will

4160

# match the first three letters of the text "jen123" but will return no

4161

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4162

#

4163

# Dictionary words containing a large number of characters that are not

4164

# letters or digits may result in unexpected findings because such characters

4165

# are treated as whitespace. The

4166

# [limits](https://cloud.google.com/dlp/limits) page contains details about

4167

# the size limits of dictionaries. For dictionaries that do not fit within

4168

# these constraints, consider using `LargeCustomDictionaryConfig` in the

4169

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4170

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

4171

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4172

# at least one phrase and every phrase must contain at least 2 characters

4173

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4174

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4175

],

4176

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4177

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4178

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4179

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4180

# Example: gs://[BUCKET_NAME]/dictionary.txt

4181

},

4182

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4183

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

4184

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4185

# specified, the entire match is returned. No more than 3 may be included.

4186

42,

4187

],

4188

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4189

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4190

# google/re2 repository on GitHub.

4191

},

4192

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

4193

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

4194

# contained within with a finding of an infoType from this list. For

4195

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

4196

# `exclusion_rule` containing `exclude_info_types.info_types` with

4197

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

4198

# with EMAIL_ADDRESS finding.

4199

# That leads to "555-222-2222@example.org" to generate only a single

4200

# finding, namely email address.

4201

{ # Type of information detected by the API.

4202

"name": "A String", # Name of the information type. Either a name of your choosing when

4203

# creating a CustomInfoType, or one of the names listed

4204

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4205

# a built-in type. InfoType names should conform to the pattern

4206

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4211

},

4212

},

4213

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4214

},

4215

],

4216

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

4217

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

4218

# When set within `InspectJobConfig`,

4219

# the maximum returned is 2000 regardless if this is set higher.

4220

# When set within `InspectContentRequest`, this field is ignored.

4221

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

4222

{ # Max findings configuration per infoType, per content item or long

4223

# running DlpJob.

4224

"maxFindings": 42, # Max findings limit for the given infoType.

4225

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

4226

# info_type should be provided. If InfoTypeLimit does not have an

4227

# info_type, the DLP API applies the limit against all info_types that

4228

# are found but not specified in another InfoTypeLimit.

4229

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4230

# creating a CustomInfoType, or one of the names listed

4231

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4232

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4233

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4234

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4235

},

4236

],

4237

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

4238

# When set within `InspectContentRequest`, the maximum returned is 2000

4239

# regardless if this is set higher.

4240

},

4241

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4242

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4243

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4244

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4245

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4246

# InfoType values returned by ListInfoTypes or listed at

4247

# https://cloud.google.com/dlp/docs/infotypes-reference.

4248

#

4249

# When no InfoTypes or CustomInfoTypes are specified in a request, the

4250

# system may automatically choose what detectors to run. By default this may

4251

# be all types, but may change over time as detectors are updated.

4252

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4253

# If you need precise control and predictability as to what detectors are

4254

# run you should specify specific InfoTypes listed in the reference,

4255

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4256

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4257

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4258

# creating a CustomInfoType, or one of the names listed

4259

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4260

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4261

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4262

},

4263

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4264

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

4265

# POSSIBLE.

4266

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

4267

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

4268

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

4269

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

4270

{ # Custom information type provided by the user. Used to find domain-specific

4271

# sensitive information configurable to the data in question.

4272

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

4273

# altered by a detection rule if the finding meets the criteria specified by

4274

# the rule. Defaults to `VERY_LIKELY` if not specified.

4275

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

4276

# infoType, when the name matches one of existing infoTypes and that infoType

4277

# is specified in `InspectContent.info_types` field. Specifying the latter

4278

# adds findings to the one detected by the system. If built-in info type is

4279

# not specified in `InspectContent.info_types` list then the name is treated

4280

# as a custom info type.

4281

"name": "A String", # Name of the information type. Either a name of your choosing when

4282

# creating a CustomInfoType, or one of the names listed

4283

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4284

# a built-in type. InfoType names should conform to the pattern

4285

# `[a-zA-Z0-9_]{1,64}`.

4286

},

4287

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

4288

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4289

# specified, the entire match is returned. No more than 3 may be included.

4290

42,

4291

],

4292

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4293

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4294

# google/re2 repository on GitHub.

4295

},

4296

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

4297

# Rules are applied in order that they are specified. Not supported for the

4298

# `surrogate_type` CustomInfoType.

4299

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

4300

# `CustomInfoType` to alter behavior under certain circumstances, depending

4301

# on the specific details of the rule. Not supported for the `surrogate_type`

4302

# custom infoType.

4303

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

4304

# proximity of hotwords.

4305

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

4306

# part of a detection rule.

4307

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

4308

# levels. For example, if a finding would be `POSSIBLE` without the

4309

# detection rule and `relative_likelihood` is 1, then it is upgraded to

4310

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

4311

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

4312

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

4313

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

4314

# a final likelihood of `LIKELY`.

4315

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

4316

},

4317

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

4318

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4319

# specified, the entire match is returned. No more than 3 may be included.

4320

42,

4321

],

4322

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4323

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4324

# google/re2 repository on GitHub.

4325

},

4326

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

4327

# The total length of the window cannot exceed 1000 characters. Note that

4328

# the finding itself will be included in the window, so that hotwords may

4329

# be used to match substrings of the finding itself. For example, the

4330

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

4331

# adjusted upwards if the area code is known to be the local area code of

4332

# a company office using the hotword regex "\(xxx\)", where "xxx"

4333

# is the area code in question.

4334

# rule.

4335

"windowBefore": 42, # Number of characters before the finding to consider.

4336

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

4342

# to be returned. It still can be used for rules matching.

4343

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

4344

# be used to match sensitive information specific to the data, such as a list

4345

# of employee IDs or job titles.

4346

#

4347

# Dictionary words are case-insensitive and all characters other than letters

4348

# and digits in the unicode [Basic Multilingual

4349

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

4350

# will be replaced with whitespace when scanning for matches, so the

4351

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

4352

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

4353

# surrounding any match must be of a different type than the adjacent

4354

# characters within the word, so letters must be next to non-letters and

4355

# digits next to non-digits. For example, the dictionary word "jen" will

4356

# match the first three letters of the text "jen123" but will return no

4357

# matches for "jennifer".

4358

#

4359

# Dictionary words containing a large number of characters that are not

4360

# letters or digits may result in unexpected findings because such characters

4361

# are treated as whitespace. The

4362

# [limits](https://cloud.google.com/dlp/limits) page contains details about

4363

# the size limits of dictionaries. For dictionaries that do not fit within

4364

# these constraints, consider using `LargeCustomDictionaryConfig` in the

4365

# `StoredInfoType` API.

4366

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

4367

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

4368

# at least one phrase and every phrase must contain at least 2 characters

4369

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

4374

# is accepted.

4375

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

4376

# Example: gs://[BUCKET_NAME]/dictionary.txt

4377

},

4378

},

4379

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

4380

# `InspectDataSource`. Not currently supported in `InspectContent`.

4381

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

4382

# `organizations/433245324/storedInfoTypes/432452342` or

4383

# `projects/project-id/storedInfoTypes/432452342`.

4384

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

4385

# inspection was created. Output-only field, populated by the system.

4386

},

4387

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

4388

# support reversing.

4389

# such as

4390

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

4391

# These types of transformations are

4392

# those that perform pseudonymization, thereby producing a "surrogate" as

4393

# output. This should be used in conjunction with a field on the

4394

# transformation such as `surrogate_info_type`. This CustomInfoType does

4395

# not support the use of `detection_rules`.

4396

},

4397

},

4398

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4399

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4400

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4401

{ # A task to execute on the completion of a job.

4402

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4403

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

4404

# Command Center (CSCC Alpha).

4405

# This action is only available for projects which are parts of

4406

# an organization and whitelisted for the alpha Cloud Security Command

4407

# Center.

4408

# The action will publish count of finding instances and their info types.

4409

# The summary of findings will be persisted in CSCC and are governed by CSCC

4410

# service-specific policy, see https://cloud.google.com/terms/service-terms

4411

# Only a single instance of this action can be specified.

4412

# Compatible with: Inspect

4413

},

4414

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

4415

# completion/failure.

4416

# completion/failure.

4417

},

4418

"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]

4419

# OutputStorageConfig. Only a single instance of this action can be

4420

# specified.

4421

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4422

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

4423

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

4424

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

4425

# from the `Finding` object. If appending to an existing table, any columns

4426

# from the predefined schema that are missing will be added. No columns in

4427

# the existing table will be deleted.

4428

#

4429

# If unspecified, then all available columns will be used for a new table or

4430

# an (existing) table with no schema, and no changes will be made to an

4431

# existing table that has a schema.

4432

# Only for use with external storage.

4433

"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]

4434

# dataset. If table_id is not set a new one will be generated

4435

# for you with the following format:

4436

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

4437

# generating the date details.

4438

#

4439

# For Inspect, each column in an existing output table must have the same

4440

# name, type, and mode of a field in the `Finding` object.

4441

#

4442

# For Risk, an existing output table should be the output of a previous

4443

# Risk analysis job run on the same source table, with the same privacy

4444

# metric and quasi-identifiers. Risk jobs that analyze the same table but

4445

# compute a different privacy metric, or use different sets of

4446

# quasi-identifiers, cannot store their results in the same table.

4447

# identified by its project_id, dataset_id, and table_name. Within a query

4448

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4449

# `<project_id>:<dataset_id>.<table_id>` or

4450

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4451

"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]

4452

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4453

"datasetId": "A String", # Dataset ID of the table.

4454

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4455

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4456

},

4457

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4458

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

4459

# message contains a single field, `DlpJobName`, which is equal to the

4460

# finished job's

4461

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

4462

# Compatible with: Inspect, Risk

4463

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

4464

# publishing access rights to the DLP API service account executing

4465

# the long running DlpJob sending the notifications.

4466

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4467

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4468

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4469

# results of the DlpJob will be applied to the entry for the resource scanned

4470

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

4471

# be deleted. InfoType naming patterns are strictly enforced when using this

4472

# feature. Note that the findings will be persisted in Cloud Data Catalog

4473

# storage and are governed by Data Catalog service-specific policy, see

4474

# https://cloud.google.com/terms/service-terms

4475

# Only a single instance of this action can be specified and only allowed if

4476

# all resources being scanned are BigQuery tables.

4477

# Compatible with: Inspect

4478

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4479

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

4480

# will publish a metric to stack driver on each infotype requested and

4481

# how many findings were found for it. CustomDetectors will be bucketed

4482

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4483

},

4484

},

4485

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4486

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

4487

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

4488

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

4489

# by project and namespace, however the namespace ID may be empty.

4490

# A partition ID identifies a grouping of entities. The grouping is always

4491

# by project and namespace, however the namespace ID may be empty.

4492

#

4493

# A partition ID contains several dimensions:

4494

# project ID and namespace ID.

4495

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

4496

"projectId": "A String", # The ID of the project to which the entities belong.

4497

},

4498

"kind": { # A representation of a Datastore kind. # The kind to process.

4499

"name": "A String", # The name of the kind.

4500

},

4501

},

4502

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

4503

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

4504

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

4505

# Used for data sources like Datastore and BigQuery.

4506

#

4507

# For BigQuery:

4508

# Required to filter out rows based on the given start and

4509

# end times. If not specified and the table was modified between the given

4510

# start and end times, the entire table will be scanned.

4511

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

4512

# `TIMESTAMP`, or `DATETIME` BigQuery column.

4513

#

4514

# For Datastore.

4515

# Valid data types of the timestamp field are: `TIMESTAMP`.

4516

# Datastore entity will be scanned if the timestamp property does not

4517

# exist or its value is empty or invalid.

4518

"name": "A String", # Name describing the field.

4519

},

4520

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

4521

# a valid start_time to avoid scanning files that have not been modified

4522

# since the last time the JobTrigger executed. This will be based on the

4523

# time of the execution of the last run of the JobTrigger.

4524

"endTime": "A String", # Exclude files or rows newer than this value.

4525

# If set to zero, no upper time limit is applied.

4526

"startTime": "A String", # Exclude files or rows older than this value.

4527

},

4528

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

4529

# bucket.

4530

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

4531

# Number of files scanned is rounded down. Must be between 0 and 100,

4532

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

4533

"fileTypes": [ # List of file type groups to include in the scan.

4534

# If empty, all files are scanned and available data format processors

4535

# are applied. In addition, the binary content of the selected files

4536

# is always scanned as well.

4537

# Images are scanned only as binary if the specified region

4538

# does not support image inspection and no file_types were specified.

4539

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

4540

"A String",

4541

],

4542

"sampleMethod": "A String",

4543

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

4544

# number of bytes scanned is rounded down. Must be between 0 and 100,

4545

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

4546

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

4547

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

4548

# than this value then the rest of the bytes are omitted. Only one

4549

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

4550

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

4551

"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

4552

# `regex_file_set` must be set.

4553

# expressions are used to allow fine-grained control over which files in the

4554

# bucket to include.

4555

#

4556

# Included files are those that match at least one item in `include_regex` and

4557

# do not match any items in `exclude_regex`. Note that a file that matches

4558

# items from both lists will _not_ be included. For a match to occur, the

4559

# entire file path (i.e., everything in the url after the bucket name) must

4560

# match the regular expression.

4561

#

4562

# For example, given the input `{bucket_name: "mybucket", include_regex:

4563

# ["directory1/.*"], exclude_regex:

4564

# ["directory1/excluded.*"]}`:

4565

#

4566

# * `gs://mybucket/directory1/myfile` will be included

4567

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

4568

# across `/`)

4569

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

4570

# full path doesn't match any items in `include_regex`)

4571

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

4572

# matches an item in `exclude_regex`)

4573

#

4574

# If `include_regex` is left empty, it will match all files by default

4575

# (this is equivalent to setting `include_regex: [".*"]`).

4576

#

4577

# Some other common use cases:

4578

#

4579

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

4580

# files in `mybucket` except for .pdf files

4581

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

4582

# include all files directly under `gs://mybucket/directory/`, without matching

4583

# across `/`

4584

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

4585

# the bucket that match at least one of these regular expressions will be

4586

# excluded from the scan.

4587

#

4588

# Regular expressions use RE2

4589

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

4590

# under the google/re2 repository on GitHub.

4591

"A String",

4592

],

4593

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

4594

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

4595

# the bucket that match at least one of these regular expressions will be

4596

# included in the set of files, except for those that also match an item in

4597

# `exclude_regex`. Leaving this field empty will match all files by default

4598

# (this is equivalent to including `.*` in the list).

4599

#

4600

# Regular expressions use RE2

4601

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

4602

# 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

4607

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

4608

#

4609

# If the url ends in a trailing slash, the bucket or directory represented

4610

# by the url will be scanned non-recursively (content in sub-directories

4611

# will not be scanned). This means that `gs://mybucket/` is equivalent to

4612

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

4613

# `gs://mybucket/directory/*`.

4614

#

4615

# Exactly one of `url` or `regex_file_set` must be set.

4616

},

4617

},

4618

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

4619

"sampleMethod": "A String",

4620

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

4621

# identified by its project_id, dataset_id, and table_name. Within a query

4622

# a table is often referenced with a string in the format of:

4623

# `<project_id>:<dataset_id>.<table_id>` or

4624

# `<project_id>.<dataset_id>.<table_id>`.

4625

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

4626

# If omitted, project ID is inferred from the API call.

4627

"datasetId": "A String", # Dataset ID of the table.

4628

"tableId": "A String", # Name of the table.

4629

},

4630

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

4631

# `actions.saveFindings.outputConfig.table` is specified, the values of

4632

# columns specified here are available in the output table under

4633

# `location.content_locations.record_location.record_key.id_values`. Nested

4634

# fields such as `person.birthdate.year` are allowed.

4635

{ # General identifier of a data field in a storage service.

4636

"name": "A String", # Name describing the field.

4637

},

4638

],

4639

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

4640

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

4641

# 100 means no limit. Defaults to 0. Only one of rows_limit and

4642

# rows_limit_percent can be specified. Cannot be used in conjunction with

4643

# TimespanConfig.

4644

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

4645

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

4646

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

4647

# Cannot be used in conjunction with TimespanConfig.

4648

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

4649

# inspection of entire columns which you know have no findings.

4650

{ # General identifier of a data field in a storage service.

4651

"name": "A String", # Name describing the field.

},

],

},

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

4656

# Early access feature is in a pre-release state and might change or have

4657

# limited support. For more information, see

4658

# https://cloud.google.com/products#product-launch-stages.

4659

# of Google Cloud Platform.

4660

"labels": { # To organize findings, these labels will be added to each finding.

4661

#

4662

# Label keys must be between 1 and 63 characters long and must conform

4663

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

4664

#

4665

# Label values must be between 0 and 63 characters long and must conform

4666

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

4667

#

4668

# No more than 10 labels can be associated with a given finding.

4669

#

4670

# Examples:

4671

# * `"environment" : "production"`

4672

# * `"pipeline" : "etl"`

4673

"a_key": "A String",

4674

},

4675

"description": "A String", # A short description of where the data is coming from. Will be stored once

4676

# in the job. 256 max length.

4677

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

4678

# meaningful such as the columns that are primary keys.

4679

"identifyingFields": [ # The columns that are the primary keys for table objects included in

4680

# ContentItem. A copy of this cell's value will stored alongside alongside

4681

# each finding so that the finding can be traced to the specific row it came

4682

# from. No more than 3 may be provided.

4683

{ # General identifier of a data field in a storage service.

4684

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

4689

# 'finding_labels' map. Request may contain others, but any missing one of

4690

# these will be rejected.

4691

#

4692

# Label keys must be between 1 and 63 characters long and must conform

4693

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

4694

#

4695

# No more than 10 keys can be required.

"A String",

],

},

},

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

4701

# `inspect_config` will be merged into the values persisted as part of the

4702

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4703

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4704

"status": "A String", # Required. A status for this trigger.

4705

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

4706

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4707

# triggeredJob is created, for example

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4708

# `projects/dlp-test-project/jobTriggers/53234423`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4709

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

4710

# errors may result in the JobTrigger automatically being paused.

4711

# Will return the last 100 errors. Whenever the JobTrigger is modified

4712

# this list will be cleared.

4713

{ # Details information about an error encountered during job execution or

4714

# the results of an unsuccessful activation of the JobTrigger.

4715

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

4716

# different programming environments, including REST APIs and RPC APIs. It is

4717

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

4718

# three pieces of data: error code, error message, and error details.

4719

#

4720

# You can find out more about this error model and how to work with it in the

4721

# [API Design Guide](https://cloud.google.com/apis/design/errors).

4722

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

4723

"message": "A String", # A developer-facing error message, which should be in English. Any

4724

# user-facing error message should be localized and sent in the

4725

# google.rpc.Status.details field, or localized by the client.

4726

"details": [ # A list of messages that carry the error details. There is a common set of

4727

# message types for APIs to use.

4728

{

4729

"a_key": "", # Properties of the object. Contains field @type with type URL.

},

],

},

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4739

},

4740

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4741

"nextPageToken": "A String", # If the next page is available then the next page token to be used

4742

# in following ListJobTriggers request.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

}</pre>

</div>

<code class="details" id="list_next">list_next(previous_request, previous_response)</code>

4748

<pre>Retrieves the next page of results.

4749

4750

Args:

4751

previous_request: The request for the previous page. (required)

4752

previous_response: The response from the request for the previous page. (required)

4753

4754

Returns:

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4755

A request object that you can call 'execute()' on to request the next

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4756

page. Returns None if there are no more items in the collection.

</pre>

</div>

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4761

<code class="details" id="patch">patch(name, body=None, x__xgafv=None)</code>

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4762

<pre>Updates a job trigger.

4763

See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.

4764

4765

Args:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4766

name: string, Required. Resource name of the project and the triggeredJob, for example

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4767

`projects/dlp-test-project/jobTriggers/53234423`. (required)

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4768

body: object, The request body.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4769

The object takes the form of:

4770

4771

{ # Request message for UpdateJobTrigger.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4772

"updateMask": "A String", # Mask to control which fields get updated.

4773

"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]

4774

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4775

"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]

4776

# needs to trigger for a job to be started. The list may contain only

4777

# a single Schedule trigger and must have at least one object.

4778

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4779

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

4780

"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]

4781

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4782

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4783

# A scheduled start time will be skipped if the previous

4784

# execution has not ended when its scheduled time occurs.

4785

#

4786

# This value must be set to a time duration greater than or equal

4787

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4788

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4789

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4790

# Early access feature is in a pre-release state and might change or have

4791

# limited support. For more information, see

4792

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4793

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4794

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4795

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4796

],

4797

"displayName": "A String", # Display name (max 100 chars)

4798

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

4799

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

4800

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

4801

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4802

# When used with redactContent only info_types and min_likelihood are currently

4803

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4804

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

4805

# included in the response; see Finding.quote.

4806

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

4807

# Exclusion rules, contained in the set are executed in the end, other

4808

# rules are executed in the order they are specified for each info type.

4809

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

4810

# circumstances, depending on the specific details of the rules within the set.

4811

"infoTypes": [ # List of infoTypes this rule set is applied to.

4812

{ # Type of information detected by the API.

4813

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4814

# creating a CustomInfoType, or one of the names listed

4815

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4816

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4817

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4818

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4819

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4820

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4821

{ # A single inspection rule to be applied to infoTypes, specified in

4822

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4823

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4824

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4825

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4826

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4827

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4828

# levels. For example, if a finding would be `POSSIBLE` without the

4829

# detection rule and `relative_likelihood` is 1, then it is upgraded to

4830

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

4831

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

4832

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

4833

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

4834

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4835

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4836

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4837

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

4838

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4839

# specified, the entire match is returned. No more than 3 may be included.

4840

42,

4841

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4842

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4843

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4844

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4845

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4846

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

4847

# The total length of the window cannot exceed 1000 characters. Note that

4848

# the finding itself will be included in the window, so that hotwords may

4849

# be used to match substrings of the finding itself. For example, the

4850

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

4851

# adjusted upwards if the area code is known to be the local area code of

4852

# a company office using the hotword regex "\(xxx\)", where "xxx"

4853

# is the area code in question.

4854

# rule.

4855

"windowBefore": 42, # Number of characters before the finding to consider.

4856

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4857

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4858

},

4859

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

4860

# `InspectionRuleSet` are removed from results.

4861

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4862

# be used to match sensitive information specific to the data, such as a list

4863

# of employee IDs or job titles.

4864

#

4865

# Dictionary words are case-insensitive and all characters other than letters

4866

# and digits in the unicode [Basic Multilingual

4867

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

4868

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4869

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

4870

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4871

# surrounding any match must be of a different type than the adjacent

4872

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4873

# digits next to non-digits. For example, the dictionary word "jen" will

4874

# match the first three letters of the text "jen123" but will return no

4875

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4876

#

4877

# Dictionary words containing a large number of characters that are not

4878

# letters or digits may result in unexpected findings because such characters

4879

# are treated as whitespace. The

4880

# [limits](https://cloud.google.com/dlp/limits) page contains details about

4881

# the size limits of dictionaries. For dictionaries that do not fit within

4882

# these constraints, consider using `LargeCustomDictionaryConfig` in the

4883

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4884

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

4885

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4886

# at least one phrase and every phrase must contain at least 2 characters

4887

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4888

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4889

],

4890

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4891

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4892

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4893

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4894

# Example: gs://[BUCKET_NAME]/dictionary.txt

4895

},

4896

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4897

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

4898

"groupIndexes": [ # The index of the submatch to extract as findings. When not

4899

# specified, the entire match is returned. No more than 3 may be included.

4900

42,

4901

],

4902

"pattern": "A String", # Pattern defining the regular expression. Its syntax

4903

# (https://github.com/google/re2/wiki/Syntax) can be found under the

4904

# google/re2 repository on GitHub.

4905

},

4906

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

4907

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

4908

# contained within with a finding of an infoType from this list. For

4909

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

4910

# `exclusion_rule` containing `exclude_info_types.info_types` with

4911

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

4912

# with EMAIL_ADDRESS finding.

4913

# That leads to "555-222-2222@example.org" to generate only a single

4914

# finding, namely email address.

4915

{ # Type of information detected by the API.

4916

"name": "A String", # Name of the information type. Either a name of your choosing when

4917

# creating a CustomInfoType, or one of the names listed

4918

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4919

# a built-in type. InfoType names should conform to the pattern

4920

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4925

},

4926

},

4927

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4928

},

4929

],

4930

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

4931

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

4932

# When set within `InspectJobConfig`,

4933

# the maximum returned is 2000 regardless if this is set higher.

4934

# When set within `InspectContentRequest`, this field is ignored.

4935

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

4936

{ # Max findings configuration per infoType, per content item or long

4937

# running DlpJob.

4938

"maxFindings": 42, # Max findings limit for the given infoType.

4939

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

4940

# info_type should be provided. If InfoTypeLimit does not have an

4941

# info_type, the DLP API applies the limit against all info_types that

4942

# are found but not specified in another InfoTypeLimit.

4943

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4944

# creating a CustomInfoType, or one of the names listed

4945

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4946

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4947

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4948

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4949

},

4950

],

4951

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

4952

# When set within `InspectContentRequest`, the maximum returned is 2000

4953

# regardless if this is set higher.

4954

},

4955

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4956

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4957

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4958

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4959

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4960

# InfoType values returned by ListInfoTypes or listed at

4961

# https://cloud.google.com/dlp/docs/infotypes-reference.

4962

#

4963

# When no InfoTypes or CustomInfoTypes are specified in a request, the

4964

# system may automatically choose what detectors to run. By default this may

4965

# be all types, but may change over time as detectors are updated.

4966

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4967

# If you need precise control and predictability as to what detectors are

4968

# run you should specify specific InfoTypes listed in the reference,

4969

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4970

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4971

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4972

# creating a CustomInfoType, or one of the names listed

4973

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4974

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

4975

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

4976

},

4977

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

4978

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

4979

# POSSIBLE.

4980

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

4981

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

4982

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

4983

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

4984

{ # Custom information type provided by the user. Used to find domain-specific

4985

# sensitive information configurable to the data in question.

4986

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

4987

# altered by a detection rule if the finding meets the criteria specified by

4988

# the rule. Defaults to `VERY_LIKELY` if not specified.

4989

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

4990

# infoType, when the name matches one of existing infoTypes and that infoType

4991

# is specified in `InspectContent.info_types` field. Specifying the latter

4992

# adds findings to the one detected by the system. If built-in info type is

4993

# not specified in `InspectContent.info_types` list then the name is treated

4994

# as a custom info type.

4995

"name": "A String", # Name of the information type. Either a name of your choosing when

4996

# creating a CustomInfoType, or one of the names listed

4997

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

4998

# a built-in type. InfoType names should conform to the pattern

4999

# `[a-zA-Z0-9_]{1,64}`.

5000

},

5001

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

5002

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5003

# specified, the entire match is returned. No more than 3 may be included.

5004

42,

5005

],

5006

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5007

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5008

# google/re2 repository on GitHub.

5009

},

5010

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

5011

# Rules are applied in order that they are specified. Not supported for the

5012

# `surrogate_type` CustomInfoType.

5013

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

5014

# `CustomInfoType` to alter behavior under certain circumstances, depending

5015

# on the specific details of the rule. Not supported for the `surrogate_type`

5016

# custom infoType.

5017

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

5018

# proximity of hotwords.

5019

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

5020

# part of a detection rule.

5021

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

5022

# levels. For example, if a finding would be `POSSIBLE` without the

5023

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5024

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5025

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5026

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5027

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5028

# a final likelihood of `LIKELY`.

5029

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

5030

},

5031

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5032

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5033

# specified, the entire match is returned. No more than 3 may be included.

5034

42,

5035

],

5036

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5037

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5038

# google/re2 repository on GitHub.

5039

},

5040

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5041

# The total length of the window cannot exceed 1000 characters. Note that

5042

# the finding itself will be included in the window, so that hotwords may

5043

# be used to match substrings of the finding itself. For example, the

5044

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

5045

# adjusted upwards if the area code is known to be the local area code of

5046

# a company office using the hotword regex "\(xxx\)", where "xxx"

5047

# is the area code in question.

5048

# rule.

5049

"windowBefore": 42, # Number of characters before the finding to consider.

5050

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

5056

# to be returned. It still can be used for rules matching.

5057

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

5058

# be used to match sensitive information specific to the data, such as a list

5059

# of employee IDs or job titles.

5060

#

5061

# Dictionary words are case-insensitive and all characters other than letters

5062

# and digits in the unicode [Basic Multilingual

5063

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5064

# will be replaced with whitespace when scanning for matches, so the

5065

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5066

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

5067

# surrounding any match must be of a different type than the adjacent

5068

# characters within the word, so letters must be next to non-letters and

5069

# digits next to non-digits. For example, the dictionary word "jen" will

5070

# match the first three letters of the text "jen123" but will return no

5071

# matches for "jennifer".

5072

#

5073

# Dictionary words containing a large number of characters that are not

5074

# letters or digits may result in unexpected findings because such characters

5075

# are treated as whitespace. The

5076

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5077

# the size limits of dictionaries. For dictionaries that do not fit within

5078

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5079

# `StoredInfoType` API.

5080

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5081

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

5082

# at least one phrase and every phrase must contain at least 2 characters

5083

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

5088

# is accepted.

5089

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

5090

# Example: gs://[BUCKET_NAME]/dictionary.txt

5091

},

5092

},

5093

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

5094

# `InspectDataSource`. Not currently supported in `InspectContent`.

5095

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

5096

# `organizations/433245324/storedInfoTypes/432452342` or

5097

# `projects/project-id/storedInfoTypes/432452342`.

5098

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

5099

# inspection was created. Output-only field, populated by the system.

5100

},

5101

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

5102

# support reversing.

5103

# such as

5104

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

5105

# These types of transformations are

5106

# those that perform pseudonymization, thereby producing a "surrogate" as

5107

# output. This should be used in conjunction with a field on the

5108

# transformation such as `surrogate_info_type`. This CustomInfoType does

5109

# not support the use of `detection_rules`.

5110

},

5111

},

5112

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5113

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5114

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5115

{ # A task to execute on the completion of a job.

5116

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5117

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

5118

# Command Center (CSCC Alpha).

5119

# This action is only available for projects which are parts of

5120

# an organization and whitelisted for the alpha Cloud Security Command

5121

# Center.

5122

# The action will publish count of finding instances and their info types.

5123

# The summary of findings will be persisted in CSCC and are governed by CSCC

5124

# service-specific policy, see https://cloud.google.com/terms/service-terms

5125

# Only a single instance of this action can be specified.

5126

# Compatible with: Inspect

5127

},

5128

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

5129

# completion/failure.

5130

# completion/failure.

5131

},

5132

"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]

5133

# OutputStorageConfig. Only a single instance of this action can be

5134

# specified.

5135

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5136

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

5137

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

5138

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

5139

# from the `Finding` object. If appending to an existing table, any columns

5140

# from the predefined schema that are missing will be added. No columns in

5141

# the existing table will be deleted.

5142

#

5143

# If unspecified, then all available columns will be used for a new table or

5144

# an (existing) table with no schema, and no changes will be made to an

5145

# existing table that has a schema.

5146

# Only for use with external storage.

5147

"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]

5148

# dataset. If table_id is not set a new one will be generated

5149

# for you with the following format:

5150

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

5151

# generating the date details.

5152

#

5153

# For Inspect, each column in an existing output table must have the same

5154

# name, type, and mode of a field in the `Finding` object.

5155

#

5156

# For Risk, an existing output table should be the output of a previous

5157

# Risk analysis job run on the same source table, with the same privacy

5158

# metric and quasi-identifiers. Risk jobs that analyze the same table but

5159

# compute a different privacy metric, or use different sets of

5160

# quasi-identifiers, cannot store their results in the same table.

5161

# identified by its project_id, dataset_id, and table_name. Within a query

5162

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5163

# `<project_id>:<dataset_id>.<table_id>` or

5164

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5165

"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]

5166

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5167

"datasetId": "A String", # Dataset ID of the table.

5168

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5169

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5170

},

5171

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5172

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

5173

# message contains a single field, `DlpJobName`, which is equal to the

5174

# finished job's

5175

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

5176

# Compatible with: Inspect, Risk

5177

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

5178

# publishing access rights to the DLP API service account executing

5179

# the long running DlpJob sending the notifications.

5180

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5181

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5182

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5183

# results of the DlpJob will be applied to the entry for the resource scanned

5184

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

5185

# be deleted. InfoType naming patterns are strictly enforced when using this

5186

# feature. Note that the findings will be persisted in Cloud Data Catalog

5187

# storage and are governed by Data Catalog service-specific policy, see

5188

# https://cloud.google.com/terms/service-terms

5189

# Only a single instance of this action can be specified and only allowed if

5190

# all resources being scanned are BigQuery tables.

5191

# Compatible with: Inspect

5192

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5193

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

5194

# will publish a metric to stack driver on each infotype requested and

5195

# how many findings were found for it. CustomDetectors will be bucketed

5196

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5197

},

5198

},

5199

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5200

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

5201

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

5202

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

5203

# by project and namespace, however the namespace ID may be empty.

5204

# A partition ID identifies a grouping of entities. The grouping is always

5205

# by project and namespace, however the namespace ID may be empty.

5206

#

5207

# A partition ID contains several dimensions:

5208

# project ID and namespace ID.

5209

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

5210

"projectId": "A String", # The ID of the project to which the entities belong.

5211

},

5212

"kind": { # A representation of a Datastore kind. # The kind to process.

5213

"name": "A String", # The name of the kind.

5214

},

5215

},

5216

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

5217

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

5218

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

5219

# Used for data sources like Datastore and BigQuery.

5220

#

5221

# For BigQuery:

5222

# Required to filter out rows based on the given start and

5223

# end times. If not specified and the table was modified between the given

5224

# start and end times, the entire table will be scanned.

5225

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

5226

# `TIMESTAMP`, or `DATETIME` BigQuery column.

5227

#

5228

# For Datastore.

5229

# Valid data types of the timestamp field are: `TIMESTAMP`.

5230

# Datastore entity will be scanned if the timestamp property does not

5231

# exist or its value is empty or invalid.

5232

"name": "A String", # Name describing the field.

5233

},

5234

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

5235

# a valid start_time to avoid scanning files that have not been modified

5236

# since the last time the JobTrigger executed. This will be based on the

5237

# time of the execution of the last run of the JobTrigger.

5238

"endTime": "A String", # Exclude files or rows newer than this value.

5239

# If set to zero, no upper time limit is applied.

5240

"startTime": "A String", # Exclude files or rows older than this value.

5241

},

5242

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

5243

# bucket.

5244

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

5245

# Number of files scanned is rounded down. Must be between 0 and 100,

5246

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

5247

"fileTypes": [ # List of file type groups to include in the scan.

5248

# If empty, all files are scanned and available data format processors

5249

# are applied. In addition, the binary content of the selected files

5250

# is always scanned as well.

5251

# Images are scanned only as binary if the specified region

5252

# does not support image inspection and no file_types were specified.

5253

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

5254

"A String",

5255

],

5256

"sampleMethod": "A String",

5257

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

5258

# number of bytes scanned is rounded down. Must be between 0 and 100,

5259

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

5260

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

5261

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

5262

# than this value then the rest of the bytes are omitted. Only one

5263

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

5264

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

5265

"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

5266

# `regex_file_set` must be set.

5267

# expressions are used to allow fine-grained control over which files in the

5268

# bucket to include.

5269

#

5270

# Included files are those that match at least one item in `include_regex` and

5271

# do not match any items in `exclude_regex`. Note that a file that matches

5272

# items from both lists will _not_ be included. For a match to occur, the

5273

# entire file path (i.e., everything in the url after the bucket name) must

5274

# match the regular expression.

5275

#

5276

# For example, given the input `{bucket_name: "mybucket", include_regex:

5277

# ["directory1/.*"], exclude_regex:

5278

# ["directory1/excluded.*"]}`:

5279

#

5280

# * `gs://mybucket/directory1/myfile` will be included

5281

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

5282

# across `/`)

5283

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

5284

# full path doesn't match any items in `include_regex`)

5285

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

5286

# matches an item in `exclude_regex`)

5287

#

5288

# If `include_regex` is left empty, it will match all files by default

5289

# (this is equivalent to setting `include_regex: [".*"]`).

5290

#

5291

# Some other common use cases:

5292

#

5293

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

5294

# files in `mybucket` except for .pdf files

5295

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

5296

# include all files directly under `gs://mybucket/directory/`, without matching

5297

# across `/`

5298

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

5299

# the bucket that match at least one of these regular expressions will be

5300

# excluded from the scan.

5301

#

5302

# Regular expressions use RE2

5303

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

5304

# under the google/re2 repository on GitHub.

5305

"A String",

5306

],

5307

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

5308

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

5309

# the bucket that match at least one of these regular expressions will be

5310

# included in the set of files, except for those that also match an item in

5311

# `exclude_regex`. Leaving this field empty will match all files by default

5312

# (this is equivalent to including `.*` in the list).

5313

#

5314

# Regular expressions use RE2

5315

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

5316

# 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

5321

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

5322

#

5323

# If the url ends in a trailing slash, the bucket or directory represented

5324

# by the url will be scanned non-recursively (content in sub-directories

5325

# will not be scanned). This means that `gs://mybucket/` is equivalent to

5326

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

5327

# `gs://mybucket/directory/*`.

5328

#

5329

# Exactly one of `url` or `regex_file_set` must be set.

5330

},

5331

},

5332

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

5333

"sampleMethod": "A String",

5334

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

5335

# identified by its project_id, dataset_id, and table_name. Within a query

5336

# a table is often referenced with a string in the format of:

5337

# `<project_id>:<dataset_id>.<table_id>` or

5338

# `<project_id>.<dataset_id>.<table_id>`.

5339

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

5340

# If omitted, project ID is inferred from the API call.

5341

"datasetId": "A String", # Dataset ID of the table.

5342

"tableId": "A String", # Name of the table.

5343

},

5344

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

5345

# `actions.saveFindings.outputConfig.table` is specified, the values of

5346

# columns specified here are available in the output table under

5347

# `location.content_locations.record_location.record_key.id_values`. Nested

5348

# fields such as `person.birthdate.year` are allowed.

5349

{ # General identifier of a data field in a storage service.

5350

"name": "A String", # Name describing the field.

5351

},

5352

],

5353

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

5354

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

5355

# 100 means no limit. Defaults to 0. Only one of rows_limit and

5356

# rows_limit_percent can be specified. Cannot be used in conjunction with

5357

# TimespanConfig.

5358

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

5359

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

5360

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

5361

# Cannot be used in conjunction with TimespanConfig.

5362

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

5363

# inspection of entire columns which you know have no findings.

5364

{ # General identifier of a data field in a storage service.

5365

"name": "A String", # Name describing the field.

},

],

},

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

5370

# Early access feature is in a pre-release state and might change or have

5371

# limited support. For more information, see

5372

# https://cloud.google.com/products#product-launch-stages.

5373

# of Google Cloud Platform.

5374

"labels": { # To organize findings, these labels will be added to each finding.

5375

#

5376

# Label keys must be between 1 and 63 characters long and must conform

5377

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

5378

#

5379

# Label values must be between 0 and 63 characters long and must conform

5380

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

5381

#

5382

# No more than 10 labels can be associated with a given finding.

5383

#

5384

# Examples:

5385

# * `"environment" : "production"`

5386

# * `"pipeline" : "etl"`

5387

"a_key": "A String",

5388

},

5389

"description": "A String", # A short description of where the data is coming from. Will be stored once

5390

# in the job. 256 max length.

5391

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

5392

# meaningful such as the columns that are primary keys.

5393

"identifyingFields": [ # The columns that are the primary keys for table objects included in

5394

# ContentItem. A copy of this cell's value will stored alongside alongside

5395

# each finding so that the finding can be traced to the specific row it came

5396

# from. No more than 3 may be provided.

5397

{ # General identifier of a data field in a storage service.

5398

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

5403

# 'finding_labels' map. Request may contain others, but any missing one of

5404

# these will be rejected.

5405

#

5406

# Label keys must be between 1 and 63 characters long and must conform

5407

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

5408

#

5409

# No more than 10 keys can be required.

"A String",

],

},

},

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

5415

# `inspect_config` will be merged into the values persisted as part of the

5416

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5417

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5418

"status": "A String", # Required. A status for this trigger.

5419

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

5420

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5421

# triggeredJob is created, for example

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5422

# `projects/dlp-test-project/jobTriggers/53234423`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5423

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

5424

# errors may result in the JobTrigger automatically being paused.

5425

# Will return the last 100 errors. Whenever the JobTrigger is modified

5426

# this list will be cleared.

5427

{ # Details information about an error encountered during job execution or

5428

# the results of an unsuccessful activation of the JobTrigger.

5429

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

5430

# different programming environments, including REST APIs and RPC APIs. It is

5431

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

5432

# three pieces of data: error code, error message, and error details.

5433

#

5434

# You can find out more about this error model and how to work with it in the

5435

# [API Design Guide](https://cloud.google.com/apis/design/errors).

5436

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

5437

"message": "A String", # A developer-facing error message, which should be in English. Any

5438

# user-facing error message should be localized and sent in the

5439

# google.rpc.Status.details field, or localized by the client.

5440

"details": [ # A list of messages that carry the error details. There is a common set of

5441

# message types for APIs to use.

5442

{

5443

"a_key": "", # Properties of the object. Contains field @type with type URL.

},

],

},

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5453

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5454

}

5455

5456

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

5463

5464

{ # Contains a configuration to make dlp api calls on a repeating basis.

5465

# See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5466

"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]

5467

# needs to trigger for a job to be started. The list may contain only

5468

# a single Schedule trigger and must have at least one object.

5469

{ # What event needs to occur for a new job to be started.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5470

"schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.

5471

"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]

5472

# example: every day (86400 seconds).

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5473

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5474

# A scheduled start time will be skipped if the previous

5475

# execution has not ended when its scheduled time occurs.

5476

#

5477

# This value must be set to a time duration greater than or equal

5478

# to 1 day and can be no longer than 60 days.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5479

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5480

"manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5481

# Early access feature is in a pre-release state and might change or have

5482

# limited support. For more information, see

5483

# https://cloud.google.com/products#product-launch-stages.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5484

# and finished.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5485

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5486

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5487

],

5488

"displayName": "A String", # Display name (max 100 chars)

5489

"createTime": "A String", # Output only. The creation timestamp of a triggeredJob.

5490

"updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.

5491

"inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.

5492

"inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5493

# When used with redactContent only info_types and min_likelihood are currently

5494

# used.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5495

"includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is

5496

# included in the response; see Finding.quote.

5497

"ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.

5498

# Exclusion rules, contained in the set are executed in the end, other

5499

# rules are executed in the order they are specified for each info type.

5500

{ # Rule set for modifying a set of infoTypes to alter behavior under certain

5501

# circumstances, depending on the specific details of the rules within the set.

5502

"infoTypes": [ # List of infoTypes this rule set is applied to.

5503

{ # Type of information detected by the API.

5504

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5505

# creating a CustomInfoType, or one of the names listed

5506

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5507

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5508

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5509

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5510

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5511

"rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5512

{ # A single inspection rule to be applied to infoTypes, specified in

5513

# `InspectionRuleSet`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5514

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5515

# proximity of hotwords.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5516

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5517

# part of a detection rule.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5518

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5519

# levels. For example, if a finding would be `POSSIBLE` without the

5520

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5521

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5522

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5523

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5524

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5525

# a final likelihood of `LIKELY`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5526

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5527

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5528

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5529

"groupIndexes": [ # The index of the submatch to extract as findings. When not

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5530

# specified, the entire match is returned. No more than 3 may be included.

5531

42,

5532

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5533

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5534

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5535

# google/re2 repository on GitHub.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5536

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5537

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5538

# The total length of the window cannot exceed 1000 characters. Note that

5539

# the finding itself will be included in the window, so that hotwords may

5540

# be used to match substrings of the finding itself. For example, the

5541

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

5542

# adjusted upwards if the area code is known to be the local area code of

5543

# a company office using the hotword regex "\(xxx\)", where "xxx"

5544

# is the area code in question.

5545

# rule.

5546

"windowBefore": 42, # Number of characters before the finding to consider.

5547

"windowAfter": 42, # Number of characters after the finding to consider.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5548

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5549

},

5550

"exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.

5551

# `InspectionRuleSet` are removed from results.

5552

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5553

# be used to match sensitive information specific to the data, such as a list

5554

# of employee IDs or job titles.

5555

#

5556

# Dictionary words are case-insensitive and all characters other than letters

5557

# and digits in the unicode [Basic Multilingual

5558

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5559

# will be replaced with whitespace when scanning for matches, so the

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5560

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5561

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5562

# surrounding any match must be of a different type than the adjacent

5563

# characters within the word, so letters must be next to non-letters and

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5564

# digits next to non-digits. For example, the dictionary word "jen" will

5565

# match the first three letters of the text "jen123" but will return no

5566

# matches for "jennifer".

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5567

#

5568

# Dictionary words containing a large number of characters that are not

5569

# letters or digits may result in unexpected findings because such characters

5570

# are treated as whitespace. The

5571

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5572

# the size limits of dictionaries. For dictionaries that do not fit within

5573

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5574

# `StoredInfoType` API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5575

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5576

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5577

# at least one phrase and every phrase must contain at least 2 characters

5578

# that are letters or digits. [required]

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5579

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5580

],

5581

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5582

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5583

# is accepted.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5584

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5585

# Example: gs://[BUCKET_NAME]/dictionary.txt

5586

},

5587

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5588

"regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.

5589

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5590

# specified, the entire match is returned. No more than 3 may be included.

5591

42,

5592

],

5593

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5594

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5595

# google/re2 repository on GitHub.

5596

},

5597

"excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.

5598

"infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or

5599

# contained within with a finding of an infoType from this list. For

5600

# example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and

5601

# `exclusion_rule` containing `exclude_info_types.info_types` with

5602

# "EMAIL_ADDRESS" the phone number findings are dropped if they overlap

5603

# with EMAIL_ADDRESS finding.

5604

# That leads to "555-222-2222@example.org" to generate only a single

5605

# finding, namely email address.

5606

{ # Type of information detected by the API.

5607

"name": "A String", # Name of the information type. Either a name of your choosing when

5608

# creating a CustomInfoType, or one of the names listed

5609

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5610

# a built-in type. InfoType names should conform to the pattern

5611

# `[a-zA-Z0-9_]{1,64}`.

},

],

},

"matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5616

},

5617

},

5618

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5619

},

5620

],

5621

"limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.

5622

"maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.

5623

# When set within `InspectJobConfig`,

5624

# the maximum returned is 2000 regardless if this is set higher.

5625

# When set within `InspectContentRequest`, this field is ignored.

5626

"maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.

5627

{ # Max findings configuration per infoType, per content item or long

5628

# running DlpJob.

5629

"maxFindings": 42, # Max findings limit for the given infoType.

5630

"infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per

5631

# info_type should be provided. If InfoTypeLimit does not have an

5632

# info_type, the DLP API applies the limit against all info_types that

5633

# are found but not specified in another InfoTypeLimit.

5634

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5635

# creating a CustomInfoType, or one of the names listed

5636

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5637

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5638

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5639

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5640

},

5641

],

5642

"maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.

5643

# When set within `InspectContentRequest`, the maximum returned is 2000

5644

# regardless if this is set higher.

5645

},

5646

"contentOptions": [ # List of options defining data content to scan.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5647

# If empty, text, images, and other content will be included.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5648

"A String",

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5649

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5650

"infoTypes": [ # Restricts what info_types to look for. The values must correspond to

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5651

# InfoType values returned by ListInfoTypes or listed at

5652

# https://cloud.google.com/dlp/docs/infotypes-reference.

5653

#

5654

# When no InfoTypes or CustomInfoTypes are specified in a request, the

5655

# system may automatically choose what detectors to run. By default this may

5656

# be all types, but may change over time as detectors are updated.

5657

#

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5658

# If you need precise control and predictability as to what detectors are

5659

# run you should specify specific InfoTypes listed in the reference,

5660

# otherwise a default list will be used, which may change over time.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5661

{ # Type of information detected by the API.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5662

"name": "A String", # Name of the information type. Either a name of your choosing when

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5663

# creating a CustomInfoType, or one of the names listed

5664

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5665

# a built-in type. InfoType names should conform to the pattern

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5666

# `[a-zA-Z0-9_]{1,64}`.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5667

},

5668

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5669

"minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is

5670

# POSSIBLE.

5671

# See https://cloud.google.com/dlp/docs/likelihood to learn more.

5672

"excludeInfoTypes": True or False, # When true, excludes type information of the findings.

5673

"customInfoTypes": [ # CustomInfoTypes provided by the user. See

5674

# https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.

5675

{ # Custom information type provided by the user. Used to find domain-specific

5676

# sensitive information configurable to the data in question.

5677

"likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be

5678

# altered by a detection rule if the finding meets the criteria specified by

5679

# the rule. Defaults to `VERY_LIKELY` if not specified.

5680

"infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in

5681

# infoType, when the name matches one of existing infoTypes and that infoType

5682

# is specified in `InspectContent.info_types` field. Specifying the latter

5683

# adds findings to the one detected by the system. If built-in info type is

5684

# not specified in `InspectContent.info_types` list then the name is treated

5685

# as a custom info type.

5686

"name": "A String", # Name of the information type. Either a name of your choosing when

5687

# creating a CustomInfoType, or one of the names listed

5688

# at https://cloud.google.com/dlp/docs/infotypes-reference when specifying

5689

# a built-in type. InfoType names should conform to the pattern

5690

# `[a-zA-Z0-9_]{1,64}`.

5691

},

5692

"regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.

5693

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5694

# specified, the entire match is returned. No more than 3 may be included.

5695

42,

5696

],

5697

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5698

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5699

# google/re2 repository on GitHub.

5700

},

5701

"detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.

5702

# Rules are applied in order that they are specified. Not supported for the

5703

# `surrogate_type` CustomInfoType.

5704

{ # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a

5705

# `CustomInfoType` to alter behavior under certain circumstances, depending

5706

# on the specific details of the rule. Not supported for the `surrogate_type`

5707

# custom infoType.

5708

"hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.

5709

# proximity of hotwords.

5710

"likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.

5711

# part of a detection rule.

5712

"relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of

5713

# levels. For example, if a finding would be `POSSIBLE` without the

5714

# detection rule and `relative_likelihood` is 1, then it is upgraded to

5715

# `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.

5716

# Likelihood may never drop below `VERY_UNLIKELY` or exceed

5717

# `VERY_LIKELY`, so applying an adjustment of 1 followed by an

5718

# adjustment of -1 when base likelihood is `VERY_LIKELY` will result in

5719

# a final likelihood of `LIKELY`.

5720

"fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.

5721

},

5722

"hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.

5723

"groupIndexes": [ # The index of the submatch to extract as findings. When not

5724

# specified, the entire match is returned. No more than 3 may be included.

5725

42,

5726

],

5727

"pattern": "A String", # Pattern defining the regular expression. Its syntax

5728

# (https://github.com/google/re2/wiki/Syntax) can be found under the

5729

# google/re2 repository on GitHub.

5730

},

5731

"proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.

5732

# The total length of the window cannot exceed 1000 characters. Note that

5733

# the finding itself will be included in the window, so that hotwords may

5734

# be used to match substrings of the finding itself. For example, the

5735

# certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be

5736

# adjusted upwards if the area code is known to be the local area code of

5737

# a company office using the hotword regex "\(xxx\)", where "xxx"

5738

# is the area code in question.

5739

# rule.

5740

"windowBefore": 42, # Number of characters before the finding to consider.

5741

"windowAfter": 42, # Number of characters after the finding to consider.

},

},

},

],

"exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding

5747

# to be returned. It still can be used for rules matching.

5748

"dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.

5749

# be used to match sensitive information specific to the data, such as a list

5750

# of employee IDs or job titles.

5751

#

5752

# Dictionary words are case-insensitive and all characters other than letters

5753

# and digits in the unicode [Basic Multilingual

5754

# Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)

5755

# will be replaced with whitespace when scanning for matches, so the

5756

# dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",

5757

# "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters

5758

# surrounding any match must be of a different type than the adjacent

5759

# characters within the word, so letters must be next to non-letters and

5760

# digits next to non-digits. For example, the dictionary word "jen" will

5761

# match the first three letters of the text "jen123" but will return no

5762

# matches for "jennifer".

5763

#

5764

# Dictionary words containing a large number of characters that are not

5765

# letters or digits may result in unexpected findings because such characters

5766

# are treated as whitespace. The

5767

# [limits](https://cloud.google.com/dlp/limits) page contains details about

5768

# the size limits of dictionaries. For dictionaries that do not fit within

5769

# these constraints, consider using `LargeCustomDictionaryConfig` in the

5770

# `StoredInfoType` API.

5771

"wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.

5772

"words": [ # Words or phrases defining the dictionary. The dictionary must contain

5773

# at least one phrase and every phrase must contain at least 2 characters

5774

# that are letters or digits. [required]

"A String",

],

},

"cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file

5779

# is accepted.

5780

"path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.

5781

# Example: gs://[BUCKET_NAME]/dictionary.txt

5782

},

5783

},

5784

"storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in

5785

# `InspectDataSource`. Not currently supported in `InspectContent`.

5786

"name": "A String", # Resource name of the requested `StoredInfoType`, for example

5787

# `organizations/433245324/storedInfoTypes/432452342` or

5788

# `projects/project-id/storedInfoTypes/432452342`.

5789

"createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for

5790

# inspection was created. Output-only field, populated by the system.

5791

},

5792

"surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that

5793

# support reversing.

5794

# such as

5795

# [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).

5796

# These types of transformations are

5797

# those that perform pseudonymization, thereby producing a "surrogate" as

5798

# output. This should be used in conjunction with a field on the

5799

# transformation such as `surrogate_info_type`. This CustomInfoType does

5800

# not support the use of `detection_rules`.

5801

},

5802

},

5803

],

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5804

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5805

"actions": [ # Actions to execute at the completion of the job.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5806

{ # A task to execute on the completion of a job.

5807

# See https://cloud.google.com/dlp/docs/concepts-actions to learn more.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5808

"publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).

5809

# Command Center (CSCC Alpha).

5810

# This action is only available for projects which are parts of

5811

# an organization and whitelisted for the alpha Cloud Security Command

5812

# Center.

5813

# The action will publish count of finding instances and their info types.

5814

# The summary of findings will be persisted in CSCC and are governed by CSCC

5815

# service-specific policy, see https://cloud.google.com/terms/service-terms

5816

# Only a single instance of this action can be specified.

5817

# Compatible with: Inspect

5818

},

5819

"jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's

5820

# completion/failure.

5821

# completion/failure.

5822

},

5823

"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]

5824

# OutputStorageConfig. Only a single instance of this action can be

5825

# specified.

5826

# Compatible with: Inspect, Risk

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5827

"outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.

5828

"outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only

5829

# used for Inspect and must be unspecified for Risk jobs. Columns are derived

5830

# from the `Finding` object. If appending to an existing table, any columns

5831

# from the predefined schema that are missing will be added. No columns in

5832

# the existing table will be deleted.

5833

#

5834

# If unspecified, then all available columns will be used for a new table or

5835

# an (existing) table with no schema, and no changes will be made to an

5836

# existing table that has a schema.

5837

# Only for use with external storage.

5838

"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]

5839

# dataset. If table_id is not set a new one will be generated

5840

# for you with the following format:

5841

# dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for

5842

# generating the date details.

5843

#

5844

# For Inspect, each column in an existing output table must have the same

5845

# name, type, and mode of a field in the `Finding` object.

5846

#

5847

# For Risk, an existing output table should be the output of a previous

5848

# Risk analysis job run on the same source table, with the same privacy

5849

# metric and quasi-identifiers. Risk jobs that analyze the same table but

5850

# compute a different privacy metric, or use different sets of

5851

# quasi-identifiers, cannot store their results in the same table.

5852

# identified by its project_id, dataset_id, and table_name. Within a query

5853

# a table is often referenced with a string in the format of:

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5854

# `<project_id>:<dataset_id>.<table_id>` or

5855

# `<project_id>.<dataset_id>.<table_id>`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5856

"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]

5857

# If omitted, project ID is inferred from the API call.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5858

"datasetId": "A String", # Dataset ID of the table.

5859

"tableId": "A String", # Name of the table.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5860

},

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5861

},

5862

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5863

"pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.

5864

# message contains a single field, `DlpJobName`, which is equal to the

5865

# finished job's

5866

# [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).

5867

# Compatible with: Inspect, Risk

5868

"topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given

5869

# publishing access rights to the DLP API service account executing

5870

# the long running DlpJob sending the notifications.

5871

# Format is projects/{project}/topics/{topic}.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5872

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5873

"publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

5874

# results of the DlpJob will be applied to the entry for the resource scanned

5875

# in Cloud Data Catalog. Any labels previously written by another DlpJob will

5876

# be deleted. InfoType naming patterns are strictly enforced when using this

5877

# feature. Note that the findings will be persisted in Cloud Data Catalog

5878

# storage and are governed by Data Catalog service-specific policy, see

5879

# https://cloud.google.com/terms/service-terms

5880

# Only a single instance of this action can be specified and only allowed if

5881

# all resources being scanned are BigQuery tables.

5882

# Compatible with: Inspect

5883

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5884

"publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.

5885

# will publish a metric to stack driver on each infotype requested and

5886

# how many findings were found for it. CustomDetectors will be bucketed

5887

# as 'Custom' under the Stackdriver label 'info_type'.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

5888

},

5889

},

5890

],

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

5891

"storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.

5892

"datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.

5893

"partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always

5894

# by project and namespace, however the namespace ID may be empty.

5895

# A partition ID identifies a grouping of entities. The grouping is always

5896

# by project and namespace, however the namespace ID may be empty.

5897

#

5898

# A partition ID contains several dimensions:

5899

# project ID and namespace ID.

5900

"namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.

5901

"projectId": "A String", # The ID of the project to which the entities belong.

5902

},

5903

"kind": { # A representation of a Datastore kind. # The kind to process.

5904

"name": "A String", # The name of the kind.

5905

},

5906

},

5907

"timespanConfig": { # Configuration of the timespan of the items to include in scanning.

5908

# Currently only supported when inspecting Google Cloud Storage and BigQuery.

5909

"timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.

5910

# Used for data sources like Datastore and BigQuery.

5911

#

5912

# For BigQuery:

5913

# Required to filter out rows based on the given start and

5914

# end times. If not specified and the table was modified between the given

5915

# start and end times, the entire table will be scanned.

5916

# The valid data types of the timestamp field are: `INTEGER`, `DATE`,

5917

# `TIMESTAMP`, or `DATETIME` BigQuery column.

5918

#

5919

# For Datastore.

5920

# Valid data types of the timestamp field are: `TIMESTAMP`.

5921

# Datastore entity will be scanned if the timestamp property does not

5922

# exist or its value is empty or invalid.

5923

"name": "A String", # Name describing the field.

5924

},

5925

"enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out

5926

# a valid start_time to avoid scanning files that have not been modified

5927

# since the last time the JobTrigger executed. This will be based on the

5928

# time of the execution of the last run of the JobTrigger.

5929

"endTime": "A String", # Exclude files or rows newer than this value.

5930

# If set to zero, no upper time limit is applied.

5931

"startTime": "A String", # Exclude files or rows older than this value.

5932

},

5933

"cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.

5934

# bucket.

5935

"filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.

5936

# Number of files scanned is rounded down. Must be between 0 and 100,

5937

# inclusively. Both 0 and 100 means no limit. Defaults to 0.

5938

"fileTypes": [ # List of file type groups to include in the scan.

5939

# If empty, all files are scanned and available data format processors

5940

# are applied. In addition, the binary content of the selected files

5941

# is always scanned as well.

5942

# Images are scanned only as binary if the specified region

5943

# does not support image inspection and no file_types were specified.

5944

# Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.

5945

"A String",

5946

],

5947

"sampleMethod": "A String",

5948

"bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The

5949

# number of bytes scanned is rounded down. Must be between 0 and 100,

5950

# inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one

5951

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

5952

"bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger

5953

# than this value then the rest of the bytes are omitted. Only one

5954

# of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.

5955

"fileSet": { # Set of files to scan. # The set of one or more files to scan.

5956

"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

5957

# `regex_file_set` must be set.

5958

# expressions are used to allow fine-grained control over which files in the

5959

# bucket to include.

5960

#

5961

# Included files are those that match at least one item in `include_regex` and

5962

# do not match any items in `exclude_regex`. Note that a file that matches

5963

# items from both lists will _not_ be included. For a match to occur, the

5964

# entire file path (i.e., everything in the url after the bucket name) must

5965

# match the regular expression.

5966

#

5967

# For example, given the input `{bucket_name: "mybucket", include_regex:

5968

# ["directory1/.*"], exclude_regex:

5969

# ["directory1/excluded.*"]}`:

5970

#

5971

# * `gs://mybucket/directory1/myfile` will be included

5972

# * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches

5973

# across `/`)

5974

# * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the

5975

# full path doesn't match any items in `include_regex`)

5976

# * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path

5977

# matches an item in `exclude_regex`)

5978

#

5979

# If `include_regex` is left empty, it will match all files by default

5980

# (this is equivalent to setting `include_regex: [".*"]`).

5981

#

5982

# Some other common use cases:

5983

#

5984

# * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all

5985

# files in `mybucket` except for .pdf files

5986

# * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will

5987

# include all files directly under `gs://mybucket/directory/`, without matching

5988

# across `/`

5989

"excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in

5990

# the bucket that match at least one of these regular expressions will be

5991

# excluded from the scan.

5992

#

5993

# Regular expressions use RE2

5994

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

5995

# under the google/re2 repository on GitHub.

5996

"A String",

5997

],

5998

"bucketName": "A String", # The name of a Cloud Storage bucket. Required.

5999

"includeRegex": [ # A list of regular expressions matching file paths to include. All files in

6000

# the bucket that match at least one of these regular expressions will be

6001

# included in the set of files, except for those that also match an item in

6002

# `exclude_regex`. Leaving this field empty will match all files by default

6003

# (this is equivalent to including `.*` in the list).

6004

#

6005

# Regular expressions use RE2

6006

# [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found

6007

# 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

6012

# `gs://<bucket>/<path>`. Trailing wildcard in the path is allowed.

6013

#

6014

# If the url ends in a trailing slash, the bucket or directory represented

6015

# by the url will be scanned non-recursively (content in sub-directories

6016

# will not be scanned). This means that `gs://mybucket/` is equivalent to

6017

# `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to

6018

# `gs://mybucket/directory/*`.

6019

#

6020

# Exactly one of `url` or `regex_file_set` must be set.

6021

},

6022

},

6023

"bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.

6024

"sampleMethod": "A String",

6025

"tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.

6026

# identified by its project_id, dataset_id, and table_name. Within a query

6027

# a table is often referenced with a string in the format of:

6028

# `<project_id>:<dataset_id>.<table_id>` or

6029

# `<project_id>.<dataset_id>.<table_id>`.

6030

"projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.

6031

# If omitted, project ID is inferred from the API call.

6032

"datasetId": "A String", # Dataset ID of the table.

6033

"tableId": "A String", # Name of the table.

6034

},

6035

"identifyingFields": [ # Table fields that may uniquely identify a row within the table. When

6036

# `actions.saveFindings.outputConfig.table` is specified, the values of

6037

# columns specified here are available in the output table under

6038

# `location.content_locations.record_location.record_key.id_values`. Nested

6039

# fields such as `person.birthdate.year` are allowed.

6040

{ # General identifier of a data field in a storage service.

6041

"name": "A String", # Name describing the field.

6042

},

6043

],

6044

"rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows

6045

# scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and

6046

# 100 means no limit. Defaults to 0. Only one of rows_limit and

6047

# rows_limit_percent can be specified. Cannot be used in conjunction with

6048

# TimespanConfig.

6049

"rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the

6050

# rest of the rows are omitted. If not set, or if set to 0, all rows will be

6051

# scanned. Only one of rows_limit and rows_limit_percent can be specified.

6052

# Cannot be used in conjunction with TimespanConfig.

6053

"excludedFields": [ # References to fields excluded from scanning. This allows you to skip

6054

# inspection of entire columns which you know have no findings.

6055

{ # General identifier of a data field in a storage service.

6056

"name": "A String", # Name describing the field.

},

],

},

"hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.

6061

# Early access feature is in a pre-release state and might change or have

6062

# limited support. For more information, see

6063

# https://cloud.google.com/products#product-launch-stages.

6064

# of Google Cloud Platform.

6065

"labels": { # To organize findings, these labels will be added to each finding.

6066

#

6067

# Label keys must be between 1 and 63 characters long and must conform

6068

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

6069

#

6070

# Label values must be between 0 and 63 characters long and must conform

6071

# to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.

6072

#

6073

# No more than 10 labels can be associated with a given finding.

6074

#

6075

# Examples:

6076

# * `"environment" : "production"`

6077

# * `"pipeline" : "etl"`

6078

"a_key": "A String",

6079

},

6080

"description": "A String", # A short description of where the data is coming from. Will be stored once

6081

# in the job. 256 max length.

6082

"tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings

6083

# meaningful such as the columns that are primary keys.

6084

"identifyingFields": [ # The columns that are the primary keys for table objects included in

6085

# ContentItem. A copy of this cell's value will stored alongside alongside

6086

# each finding so that the finding can be traced to the specific row it came

6087

# from. No more than 3 may be provided.

6088

{ # General identifier of a data field in a storage service.

6089

"name": "A String", # Name describing the field.

},

],

},

"requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their

6094

# 'finding_labels' map. Request may contain others, but any missing one of

6095

# these will be rejected.

6096

#

6097

# Label keys must be between 1 and 63 characters long and must conform

6098

# to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.

6099

#

6100

# No more than 10 keys can be required.

"A String",

],

},

},

"inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.

6106

# `inspect_config` will be merged into the values persisted as part of the

6107

# template.

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6108

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6109

"status": "A String", # Required. A status for this trigger.

6110

"lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.

6111

"name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the

Bu Sun Kim

2019-06-14 16:50:42 -0700

[diff] [blame]

6112

# triggeredJob is created, for example

Dan O'Meara

2020-05-01 07:42:23 -0700

[diff] [blame]

6113

# `projects/dlp-test-project/jobTriggers/53234423`.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

6114

"errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated

6115

# errors may result in the JobTrigger automatically being paused.

6116

# Will return the last 100 errors. Whenever the JobTrigger is modified

6117

# this list will be cleared.

6118

{ # Details information about an error encountered during job execution or

6119

# the results of an unsuccessful activation of the JobTrigger.

6120

"details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.

6121

# different programming environments, including REST APIs and RPC APIs. It is

6122

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

6123

# three pieces of data: error code, error message, and error details.

6124

#

6125

# You can find out more about this error model and how to work with it in the

6126

# [API Design Guide](https://cloud.google.com/apis/design/errors).

6127

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

6128

"message": "A String", # A developer-facing error message, which should be in English. Any

6129

# user-facing error message should be localized and sent in the

6130

# google.rpc.Status.details field, or localized by the client.

6131

"details": [ # A list of messages that carry the error details. There is a common set of

6132

# message types for APIs to use.

6133

{

6134

"a_key": "", # Properties of the object. Contains field @type with type URL.

},

],

},

"timestamps": [ # The times the error occurred.

"A String",

],

},

],

"description": "A String", # User provided description (max 256 chars)

Bu Sun Kim