Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / python / google-api-python-client / dd49464a6262c0d1f71efcf11f131e2f591fe5f6 / . / docs / dyn / dlp_v2.projects.jobTriggers.html
blob: 723e13c96143219b4131fe34bd2c1015d34fa15e [file] [log] [blame]
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1<html><body>
2<style>
3
4body, h1, h2, h3, div, span, p, pre, a {
5 margin: 0;
6 padding: 0;
7 border: 0;
8 font-weight: inherit;
9 font-style: inherit;
10 font-size: 100%;
11 font-family: inherit;
12 vertical-align: baseline;
13}
14
15body {
16 font-size: 13px;
17 padding: 1em;
18}
19
20h1 {
21 font-size: 26px;
22 margin-bottom: 1em;
23}
24
25h2 {
26 font-size: 24px;
27 margin-bottom: 1em;
28}
29
30h3 {
31 font-size: 20px;
32 margin-bottom: 1em;
33 margin-top: 1em;
34}
35
36pre, code {
37 line-height: 1.5;
38 font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
39}
40
41pre {
42 margin-top: 0.5em;
43}
44
45h1, h2, h3, p {
46 font-family: Arial, sans serif;
47}
48
49h1, h2, h3 {
50 border-bottom: solid #CCC 1px;
51}
52
53.toc_element {
54 margin-top: 0.5em;
55}
56
57.firstline {
58 margin-left: 2 em;
59}
60
61.method {
62 margin-top: 1em;
63 border: solid 1px #CCC;
64 padding: 1em;
65 background: #EEE;
66}
67
68.details {
69 font-weight: bold;
70 font-size: 14px;
71}
72
73</style>
74
75<h1><a href="dlp_v2.html">Cloud Data Loss Prevention (DLP) API</a> . <a href="dlp_v2.projects.html">projects</a> . <a href="dlp_v2.projects.jobTriggers.html">jobTriggers</a></h1>
76<h2>Instance Methods</h2>
77<p class="toc_element">
78 <code><a href="#activate">activate(name, body=None, x__xgafv=None)</a></code></p>
79<p class="firstline">Activate a job trigger. Causes the immediate execute of a trigger</p>
80<p class="toc_element">
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]81 <code><a href="#create">create(parent, body=None, x__xgafv=None)</a></code></p>
Bu Sun Kim715bd7f2019-06-14 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<p class="toc_element">
84 <code><a href="#delete">delete(name, x__xgafv=None)</a></code></p>
85<p class="firstline">Deletes a job trigger.</p>
86<p class="toc_element">
87 <code><a href="#get">get(name, x__xgafv=None)</a></code></p>
88<p class="firstline">Gets a job trigger.</p>
89<p class="toc_element">
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]90 <code><a href="#list">list(parent, orderBy=None, pageSize=None, pageToken=None, x__xgafv=None, locationId=None, filter=None)</a></code></p>
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]91<p class="firstline">Lists job triggers.</p>
92<p class="toc_element">
93 <code><a href="#list_next">list_next(previous_request, previous_response)</a></code></p>
94<p class="firstline">Retrieves the next page of results.</p>
95<p class="toc_element">
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]96 <code><a href="#patch">patch(name, body=None, x__xgafv=None)</a></code></p>
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]97<p class="firstline">Updates a job trigger.</p>
98<h3>Method Details</h3>
99<div class="method">
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
102instead of waiting on the trigger event to occur.
103
104Args:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]105 name: string, Required. Resource name of the trigger to activate, for example
Bu Sun Kim715bd7f2019-06-14 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.
114 Allowed values
115 1 - v1 error format
116 2 - v2 error format
117
118Returns:
119 An object of the form:
120
121 { # Combines all of the information about a DLP job.
122 "errors": [ # A stream of errors encountered running the job.
123 { # Details information about an error encountered during job execution or
124 # the results of an unsuccessful activation of the JobTrigger.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]125 "timestamps": [ # The times the error occurred.
126 "A String",
127 ],
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]128 "details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]129 # different programming environments, including REST APIs and RPC APIs. It is
130 # used by [gRPC](https://github.com/grpc). Each `Status` message contains
131 # three pieces of data: error code, error message, and error details.
132 #
133 # You can find out more about this error model and how to work with it in the
134 # [API Design Guide](https://cloud.google.com/apis/design/errors).
135 "message": "A String", # A developer-facing error message, which should be in English. Any
136 # user-facing error message should be localized and sent in the
137 # google.rpc.Status.details field, or localized by the client.
138 "code": 42, # The status code, which should be an enum value of google.rpc.Code.
139 "details": [ # A list of messages that carry the error details. There is a common set of
140 # message types for APIs to use.
141 {
142 "a_key": "", # Properties of the object. Contains field @type with type URL.
143 },
144 ],
145 },
146 },
147 ],
148 "name": "A String", # The server-assigned name.
149 "inspectDetails": { # The results of an inspect DataSource job. # Results from inspecting a data source.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]150 "requestedOptions": { # Snapshot of the inspection configuration. # The configuration used for this job.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]151 "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
152 # this run.
153 # to be detected) to be used anywhere you otherwise would normally specify
154 # InspectConfig. See https://cloud.google.com/dlp/docs/concepts-templates
155 # to learn more.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]156 "updateTime": "A String", # Output only. The last update timestamp of an inspectTemplate.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]157 "displayName": "A String", # Display name (max 256 chars).
158 "description": "A String", # Short description (max 256 chars).
159 "inspectConfig": { # Configuration description of the scanning process. # The core content of the template. Configuration of the scanning process.
160 # When used with redactContent only info_types and min_likelihood are currently
161 # used.
162 "excludeInfoTypes": True or False, # When true, excludes type information of the findings.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]163 "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]164 "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
165 # When set within `InspectContentRequest`, the maximum returned is 2000
166 # regardless if this is set higher.
167 "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
168 { # Max findings configuration per infoType, per content item or long
169 # running DlpJob.
170 "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per
171 # info_type should be provided. If InfoTypeLimit does not have an
172 # info_type, the DLP API applies the limit against all info_types that
173 # are found but not specified in another InfoTypeLimit.
174 "name": "A String", # Name of the information type. Either a name of your choosing when
175 # creating a CustomInfoType, or one of the names listed
176 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
177 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]178 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]179 },
180 "maxFindings": 42, # Max findings limit for the given infoType.
181 },
182 ],
183 "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]184 # When set within `InspectJobConfig`,
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]185 # the maximum returned is 2000 regardless if this is set higher.
186 # When set within `InspectContentRequest`, this field is ignored.
187 },
188 "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
189 # POSSIBLE.
190 # See https://cloud.google.com/dlp/docs/likelihood to learn more.
191 "customInfoTypes": [ # CustomInfoTypes provided by the user. See
192 # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.
193 { # Custom information type provided by the user. Used to find domain-specific
194 # sensitive information configurable to the data in question.
195 "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
196 "pattern": "A String", # Pattern defining the regular expression. Its syntax
197 # (https://github.com/google/re2/wiki/Syntax) can be found under the
198 # google/re2 repository on GitHub.
199 "groupIndexes": [ # The index of the submatch to extract as findings. When not
200 # specified, the entire match is returned. No more than 3 may be included.
201 42,
202 ],
203 },
204 "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
205 # support reversing.
206 # such as
207 # [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).
208 # These types of transformations are
209 # those that perform pseudonymization, thereby producing a "surrogate" as
210 # output. This should be used in conjunction with a field on the
211 # transformation such as `surrogate_info_type`. This CustomInfoType does
212 # not support the use of `detection_rules`.
213 },
214 "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in
215 # infoType, when the name matches one of existing infoTypes and that infoType
216 # is specified in `InspectContent.info_types` field. Specifying the latter
217 # adds findings to the one detected by the system. If built-in info type is
218 # not specified in `InspectContent.info_types` list then the name is treated
219 # as a custom info type.
220 "name": "A String", # Name of the information type. Either a name of your choosing when
221 # creating a CustomInfoType, or one of the names listed
222 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
223 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]224 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]225 },
226 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
227 # be used to match sensitive information specific to the data, such as a list
228 # of employee IDs or job titles.
229 #
230 # Dictionary words are case-insensitive and all characters other than letters
231 # and digits in the unicode [Basic Multilingual
232 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
233 # will be replaced with whitespace when scanning for matches, so the
234 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
235 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
236 # surrounding any match must be of a different type than the adjacent
237 # characters within the word, so letters must be next to non-letters and
238 # digits next to non-digits. For example, the dictionary word "jen" will
239 # match the first three letters of the text "jen123" but will return no
240 # matches for "jennifer".
241 #
242 # Dictionary words containing a large number of characters that are not
243 # letters or digits may result in unexpected findings because such characters
244 # are treated as whitespace. The
245 # [limits](https://cloud.google.com/dlp/limits) page contains details about
246 # the size limits of dictionaries. For dictionaries that do not fit within
247 # these constraints, consider using `LargeCustomDictionaryConfig` in the
248 # `StoredInfoType` API.
249 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
250 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
251 # at least one phrase and every phrase must contain at least 2 characters
252 # that are letters or digits. [required]
253 "A String",
254 ],
255 },
256 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
257 # is accepted.
258 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
259 # Example: gs://[BUCKET_NAME]/dictionary.txt
260 },
261 },
262 "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
263 # `InspectDataSource`. Not currently supported in `InspectContent`.
264 "name": "A String", # Resource name of the requested `StoredInfoType`, for example
265 # `organizations/433245324/storedInfoTypes/432452342` or
266 # `projects/project-id/storedInfoTypes/432452342`.
267 "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
268 # inspection was created. Output-only field, populated by the system.
269 },
270 "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.
271 # Rules are applied in order that they are specified. Not supported for the
272 # `surrogate_type` CustomInfoType.
273 { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a
274 # `CustomInfoType` to alter behavior under certain circumstances, depending
275 # on the specific details of the rule. Not supported for the `surrogate_type`
276 # custom infoType.
277 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
278 # proximity of hotwords.
279 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
280 # The total length of the window cannot exceed 1000 characters. Note that
281 # the finding itself will be included in the window, so that hotwords may
282 # be used to match substrings of the finding itself. For example, the
283 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
284 # adjusted upwards if the area code is known to be the local area code of
285 # a company office using the hotword regex "\(xxx\)", where "xxx"
286 # is the area code in question.
287 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]288 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]289 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]290 },
291 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
292 "pattern": "A String", # Pattern defining the regular expression. Its syntax
293 # (https://github.com/google/re2/wiki/Syntax) can be found under the
294 # google/re2 repository on GitHub.
295 "groupIndexes": [ # The index of the submatch to extract as findings. When not
296 # specified, the entire match is returned. No more than 3 may be included.
297 42,
298 ],
299 },
300 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
301 # part of a detection rule.
302 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
303 # levels. For example, if a finding would be `POSSIBLE` without the
304 # detection rule and `relative_likelihood` is 1, then it is upgraded to
305 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
306 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
307 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
308 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
309 # a final likelihood of `LIKELY`.
310 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
311 },
312 },
313 },
314 ],
315 "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding
316 # to be returned. It still can be used for rules matching.
317 "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be
318 # altered by a detection rule if the finding meets the criteria specified by
319 # the rule. Defaults to `VERY_LIKELY` if not specified.
320 },
321 ],
322 "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
323 # included in the response; see Finding.quote.
324 "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.
325 # Exclusion rules, contained in the set are executed in the end, other
326 # rules are executed in the order they are specified for each info type.
327 { # Rule set for modifying a set of infoTypes to alter behavior under certain
328 # circumstances, depending on the specific details of the rules within the set.
329 "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
330 { # A single inspection rule to be applied to infoTypes, specified in
331 # `InspectionRuleSet`.
332 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
333 # proximity of hotwords.
334 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
335 # The total length of the window cannot exceed 1000 characters. Note that
336 # the finding itself will be included in the window, so that hotwords may
337 # be used to match substrings of the finding itself. For example, the
338 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
339 # adjusted upwards if the area code is known to be the local area code of
340 # a company office using the hotword regex "\(xxx\)", where "xxx"
341 # is the area code in question.
342 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]343 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]344 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]345 },
346 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
347 "pattern": "A String", # Pattern defining the regular expression. Its syntax
348 # (https://github.com/google/re2/wiki/Syntax) can be found under the
349 # google/re2 repository on GitHub.
350 "groupIndexes": [ # The index of the submatch to extract as findings. When not
351 # specified, the entire match is returned. No more than 3 may be included.
352 42,
353 ],
354 },
355 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
356 # part of a detection rule.
357 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
358 # levels. For example, if a finding would be `POSSIBLE` without the
359 # detection rule and `relative_likelihood` is 1, then it is upgraded to
360 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
361 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
362 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
363 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
364 # a final likelihood of `LIKELY`.
365 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
366 },
367 },
368 "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
369 # `InspectionRuleSet` are removed from results.
370 "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
371 "pattern": "A String", # Pattern defining the regular expression. Its syntax
372 # (https://github.com/google/re2/wiki/Syntax) can be found under the
373 # google/re2 repository on GitHub.
374 "groupIndexes": [ # The index of the submatch to extract as findings. When not
375 # specified, the entire match is returned. No more than 3 may be included.
376 42,
377 ],
378 },
379 "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.
380 "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or
381 # contained within with a finding of an infoType from this list. For
382 # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and
383 # `exclusion_rule` containing `exclude_info_types.info_types` with
384 # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap
385 # with EMAIL_ADDRESS finding.
386 # That leads to "555-222-2222@example.org" to generate only a single
387 # finding, namely email address.
388 { # Type of information detected by the API.
389 "name": "A String", # Name of the information type. Either a name of your choosing when
390 # creating a CustomInfoType, or one of the names listed
391 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
392 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]393 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]394 },
395 ],
396 },
397 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
398 # be used to match sensitive information specific to the data, such as a list
399 # of employee IDs or job titles.
400 #
401 # Dictionary words are case-insensitive and all characters other than letters
402 # and digits in the unicode [Basic Multilingual
403 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
404 # will be replaced with whitespace when scanning for matches, so the
405 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
406 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
407 # surrounding any match must be of a different type than the adjacent
408 # characters within the word, so letters must be next to non-letters and
409 # digits next to non-digits. For example, the dictionary word "jen" will
410 # match the first three letters of the text "jen123" but will return no
411 # matches for "jennifer".
412 #
413 # Dictionary words containing a large number of characters that are not
414 # letters or digits may result in unexpected findings because such characters
415 # are treated as whitespace. The
416 # [limits](https://cloud.google.com/dlp/limits) page contains details about
417 # the size limits of dictionaries. For dictionaries that do not fit within
418 # these constraints, consider using `LargeCustomDictionaryConfig` in the
419 # `StoredInfoType` API.
420 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
421 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
422 # at least one phrase and every phrase must contain at least 2 characters
423 # that are letters or digits. [required]
424 "A String",
425 ],
426 },
427 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
428 # is accepted.
429 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
430 # Example: gs://[BUCKET_NAME]/dictionary.txt
431 },
432 },
433 "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
434 },
435 },
436 ],
437 "infoTypes": [ # List of infoTypes this rule set is applied to.
438 { # Type of information detected by the API.
439 "name": "A String", # Name of the information type. Either a name of your choosing when
440 # creating a CustomInfoType, or one of the names listed
441 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
442 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]443 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]444 },
445 ],
446 },
447 ],
448 "contentOptions": [ # List of options defining data content to scan.
449 # If empty, text, images, and other content will be included.
450 "A String",
451 ],
452 "infoTypes": [ # Restricts what info_types to look for. The values must correspond to
453 # InfoType values returned by ListInfoTypes or listed at
454 # https://cloud.google.com/dlp/docs/infotypes-reference.
455 #
456 # When no InfoTypes or CustomInfoTypes are specified in a request, the
457 # system may automatically choose what detectors to run. By default this may
458 # be all types, but may change over time as detectors are updated.
459 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]460 # If you need precise control and predictability as to what detectors are
461 # run you should specify specific InfoTypes listed in the reference,
462 # otherwise a default list will be used, which may change over time.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]463 { # Type of information detected by the API.
464 "name": "A String", # Name of the information type. Either a name of your choosing when
465 # creating a CustomInfoType, or one of the names listed
466 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
467 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]468 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]469 },
470 ],
471 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]472 "createTime": "A String", # Output only. The creation timestamp of an inspectTemplate.
473 "name": "A String", # Output only. The template name.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]474 #
475 # The template will have one of the following formats:
476 # `projects/PROJECT_ID/inspectTemplates/TEMPLATE_ID` OR
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]477 # `organizations/ORGANIZATION_ID/inspectTemplates/TEMPLATE_ID`;
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]478 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]479 "jobConfig": { # Controls what and how to inspect for findings. # Inspect config.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]480 "storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]481 "cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]482 # bucket.
483 "bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger
484 # than this value then the rest of the bytes are omitted. Only one
485 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
486 "sampleMethod": "A String",
487 "fileSet": { # Set of files to scan. # The set of one or more files to scan.
488 "url": "A String", # The Cloud Storage url of the file(s) to scan, in the format
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]489 # `gs://&lt;bucket&gt;/&lt;path&gt;`. Trailing wildcard in the path is allowed.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]490 #
491 # If the url ends in a trailing slash, the bucket or directory represented
492 # by the url will be scanned non-recursively (content in sub-directories
493 # will not be scanned). This means that `gs://mybucket/` is equivalent to
494 # `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
495 # `gs://mybucket/directory/*`.
496 #
497 # Exactly one of `url` or `regex_file_set` must be set.
498 "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
499 # `regex_file_set` must be set.
500 # expressions are used to allow fine-grained control over which files in the
501 # bucket to include.
502 #
503 # Included files are those that match at least one item in `include_regex` and
504 # do not match any items in `exclude_regex`. Note that a file that matches
505 # items from both lists will _not_ be included. For a match to occur, the
506 # entire file path (i.e., everything in the url after the bucket name) must
507 # match the regular expression.
508 #
509 # For example, given the input `{bucket_name: "mybucket", include_regex:
510 # ["directory1/.*"], exclude_regex:
511 # ["directory1/excluded.*"]}`:
512 #
513 # * `gs://mybucket/directory1/myfile` will be included
514 # * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches
515 # across `/`)
516 # * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the
517 # full path doesn't match any items in `include_regex`)
518 # * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path
519 # matches an item in `exclude_regex`)
520 #
521 # If `include_regex` is left empty, it will match all files by default
522 # (this is equivalent to setting `include_regex: [".*"]`).
523 #
524 # Some other common use cases:
525 #
526 # * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all
527 # files in `mybucket` except for .pdf files
528 # * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will
529 # include all files directly under `gs://mybucket/directory/`, without matching
530 # across `/`
531 "excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in
532 # the bucket that match at least one of these regular expressions will be
533 # excluded from the scan.
534 #
535 # Regular expressions use RE2
536 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
537 # under the google/re2 repository on GitHub.
538 "A String",
539 ],
540 "bucketName": "A String", # The name of a Cloud Storage bucket. Required.
541 "includeRegex": [ # A list of regular expressions matching file paths to include. All files in
542 # the bucket that match at least one of these regular expressions will be
543 # included in the set of files, except for those that also match an item in
544 # `exclude_regex`. Leaving this field empty will match all files by default
545 # (this is equivalent to including `.*` in the list).
546 #
547 # Regular expressions use RE2
548 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
549 # under the google/re2 repository on GitHub.
550 "A String",
551 ],
552 },
553 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]554 "filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.
555 # Number of files scanned is rounded down. Must be between 0 and 100,
556 # inclusively. Both 0 and 100 means no limit. Defaults to 0.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]557 "bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The
558 # number of bytes scanned is rounded down. Must be between 0 and 100,
559 # inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one
560 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]561 "fileTypes": [ # List of file type groups to include in the scan.
562 # If empty, all files are scanned and available data format processors
563 # are applied. In addition, the binary content of the selected files
564 # is always scanned as well.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]565 # Images are scanned only as binary if the specified region
566 # does not support image inspection and no file_types were specified.
567 # Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]568 "A String",
569 ],
570 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]571 "datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
572 "partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always
573 # by project and namespace, however the namespace ID may be empty.
574 # A partition ID identifies a grouping of entities. The grouping is always
575 # by project and namespace, however the namespace ID may be empty.
576 #
577 # A partition ID contains several dimensions:
578 # project ID and namespace ID.
579 "projectId": "A String", # The ID of the project to which the entities belong.
580 "namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
581 },
582 "kind": { # A representation of a Datastore kind. # The kind to process.
583 "name": "A String", # The name of the kind.
584 },
585 },
586 "bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
587 "excludedFields": [ # References to fields excluded from scanning. This allows you to skip
588 # inspection of entire columns which you know have no findings.
589 { # General identifier of a data field in a storage service.
590 "name": "A String", # Name describing the field.
591 },
592 ],
593 "rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the
594 # rest of the rows are omitted. If not set, or if set to 0, all rows will be
595 # scanned. Only one of rows_limit and rows_limit_percent can be specified.
596 # Cannot be used in conjunction with TimespanConfig.
597 "sampleMethod": "A String",
598 "identifyingFields": [ # Table fields that may uniquely identify a row within the table. When
599 # `actions.saveFindings.outputConfig.table` is specified, the values of
600 # columns specified here are available in the output table under
601 # `location.content_locations.record_location.record_key.id_values`. Nested
602 # fields such as `person.birthdate.year` are allowed.
603 { # General identifier of a data field in a storage service.
604 "name": "A String", # Name describing the field.
605 },
606 ],
607 "rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows
608 # scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and
609 # 100 means no limit. Defaults to 0. Only one of rows_limit and
610 # rows_limit_percent can be specified. Cannot be used in conjunction with
611 # TimespanConfig.
612 "tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.
613 # identified by its project_id, dataset_id, and table_name. Within a query
614 # a table is often referenced with a string in the format of:
615 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
616 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
617 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
618 # If omitted, project ID is inferred from the API call.
619 "tableId": "A String", # Name of the table.
620 "datasetId": "A String", # Dataset ID of the table.
621 },
622 },
623 "timespanConfig": { # Configuration of the timespan of the items to include in scanning.
624 # Currently only supported when inspecting Google Cloud Storage and BigQuery.
625 "timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.
626 # Used for data sources like Datastore and BigQuery.
627 #
628 # For BigQuery:
629 # Required to filter out rows based on the given start and
630 # end times. If not specified and the table was modified between the given
631 # start and end times, the entire table will be scanned.
632 # The valid data types of the timestamp field are: `INTEGER`, `DATE`,
633 # `TIMESTAMP`, or `DATETIME` BigQuery column.
634 #
635 # For Datastore.
636 # Valid data types of the timestamp field are: `TIMESTAMP`.
637 # Datastore entity will be scanned if the timestamp property does not
638 # exist or its value is empty or invalid.
639 "name": "A String", # Name describing the field.
640 },
641 "endTime": "A String", # Exclude files or rows newer than this value.
642 # If set to zero, no upper time limit is applied.
643 "startTime": "A String", # Exclude files or rows older than this value.
644 "enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out
645 # a valid start_time to avoid scanning files that have not been modified
646 # since the last time the JobTrigger executed. This will be based on the
647 # time of the execution of the last run of the JobTrigger.
648 },
649 "hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.
650 # Early access feature is in a pre-release state and might change or have
651 # limited support. For more information, see
652 # https://cloud.google.com/products#product-launch-stages.
653 # of Google Cloud Platform.
654 "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings
655 # meaningful such as the columns that are primary keys.
656 "identifyingFields": [ # The columns that are the primary keys for table objects included in
657 # ContentItem. A copy of this cell's value will stored alongside alongside
658 # each finding so that the finding can be traced to the specific row it came
659 # from. No more than 3 may be provided.
660 { # General identifier of a data field in a storage service.
661 "name": "A String", # Name describing the field.
662 },
663 ],
664 },
665 "labels": { # To organize findings, these labels will be added to each finding.
666 #
667 # Label keys must be between 1 and 63 characters long and must conform
668 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
669 #
670 # Label values must be between 0 and 63 characters long and must conform
671 # to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.
672 #
673 # No more than 10 labels can be associated with a given finding.
674 #
675 # Examples:
676 # * `"environment" : "production"`
677 # * `"pipeline" : "etl"`
678 "a_key": "A String",
679 },
680 "requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their
681 # 'finding_labels' map. Request may contain others, but any missing one of
682 # these will be rejected.
683 #
684 # Label keys must be between 1 and 63 characters long and must conform
685 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
686 #
687 # No more than 10 keys can be required.
688 "A String",
689 ],
690 "description": "A String", # A short description of where the data is coming from. Will be stored once
691 # in the job. 256 max length.
692 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]693 },
694 "inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.
695 # When used with redactContent only info_types and min_likelihood are currently
696 # used.
697 "excludeInfoTypes": True or False, # When true, excludes type information of the findings.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]698 "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]699 "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
700 # When set within `InspectContentRequest`, the maximum returned is 2000
701 # regardless if this is set higher.
702 "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
703 { # Max findings configuration per infoType, per content item or long
704 # running DlpJob.
705 "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per
706 # info_type should be provided. If InfoTypeLimit does not have an
707 # info_type, the DLP API applies the limit against all info_types that
708 # are found but not specified in another InfoTypeLimit.
709 "name": "A String", # Name of the information type. Either a name of your choosing when
710 # creating a CustomInfoType, or one of the names listed
711 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
712 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]713 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]714 },
715 "maxFindings": 42, # Max findings limit for the given infoType.
716 },
717 ],
718 "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]719 # When set within `InspectJobConfig`,
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]720 # the maximum returned is 2000 regardless if this is set higher.
721 # When set within `InspectContentRequest`, this field is ignored.
722 },
723 "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
724 # POSSIBLE.
725 # See https://cloud.google.com/dlp/docs/likelihood to learn more.
726 "customInfoTypes": [ # CustomInfoTypes provided by the user. See
727 # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.
728 { # Custom information type provided by the user. Used to find domain-specific
729 # sensitive information configurable to the data in question.
730 "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
731 "pattern": "A String", # Pattern defining the regular expression. Its syntax
732 # (https://github.com/google/re2/wiki/Syntax) can be found under the
733 # google/re2 repository on GitHub.
734 "groupIndexes": [ # The index of the submatch to extract as findings. When not
735 # specified, the entire match is returned. No more than 3 may be included.
736 42,
737 ],
738 },
739 "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
740 # support reversing.
741 # such as
742 # [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).
743 # These types of transformations are
744 # those that perform pseudonymization, thereby producing a "surrogate" as
745 # output. This should be used in conjunction with a field on the
746 # transformation such as `surrogate_info_type`. This CustomInfoType does
747 # not support the use of `detection_rules`.
748 },
749 "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in
750 # infoType, when the name matches one of existing infoTypes and that infoType
751 # is specified in `InspectContent.info_types` field. Specifying the latter
752 # adds findings to the one detected by the system. If built-in info type is
753 # not specified in `InspectContent.info_types` list then the name is treated
754 # as a custom info type.
755 "name": "A String", # Name of the information type. Either a name of your choosing when
756 # creating a CustomInfoType, or one of the names listed
757 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
758 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]759 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]760 },
761 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
762 # be used to match sensitive information specific to the data, such as a list
763 # of employee IDs or job titles.
764 #
765 # Dictionary words are case-insensitive and all characters other than letters
766 # and digits in the unicode [Basic Multilingual
767 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
768 # will be replaced with whitespace when scanning for matches, so the
769 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
770 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
771 # surrounding any match must be of a different type than the adjacent
772 # characters within the word, so letters must be next to non-letters and
773 # digits next to non-digits. For example, the dictionary word "jen" will
774 # match the first three letters of the text "jen123" but will return no
775 # matches for "jennifer".
776 #
777 # Dictionary words containing a large number of characters that are not
778 # letters or digits may result in unexpected findings because such characters
779 # are treated as whitespace. The
780 # [limits](https://cloud.google.com/dlp/limits) page contains details about
781 # the size limits of dictionaries. For dictionaries that do not fit within
782 # these constraints, consider using `LargeCustomDictionaryConfig` in the
783 # `StoredInfoType` API.
784 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
785 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
786 # at least one phrase and every phrase must contain at least 2 characters
787 # that are letters or digits. [required]
788 "A String",
789 ],
790 },
791 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
792 # is accepted.
793 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
794 # Example: gs://[BUCKET_NAME]/dictionary.txt
795 },
796 },
797 "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
798 # `InspectDataSource`. Not currently supported in `InspectContent`.
799 "name": "A String", # Resource name of the requested `StoredInfoType`, for example
800 # `organizations/433245324/storedInfoTypes/432452342` or
801 # `projects/project-id/storedInfoTypes/432452342`.
802 "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
803 # inspection was created. Output-only field, populated by the system.
804 },
805 "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.
806 # Rules are applied in order that they are specified. Not supported for the
807 # `surrogate_type` CustomInfoType.
808 { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a
809 # `CustomInfoType` to alter behavior under certain circumstances, depending
810 # on the specific details of the rule. Not supported for the `surrogate_type`
811 # custom infoType.
812 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
813 # proximity of hotwords.
814 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
815 # The total length of the window cannot exceed 1000 characters. Note that
816 # the finding itself will be included in the window, so that hotwords may
817 # be used to match substrings of the finding itself. For example, the
818 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
819 # adjusted upwards if the area code is known to be the local area code of
820 # a company office using the hotword regex "\(xxx\)", where "xxx"
821 # is the area code in question.
822 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]823 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]824 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]825 },
826 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
827 "pattern": "A String", # Pattern defining the regular expression. Its syntax
828 # (https://github.com/google/re2/wiki/Syntax) can be found under the
829 # google/re2 repository on GitHub.
830 "groupIndexes": [ # The index of the submatch to extract as findings. When not
831 # specified, the entire match is returned. No more than 3 may be included.
832 42,
833 ],
834 },
835 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
836 # part of a detection rule.
837 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
838 # levels. For example, if a finding would be `POSSIBLE` without the
839 # detection rule and `relative_likelihood` is 1, then it is upgraded to
840 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
841 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
842 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
843 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
844 # a final likelihood of `LIKELY`.
845 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
846 },
847 },
848 },
849 ],
850 "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding
851 # to be returned. It still can be used for rules matching.
852 "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be
853 # altered by a detection rule if the finding meets the criteria specified by
854 # the rule. Defaults to `VERY_LIKELY` if not specified.
855 },
856 ],
857 "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
858 # included in the response; see Finding.quote.
859 "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.
860 # Exclusion rules, contained in the set are executed in the end, other
861 # rules are executed in the order they are specified for each info type.
862 { # Rule set for modifying a set of infoTypes to alter behavior under certain
863 # circumstances, depending on the specific details of the rules within the set.
864 "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
865 { # A single inspection rule to be applied to infoTypes, specified in
866 # `InspectionRuleSet`.
867 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
868 # proximity of hotwords.
869 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
870 # The total length of the window cannot exceed 1000 characters. Note that
871 # the finding itself will be included in the window, so that hotwords may
872 # be used to match substrings of the finding itself. For example, the
873 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
874 # adjusted upwards if the area code is known to be the local area code of
875 # a company office using the hotword regex "\(xxx\)", where "xxx"
876 # is the area code in question.
877 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]878 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]879 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]880 },
881 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
882 "pattern": "A String", # Pattern defining the regular expression. Its syntax
883 # (https://github.com/google/re2/wiki/Syntax) can be found under the
884 # google/re2 repository on GitHub.
885 "groupIndexes": [ # The index of the submatch to extract as findings. When not
886 # specified, the entire match is returned. No more than 3 may be included.
887 42,
888 ],
889 },
890 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
891 # part of a detection rule.
892 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
893 # levels. For example, if a finding would be `POSSIBLE` without the
894 # detection rule and `relative_likelihood` is 1, then it is upgraded to
895 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
896 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
897 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
898 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
899 # a final likelihood of `LIKELY`.
900 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
901 },
902 },
903 "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
904 # `InspectionRuleSet` are removed from results.
905 "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
906 "pattern": "A String", # Pattern defining the regular expression. Its syntax
907 # (https://github.com/google/re2/wiki/Syntax) can be found under the
908 # google/re2 repository on GitHub.
909 "groupIndexes": [ # The index of the submatch to extract as findings. When not
910 # specified, the entire match is returned. No more than 3 may be included.
911 42,
912 ],
913 },
914 "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.
915 "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or
916 # contained within with a finding of an infoType from this list. For
917 # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and
918 # `exclusion_rule` containing `exclude_info_types.info_types` with
919 # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap
920 # with EMAIL_ADDRESS finding.
921 # That leads to "555-222-2222@example.org" to generate only a single
922 # finding, namely email address.
923 { # Type of information detected by the API.
924 "name": "A String", # Name of the information type. Either a name of your choosing when
925 # creating a CustomInfoType, or one of the names listed
926 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
927 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]928 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]929 },
930 ],
931 },
932 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
933 # be used to match sensitive information specific to the data, such as a list
934 # of employee IDs or job titles.
935 #
936 # Dictionary words are case-insensitive and all characters other than letters
937 # and digits in the unicode [Basic Multilingual
938 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
939 # will be replaced with whitespace when scanning for matches, so the
940 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
941 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
942 # surrounding any match must be of a different type than the adjacent
943 # characters within the word, so letters must be next to non-letters and
944 # digits next to non-digits. For example, the dictionary word "jen" will
945 # match the first three letters of the text "jen123" but will return no
946 # matches for "jennifer".
947 #
948 # Dictionary words containing a large number of characters that are not
949 # letters or digits may result in unexpected findings because such characters
950 # are treated as whitespace. The
951 # [limits](https://cloud.google.com/dlp/limits) page contains details about
952 # the size limits of dictionaries. For dictionaries that do not fit within
953 # these constraints, consider using `LargeCustomDictionaryConfig` in the
954 # `StoredInfoType` API.
955 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
956 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
957 # at least one phrase and every phrase must contain at least 2 characters
958 # that are letters or digits. [required]
959 "A String",
960 ],
961 },
962 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
963 # is accepted.
964 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
965 # Example: gs://[BUCKET_NAME]/dictionary.txt
966 },
967 },
968 "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
969 },
970 },
971 ],
972 "infoTypes": [ # List of infoTypes this rule set is applied to.
973 { # Type of information detected by the API.
974 "name": "A String", # Name of the information type. Either a name of your choosing when
975 # creating a CustomInfoType, or one of the names listed
976 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
977 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]978 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]979 },
980 ],
981 },
982 ],
983 "contentOptions": [ # List of options defining data content to scan.
984 # If empty, text, images, and other content will be included.
985 "A String",
986 ],
987 "infoTypes": [ # Restricts what info_types to look for. The values must correspond to
988 # InfoType values returned by ListInfoTypes or listed at
989 # https://cloud.google.com/dlp/docs/infotypes-reference.
990 #
991 # When no InfoTypes or CustomInfoTypes are specified in a request, the
992 # system may automatically choose what detectors to run. By default this may
993 # be all types, but may change over time as detectors are updated.
994 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]995 # If you need precise control and predictability as to what detectors are
996 # run you should specify specific InfoTypes listed in the reference,
997 # otherwise a default list will be used, which may change over time.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]998 { # Type of information detected by the API.
999 "name": "A String", # Name of the information type. Either a name of your choosing when
1000 # creating a CustomInfoType, or one of the names listed
1001 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
1002 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1003 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1004 },
1005 ],
1006 },
1007 "inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.
1008 # `inspect_config` will be merged into the values persisted as part of the
1009 # template.
1010 "actions": [ # Actions to execute at the completion of the job.
1011 { # A task to execute on the completion of a job.
1012 # See https://cloud.google.com/dlp/docs/concepts-actions to learn more.
1013 "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
1014 # OutputStorageConfig. Only a single instance of this action can be
1015 # specified.
1016 # Compatible with: Inspect, Risk
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1017 "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1018 "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
1019 # dataset. If table_id is not set a new one will be generated
1020 # for you with the following format:
1021 # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for
1022 # generating the date details.
1023 #
1024 # For Inspect, each column in an existing output table must have the same
1025 # name, type, and mode of a field in the `Finding` object.
1026 #
1027 # For Risk, an existing output table should be the output of a previous
1028 # Risk analysis job run on the same source table, with the same privacy
1029 # metric and quasi-identifiers. Risk jobs that analyze the same table but
1030 # compute a different privacy metric, or use different sets of
1031 # quasi-identifiers, cannot store their results in the same table.
1032 # identified by its project_id, dataset_id, and table_name. Within a query
1033 # a table is often referenced with a string in the format of:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1034 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
1035 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1036 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
1037 # If omitted, project ID is inferred from the API call.
1038 "tableId": "A String", # Name of the table.
1039 "datasetId": "A String", # Dataset ID of the table.
1040 },
1041 "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only
1042 # used for Inspect and must be unspecified for Risk jobs. Columns are derived
1043 # from the `Finding` object. If appending to an existing table, any columns
1044 # from the predefined schema that are missing will be added. No columns in
1045 # the existing table will be deleted.
1046 #
1047 # If unspecified, then all available columns will be used for a new table or
1048 # an (existing) table with no schema, and no changes will be made to an
1049 # existing table that has a schema.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1050 # Only for use with external storage.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1051 },
1052 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1053 "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1054 # completion/failure.
1055 # completion/failure.
1056 },
1057 "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
1058 # Command Center (CSCC Alpha).
1059 # This action is only available for projects which are parts of
1060 # an organization and whitelisted for the alpha Cloud Security Command
1061 # Center.
1062 # The action will publish count of finding instances and their info types.
1063 # The summary of findings will be persisted in CSCC and are governed by CSCC
1064 # service-specific policy, see https://cloud.google.com/terms/service-terms
1065 # Only a single instance of this action can be specified.
1066 # Compatible with: Inspect
1067 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1068 "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.
1069 # will publish a metric to stack driver on each infotype requested and
1070 # how many findings were found for it. CustomDetectors will be bucketed
1071 # as 'Custom' under the Stackdriver label 'info_type'.
1072 },
1073 "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.
1074 # results of the DlpJob will be applied to the entry for the resource scanned
1075 # in Cloud Data Catalog. Any labels previously written by another DlpJob will
1076 # be deleted. InfoType naming patterns are strictly enforced when using this
1077 # feature. Note that the findings will be persisted in Cloud Data Catalog
1078 # storage and are governed by Data Catalog service-specific policy, see
1079 # https://cloud.google.com/terms/service-terms
1080 # Only a single instance of this action can be specified and only allowed if
1081 # all resources being scanned are BigQuery tables.
1082 # Compatible with: Inspect
1083 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1084 "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
1085 # message contains a single field, `DlpJobName`, which is equal to the
1086 # finished job's
1087 # [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
1088 # Compatible with: Inspect, Risk
1089 "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given
1090 # publishing access rights to the DLP API service account executing
1091 # the long running DlpJob sending the notifications.
1092 # Format is projects/{project}/topics/{topic}.
1093 },
1094 },
1095 ],
1096 },
1097 },
1098 "result": { # All result fields mentioned below are updated while the job is processing. # A summary of the outcome of this inspect job.
1099 "infoTypeStats": [ # Statistics of how many instances of each info type were found during
1100 # inspect job.
1101 { # Statistics regarding a specific InfoType.
1102 "count": "A String", # Number of findings for this infoType.
1103 "infoType": { # Type of information detected by the API. # The type of finding this stat is for.
1104 "name": "A String", # Name of the information type. Either a name of your choosing when
1105 # creating a CustomInfoType, or one of the names listed
1106 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
1107 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1108 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1109 },
1110 },
1111 ],
1112 "totalEstimatedBytes": "A String", # Estimate of the number of bytes to process.
1113 "processedBytes": "A String", # Total size in bytes that were processed.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1114 "hybridStats": { # Statistics related to processing hybrid inspect requests. # Statistics related to the processing of hybrid inspect.
1115 # Early access feature is in a pre-release state and might change or have
1116 # limited support. For more information, see
1117 # https://cloud.google.com/products#product-launch-stages.
1118 "abortedCount": "A String", # The number of hybrid inspection requests aborted because the job ran
1119 # out of quota or was ended before they could be processed.
1120 "pendingCount": "A String", # The number of hybrid requests currently being processed. Only populated
1121 # when called via method `getDlpJob`.
1122 # A burst of traffic may cause hybrid inspect requests to be enqueued.
1123 # Processing will take place as quickly as possible, but resource limitations
1124 # may impact how long a request is enqueued for.
1125 "processedCount": "A String", # The number of hybrid inspection requests processed within this job.
1126 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1127 },
1128 },
1129 "riskDetails": { # Result of a risk analysis operation request. # Results from analyzing risk of a data source.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1130 "numericalStatsResult": { # Result of the numerical stats computation. # Numerical stats result
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1131 "quantileValues": [ # List of 99 values that partition the set of field values into 100 equal
1132 # sized buckets.
1133 { # Set of primitive values supported by the system.
1134 # Note that for the purposes of inspection or transformation, the number
1135 # of bytes considered to comprise a 'Value' is based on its representation
1136 # as a UTF-8 encoded string. For example, if 'integer_value' is set to
1137 # 123456789, the number of bytes would be counted as 9, even though an
1138 # int64 only holds up to 8 bytes of data.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1139 "floatValue": 3.14, # float
1140 "timestampValue": "A String", # timestamp
1141 "dayOfWeekValue": "A String", # day of week
1142 "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1143 # or are specified elsewhere. An API may choose to allow leap seconds. Related
1144 # types are google.type.Date and `google.protobuf.Timestamp`.
1145 "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
1146 # to allow the value "24:00:00" for scenarios like business closing time.
1147 "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
1148 "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
1149 # allow the value 60 if it allows leap-seconds.
1150 "minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
1151 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1152 "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1153 # and time zone are either specified elsewhere or are not significant. The date
1154 # is relative to the Proleptic Gregorian Calendar. This can represent:
1155 #
1156 # * A full date, with non-zero year, month and day values
1157 # * A month and day value, with a zero year, e.g. an anniversary
1158 # * A year on its own, with zero month and day values
1159 # * A year and month value, with a zero day, e.g. a credit card expiration date
1160 #
1161 # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1162 "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
1163 # month and day.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1164 "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
1165 # if specifying a year by itself or a year and month where the day is not
1166 # significant.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1167 "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
1168 # a year.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1169 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1170 "stringValue": "A String", # string
1171 "booleanValue": True or False, # boolean
1172 "integerValue": "A String", # integer
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1173 },
1174 ],
1175 "maxValue": { # Set of primitive values supported by the system. # Maximum value appearing in the column.
1176 # Note that for the purposes of inspection or transformation, the number
1177 # of bytes considered to comprise a 'Value' is based on its representation
1178 # as a UTF-8 encoded string. For example, if 'integer_value' is set to
1179 # 123456789, the number of bytes would be counted as 9, even though an
1180 # int64 only holds up to 8 bytes of data.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1181 "floatValue": 3.14, # float
1182 "timestampValue": "A String", # timestamp
1183 "dayOfWeekValue": "A String", # day of week
1184 "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1185 # or are specified elsewhere. An API may choose to allow leap seconds. Related
1186 # types are google.type.Date and `google.protobuf.Timestamp`.
1187 "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
1188 # to allow the value "24:00:00" for scenarios like business closing time.
1189 "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
1190 "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
1191 # allow the value 60 if it allows leap-seconds.
1192 "minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
1193 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1194 "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1195 # and time zone are either specified elsewhere or are not significant. The date
1196 # is relative to the Proleptic Gregorian Calendar. This can represent:
1197 #
1198 # * A full date, with non-zero year, month and day values
1199 # * A month and day value, with a zero year, e.g. an anniversary
1200 # * A year on its own, with zero month and day values
1201 # * A year and month value, with a zero day, e.g. a credit card expiration date
1202 #
1203 # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1204 "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
1205 # month and day.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1206 "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
1207 # if specifying a year by itself or a year and month where the day is not
1208 # significant.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1209 "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
1210 # a year.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1211 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1212 "stringValue": "A String", # string
1213 "booleanValue": True or False, # boolean
1214 "integerValue": "A String", # integer
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1215 },
1216 "minValue": { # Set of primitive values supported by the system. # Minimum value appearing in the column.
1217 # Note that for the purposes of inspection or transformation, the number
1218 # of bytes considered to comprise a 'Value' is based on its representation
1219 # as a UTF-8 encoded string. For example, if 'integer_value' is set to
1220 # 123456789, the number of bytes would be counted as 9, even though an
1221 # int64 only holds up to 8 bytes of data.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1222 "floatValue": 3.14, # float
1223 "timestampValue": "A String", # timestamp
1224 "dayOfWeekValue": "A String", # day of week
1225 "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1226 # or are specified elsewhere. An API may choose to allow leap seconds. Related
1227 # types are google.type.Date and `google.protobuf.Timestamp`.
1228 "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
1229 # to allow the value "24:00:00" for scenarios like business closing time.
1230 "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
1231 "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
1232 # allow the value 60 if it allows leap-seconds.
1233 "minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
1234 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1235 "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1236 # and time zone are either specified elsewhere or are not significant. The date
1237 # is relative to the Proleptic Gregorian Calendar. This can represent:
1238 #
1239 # * A full date, with non-zero year, month and day values
1240 # * A month and day value, with a zero year, e.g. an anniversary
1241 # * A year on its own, with zero month and day values
1242 # * A year and month value, with a zero day, e.g. a credit card expiration date
1243 #
1244 # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1245 "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
1246 # month and day.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1247 "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
1248 # if specifying a year by itself or a year and month where the day is not
1249 # significant.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1250 "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
1251 # a year.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1252 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1253 "stringValue": "A String", # string
1254 "booleanValue": True or False, # boolean
1255 "integerValue": "A String", # integer
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1256 },
1257 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1258 "kMapEstimationResult": { # Result of the reidentifiability analysis. Note that these results are an # K-map result
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1259 # estimation, not exact values.
1260 "kMapEstimationHistogram": [ # The intervals [min_anonymity, max_anonymity] do not overlap. If a value
1261 # doesn't correspond to any such interval, the associated frequency is
1262 # zero. For example, the following records:
1263 # {min_anonymity: 1, max_anonymity: 1, frequency: 17}
1264 # {min_anonymity: 2, max_anonymity: 3, frequency: 42}
1265 # {min_anonymity: 5, max_anonymity: 10, frequency: 99}
1266 # mean that there are no record with an estimated anonymity of 4, 5, or
1267 # larger than 10.
1268 { # A KMapEstimationHistogramBucket message with the following values:
1269 # min_anonymity: 3
1270 # max_anonymity: 5
1271 # frequency: 42
1272 # means that there are 42 records whose quasi-identifier values correspond
1273 # to 3, 4 or 5 people in the overlying population. An important particular
1274 # case is when min_anonymity = max_anonymity = 1: the frequency field then
1275 # corresponds to the number of uniquely identifiable records.
1276 "bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total
1277 # number of classes returned per bucket is capped at 20.
1278 { # A tuple of values for the quasi-identifier columns.
1279 "estimatedAnonymity": "A String", # The estimated anonymity for these quasi-identifier values.
1280 "quasiIdsValues": [ # The quasi-identifier values.
1281 { # Set of primitive values supported by the system.
1282 # Note that for the purposes of inspection or transformation, the number
1283 # of bytes considered to comprise a 'Value' is based on its representation
1284 # as a UTF-8 encoded string. For example, if 'integer_value' is set to
1285 # 123456789, the number of bytes would be counted as 9, even though an
1286 # int64 only holds up to 8 bytes of data.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1287 "floatValue": 3.14, # float
1288 "timestampValue": "A String", # timestamp
1289 "dayOfWeekValue": "A String", # day of week
1290 "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1291 # or are specified elsewhere. An API may choose to allow leap seconds. Related
1292 # types are google.type.Date and `google.protobuf.Timestamp`.
1293 "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
1294 # to allow the value "24:00:00" for scenarios like business closing time.
1295 "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
1296 "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
1297 # allow the value 60 if it allows leap-seconds.
1298 "minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
1299 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1300 "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1301 # and time zone are either specified elsewhere or are not significant. The date
1302 # is relative to the Proleptic Gregorian Calendar. This can represent:
1303 #
1304 # * A full date, with non-zero year, month and day values
1305 # * A month and day value, with a zero year, e.g. an anniversary
1306 # * A year on its own, with zero month and day values
1307 # * A year and month value, with a zero day, e.g. a credit card expiration date
1308 #
1309 # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1310 "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
1311 # month and day.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1312 "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
1313 # if specifying a year by itself or a year and month where the day is not
1314 # significant.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1315 "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
1316 # a year.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1317 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1318 "stringValue": "A String", # string
1319 "booleanValue": True or False, # boolean
1320 "integerValue": "A String", # integer
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1321 },
1322 ],
1323 },
1324 ],
1325 "minAnonymity": "A String", # Always positive.
1326 "bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
1327 "maxAnonymity": "A String", # Always greater than or equal to min_anonymity.
1328 "bucketSize": "A String", # Number of records within these anonymity bounds.
1329 },
1330 ],
1331 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1332 "kAnonymityResult": { # Result of the k-anonymity computation. # K-anonymity result
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1333 "equivalenceClassHistogramBuckets": [ # Histogram of k-anonymity equivalence classes.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1334 { # Histogram of k-anonymity equivalence classes.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1335 "bucketValues": [ # Sample of equivalence classes in this bucket. The total number of
1336 # classes returned per bucket is capped at 20.
1337 { # The set of columns' values that share the same ldiversity value
1338 "quasiIdsValues": [ # Set of values defining the equivalence class. One value per
1339 # quasi-identifier column in the original KAnonymity metric message.
1340 # The order is always the same as the original request.
1341 { # Set of primitive values supported by the system.
1342 # Note that for the purposes of inspection or transformation, the number
1343 # of bytes considered to comprise a 'Value' is based on its representation
1344 # as a UTF-8 encoded string. For example, if 'integer_value' is set to
1345 # 123456789, the number of bytes would be counted as 9, even though an
1346 # int64 only holds up to 8 bytes of data.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1347 "floatValue": 3.14, # float
1348 "timestampValue": "A String", # timestamp
1349 "dayOfWeekValue": "A String", # day of week
1350 "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1351 # or are specified elsewhere. An API may choose to allow leap seconds. Related
1352 # types are google.type.Date and `google.protobuf.Timestamp`.
1353 "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
1354 # to allow the value "24:00:00" for scenarios like business closing time.
1355 "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
1356 "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
1357 # allow the value 60 if it allows leap-seconds.
1358 "minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
1359 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1360 "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1361 # and time zone are either specified elsewhere or are not significant. The date
1362 # is relative to the Proleptic Gregorian Calendar. This can represent:
1363 #
1364 # * A full date, with non-zero year, month and day values
1365 # * A month and day value, with a zero year, e.g. an anniversary
1366 # * A year on its own, with zero month and day values
1367 # * A year and month value, with a zero day, e.g. a credit card expiration date
1368 #
1369 # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1370 "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
1371 # month and day.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1372 "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
1373 # if specifying a year by itself or a year and month where the day is not
1374 # significant.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1375 "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
1376 # a year.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1377 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1378 "stringValue": "A String", # string
1379 "booleanValue": True or False, # boolean
1380 "integerValue": "A String", # integer
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1381 },
1382 ],
1383 "equivalenceClassSize": "A String", # Size of the equivalence class, for example number of rows with the
1384 # above set of values.
1385 },
1386 ],
1387 "bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
1388 "equivalenceClassSizeLowerBound": "A String", # Lower bound on the size of the equivalence classes in this bucket.
1389 "equivalenceClassSizeUpperBound": "A String", # Upper bound on the size of the equivalence classes in this bucket.
1390 "bucketSize": "A String", # Total number of equivalence classes in this bucket.
1391 },
1392 ],
1393 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1394 "lDiversityResult": { # Result of the l-diversity computation. # L-divesity result
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1395 "sensitiveValueFrequencyHistogramBuckets": [ # Histogram of l-diversity equivalence class sensitive value frequencies.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1396 { # Histogram of l-diversity equivalence class sensitive value frequencies.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1397 "bucketValues": [ # Sample of equivalence classes in this bucket. The total number of
1398 # classes returned per bucket is capped at 20.
1399 { # The set of columns' values that share the same ldiversity value.
1400 "numDistinctSensitiveValues": "A String", # Number of distinct sensitive values in this equivalence class.
1401 "quasiIdsValues": [ # Quasi-identifier values defining the k-anonymity equivalence
1402 # class. The order is always the same as the original request.
1403 { # Set of primitive values supported by the system.
1404 # Note that for the purposes of inspection or transformation, the number
1405 # of bytes considered to comprise a 'Value' is based on its representation
1406 # as a UTF-8 encoded string. For example, if 'integer_value' is set to
1407 # 123456789, the number of bytes would be counted as 9, even though an
1408 # int64 only holds up to 8 bytes of data.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1409 "floatValue": 3.14, # float
1410 "timestampValue": "A String", # timestamp
1411 "dayOfWeekValue": "A String", # day of week
1412 "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1413 # or are specified elsewhere. An API may choose to allow leap seconds. Related
1414 # types are google.type.Date and `google.protobuf.Timestamp`.
1415 "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
1416 # to allow the value "24:00:00" for scenarios like business closing time.
1417 "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
1418 "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
1419 # allow the value 60 if it allows leap-seconds.
1420 "minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
1421 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1422 "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1423 # and time zone are either specified elsewhere or are not significant. The date
1424 # is relative to the Proleptic Gregorian Calendar. This can represent:
1425 #
1426 # * A full date, with non-zero year, month and day values
1427 # * A month and day value, with a zero year, e.g. an anniversary
1428 # * A year on its own, with zero month and day values
1429 # * A year and month value, with a zero day, e.g. a credit card expiration date
1430 #
1431 # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1432 "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
1433 # month and day.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1434 "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
1435 # if specifying a year by itself or a year and month where the day is not
1436 # significant.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1437 "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
1438 # a year.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1439 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1440 "stringValue": "A String", # string
1441 "booleanValue": True or False, # boolean
1442 "integerValue": "A String", # integer
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1443 },
1444 ],
1445 "topSensitiveValues": [ # Estimated frequencies of top sensitive values.
1446 { # A value of a field, including its frequency.
1447 "count": "A String", # How many times the value is contained in the field.
1448 "value": { # Set of primitive values supported by the system. # A value contained in the field in question.
1449 # Note that for the purposes of inspection or transformation, the number
1450 # of bytes considered to comprise a 'Value' is based on its representation
1451 # as a UTF-8 encoded string. For example, if 'integer_value' is set to
1452 # 123456789, the number of bytes would be counted as 9, even though an
1453 # int64 only holds up to 8 bytes of data.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1454 "floatValue": 3.14, # float
1455 "timestampValue": "A String", # timestamp
1456 "dayOfWeekValue": "A String", # day of week
1457 "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1458 # or are specified elsewhere. An API may choose to allow leap seconds. Related
1459 # types are google.type.Date and `google.protobuf.Timestamp`.
1460 "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
1461 # to allow the value "24:00:00" for scenarios like business closing time.
1462 "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
1463 "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
1464 # allow the value 60 if it allows leap-seconds.
1465 "minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
1466 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1467 "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1468 # and time zone are either specified elsewhere or are not significant. The date
1469 # is relative to the Proleptic Gregorian Calendar. This can represent:
1470 #
1471 # * A full date, with non-zero year, month and day values
1472 # * A month and day value, with a zero year, e.g. an anniversary
1473 # * A year on its own, with zero month and day values
1474 # * A year and month value, with a zero day, e.g. a credit card expiration date
1475 #
1476 # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1477 "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
1478 # month and day.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1479 "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
1480 # if specifying a year by itself or a year and month where the day is not
1481 # significant.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1482 "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
1483 # a year.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1484 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1485 "stringValue": "A String", # string
1486 "booleanValue": True or False, # boolean
1487 "integerValue": "A String", # integer
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1488 },
1489 },
1490 ],
1491 "equivalenceClassSize": "A String", # Size of the k-anonymity equivalence class.
1492 },
1493 ],
1494 "bucketValueCount": "A String", # Total number of distinct equivalence classes in this bucket.
1495 "bucketSize": "A String", # Total number of equivalence classes in this bucket.
1496 "sensitiveValueFrequencyUpperBound": "A String", # Upper bound on the sensitive value frequencies of the equivalence
1497 # classes in this bucket.
1498 "sensitiveValueFrequencyLowerBound": "A String", # Lower bound on the sensitive value frequencies of the equivalence
1499 # classes in this bucket.
1500 },
1501 ],
1502 },
1503 "requestedPrivacyMetric": { # Privacy metric to compute for reidentification risk analysis. # Privacy metric to compute.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1504 "numericalStatsConfig": { # Compute numerical stats over an individual column, including # Numerical stats
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1505 # min, max, and quantiles.
1506 "field": { # General identifier of a data field in a storage service. # Field to compute numerical stats on. Supported types are
1507 # integer, float, date, datetime, timestamp, time.
1508 "name": "A String", # Name describing the field.
1509 },
1510 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1511 "kMapEstimationConfig": { # Reidentifiability metric. This corresponds to a risk model similar to what # k-map
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1512 # is called "journalist risk" in the literature, except the attack dataset is
1513 # statistically modeled instead of being perfectly known. This can be done
1514 # using publicly available data (like the US Census), or using a custom
1515 # statistical model (indicated as one or several BigQuery tables), or by
1516 # extrapolating from the distribution of values in the input dataset.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1517 "regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1518 # Set if no column is tagged with a region-specific InfoType (like
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1519 # US_ZIP_5) or a region code.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1520 "quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two columns can have the
1521 # same tag.
1522 { # A column with a semantic tag attached.
1523 "field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1524 "name": "A String", # Name describing the field.
1525 },
1526 "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must
1527 # indicate an auxiliary table that contains statistical information on
1528 # the possible values of this column (below).
1529 "infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public
1530 # dataset as a statistical model of population, if available. We
1531 # currently support US ZIP codes, region codes, ages and genders.
1532 # To programmatically obtain the list of supported InfoTypes, use
1533 # ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
1534 "name": "A String", # Name of the information type. Either a name of your choosing when
1535 # creating a CustomInfoType, or one of the names listed
1536 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
1537 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1538 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1539 },
1540 "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
1541 # the distribution of values in the input data
1542 # empty messages in your APIs. A typical example is to use it as the request
1543 # or the response type of an API method. For instance:
1544 #
1545 # service Foo {
1546 # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);
1547 # }
1548 #
1549 # The JSON representation for `Empty` is empty JSON object `{}`.
1550 },
1551 },
1552 ],
1553 "auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag
1554 # used to tag a quasi-identifiers column must appear in exactly one column
1555 # of one auxiliary table.
1556 { # An auxiliary table contains statistical information on the relative
1557 # frequency of different quasi-identifiers values. It has one or several
1558 # quasi-identifiers columns, and one column that indicates the relative
1559 # frequency of each quasi-identifier tuple.
1560 # If a tuple is present in the data but not in the auxiliary table, the
1561 # corresponding relative frequency is assumed to be zero (and thus, the
1562 # tuple is highly reidentifiable).
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1563 "table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1564 # identified by its project_id, dataset_id, and table_name. Within a query
1565 # a table is often referenced with a string in the format of:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1566 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
1567 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1568 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
1569 # If omitted, project ID is inferred from the API call.
1570 "tableId": "A String", # Name of the table.
1571 "datasetId": "A String", # Dataset ID of the table.
1572 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1573 "quasiIds": [ # Required. Quasi-identifier columns.
1574 { # A quasi-identifier column has a custom_tag, used to know which column
1575 # in the data corresponds to which column in the statistical model.
1576 "field": { # General identifier of a data field in a storage service. # Identifies the column.
1577 "name": "A String", # Name describing the field.
1578 },
1579 "customTag": "A String", # A auxiliary field.
1580 },
1581 ],
1582 "relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number
1583 # between 0 and 1 (inclusive). Null values are assumed to be zero.
1584 "name": "A String", # Name describing the field.
1585 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1586 },
1587 ],
1588 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1589 "lDiversityConfig": { # l-diversity metric, used for analysis of reidentification risk. # l-diversity
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1590 "sensitiveAttribute": { # General identifier of a data field in a storage service. # Sensitive field for computing the l-value.
1591 "name": "A String", # Name describing the field.
1592 },
1593 "quasiIds": [ # Set of quasi-identifiers indicating how equivalence classes are
1594 # defined for the l-diversity computation. When multiple fields are
1595 # specified, they are considered a single composite key.
1596 { # General identifier of a data field in a storage service.
1597 "name": "A String", # Name describing the field.
1598 },
1599 ],
1600 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1601 "kAnonymityConfig": { # k-anonymity metric, used for analysis of reidentification risk. # K-anonymity
1602 "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
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1603 # single individual. If the same entity_id is associated to multiple
1604 # quasi-identifier tuples over distinct rows, we consider the entire
1605 # collection of tuples as the composite quasi-identifier. This collection
1606 # is a multiset: the order in which the different tuples appear in the
1607 # dataset is ignored, but their frequency is taken into account.
1608 #
1609 # Important note: a maximum of 1000 rows can be associated to a single
1610 # entity ID. If more rows are associated with the same entity ID, some
1611 # might be ignored.
1612 # single person. For example, in medical records the `EntityId` might be a
1613 # patient identifier, or for financial records it might be an account
1614 # identifier. This message is used when generalizations or analysis must take
1615 # into account that multiple rows correspond to the same entity.
1616 "field": { # General identifier of a data field in a storage service. # Composite key indicating which field contains the entity identifier.
1617 "name": "A String", # Name describing the field.
1618 },
1619 },
1620 "quasiIds": [ # Set of fields to compute k-anonymity over. When multiple fields are
1621 # specified, they are considered a single composite key. Structs and
1622 # repeated data types are not supported; however, nested fields are
1623 # supported so long as they are not structs themselves or nested within
1624 # a repeated field.
1625 { # General identifier of a data field in a storage service.
1626 "name": "A String", # Name describing the field.
1627 },
1628 ],
1629 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1630 "categoricalStatsConfig": { # Compute numerical stats over an individual column, including # Categorical stats
1631 # number of distinct values and value count distribution.
1632 "field": { # General identifier of a data field in a storage service. # Field to compute categorical stats on. All column types are
1633 # supported except for arrays and structs. However, it may be more
1634 # informative to use NumericalStats when the field type is supported,
1635 # depending on the data.
1636 "name": "A String", # Name describing the field.
1637 },
1638 },
1639 "deltaPresenceEstimationConfig": { # δ-presence metric, used to estimate how likely it is for an attacker to # delta-presence
1640 # figure out that one given individual appears in a de-identified dataset.
1641 # Similarly to the k-map metric, we cannot compute δ-presence exactly without
1642 # knowing the attack dataset, so we use a statistical model instead.
1643 "regionCode": "A String", # ISO 3166-1 alpha-2 region code to use in the statistical modeling.
1644 # Set if no column is tagged with a region-specific InfoType (like
1645 # US_ZIP_5) or a region code.
1646 "quasiIds": [ # Required. Fields considered to be quasi-identifiers. No two fields can have the
1647 # same tag.
1648 { # A column with a semantic tag attached.
1649 "field": { # General identifier of a data field in a storage service. # Required. Identifies the column.
1650 "name": "A String", # Name describing the field.
1651 },
1652 "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must
1653 # indicate an auxiliary table that contains statistical information on
1654 # the possible values of this column (below).
1655 "infoType": { # Type of information detected by the API. # A column can be tagged with a InfoType to use the relevant public
1656 # dataset as a statistical model of population, if available. We
1657 # currently support US ZIP codes, region codes, ages and genders.
1658 # To programmatically obtain the list of supported InfoTypes, use
1659 # ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
1660 "name": "A String", # Name of the information type. Either a name of your choosing when
1661 # creating a CustomInfoType, or one of the names listed
1662 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
1663 # a built-in type. InfoType names should conform to the pattern
1664 # `[a-zA-Z0-9_]{1,64}`.
1665 },
1666 "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
1667 # the distribution of values in the input data
1668 # empty messages in your APIs. A typical example is to use it as the request
1669 # or the response type of an API method. For instance:
1670 #
1671 # service Foo {
1672 # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);
1673 # }
1674 #
1675 # The JSON representation for `Empty` is empty JSON object `{}`.
1676 },
1677 },
1678 ],
1679 "auxiliaryTables": [ # Several auxiliary tables can be used in the analysis. Each custom_tag
1680 # used to tag a quasi-identifiers field must appear in exactly one
1681 # field of one auxiliary table.
1682 { # An auxiliary table containing statistical information on the relative
1683 # frequency of different quasi-identifiers values. It has one or several
1684 # quasi-identifiers columns, and one column that indicates the relative
1685 # frequency of each quasi-identifier tuple.
1686 # If a tuple is present in the data but not in the auxiliary table, the
1687 # corresponding relative frequency is assumed to be zero (and thus, the
1688 # tuple is highly reidentifiable).
1689 "relativeFrequency": { # General identifier of a data field in a storage service. # Required. The relative frequency column must contain a floating-point number
1690 # between 0 and 1 (inclusive). Null values are assumed to be zero.
1691 "name": "A String", # Name describing the field.
1692 },
1693 "quasiIds": [ # Required. Quasi-identifier columns.
1694 { # A quasi-identifier column has a custom_tag, used to know which column
1695 # in the data corresponds to which column in the statistical model.
1696 "field": { # General identifier of a data field in a storage service. # Identifies the column.
1697 "name": "A String", # Name describing the field.
1698 },
1699 "customTag": "A String", # A column can be tagged with a custom tag. In this case, the user must
1700 # indicate an auxiliary table that contains statistical information on
1701 # the possible values of this column (below).
1702 },
1703 ],
1704 "table": { # Message defining the location of a BigQuery table. A table is uniquely # Required. Auxiliary table location.
1705 # identified by its project_id, dataset_id, and table_name. Within a query
1706 # a table is often referenced with a string in the format of:
1707 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
1708 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
1709 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
1710 # If omitted, project ID is inferred from the API call.
1711 "tableId": "A String", # Name of the table.
1712 "datasetId": "A String", # Dataset ID of the table.
1713 },
1714 },
1715 ],
1716 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1717 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1718 "categoricalStatsResult": { # Result of the categorical stats computation. # Categorical stats result
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1719 "valueFrequencyHistogramBuckets": [ # Histogram of value frequencies in the column.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1720 { # Histogram of value frequencies in the column.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1721 "bucketValues": [ # Sample of value frequencies in this bucket. The total number of
1722 # values returned per bucket is capped at 20.
1723 { # A value of a field, including its frequency.
1724 "count": "A String", # How many times the value is contained in the field.
1725 "value": { # Set of primitive values supported by the system. # A value contained in the field in question.
1726 # Note that for the purposes of inspection or transformation, the number
1727 # of bytes considered to comprise a 'Value' is based on its representation
1728 # as a UTF-8 encoded string. For example, if 'integer_value' is set to
1729 # 123456789, the number of bytes would be counted as 9, even though an
1730 # int64 only holds up to 8 bytes of data.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1731 "floatValue": 3.14, # float
1732 "timestampValue": "A String", # timestamp
1733 "dayOfWeekValue": "A String", # day of week
1734 "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1735 # or are specified elsewhere. An API may choose to allow leap seconds. Related
1736 # types are google.type.Date and `google.protobuf.Timestamp`.
1737 "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
1738 # to allow the value "24:00:00" for scenarios like business closing time.
1739 "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
1740 "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
1741 # allow the value 60 if it allows leap-seconds.
1742 "minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
1743 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1744 "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1745 # and time zone are either specified elsewhere or are not significant. The date
1746 # is relative to the Proleptic Gregorian Calendar. This can represent:
1747 #
1748 # * A full date, with non-zero year, month and day values
1749 # * A month and day value, with a zero year, e.g. an anniversary
1750 # * A year on its own, with zero month and day values
1751 # * A year and month value, with a zero day, e.g. a credit card expiration date
1752 #
1753 # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1754 "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
1755 # month and day.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1756 "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
1757 # if specifying a year by itself or a year and month where the day is not
1758 # significant.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1759 "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
1760 # a year.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1761 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1762 "stringValue": "A String", # string
1763 "booleanValue": True or False, # boolean
1764 "integerValue": "A String", # integer
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1765 },
1766 },
1767 ],
1768 "bucketValueCount": "A String", # Total number of distinct values in this bucket.
1769 "valueFrequencyUpperBound": "A String", # Upper bound on the value frequency of the values in this bucket.
1770 "valueFrequencyLowerBound": "A String", # Lower bound on the value frequency of the values in this bucket.
1771 "bucketSize": "A String", # Total number of values in this bucket.
1772 },
1773 ],
1774 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1775 "deltaPresenceEstimationResult": { # Result of the δ-presence computation. Note that these results are an # Delta-presence result
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1776 # estimation, not exact values.
1777 "deltaPresenceEstimationHistogram": [ # The intervals [min_probability, max_probability) do not overlap. If a
1778 # value doesn't correspond to any such interval, the associated frequency
1779 # is zero. For example, the following records:
1780 # {min_probability: 0, max_probability: 0.1, frequency: 17}
1781 # {min_probability: 0.2, max_probability: 0.3, frequency: 42}
1782 # {min_probability: 0.3, max_probability: 0.4, frequency: 99}
1783 # mean that there are no record with an estimated probability in [0.1, 0.2)
1784 # nor larger or equal to 0.4.
1785 { # A DeltaPresenceEstimationHistogramBucket message with the following
1786 # values:
1787 # min_probability: 0.1
1788 # max_probability: 0.2
1789 # frequency: 42
1790 # means that there are 42 records for which δ is in [0.1, 0.2). An
1791 # important particular case is when min_probability = max_probability = 1:
1792 # then, every individual who shares this quasi-identifier combination is in
1793 # the dataset.
1794 "bucketValues": [ # Sample of quasi-identifier tuple values in this bucket. The total
1795 # number of classes returned per bucket is capped at 20.
1796 { # A tuple of values for the quasi-identifier columns.
1797 "quasiIdsValues": [ # The quasi-identifier values.
1798 { # Set of primitive values supported by the system.
1799 # Note that for the purposes of inspection or transformation, the number
1800 # of bytes considered to comprise a 'Value' is based on its representation
1801 # as a UTF-8 encoded string. For example, if 'integer_value' is set to
1802 # 123456789, the number of bytes would be counted as 9, even though an
1803 # int64 only holds up to 8 bytes of data.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1804 "floatValue": 3.14, # float
1805 "timestampValue": "A String", # timestamp
1806 "dayOfWeekValue": "A String", # day of week
1807 "timeValue": { # Represents a time of day. The date and time zone are either not significant # time of day
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1808 # or are specified elsewhere. An API may choose to allow leap seconds. Related
1809 # types are google.type.Date and `google.protobuf.Timestamp`.
1810 "hours": 42, # Hours of day in 24 hour format. Should be from 0 to 23. An API may choose
1811 # to allow the value "24:00:00" for scenarios like business closing time.
1812 "nanos": 42, # Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999.
1813 "seconds": 42, # Seconds of minutes of the time. Must normally be from 0 to 59. An API may
1814 # allow the value 60 if it allows leap-seconds.
1815 "minutes": 42, # Minutes of hour of day. Must be from 0 to 59.
1816 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1817 "dateValue": { # Represents a whole or partial calendar date, e.g. a birthday. The time of day # date
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1818 # and time zone are either specified elsewhere or are not significant. The date
1819 # is relative to the Proleptic Gregorian Calendar. This can represent:
1820 #
1821 # * A full date, with non-zero year, month and day values
1822 # * A month and day value, with a zero year, e.g. an anniversary
1823 # * A year on its own, with zero month and day values
1824 # * A year and month value, with a zero day, e.g. a credit card expiration date
1825 #
1826 # Related types are google.type.TimeOfDay and `google.protobuf.Timestamp`.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1827 "month": 42, # Month of year. Must be from 1 to 12, or 0 if specifying a year without a
1828 # month and day.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1829 "day": 42, # Day of month. Must be from 1 to 31 and valid for the year and month, or 0
1830 # if specifying a year by itself or a year and month where the day is not
1831 # significant.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1832 "year": 42, # Year of date. Must be from 1 to 9999, or 0 if specifying a date without
1833 # a year.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1834 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1835 "stringValue": "A String", # string
1836 "booleanValue": True or False, # boolean
1837 "integerValue": "A String", # integer
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1838 },
1839 ],
1840 "estimatedProbability": 3.14, # The estimated probability that a given individual sharing these
1841 # quasi-identifier values is in the dataset. This value, typically called
1842 # δ, is the ratio between the number of records in the dataset with these
1843 # quasi-identifier values, and the total number of individuals (inside
1844 # *and* outside the dataset) with these quasi-identifier values.
1845 # For example, if there are 15 individuals in the dataset who share the
1846 # same quasi-identifier values, and an estimated 100 people in the entire
1847 # population with these values, then δ is 0.15.
1848 },
1849 ],
1850 "bucketValueCount": "A String", # Total number of distinct quasi-identifier tuple values in this bucket.
1851 "bucketSize": "A String", # Number of records within these probability bounds.
1852 "maxProbability": 3.14, # Always greater than or equal to min_probability.
1853 "minProbability": 3.14, # Between 0 and 1.
1854 },
1855 ],
1856 },
1857 "requestedSourceTable": { # Message defining the location of a BigQuery table. A table is uniquely # Input dataset to compute metrics over.
1858 # identified by its project_id, dataset_id, and table_name. Within a query
1859 # a table is often referenced with a string in the format of:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1860 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
1861 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1862 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
1863 # If omitted, project ID is inferred from the API call.
1864 "tableId": "A String", # Name of the table.
1865 "datasetId": "A String", # Dataset ID of the table.
1866 },
1867 },
1868 "state": "A String", # State of a job.
1869 "jobTriggerName": "A String", # If created by a job trigger, the resource name of the trigger that
1870 # instantiated the job.
1871 "startTime": "A String", # Time when the job started.
1872 "endTime": "A String", # Time when the job finished.
1873 "type": "A String", # The type of job.
1874 "createTime": "A String", # Time when the job was created.
1875 }</pre>
1876</div>
1877
1878<div class="method">
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1879 <code class="details" id="create">create(parent, body=None, x__xgafv=None)</code>
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1880 <pre>Creates a job trigger to run DLP actions such as scanning storage for
1881sensitive information on a set schedule.
1882See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.
1883
1884Args:
Dan O'Mearadd494642020-05-01 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 Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1887 The object takes the form of:
1888
1889{ # Request message for CreateJobTrigger.
1890 "triggerId": "A String", # The trigger id can contain uppercase and lowercase letters,
1891 # numbers, and hyphens; that is, it must match the regular
1892 # expression: `[a-zA-Z\\d-_]+`. The maximum length is 100
1893 # characters. Can be empty to allow the system to generate one.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1894 "locationId": "A String", # The geographic location to store the job trigger. Reserved for
1895 # future extensions.
1896 "jobTrigger": { # Contains a configuration to make dlp api calls on a repeating basis. # Required. The JobTrigger to create.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1897 # See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1898 "status": "A String", # Required. A status for this trigger.
1899 "updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
1900 "errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1901 # errors may result in the JobTrigger automatically being paused.
1902 # Will return the last 100 errors. Whenever the JobTrigger is modified
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1903 # this list will be cleared.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1904 { # Details information about an error encountered during job execution or
1905 # the results of an unsuccessful activation of the JobTrigger.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1906 "timestamps": [ # The times the error occurred.
1907 "A String",
1908 ],
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1909 "details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1910 # different programming environments, including REST APIs and RPC APIs. It is
1911 # used by [gRPC](https://github.com/grpc). Each `Status` message contains
1912 # three pieces of data: error code, error message, and error details.
1913 #
1914 # You can find out more about this error model and how to work with it in the
1915 # [API Design Guide](https://cloud.google.com/apis/design/errors).
1916 "message": "A String", # A developer-facing error message, which should be in English. Any
1917 # user-facing error message should be localized and sent in the
1918 # google.rpc.Status.details field, or localized by the client.
1919 "code": 42, # The status code, which should be an enum value of google.rpc.Code.
1920 "details": [ # A list of messages that carry the error details. There is a common set of
1921 # message types for APIs to use.
1922 {
1923 "a_key": "", # Properties of the object. Contains field @type with type URL.
1924 },
1925 ],
1926 },
1927 },
1928 ],
1929 "displayName": "A String", # Display name (max 100 chars)
1930 "description": "A String", # User provided description (max 256 chars)
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1931 "triggers": [ # A list of triggers which will be OR'ed together. Only one in the list
1932 # needs to trigger for a job to be started. The list may contain only
1933 # a single Schedule trigger and must have at least one object.
1934 { # What event needs to occur for a new job to be started.
1935 "manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.
1936 # Early access feature is in a pre-release state and might change or have
1937 # limited support. For more information, see
1938 # https://cloud.google.com/products#product-launch-stages.
1939 # and finished.
1940 },
1941 "schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.
1942 "recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For
1943 # example: every day (86400 seconds).
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1944 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1945 # A scheduled start time will be skipped if the previous
1946 # execution has not ended when its scheduled time occurs.
1947 #
1948 # This value must be set to a time duration greater than or equal
1949 # to 1 day and can be no longer than 60 days.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1950 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1951 },
1952 ],
1953 "inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
1954 "storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
1955 "cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1956 # bucket.
1957 "bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger
1958 # than this value then the rest of the bytes are omitted. Only one
1959 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
1960 "sampleMethod": "A String",
1961 "fileSet": { # Set of files to scan. # The set of one or more files to scan.
1962 "url": "A String", # The Cloud Storage url of the file(s) to scan, in the format
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]1963 # `gs://&lt;bucket&gt;/&lt;path&gt;`. Trailing wildcard in the path is allowed.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]1964 #
1965 # If the url ends in a trailing slash, the bucket or directory represented
1966 # by the url will be scanned non-recursively (content in sub-directories
1967 # will not be scanned). This means that `gs://mybucket/` is equivalent to
1968 # `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
1969 # `gs://mybucket/directory/*`.
1970 #
1971 # Exactly one of `url` or `regex_file_set` must be set.
1972 "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
1973 # `regex_file_set` must be set.
1974 # expressions are used to allow fine-grained control over which files in the
1975 # bucket to include.
1976 #
1977 # Included files are those that match at least one item in `include_regex` and
1978 # do not match any items in `exclude_regex`. Note that a file that matches
1979 # items from both lists will _not_ be included. For a match to occur, the
1980 # entire file path (i.e., everything in the url after the bucket name) must
1981 # match the regular expression.
1982 #
1983 # For example, given the input `{bucket_name: "mybucket", include_regex:
1984 # ["directory1/.*"], exclude_regex:
1985 # ["directory1/excluded.*"]}`:
1986 #
1987 # * `gs://mybucket/directory1/myfile` will be included
1988 # * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches
1989 # across `/`)
1990 # * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the
1991 # full path doesn't match any items in `include_regex`)
1992 # * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path
1993 # matches an item in `exclude_regex`)
1994 #
1995 # If `include_regex` is left empty, it will match all files by default
1996 # (this is equivalent to setting `include_regex: [".*"]`).
1997 #
1998 # Some other common use cases:
1999 #
2000 # * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all
2001 # files in `mybucket` except for .pdf files
2002 # * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will
2003 # include all files directly under `gs://mybucket/directory/`, without matching
2004 # across `/`
2005 "excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in
2006 # the bucket that match at least one of these regular expressions will be
2007 # excluded from the scan.
2008 #
2009 # Regular expressions use RE2
2010 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
2011 # under the google/re2 repository on GitHub.
2012 "A String",
2013 ],
2014 "bucketName": "A String", # The name of a Cloud Storage bucket. Required.
2015 "includeRegex": [ # A list of regular expressions matching file paths to include. All files in
2016 # the bucket that match at least one of these regular expressions will be
2017 # included in the set of files, except for those that also match an item in
2018 # `exclude_regex`. Leaving this field empty will match all files by default
2019 # (this is equivalent to including `.*` in the list).
2020 #
2021 # Regular expressions use RE2
2022 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
2023 # under the google/re2 repository on GitHub.
2024 "A String",
2025 ],
2026 },
2027 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2028 "filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.
2029 # Number of files scanned is rounded down. Must be between 0 and 100,
2030 # inclusively. Both 0 and 100 means no limit. Defaults to 0.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2031 "bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The
2032 # number of bytes scanned is rounded down. Must be between 0 and 100,
2033 # inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one
2034 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2035 "fileTypes": [ # List of file type groups to include in the scan.
2036 # If empty, all files are scanned and available data format processors
2037 # are applied. In addition, the binary content of the selected files
2038 # is always scanned as well.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2039 # Images are scanned only as binary if the specified region
2040 # does not support image inspection and no file_types were specified.
2041 # Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2042 "A String",
2043 ],
2044 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2045 "datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
2046 "partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always
2047 # by project and namespace, however the namespace ID may be empty.
2048 # A partition ID identifies a grouping of entities. The grouping is always
2049 # by project and namespace, however the namespace ID may be empty.
2050 #
2051 # A partition ID contains several dimensions:
2052 # project ID and namespace ID.
2053 "projectId": "A String", # The ID of the project to which the entities belong.
2054 "namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
2055 },
2056 "kind": { # A representation of a Datastore kind. # The kind to process.
2057 "name": "A String", # The name of the kind.
2058 },
2059 },
2060 "bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
2061 "excludedFields": [ # References to fields excluded from scanning. This allows you to skip
2062 # inspection of entire columns which you know have no findings.
2063 { # General identifier of a data field in a storage service.
2064 "name": "A String", # Name describing the field.
2065 },
2066 ],
2067 "rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the
2068 # rest of the rows are omitted. If not set, or if set to 0, all rows will be
2069 # scanned. Only one of rows_limit and rows_limit_percent can be specified.
2070 # Cannot be used in conjunction with TimespanConfig.
2071 "sampleMethod": "A String",
2072 "identifyingFields": [ # Table fields that may uniquely identify a row within the table. When
2073 # `actions.saveFindings.outputConfig.table` is specified, the values of
2074 # columns specified here are available in the output table under
2075 # `location.content_locations.record_location.record_key.id_values`. Nested
2076 # fields such as `person.birthdate.year` are allowed.
2077 { # General identifier of a data field in a storage service.
2078 "name": "A String", # Name describing the field.
2079 },
2080 ],
2081 "rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows
2082 # scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and
2083 # 100 means no limit. Defaults to 0. Only one of rows_limit and
2084 # rows_limit_percent can be specified. Cannot be used in conjunction with
2085 # TimespanConfig.
2086 "tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.
2087 # identified by its project_id, dataset_id, and table_name. Within a query
2088 # a table is often referenced with a string in the format of:
2089 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
2090 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
2091 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
2092 # If omitted, project ID is inferred from the API call.
2093 "tableId": "A String", # Name of the table.
2094 "datasetId": "A String", # Dataset ID of the table.
2095 },
2096 },
2097 "timespanConfig": { # Configuration of the timespan of the items to include in scanning.
2098 # Currently only supported when inspecting Google Cloud Storage and BigQuery.
2099 "timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.
2100 # Used for data sources like Datastore and BigQuery.
2101 #
2102 # For BigQuery:
2103 # Required to filter out rows based on the given start and
2104 # end times. If not specified and the table was modified between the given
2105 # start and end times, the entire table will be scanned.
2106 # The valid data types of the timestamp field are: `INTEGER`, `DATE`,
2107 # `TIMESTAMP`, or `DATETIME` BigQuery column.
2108 #
2109 # For Datastore.
2110 # Valid data types of the timestamp field are: `TIMESTAMP`.
2111 # Datastore entity will be scanned if the timestamp property does not
2112 # exist or its value is empty or invalid.
2113 "name": "A String", # Name describing the field.
2114 },
2115 "endTime": "A String", # Exclude files or rows newer than this value.
2116 # If set to zero, no upper time limit is applied.
2117 "startTime": "A String", # Exclude files or rows older than this value.
2118 "enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out
2119 # a valid start_time to avoid scanning files that have not been modified
2120 # since the last time the JobTrigger executed. This will be based on the
2121 # time of the execution of the last run of the JobTrigger.
2122 },
2123 "hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.
2124 # Early access feature is in a pre-release state and might change or have
2125 # limited support. For more information, see
2126 # https://cloud.google.com/products#product-launch-stages.
2127 # of Google Cloud Platform.
2128 "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings
2129 # meaningful such as the columns that are primary keys.
2130 "identifyingFields": [ # The columns that are the primary keys for table objects included in
2131 # ContentItem. A copy of this cell's value will stored alongside alongside
2132 # each finding so that the finding can be traced to the specific row it came
2133 # from. No more than 3 may be provided.
2134 { # General identifier of a data field in a storage service.
2135 "name": "A String", # Name describing the field.
2136 },
2137 ],
2138 },
2139 "labels": { # To organize findings, these labels will be added to each finding.
2140 #
2141 # Label keys must be between 1 and 63 characters long and must conform
2142 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
2143 #
2144 # Label values must be between 0 and 63 characters long and must conform
2145 # to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.
2146 #
2147 # No more than 10 labels can be associated with a given finding.
2148 #
2149 # Examples:
2150 # * `"environment" : "production"`
2151 # * `"pipeline" : "etl"`
2152 "a_key": "A String",
2153 },
2154 "requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their
2155 # 'finding_labels' map. Request may contain others, but any missing one of
2156 # these will be rejected.
2157 #
2158 # Label keys must be between 1 and 63 characters long and must conform
2159 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
2160 #
2161 # No more than 10 keys can be required.
2162 "A String",
2163 ],
2164 "description": "A String", # A short description of where the data is coming from. Will be stored once
2165 # in the job. 256 max length.
2166 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2167 },
2168 "inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.
2169 # When used with redactContent only info_types and min_likelihood are currently
2170 # used.
2171 "excludeInfoTypes": True or False, # When true, excludes type information of the findings.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2172 "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2173 "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
2174 # When set within `InspectContentRequest`, the maximum returned is 2000
2175 # regardless if this is set higher.
2176 "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
2177 { # Max findings configuration per infoType, per content item or long
2178 # running DlpJob.
2179 "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per
2180 # info_type should be provided. If InfoTypeLimit does not have an
2181 # info_type, the DLP API applies the limit against all info_types that
2182 # are found but not specified in another InfoTypeLimit.
2183 "name": "A String", # Name of the information type. Either a name of your choosing when
2184 # creating a CustomInfoType, or one of the names listed
2185 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
2186 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2187 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2188 },
2189 "maxFindings": 42, # Max findings limit for the given infoType.
2190 },
2191 ],
2192 "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2193 # When set within `InspectJobConfig`,
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2194 # the maximum returned is 2000 regardless if this is set higher.
2195 # When set within `InspectContentRequest`, this field is ignored.
2196 },
2197 "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
2198 # POSSIBLE.
2199 # See https://cloud.google.com/dlp/docs/likelihood to learn more.
2200 "customInfoTypes": [ # CustomInfoTypes provided by the user. See
2201 # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.
2202 { # Custom information type provided by the user. Used to find domain-specific
2203 # sensitive information configurable to the data in question.
2204 "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
2205 "pattern": "A String", # Pattern defining the regular expression. Its syntax
2206 # (https://github.com/google/re2/wiki/Syntax) can be found under the
2207 # google/re2 repository on GitHub.
2208 "groupIndexes": [ # The index of the submatch to extract as findings. When not
2209 # specified, the entire match is returned. No more than 3 may be included.
2210 42,
2211 ],
2212 },
2213 "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
2214 # support reversing.
2215 # such as
2216 # [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).
2217 # These types of transformations are
2218 # those that perform pseudonymization, thereby producing a "surrogate" as
2219 # output. This should be used in conjunction with a field on the
2220 # transformation such as `surrogate_info_type`. This CustomInfoType does
2221 # not support the use of `detection_rules`.
2222 },
2223 "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in
2224 # infoType, when the name matches one of existing infoTypes and that infoType
2225 # is specified in `InspectContent.info_types` field. Specifying the latter
2226 # adds findings to the one detected by the system. If built-in info type is
2227 # not specified in `InspectContent.info_types` list then the name is treated
2228 # as a custom info type.
2229 "name": "A String", # Name of the information type. Either a name of your choosing when
2230 # creating a CustomInfoType, or one of the names listed
2231 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
2232 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2233 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2234 },
2235 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
2236 # be used to match sensitive information specific to the data, such as a list
2237 # of employee IDs or job titles.
2238 #
2239 # Dictionary words are case-insensitive and all characters other than letters
2240 # and digits in the unicode [Basic Multilingual
2241 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
2242 # will be replaced with whitespace when scanning for matches, so the
2243 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
2244 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
2245 # surrounding any match must be of a different type than the adjacent
2246 # characters within the word, so letters must be next to non-letters and
2247 # digits next to non-digits. For example, the dictionary word "jen" will
2248 # match the first three letters of the text "jen123" but will return no
2249 # matches for "jennifer".
2250 #
2251 # Dictionary words containing a large number of characters that are not
2252 # letters or digits may result in unexpected findings because such characters
2253 # are treated as whitespace. The
2254 # [limits](https://cloud.google.com/dlp/limits) page contains details about
2255 # the size limits of dictionaries. For dictionaries that do not fit within
2256 # these constraints, consider using `LargeCustomDictionaryConfig` in the
2257 # `StoredInfoType` API.
2258 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
2259 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
2260 # at least one phrase and every phrase must contain at least 2 characters
2261 # that are letters or digits. [required]
2262 "A String",
2263 ],
2264 },
2265 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
2266 # is accepted.
2267 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
2268 # Example: gs://[BUCKET_NAME]/dictionary.txt
2269 },
2270 },
2271 "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
2272 # `InspectDataSource`. Not currently supported in `InspectContent`.
2273 "name": "A String", # Resource name of the requested `StoredInfoType`, for example
2274 # `organizations/433245324/storedInfoTypes/432452342` or
2275 # `projects/project-id/storedInfoTypes/432452342`.
2276 "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
2277 # inspection was created. Output-only field, populated by the system.
2278 },
2279 "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.
2280 # Rules are applied in order that they are specified. Not supported for the
2281 # `surrogate_type` CustomInfoType.
2282 { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a
2283 # `CustomInfoType` to alter behavior under certain circumstances, depending
2284 # on the specific details of the rule. Not supported for the `surrogate_type`
2285 # custom infoType.
2286 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
2287 # proximity of hotwords.
2288 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
2289 # The total length of the window cannot exceed 1000 characters. Note that
2290 # the finding itself will be included in the window, so that hotwords may
2291 # be used to match substrings of the finding itself. For example, the
2292 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
2293 # adjusted upwards if the area code is known to be the local area code of
2294 # a company office using the hotword regex "\(xxx\)", where "xxx"
2295 # is the area code in question.
2296 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2297 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2298 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2299 },
2300 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
2301 "pattern": "A String", # Pattern defining the regular expression. Its syntax
2302 # (https://github.com/google/re2/wiki/Syntax) can be found under the
2303 # google/re2 repository on GitHub.
2304 "groupIndexes": [ # The index of the submatch to extract as findings. When not
2305 # specified, the entire match is returned. No more than 3 may be included.
2306 42,
2307 ],
2308 },
2309 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
2310 # part of a detection rule.
2311 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
2312 # levels. For example, if a finding would be `POSSIBLE` without the
2313 # detection rule and `relative_likelihood` is 1, then it is upgraded to
2314 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
2315 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
2316 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
2317 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
2318 # a final likelihood of `LIKELY`.
2319 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
2320 },
2321 },
2322 },
2323 ],
2324 "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding
2325 # to be returned. It still can be used for rules matching.
2326 "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be
2327 # altered by a detection rule if the finding meets the criteria specified by
2328 # the rule. Defaults to `VERY_LIKELY` if not specified.
2329 },
2330 ],
2331 "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
2332 # included in the response; see Finding.quote.
2333 "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.
2334 # Exclusion rules, contained in the set are executed in the end, other
2335 # rules are executed in the order they are specified for each info type.
2336 { # Rule set for modifying a set of infoTypes to alter behavior under certain
2337 # circumstances, depending on the specific details of the rules within the set.
2338 "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
2339 { # A single inspection rule to be applied to infoTypes, specified in
2340 # `InspectionRuleSet`.
2341 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
2342 # proximity of hotwords.
2343 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
2344 # The total length of the window cannot exceed 1000 characters. Note that
2345 # the finding itself will be included in the window, so that hotwords may
2346 # be used to match substrings of the finding itself. For example, the
2347 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
2348 # adjusted upwards if the area code is known to be the local area code of
2349 # a company office using the hotword regex "\(xxx\)", where "xxx"
2350 # is the area code in question.
2351 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2352 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2353 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2354 },
2355 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
2356 "pattern": "A String", # Pattern defining the regular expression. Its syntax
2357 # (https://github.com/google/re2/wiki/Syntax) can be found under the
2358 # google/re2 repository on GitHub.
2359 "groupIndexes": [ # The index of the submatch to extract as findings. When not
2360 # specified, the entire match is returned. No more than 3 may be included.
2361 42,
2362 ],
2363 },
2364 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
2365 # part of a detection rule.
2366 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
2367 # levels. For example, if a finding would be `POSSIBLE` without the
2368 # detection rule and `relative_likelihood` is 1, then it is upgraded to
2369 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
2370 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
2371 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
2372 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
2373 # a final likelihood of `LIKELY`.
2374 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
2375 },
2376 },
2377 "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
2378 # `InspectionRuleSet` are removed from results.
2379 "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
2380 "pattern": "A String", # Pattern defining the regular expression. Its syntax
2381 # (https://github.com/google/re2/wiki/Syntax) can be found under the
2382 # google/re2 repository on GitHub.
2383 "groupIndexes": [ # The index of the submatch to extract as findings. When not
2384 # specified, the entire match is returned. No more than 3 may be included.
2385 42,
2386 ],
2387 },
2388 "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.
2389 "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or
2390 # contained within with a finding of an infoType from this list. For
2391 # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and
2392 # `exclusion_rule` containing `exclude_info_types.info_types` with
2393 # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap
2394 # with EMAIL_ADDRESS finding.
2395 # That leads to "555-222-2222@example.org" to generate only a single
2396 # finding, namely email address.
2397 { # Type of information detected by the API.
2398 "name": "A String", # Name of the information type. Either a name of your choosing when
2399 # creating a CustomInfoType, or one of the names listed
2400 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
2401 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2402 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2403 },
2404 ],
2405 },
2406 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
2407 # be used to match sensitive information specific to the data, such as a list
2408 # of employee IDs or job titles.
2409 #
2410 # Dictionary words are case-insensitive and all characters other than letters
2411 # and digits in the unicode [Basic Multilingual
2412 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
2413 # will be replaced with whitespace when scanning for matches, so the
2414 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
2415 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
2416 # surrounding any match must be of a different type than the adjacent
2417 # characters within the word, so letters must be next to non-letters and
2418 # digits next to non-digits. For example, the dictionary word "jen" will
2419 # match the first three letters of the text "jen123" but will return no
2420 # matches for "jennifer".
2421 #
2422 # Dictionary words containing a large number of characters that are not
2423 # letters or digits may result in unexpected findings because such characters
2424 # are treated as whitespace. The
2425 # [limits](https://cloud.google.com/dlp/limits) page contains details about
2426 # the size limits of dictionaries. For dictionaries that do not fit within
2427 # these constraints, consider using `LargeCustomDictionaryConfig` in the
2428 # `StoredInfoType` API.
2429 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
2430 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
2431 # at least one phrase and every phrase must contain at least 2 characters
2432 # that are letters or digits. [required]
2433 "A String",
2434 ],
2435 },
2436 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
2437 # is accepted.
2438 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
2439 # Example: gs://[BUCKET_NAME]/dictionary.txt
2440 },
2441 },
2442 "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
2443 },
2444 },
2445 ],
2446 "infoTypes": [ # List of infoTypes this rule set is applied to.
2447 { # Type of information detected by the API.
2448 "name": "A String", # Name of the information type. Either a name of your choosing when
2449 # creating a CustomInfoType, or one of the names listed
2450 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
2451 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2452 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2453 },
2454 ],
2455 },
2456 ],
2457 "contentOptions": [ # List of options defining data content to scan.
2458 # If empty, text, images, and other content will be included.
2459 "A String",
2460 ],
2461 "infoTypes": [ # Restricts what info_types to look for. The values must correspond to
2462 # InfoType values returned by ListInfoTypes or listed at
2463 # https://cloud.google.com/dlp/docs/infotypes-reference.
2464 #
2465 # When no InfoTypes or CustomInfoTypes are specified in a request, the
2466 # system may automatically choose what detectors to run. By default this may
2467 # be all types, but may change over time as detectors are updated.
2468 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2469 # If you need precise control and predictability as to what detectors are
2470 # run you should specify specific InfoTypes listed in the reference,
2471 # otherwise a default list will be used, which may change over time.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2472 { # Type of information detected by the API.
2473 "name": "A String", # Name of the information type. Either a name of your choosing when
2474 # creating a CustomInfoType, or one of the names listed
2475 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
2476 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2477 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2478 },
2479 ],
2480 },
2481 "inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.
2482 # `inspect_config` will be merged into the values persisted as part of the
2483 # template.
2484 "actions": [ # Actions to execute at the completion of the job.
2485 { # A task to execute on the completion of a job.
2486 # See https://cloud.google.com/dlp/docs/concepts-actions to learn more.
2487 "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
2488 # OutputStorageConfig. Only a single instance of this action can be
2489 # specified.
2490 # Compatible with: Inspect, Risk
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2491 "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2492 "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
2493 # dataset. If table_id is not set a new one will be generated
2494 # for you with the following format:
2495 # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for
2496 # generating the date details.
2497 #
2498 # For Inspect, each column in an existing output table must have the same
2499 # name, type, and mode of a field in the `Finding` object.
2500 #
2501 # For Risk, an existing output table should be the output of a previous
2502 # Risk analysis job run on the same source table, with the same privacy
2503 # metric and quasi-identifiers. Risk jobs that analyze the same table but
2504 # compute a different privacy metric, or use different sets of
2505 # quasi-identifiers, cannot store their results in the same table.
2506 # identified by its project_id, dataset_id, and table_name. Within a query
2507 # a table is often referenced with a string in the format of:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2508 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
2509 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2510 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
2511 # If omitted, project ID is inferred from the API call.
2512 "tableId": "A String", # Name of the table.
2513 "datasetId": "A String", # Dataset ID of the table.
2514 },
2515 "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only
2516 # used for Inspect and must be unspecified for Risk jobs. Columns are derived
2517 # from the `Finding` object. If appending to an existing table, any columns
2518 # from the predefined schema that are missing will be added. No columns in
2519 # the existing table will be deleted.
2520 #
2521 # If unspecified, then all available columns will be used for a new table or
2522 # an (existing) table with no schema, and no changes will be made to an
2523 # existing table that has a schema.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2524 # Only for use with external storage.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2525 },
2526 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2527 "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2528 # completion/failure.
2529 # completion/failure.
2530 },
2531 "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
2532 # Command Center (CSCC Alpha).
2533 # This action is only available for projects which are parts of
2534 # an organization and whitelisted for the alpha Cloud Security Command
2535 # Center.
2536 # The action will publish count of finding instances and their info types.
2537 # The summary of findings will be persisted in CSCC and are governed by CSCC
2538 # service-specific policy, see https://cloud.google.com/terms/service-terms
2539 # Only a single instance of this action can be specified.
2540 # Compatible with: Inspect
2541 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2542 "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.
2543 # will publish a metric to stack driver on each infotype requested and
2544 # how many findings were found for it. CustomDetectors will be bucketed
2545 # as 'Custom' under the Stackdriver label 'info_type'.
2546 },
2547 "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.
2548 # results of the DlpJob will be applied to the entry for the resource scanned
2549 # in Cloud Data Catalog. Any labels previously written by another DlpJob will
2550 # be deleted. InfoType naming patterns are strictly enforced when using this
2551 # feature. Note that the findings will be persisted in Cloud Data Catalog
2552 # storage and are governed by Data Catalog service-specific policy, see
2553 # https://cloud.google.com/terms/service-terms
2554 # Only a single instance of this action can be specified and only allowed if
2555 # all resources being scanned are BigQuery tables.
2556 # Compatible with: Inspect
2557 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2558 "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
2559 # message contains a single field, `DlpJobName`, which is equal to the
2560 # finished job's
2561 # [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
2562 # Compatible with: Inspect, Risk
2563 "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given
2564 # publishing access rights to the DLP API service account executing
2565 # the long running DlpJob sending the notifications.
2566 # Format is projects/{project}/topics/{topic}.
2567 },
2568 },
2569 ],
2570 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2571 "lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
2572 "createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2573 "name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the
2574 # triggeredJob is created, for example
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2575 # `projects/dlp-test-project/jobTriggers/53234423`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2576 },
2577 }
2578
2579 x__xgafv: string, V1 error format.
2580 Allowed values
2581 1 - v1 error format
2582 2 - v2 error format
2583
2584Returns:
2585 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.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2589 "status": "A String", # Required. A status for this trigger.
2590 "updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
2591 "errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2592 # errors may result in the JobTrigger automatically being paused.
2593 # Will return the last 100 errors. Whenever the JobTrigger is modified
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2594 # this list will be cleared.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2595 { # Details information about an error encountered during job execution or
2596 # the results of an unsuccessful activation of the JobTrigger.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2597 "timestamps": [ # The times the error occurred.
2598 "A String",
2599 ],
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2600 "details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2601 # different programming environments, including REST APIs and RPC APIs. It is
2602 # used by [gRPC](https://github.com/grpc). Each `Status` message contains
2603 # three pieces of data: error code, error message, and error details.
2604 #
2605 # You can find out more about this error model and how to work with it in the
2606 # [API Design Guide](https://cloud.google.com/apis/design/errors).
2607 "message": "A String", # A developer-facing error message, which should be in English. Any
2608 # user-facing error message should be localized and sent in the
2609 # google.rpc.Status.details field, or localized by the client.
2610 "code": 42, # The status code, which should be an enum value of google.rpc.Code.
2611 "details": [ # A list of messages that carry the error details. There is a common set of
2612 # message types for APIs to use.
2613 {
2614 "a_key": "", # Properties of the object. Contains field @type with type URL.
2615 },
2616 ],
2617 },
2618 },
2619 ],
2620 "displayName": "A String", # Display name (max 100 chars)
2621 "description": "A String", # User provided description (max 256 chars)
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2622 "triggers": [ # A list of triggers which will be OR'ed together. Only one in the list
2623 # needs to trigger for a job to be started. The list may contain only
2624 # a single Schedule trigger and must have at least one object.
2625 { # What event needs to occur for a new job to be started.
2626 "manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.
2627 # Early access feature is in a pre-release state and might change or have
2628 # limited support. For more information, see
2629 # https://cloud.google.com/products#product-launch-stages.
2630 # and finished.
2631 },
2632 "schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.
2633 "recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For
2634 # example: every day (86400 seconds).
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2635 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2636 # A scheduled start time will be skipped if the previous
2637 # execution has not ended when its scheduled time occurs.
2638 #
2639 # This value must be set to a time duration greater than or equal
2640 # to 1 day and can be no longer than 60 days.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2641 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2642 },
2643 ],
2644 "inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
2645 "storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
2646 "cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2647 # bucket.
2648 "bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger
2649 # than this value then the rest of the bytes are omitted. Only one
2650 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
2651 "sampleMethod": "A String",
2652 "fileSet": { # Set of files to scan. # The set of one or more files to scan.
2653 "url": "A String", # The Cloud Storage url of the file(s) to scan, in the format
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2654 # `gs://&lt;bucket&gt;/&lt;path&gt;`. Trailing wildcard in the path is allowed.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2655 #
2656 # If the url ends in a trailing slash, the bucket or directory represented
2657 # by the url will be scanned non-recursively (content in sub-directories
2658 # will not be scanned). This means that `gs://mybucket/` is equivalent to
2659 # `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
2660 # `gs://mybucket/directory/*`.
2661 #
2662 # Exactly one of `url` or `regex_file_set` must be set.
2663 "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
2664 # `regex_file_set` must be set.
2665 # expressions are used to allow fine-grained control over which files in the
2666 # bucket to include.
2667 #
2668 # Included files are those that match at least one item in `include_regex` and
2669 # do not match any items in `exclude_regex`. Note that a file that matches
2670 # items from both lists will _not_ be included. For a match to occur, the
2671 # entire file path (i.e., everything in the url after the bucket name) must
2672 # match the regular expression.
2673 #
2674 # For example, given the input `{bucket_name: "mybucket", include_regex:
2675 # ["directory1/.*"], exclude_regex:
2676 # ["directory1/excluded.*"]}`:
2677 #
2678 # * `gs://mybucket/directory1/myfile` will be included
2679 # * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches
2680 # across `/`)
2681 # * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the
2682 # full path doesn't match any items in `include_regex`)
2683 # * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path
2684 # matches an item in `exclude_regex`)
2685 #
2686 # If `include_regex` is left empty, it will match all files by default
2687 # (this is equivalent to setting `include_regex: [".*"]`).
2688 #
2689 # Some other common use cases:
2690 #
2691 # * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all
2692 # files in `mybucket` except for .pdf files
2693 # * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will
2694 # include all files directly under `gs://mybucket/directory/`, without matching
2695 # across `/`
2696 "excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in
2697 # the bucket that match at least one of these regular expressions will be
2698 # excluded from the scan.
2699 #
2700 # Regular expressions use RE2
2701 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
2702 # under the google/re2 repository on GitHub.
2703 "A String",
2704 ],
2705 "bucketName": "A String", # The name of a Cloud Storage bucket. Required.
2706 "includeRegex": [ # A list of regular expressions matching file paths to include. All files in
2707 # the bucket that match at least one of these regular expressions will be
2708 # included in the set of files, except for those that also match an item in
2709 # `exclude_regex`. Leaving this field empty will match all files by default
2710 # (this is equivalent to including `.*` in the list).
2711 #
2712 # Regular expressions use RE2
2713 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
2714 # under the google/re2 repository on GitHub.
2715 "A String",
2716 ],
2717 },
2718 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2719 "filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.
2720 # Number of files scanned is rounded down. Must be between 0 and 100,
2721 # inclusively. Both 0 and 100 means no limit. Defaults to 0.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2722 "bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The
2723 # number of bytes scanned is rounded down. Must be between 0 and 100,
2724 # inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one
2725 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2726 "fileTypes": [ # List of file type groups to include in the scan.
2727 # If empty, all files are scanned and available data format processors
2728 # are applied. In addition, the binary content of the selected files
2729 # is always scanned as well.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2730 # Images are scanned only as binary if the specified region
2731 # does not support image inspection and no file_types were specified.
2732 # Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2733 "A String",
2734 ],
2735 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2736 "datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
2737 "partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always
2738 # by project and namespace, however the namespace ID may be empty.
2739 # A partition ID identifies a grouping of entities. The grouping is always
2740 # by project and namespace, however the namespace ID may be empty.
2741 #
2742 # A partition ID contains several dimensions:
2743 # project ID and namespace ID.
2744 "projectId": "A String", # The ID of the project to which the entities belong.
2745 "namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
2746 },
2747 "kind": { # A representation of a Datastore kind. # The kind to process.
2748 "name": "A String", # The name of the kind.
2749 },
2750 },
2751 "bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
2752 "excludedFields": [ # References to fields excluded from scanning. This allows you to skip
2753 # inspection of entire columns which you know have no findings.
2754 { # General identifier of a data field in a storage service.
2755 "name": "A String", # Name describing the field.
2756 },
2757 ],
2758 "rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the
2759 # rest of the rows are omitted. If not set, or if set to 0, all rows will be
2760 # scanned. Only one of rows_limit and rows_limit_percent can be specified.
2761 # Cannot be used in conjunction with TimespanConfig.
2762 "sampleMethod": "A String",
2763 "identifyingFields": [ # Table fields that may uniquely identify a row within the table. When
2764 # `actions.saveFindings.outputConfig.table` is specified, the values of
2765 # columns specified here are available in the output table under
2766 # `location.content_locations.record_location.record_key.id_values`. Nested
2767 # fields such as `person.birthdate.year` are allowed.
2768 { # General identifier of a data field in a storage service.
2769 "name": "A String", # Name describing the field.
2770 },
2771 ],
2772 "rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows
2773 # scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and
2774 # 100 means no limit. Defaults to 0. Only one of rows_limit and
2775 # rows_limit_percent can be specified. Cannot be used in conjunction with
2776 # TimespanConfig.
2777 "tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.
2778 # identified by its project_id, dataset_id, and table_name. Within a query
2779 # a table is often referenced with a string in the format of:
2780 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
2781 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
2782 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
2783 # If omitted, project ID is inferred from the API call.
2784 "tableId": "A String", # Name of the table.
2785 "datasetId": "A String", # Dataset ID of the table.
2786 },
2787 },
2788 "timespanConfig": { # Configuration of the timespan of the items to include in scanning.
2789 # Currently only supported when inspecting Google Cloud Storage and BigQuery.
2790 "timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.
2791 # Used for data sources like Datastore and BigQuery.
2792 #
2793 # For BigQuery:
2794 # Required to filter out rows based on the given start and
2795 # end times. If not specified and the table was modified between the given
2796 # start and end times, the entire table will be scanned.
2797 # The valid data types of the timestamp field are: `INTEGER`, `DATE`,
2798 # `TIMESTAMP`, or `DATETIME` BigQuery column.
2799 #
2800 # For Datastore.
2801 # Valid data types of the timestamp field are: `TIMESTAMP`.
2802 # Datastore entity will be scanned if the timestamp property does not
2803 # exist or its value is empty or invalid.
2804 "name": "A String", # Name describing the field.
2805 },
2806 "endTime": "A String", # Exclude files or rows newer than this value.
2807 # If set to zero, no upper time limit is applied.
2808 "startTime": "A String", # Exclude files or rows older than this value.
2809 "enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out
2810 # a valid start_time to avoid scanning files that have not been modified
2811 # since the last time the JobTrigger executed. This will be based on the
2812 # time of the execution of the last run of the JobTrigger.
2813 },
2814 "hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.
2815 # Early access feature is in a pre-release state and might change or have
2816 # limited support. For more information, see
2817 # https://cloud.google.com/products#product-launch-stages.
2818 # of Google Cloud Platform.
2819 "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings
2820 # meaningful such as the columns that are primary keys.
2821 "identifyingFields": [ # The columns that are the primary keys for table objects included in
2822 # ContentItem. A copy of this cell's value will stored alongside alongside
2823 # each finding so that the finding can be traced to the specific row it came
2824 # from. No more than 3 may be provided.
2825 { # General identifier of a data field in a storage service.
2826 "name": "A String", # Name describing the field.
2827 },
2828 ],
2829 },
2830 "labels": { # To organize findings, these labels will be added to each finding.
2831 #
2832 # Label keys must be between 1 and 63 characters long and must conform
2833 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
2834 #
2835 # Label values must be between 0 and 63 characters long and must conform
2836 # to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.
2837 #
2838 # No more than 10 labels can be associated with a given finding.
2839 #
2840 # Examples:
2841 # * `"environment" : "production"`
2842 # * `"pipeline" : "etl"`
2843 "a_key": "A String",
2844 },
2845 "requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their
2846 # 'finding_labels' map. Request may contain others, but any missing one of
2847 # these will be rejected.
2848 #
2849 # Label keys must be between 1 and 63 characters long and must conform
2850 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
2851 #
2852 # No more than 10 keys can be required.
2853 "A String",
2854 ],
2855 "description": "A String", # A short description of where the data is coming from. Will be stored once
2856 # in the job. 256 max length.
2857 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2858 },
2859 "inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.
2860 # When used with redactContent only info_types and min_likelihood are currently
2861 # used.
2862 "excludeInfoTypes": True or False, # When true, excludes type information of the findings.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2863 "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2864 "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
2865 # When set within `InspectContentRequest`, the maximum returned is 2000
2866 # regardless if this is set higher.
2867 "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
2868 { # Max findings configuration per infoType, per content item or long
2869 # running DlpJob.
2870 "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per
2871 # info_type should be provided. If InfoTypeLimit does not have an
2872 # info_type, the DLP API applies the limit against all info_types that
2873 # are found but not specified in another InfoTypeLimit.
2874 "name": "A String", # Name of the information type. Either a name of your choosing when
2875 # creating a CustomInfoType, or one of the names listed
2876 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
2877 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2878 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2879 },
2880 "maxFindings": 42, # Max findings limit for the given infoType.
2881 },
2882 ],
2883 "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2884 # When set within `InspectJobConfig`,
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2885 # the maximum returned is 2000 regardless if this is set higher.
2886 # When set within `InspectContentRequest`, this field is ignored.
2887 },
2888 "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
2889 # POSSIBLE.
2890 # See https://cloud.google.com/dlp/docs/likelihood to learn more.
2891 "customInfoTypes": [ # CustomInfoTypes provided by the user. See
2892 # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.
2893 { # Custom information type provided by the user. Used to find domain-specific
2894 # sensitive information configurable to the data in question.
2895 "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
2896 "pattern": "A String", # Pattern defining the regular expression. Its syntax
2897 # (https://github.com/google/re2/wiki/Syntax) can be found under the
2898 # google/re2 repository on GitHub.
2899 "groupIndexes": [ # The index of the submatch to extract as findings. When not
2900 # specified, the entire match is returned. No more than 3 may be included.
2901 42,
2902 ],
2903 },
2904 "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
2905 # support reversing.
2906 # such as
2907 # [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).
2908 # These types of transformations are
2909 # those that perform pseudonymization, thereby producing a "surrogate" as
2910 # output. This should be used in conjunction with a field on the
2911 # transformation such as `surrogate_info_type`. This CustomInfoType does
2912 # not support the use of `detection_rules`.
2913 },
2914 "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in
2915 # infoType, when the name matches one of existing infoTypes and that infoType
2916 # is specified in `InspectContent.info_types` field. Specifying the latter
2917 # adds findings to the one detected by the system. If built-in info type is
2918 # not specified in `InspectContent.info_types` list then the name is treated
2919 # as a custom info type.
2920 "name": "A String", # Name of the information type. Either a name of your choosing when
2921 # creating a CustomInfoType, or one of the names listed
2922 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
2923 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2924 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2925 },
2926 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
2927 # be used to match sensitive information specific to the data, such as a list
2928 # of employee IDs or job titles.
2929 #
2930 # Dictionary words are case-insensitive and all characters other than letters
2931 # and digits in the unicode [Basic Multilingual
2932 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
2933 # will be replaced with whitespace when scanning for matches, so the
2934 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
2935 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
2936 # surrounding any match must be of a different type than the adjacent
2937 # characters within the word, so letters must be next to non-letters and
2938 # digits next to non-digits. For example, the dictionary word "jen" will
2939 # match the first three letters of the text "jen123" but will return no
2940 # matches for "jennifer".
2941 #
2942 # Dictionary words containing a large number of characters that are not
2943 # letters or digits may result in unexpected findings because such characters
2944 # are treated as whitespace. The
2945 # [limits](https://cloud.google.com/dlp/limits) page contains details about
2946 # the size limits of dictionaries. For dictionaries that do not fit within
2947 # these constraints, consider using `LargeCustomDictionaryConfig` in the
2948 # `StoredInfoType` API.
2949 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
2950 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
2951 # at least one phrase and every phrase must contain at least 2 characters
2952 # that are letters or digits. [required]
2953 "A String",
2954 ],
2955 },
2956 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
2957 # is accepted.
2958 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
2959 # Example: gs://[BUCKET_NAME]/dictionary.txt
2960 },
2961 },
2962 "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
2963 # `InspectDataSource`. Not currently supported in `InspectContent`.
2964 "name": "A String", # Resource name of the requested `StoredInfoType`, for example
2965 # `organizations/433245324/storedInfoTypes/432452342` or
2966 # `projects/project-id/storedInfoTypes/432452342`.
2967 "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
2968 # inspection was created. Output-only field, populated by the system.
2969 },
2970 "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.
2971 # Rules are applied in order that they are specified. Not supported for the
2972 # `surrogate_type` CustomInfoType.
2973 { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a
2974 # `CustomInfoType` to alter behavior under certain circumstances, depending
2975 # on the specific details of the rule. Not supported for the `surrogate_type`
2976 # custom infoType.
2977 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
2978 # proximity of hotwords.
2979 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
2980 # The total length of the window cannot exceed 1000 characters. Note that
2981 # the finding itself will be included in the window, so that hotwords may
2982 # be used to match substrings of the finding itself. For example, the
2983 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
2984 # adjusted upwards if the area code is known to be the local area code of
2985 # a company office using the hotword regex "\(xxx\)", where "xxx"
2986 # is the area code in question.
2987 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2988 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]2989 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]2990 },
2991 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
2992 "pattern": "A String", # Pattern defining the regular expression. Its syntax
2993 # (https://github.com/google/re2/wiki/Syntax) can be found under the
2994 # google/re2 repository on GitHub.
2995 "groupIndexes": [ # The index of the submatch to extract as findings. When not
2996 # specified, the entire match is returned. No more than 3 may be included.
2997 42,
2998 ],
2999 },
3000 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
3001 # part of a detection rule.
3002 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
3003 # levels. For example, if a finding would be `POSSIBLE` without the
3004 # detection rule and `relative_likelihood` is 1, then it is upgraded to
3005 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
3006 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
3007 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
3008 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
3009 # a final likelihood of `LIKELY`.
3010 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
3011 },
3012 },
3013 },
3014 ],
3015 "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding
3016 # to be returned. It still can be used for rules matching.
3017 "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be
3018 # altered by a detection rule if the finding meets the criteria specified by
3019 # the rule. Defaults to `VERY_LIKELY` if not specified.
3020 },
3021 ],
3022 "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
3023 # included in the response; see Finding.quote.
3024 "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.
3025 # Exclusion rules, contained in the set are executed in the end, other
3026 # rules are executed in the order they are specified for each info type.
3027 { # Rule set for modifying a set of infoTypes to alter behavior under certain
3028 # circumstances, depending on the specific details of the rules within the set.
3029 "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
3030 { # A single inspection rule to be applied to infoTypes, specified in
3031 # `InspectionRuleSet`.
3032 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
3033 # proximity of hotwords.
3034 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
3035 # The total length of the window cannot exceed 1000 characters. Note that
3036 # the finding itself will be included in the window, so that hotwords may
3037 # be used to match substrings of the finding itself. For example, the
3038 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
3039 # adjusted upwards if the area code is known to be the local area code of
3040 # a company office using the hotword regex "\(xxx\)", where "xxx"
3041 # is the area code in question.
3042 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3043 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3044 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3045 },
3046 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
3047 "pattern": "A String", # Pattern defining the regular expression. Its syntax
3048 # (https://github.com/google/re2/wiki/Syntax) can be found under the
3049 # google/re2 repository on GitHub.
3050 "groupIndexes": [ # The index of the submatch to extract as findings. When not
3051 # specified, the entire match is returned. No more than 3 may be included.
3052 42,
3053 ],
3054 },
3055 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
3056 # part of a detection rule.
3057 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
3058 # levels. For example, if a finding would be `POSSIBLE` without the
3059 # detection rule and `relative_likelihood` is 1, then it is upgraded to
3060 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
3061 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
3062 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
3063 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
3064 # a final likelihood of `LIKELY`.
3065 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
3066 },
3067 },
3068 "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
3069 # `InspectionRuleSet` are removed from results.
3070 "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
3071 "pattern": "A String", # Pattern defining the regular expression. Its syntax
3072 # (https://github.com/google/re2/wiki/Syntax) can be found under the
3073 # google/re2 repository on GitHub.
3074 "groupIndexes": [ # The index of the submatch to extract as findings. When not
3075 # specified, the entire match is returned. No more than 3 may be included.
3076 42,
3077 ],
3078 },
3079 "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.
3080 "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or
3081 # contained within with a finding of an infoType from this list. For
3082 # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and
3083 # `exclusion_rule` containing `exclude_info_types.info_types` with
3084 # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap
3085 # with EMAIL_ADDRESS finding.
3086 # That leads to "555-222-2222@example.org" to generate only a single
3087 # finding, namely email address.
3088 { # Type of information detected by the API.
3089 "name": "A String", # Name of the information type. Either a name of your choosing when
3090 # creating a CustomInfoType, or one of the names listed
3091 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
3092 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3093 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3094 },
3095 ],
3096 },
3097 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
3098 # be used to match sensitive information specific to the data, such as a list
3099 # of employee IDs or job titles.
3100 #
3101 # Dictionary words are case-insensitive and all characters other than letters
3102 # and digits in the unicode [Basic Multilingual
3103 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
3104 # will be replaced with whitespace when scanning for matches, so the
3105 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
3106 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
3107 # surrounding any match must be of a different type than the adjacent
3108 # characters within the word, so letters must be next to non-letters and
3109 # digits next to non-digits. For example, the dictionary word "jen" will
3110 # match the first three letters of the text "jen123" but will return no
3111 # matches for "jennifer".
3112 #
3113 # Dictionary words containing a large number of characters that are not
3114 # letters or digits may result in unexpected findings because such characters
3115 # are treated as whitespace. The
3116 # [limits](https://cloud.google.com/dlp/limits) page contains details about
3117 # the size limits of dictionaries. For dictionaries that do not fit within
3118 # these constraints, consider using `LargeCustomDictionaryConfig` in the
3119 # `StoredInfoType` API.
3120 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
3121 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
3122 # at least one phrase and every phrase must contain at least 2 characters
3123 # that are letters or digits. [required]
3124 "A String",
3125 ],
3126 },
3127 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
3128 # is accepted.
3129 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
3130 # Example: gs://[BUCKET_NAME]/dictionary.txt
3131 },
3132 },
3133 "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
3134 },
3135 },
3136 ],
3137 "infoTypes": [ # List of infoTypes this rule set is applied to.
3138 { # Type of information detected by the API.
3139 "name": "A String", # Name of the information type. Either a name of your choosing when
3140 # creating a CustomInfoType, or one of the names listed
3141 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
3142 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3143 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3144 },
3145 ],
3146 },
3147 ],
3148 "contentOptions": [ # List of options defining data content to scan.
3149 # If empty, text, images, and other content will be included.
3150 "A String",
3151 ],
3152 "infoTypes": [ # Restricts what info_types to look for. The values must correspond to
3153 # InfoType values returned by ListInfoTypes or listed at
3154 # https://cloud.google.com/dlp/docs/infotypes-reference.
3155 #
3156 # When no InfoTypes or CustomInfoTypes are specified in a request, the
3157 # system may automatically choose what detectors to run. By default this may
3158 # be all types, but may change over time as detectors are updated.
3159 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3160 # If you need precise control and predictability as to what detectors are
3161 # run you should specify specific InfoTypes listed in the reference,
3162 # otherwise a default list will be used, which may change over time.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3163 { # Type of information detected by the API.
3164 "name": "A String", # Name of the information type. Either a name of your choosing when
3165 # creating a CustomInfoType, or one of the names listed
3166 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
3167 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3168 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3169 },
3170 ],
3171 },
3172 "inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.
3173 # `inspect_config` will be merged into the values persisted as part of the
3174 # template.
3175 "actions": [ # Actions to execute at the completion of the job.
3176 { # A task to execute on the completion of a job.
3177 # See https://cloud.google.com/dlp/docs/concepts-actions to learn more.
3178 "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
3179 # OutputStorageConfig. Only a single instance of this action can be
3180 # specified.
3181 # Compatible with: Inspect, Risk
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3182 "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3183 "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
3184 # dataset. If table_id is not set a new one will be generated
3185 # for you with the following format:
3186 # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for
3187 # generating the date details.
3188 #
3189 # For Inspect, each column in an existing output table must have the same
3190 # name, type, and mode of a field in the `Finding` object.
3191 #
3192 # For Risk, an existing output table should be the output of a previous
3193 # Risk analysis job run on the same source table, with the same privacy
3194 # metric and quasi-identifiers. Risk jobs that analyze the same table but
3195 # compute a different privacy metric, or use different sets of
3196 # quasi-identifiers, cannot store their results in the same table.
3197 # identified by its project_id, dataset_id, and table_name. Within a query
3198 # a table is often referenced with a string in the format of:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3199 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
3200 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3201 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
3202 # If omitted, project ID is inferred from the API call.
3203 "tableId": "A String", # Name of the table.
3204 "datasetId": "A String", # Dataset ID of the table.
3205 },
3206 "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only
3207 # used for Inspect and must be unspecified for Risk jobs. Columns are derived
3208 # from the `Finding` object. If appending to an existing table, any columns
3209 # from the predefined schema that are missing will be added. No columns in
3210 # the existing table will be deleted.
3211 #
3212 # If unspecified, then all available columns will be used for a new table or
3213 # an (existing) table with no schema, and no changes will be made to an
3214 # existing table that has a schema.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3215 # Only for use with external storage.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3216 },
3217 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3218 "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3219 # completion/failure.
3220 # completion/failure.
3221 },
3222 "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
3223 # Command Center (CSCC Alpha).
3224 # This action is only available for projects which are parts of
3225 # an organization and whitelisted for the alpha Cloud Security Command
3226 # Center.
3227 # The action will publish count of finding instances and their info types.
3228 # The summary of findings will be persisted in CSCC and are governed by CSCC
3229 # service-specific policy, see https://cloud.google.com/terms/service-terms
3230 # Only a single instance of this action can be specified.
3231 # Compatible with: Inspect
3232 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3233 "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.
3234 # will publish a metric to stack driver on each infotype requested and
3235 # how many findings were found for it. CustomDetectors will be bucketed
3236 # as 'Custom' under the Stackdriver label 'info_type'.
3237 },
3238 "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.
3239 # results of the DlpJob will be applied to the entry for the resource scanned
3240 # in Cloud Data Catalog. Any labels previously written by another DlpJob will
3241 # be deleted. InfoType naming patterns are strictly enforced when using this
3242 # feature. Note that the findings will be persisted in Cloud Data Catalog
3243 # storage and are governed by Data Catalog service-specific policy, see
3244 # https://cloud.google.com/terms/service-terms
3245 # Only a single instance of this action can be specified and only allowed if
3246 # all resources being scanned are BigQuery tables.
3247 # Compatible with: Inspect
3248 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3249 "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
3250 # message contains a single field, `DlpJobName`, which is equal to the
3251 # finished job's
3252 # [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
3253 # Compatible with: Inspect, Risk
3254 "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given
3255 # publishing access rights to the DLP API service account executing
3256 # the long running DlpJob sending the notifications.
3257 # Format is projects/{project}/topics/{topic}.
3258 },
3259 },
3260 ],
3261 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3262 "lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
3263 "createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3264 "name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the
3265 # triggeredJob is created, for example
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3266 # `projects/dlp-test-project/jobTriggers/53234423`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3267 }</pre>
3268</div>
3269
3270<div class="method">
3271 <code class="details" id="delete">delete(name, x__xgafv=None)</code>
3272 <pre>Deletes a job trigger.
3273See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.
3274
3275Args:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3276 name: string, Required. Resource name of the project and the triggeredJob, for example
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3277`projects/dlp-test-project/jobTriggers/53234423`. (required)
3278 x__xgafv: string, V1 error format.
3279 Allowed values
3280 1 - v1 error format
3281 2 - v2 error format
3282
3283Returns:
3284 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 `{}`.
3295 }</pre>
3296</div>
3297
3298<div class="method">
3299 <code class="details" id="get">get(name, x__xgafv=None)</code>
3300 <pre>Gets a job trigger.
3301See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.
3302
3303Args:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3304 name: string, Required. Resource name of the project and the triggeredJob, for example
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3305`projects/dlp-test-project/jobTriggers/53234423`. (required)
3306 x__xgafv: string, V1 error format.
3307 Allowed values
3308 1 - v1 error format
3309 2 - v2 error format
3310
3311Returns:
3312 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.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3316 "status": "A String", # Required. A status for this trigger.
3317 "updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
3318 "errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3319 # errors may result in the JobTrigger automatically being paused.
3320 # Will return the last 100 errors. Whenever the JobTrigger is modified
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3321 # this list will be cleared.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3322 { # Details information about an error encountered during job execution or
3323 # the results of an unsuccessful activation of the JobTrigger.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3324 "timestamps": [ # The times the error occurred.
3325 "A String",
3326 ],
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3327 "details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3328 # different programming environments, including REST APIs and RPC APIs. It is
3329 # used by [gRPC](https://github.com/grpc). Each `Status` message contains
3330 # three pieces of data: error code, error message, and error details.
3331 #
3332 # You can find out more about this error model and how to work with it in the
3333 # [API Design Guide](https://cloud.google.com/apis/design/errors).
3334 "message": "A String", # A developer-facing error message, which should be in English. Any
3335 # user-facing error message should be localized and sent in the
3336 # google.rpc.Status.details field, or localized by the client.
3337 "code": 42, # The status code, which should be an enum value of google.rpc.Code.
3338 "details": [ # A list of messages that carry the error details. There is a common set of
3339 # message types for APIs to use.
3340 {
3341 "a_key": "", # Properties of the object. Contains field @type with type URL.
3342 },
3343 ],
3344 },
3345 },
3346 ],
3347 "displayName": "A String", # Display name (max 100 chars)
3348 "description": "A String", # User provided description (max 256 chars)
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3349 "triggers": [ # A list of triggers which will be OR'ed together. Only one in the list
3350 # needs to trigger for a job to be started. The list may contain only
3351 # a single Schedule trigger and must have at least one object.
3352 { # What event needs to occur for a new job to be started.
3353 "manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.
3354 # Early access feature is in a pre-release state and might change or have
3355 # limited support. For more information, see
3356 # https://cloud.google.com/products#product-launch-stages.
3357 # and finished.
3358 },
3359 "schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.
3360 "recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For
3361 # example: every day (86400 seconds).
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3362 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3363 # A scheduled start time will be skipped if the previous
3364 # execution has not ended when its scheduled time occurs.
3365 #
3366 # This value must be set to a time duration greater than or equal
3367 # to 1 day and can be no longer than 60 days.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3368 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3369 },
3370 ],
3371 "inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
3372 "storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
3373 "cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3374 # bucket.
3375 "bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger
3376 # than this value then the rest of the bytes are omitted. Only one
3377 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
3378 "sampleMethod": "A String",
3379 "fileSet": { # Set of files to scan. # The set of one or more files to scan.
3380 "url": "A String", # The Cloud Storage url of the file(s) to scan, in the format
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3381 # `gs://&lt;bucket&gt;/&lt;path&gt;`. Trailing wildcard in the path is allowed.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3382 #
3383 # If the url ends in a trailing slash, the bucket or directory represented
3384 # by the url will be scanned non-recursively (content in sub-directories
3385 # will not be scanned). This means that `gs://mybucket/` is equivalent to
3386 # `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
3387 # `gs://mybucket/directory/*`.
3388 #
3389 # Exactly one of `url` or `regex_file_set` must be set.
3390 "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
3391 # `regex_file_set` must be set.
3392 # expressions are used to allow fine-grained control over which files in the
3393 # bucket to include.
3394 #
3395 # Included files are those that match at least one item in `include_regex` and
3396 # do not match any items in `exclude_regex`. Note that a file that matches
3397 # items from both lists will _not_ be included. For a match to occur, the
3398 # entire file path (i.e., everything in the url after the bucket name) must
3399 # match the regular expression.
3400 #
3401 # For example, given the input `{bucket_name: "mybucket", include_regex:
3402 # ["directory1/.*"], exclude_regex:
3403 # ["directory1/excluded.*"]}`:
3404 #
3405 # * `gs://mybucket/directory1/myfile` will be included
3406 # * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches
3407 # across `/`)
3408 # * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the
3409 # full path doesn't match any items in `include_regex`)
3410 # * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path
3411 # matches an item in `exclude_regex`)
3412 #
3413 # If `include_regex` is left empty, it will match all files by default
3414 # (this is equivalent to setting `include_regex: [".*"]`).
3415 #
3416 # Some other common use cases:
3417 #
3418 # * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all
3419 # files in `mybucket` except for .pdf files
3420 # * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will
3421 # include all files directly under `gs://mybucket/directory/`, without matching
3422 # across `/`
3423 "excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in
3424 # the bucket that match at least one of these regular expressions will be
3425 # excluded from the scan.
3426 #
3427 # Regular expressions use RE2
3428 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
3429 # under the google/re2 repository on GitHub.
3430 "A String",
3431 ],
3432 "bucketName": "A String", # The name of a Cloud Storage bucket. Required.
3433 "includeRegex": [ # A list of regular expressions matching file paths to include. All files in
3434 # the bucket that match at least one of these regular expressions will be
3435 # included in the set of files, except for those that also match an item in
3436 # `exclude_regex`. Leaving this field empty will match all files by default
3437 # (this is equivalent to including `.*` in the list).
3438 #
3439 # Regular expressions use RE2
3440 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
3441 # under the google/re2 repository on GitHub.
3442 "A String",
3443 ],
3444 },
3445 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3446 "filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.
3447 # Number of files scanned is rounded down. Must be between 0 and 100,
3448 # inclusively. Both 0 and 100 means no limit. Defaults to 0.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3449 "bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The
3450 # number of bytes scanned is rounded down. Must be between 0 and 100,
3451 # inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one
3452 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3453 "fileTypes": [ # List of file type groups to include in the scan.
3454 # If empty, all files are scanned and available data format processors
3455 # are applied. In addition, the binary content of the selected files
3456 # is always scanned as well.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3457 # Images are scanned only as binary if the specified region
3458 # does not support image inspection and no file_types were specified.
3459 # Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3460 "A String",
3461 ],
3462 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3463 "datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
3464 "partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always
3465 # by project and namespace, however the namespace ID may be empty.
3466 # A partition ID identifies a grouping of entities. The grouping is always
3467 # by project and namespace, however the namespace ID may be empty.
3468 #
3469 # A partition ID contains several dimensions:
3470 # project ID and namespace ID.
3471 "projectId": "A String", # The ID of the project to which the entities belong.
3472 "namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
3473 },
3474 "kind": { # A representation of a Datastore kind. # The kind to process.
3475 "name": "A String", # The name of the kind.
3476 },
3477 },
3478 "bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
3479 "excludedFields": [ # References to fields excluded from scanning. This allows you to skip
3480 # inspection of entire columns which you know have no findings.
3481 { # General identifier of a data field in a storage service.
3482 "name": "A String", # Name describing the field.
3483 },
3484 ],
3485 "rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the
3486 # rest of the rows are omitted. If not set, or if set to 0, all rows will be
3487 # scanned. Only one of rows_limit and rows_limit_percent can be specified.
3488 # Cannot be used in conjunction with TimespanConfig.
3489 "sampleMethod": "A String",
3490 "identifyingFields": [ # Table fields that may uniquely identify a row within the table. When
3491 # `actions.saveFindings.outputConfig.table` is specified, the values of
3492 # columns specified here are available in the output table under
3493 # `location.content_locations.record_location.record_key.id_values`. Nested
3494 # fields such as `person.birthdate.year` are allowed.
3495 { # General identifier of a data field in a storage service.
3496 "name": "A String", # Name describing the field.
3497 },
3498 ],
3499 "rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows
3500 # scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and
3501 # 100 means no limit. Defaults to 0. Only one of rows_limit and
3502 # rows_limit_percent can be specified. Cannot be used in conjunction with
3503 # TimespanConfig.
3504 "tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.
3505 # identified by its project_id, dataset_id, and table_name. Within a query
3506 # a table is often referenced with a string in the format of:
3507 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
3508 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
3509 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
3510 # If omitted, project ID is inferred from the API call.
3511 "tableId": "A String", # Name of the table.
3512 "datasetId": "A String", # Dataset ID of the table.
3513 },
3514 },
3515 "timespanConfig": { # Configuration of the timespan of the items to include in scanning.
3516 # Currently only supported when inspecting Google Cloud Storage and BigQuery.
3517 "timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.
3518 # Used for data sources like Datastore and BigQuery.
3519 #
3520 # For BigQuery:
3521 # Required to filter out rows based on the given start and
3522 # end times. If not specified and the table was modified between the given
3523 # start and end times, the entire table will be scanned.
3524 # The valid data types of the timestamp field are: `INTEGER`, `DATE`,
3525 # `TIMESTAMP`, or `DATETIME` BigQuery column.
3526 #
3527 # For Datastore.
3528 # Valid data types of the timestamp field are: `TIMESTAMP`.
3529 # Datastore entity will be scanned if the timestamp property does not
3530 # exist or its value is empty or invalid.
3531 "name": "A String", # Name describing the field.
3532 },
3533 "endTime": "A String", # Exclude files or rows newer than this value.
3534 # If set to zero, no upper time limit is applied.
3535 "startTime": "A String", # Exclude files or rows older than this value.
3536 "enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out
3537 # a valid start_time to avoid scanning files that have not been modified
3538 # since the last time the JobTrigger executed. This will be based on the
3539 # time of the execution of the last run of the JobTrigger.
3540 },
3541 "hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.
3542 # Early access feature is in a pre-release state and might change or have
3543 # limited support. For more information, see
3544 # https://cloud.google.com/products#product-launch-stages.
3545 # of Google Cloud Platform.
3546 "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings
3547 # meaningful such as the columns that are primary keys.
3548 "identifyingFields": [ # The columns that are the primary keys for table objects included in
3549 # ContentItem. A copy of this cell's value will stored alongside alongside
3550 # each finding so that the finding can be traced to the specific row it came
3551 # from. No more than 3 may be provided.
3552 { # General identifier of a data field in a storage service.
3553 "name": "A String", # Name describing the field.
3554 },
3555 ],
3556 },
3557 "labels": { # To organize findings, these labels will be added to each finding.
3558 #
3559 # Label keys must be between 1 and 63 characters long and must conform
3560 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
3561 #
3562 # Label values must be between 0 and 63 characters long and must conform
3563 # to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.
3564 #
3565 # No more than 10 labels can be associated with a given finding.
3566 #
3567 # Examples:
3568 # * `"environment" : "production"`
3569 # * `"pipeline" : "etl"`
3570 "a_key": "A String",
3571 },
3572 "requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their
3573 # 'finding_labels' map. Request may contain others, but any missing one of
3574 # these will be rejected.
3575 #
3576 # Label keys must be between 1 and 63 characters long and must conform
3577 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
3578 #
3579 # No more than 10 keys can be required.
3580 "A String",
3581 ],
3582 "description": "A String", # A short description of where the data is coming from. Will be stored once
3583 # in the job. 256 max length.
3584 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3585 },
3586 "inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.
3587 # When used with redactContent only info_types and min_likelihood are currently
3588 # used.
3589 "excludeInfoTypes": True or False, # When true, excludes type information of the findings.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3590 "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3591 "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
3592 # When set within `InspectContentRequest`, the maximum returned is 2000
3593 # regardless if this is set higher.
3594 "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
3595 { # Max findings configuration per infoType, per content item or long
3596 # running DlpJob.
3597 "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per
3598 # info_type should be provided. If InfoTypeLimit does not have an
3599 # info_type, the DLP API applies the limit against all info_types that
3600 # are found but not specified in another InfoTypeLimit.
3601 "name": "A String", # Name of the information type. Either a name of your choosing when
3602 # creating a CustomInfoType, or one of the names listed
3603 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
3604 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3605 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3606 },
3607 "maxFindings": 42, # Max findings limit for the given infoType.
3608 },
3609 ],
3610 "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3611 # When set within `InspectJobConfig`,
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3612 # the maximum returned is 2000 regardless if this is set higher.
3613 # When set within `InspectContentRequest`, this field is ignored.
3614 },
3615 "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
3616 # POSSIBLE.
3617 # See https://cloud.google.com/dlp/docs/likelihood to learn more.
3618 "customInfoTypes": [ # CustomInfoTypes provided by the user. See
3619 # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.
3620 { # Custom information type provided by the user. Used to find domain-specific
3621 # sensitive information configurable to the data in question.
3622 "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
3623 "pattern": "A String", # Pattern defining the regular expression. Its syntax
3624 # (https://github.com/google/re2/wiki/Syntax) can be found under the
3625 # google/re2 repository on GitHub.
3626 "groupIndexes": [ # The index of the submatch to extract as findings. When not
3627 # specified, the entire match is returned. No more than 3 may be included.
3628 42,
3629 ],
3630 },
3631 "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
3632 # support reversing.
3633 # such as
3634 # [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).
3635 # These types of transformations are
3636 # those that perform pseudonymization, thereby producing a "surrogate" as
3637 # output. This should be used in conjunction with a field on the
3638 # transformation such as `surrogate_info_type`. This CustomInfoType does
3639 # not support the use of `detection_rules`.
3640 },
3641 "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in
3642 # infoType, when the name matches one of existing infoTypes and that infoType
3643 # is specified in `InspectContent.info_types` field. Specifying the latter
3644 # adds findings to the one detected by the system. If built-in info type is
3645 # not specified in `InspectContent.info_types` list then the name is treated
3646 # as a custom info type.
3647 "name": "A String", # Name of the information type. Either a name of your choosing when
3648 # creating a CustomInfoType, or one of the names listed
3649 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
3650 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3651 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3652 },
3653 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
3654 # be used to match sensitive information specific to the data, such as a list
3655 # of employee IDs or job titles.
3656 #
3657 # Dictionary words are case-insensitive and all characters other than letters
3658 # and digits in the unicode [Basic Multilingual
3659 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
3660 # will be replaced with whitespace when scanning for matches, so the
3661 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
3662 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
3663 # surrounding any match must be of a different type than the adjacent
3664 # characters within the word, so letters must be next to non-letters and
3665 # digits next to non-digits. For example, the dictionary word "jen" will
3666 # match the first three letters of the text "jen123" but will return no
3667 # matches for "jennifer".
3668 #
3669 # Dictionary words containing a large number of characters that are not
3670 # letters or digits may result in unexpected findings because such characters
3671 # are treated as whitespace. The
3672 # [limits](https://cloud.google.com/dlp/limits) page contains details about
3673 # the size limits of dictionaries. For dictionaries that do not fit within
3674 # these constraints, consider using `LargeCustomDictionaryConfig` in the
3675 # `StoredInfoType` API.
3676 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
3677 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
3678 # at least one phrase and every phrase must contain at least 2 characters
3679 # that are letters or digits. [required]
3680 "A String",
3681 ],
3682 },
3683 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
3684 # is accepted.
3685 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
3686 # Example: gs://[BUCKET_NAME]/dictionary.txt
3687 },
3688 },
3689 "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
3690 # `InspectDataSource`. Not currently supported in `InspectContent`.
3691 "name": "A String", # Resource name of the requested `StoredInfoType`, for example
3692 # `organizations/433245324/storedInfoTypes/432452342` or
3693 # `projects/project-id/storedInfoTypes/432452342`.
3694 "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
3695 # inspection was created. Output-only field, populated by the system.
3696 },
3697 "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.
3698 # Rules are applied in order that they are specified. Not supported for the
3699 # `surrogate_type` CustomInfoType.
3700 { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a
3701 # `CustomInfoType` to alter behavior under certain circumstances, depending
3702 # on the specific details of the rule. Not supported for the `surrogate_type`
3703 # custom infoType.
3704 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
3705 # proximity of hotwords.
3706 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
3707 # The total length of the window cannot exceed 1000 characters. Note that
3708 # the finding itself will be included in the window, so that hotwords may
3709 # be used to match substrings of the finding itself. For example, the
3710 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
3711 # adjusted upwards if the area code is known to be the local area code of
3712 # a company office using the hotword regex "\(xxx\)", where "xxx"
3713 # is the area code in question.
3714 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3715 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3716 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3717 },
3718 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
3719 "pattern": "A String", # Pattern defining the regular expression. Its syntax
3720 # (https://github.com/google/re2/wiki/Syntax) can be found under the
3721 # google/re2 repository on GitHub.
3722 "groupIndexes": [ # The index of the submatch to extract as findings. When not
3723 # specified, the entire match is returned. No more than 3 may be included.
3724 42,
3725 ],
3726 },
3727 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
3728 # part of a detection rule.
3729 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
3730 # levels. For example, if a finding would be `POSSIBLE` without the
3731 # detection rule and `relative_likelihood` is 1, then it is upgraded to
3732 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
3733 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
3734 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
3735 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
3736 # a final likelihood of `LIKELY`.
3737 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
3738 },
3739 },
3740 },
3741 ],
3742 "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding
3743 # to be returned. It still can be used for rules matching.
3744 "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be
3745 # altered by a detection rule if the finding meets the criteria specified by
3746 # the rule. Defaults to `VERY_LIKELY` if not specified.
3747 },
3748 ],
3749 "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
3750 # included in the response; see Finding.quote.
3751 "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.
3752 # Exclusion rules, contained in the set are executed in the end, other
3753 # rules are executed in the order they are specified for each info type.
3754 { # Rule set for modifying a set of infoTypes to alter behavior under certain
3755 # circumstances, depending on the specific details of the rules within the set.
3756 "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
3757 { # A single inspection rule to be applied to infoTypes, specified in
3758 # `InspectionRuleSet`.
3759 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
3760 # proximity of hotwords.
3761 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
3762 # The total length of the window cannot exceed 1000 characters. Note that
3763 # the finding itself will be included in the window, so that hotwords may
3764 # be used to match substrings of the finding itself. For example, the
3765 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
3766 # adjusted upwards if the area code is known to be the local area code of
3767 # a company office using the hotword regex "\(xxx\)", where "xxx"
3768 # is the area code in question.
3769 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3770 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3771 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3772 },
3773 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
3774 "pattern": "A String", # Pattern defining the regular expression. Its syntax
3775 # (https://github.com/google/re2/wiki/Syntax) can be found under the
3776 # google/re2 repository on GitHub.
3777 "groupIndexes": [ # The index of the submatch to extract as findings. When not
3778 # specified, the entire match is returned. No more than 3 may be included.
3779 42,
3780 ],
3781 },
3782 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
3783 # part of a detection rule.
3784 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
3785 # levels. For example, if a finding would be `POSSIBLE` without the
3786 # detection rule and `relative_likelihood` is 1, then it is upgraded to
3787 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
3788 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
3789 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
3790 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
3791 # a final likelihood of `LIKELY`.
3792 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
3793 },
3794 },
3795 "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
3796 # `InspectionRuleSet` are removed from results.
3797 "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
3798 "pattern": "A String", # Pattern defining the regular expression. Its syntax
3799 # (https://github.com/google/re2/wiki/Syntax) can be found under the
3800 # google/re2 repository on GitHub.
3801 "groupIndexes": [ # The index of the submatch to extract as findings. When not
3802 # specified, the entire match is returned. No more than 3 may be included.
3803 42,
3804 ],
3805 },
3806 "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.
3807 "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or
3808 # contained within with a finding of an infoType from this list. For
3809 # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and
3810 # `exclusion_rule` containing `exclude_info_types.info_types` with
3811 # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap
3812 # with EMAIL_ADDRESS finding.
3813 # That leads to "555-222-2222@example.org" to generate only a single
3814 # finding, namely email address.
3815 { # Type of information detected by the API.
3816 "name": "A String", # Name of the information type. Either a name of your choosing when
3817 # creating a CustomInfoType, or one of the names listed
3818 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
3819 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3820 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3821 },
3822 ],
3823 },
3824 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
3825 # be used to match sensitive information specific to the data, such as a list
3826 # of employee IDs or job titles.
3827 #
3828 # Dictionary words are case-insensitive and all characters other than letters
3829 # and digits in the unicode [Basic Multilingual
3830 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
3831 # will be replaced with whitespace when scanning for matches, so the
3832 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
3833 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
3834 # surrounding any match must be of a different type than the adjacent
3835 # characters within the word, so letters must be next to non-letters and
3836 # digits next to non-digits. For example, the dictionary word "jen" will
3837 # match the first three letters of the text "jen123" but will return no
3838 # matches for "jennifer".
3839 #
3840 # Dictionary words containing a large number of characters that are not
3841 # letters or digits may result in unexpected findings because such characters
3842 # are treated as whitespace. The
3843 # [limits](https://cloud.google.com/dlp/limits) page contains details about
3844 # the size limits of dictionaries. For dictionaries that do not fit within
3845 # these constraints, consider using `LargeCustomDictionaryConfig` in the
3846 # `StoredInfoType` API.
3847 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
3848 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
3849 # at least one phrase and every phrase must contain at least 2 characters
3850 # that are letters or digits. [required]
3851 "A String",
3852 ],
3853 },
3854 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
3855 # is accepted.
3856 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
3857 # Example: gs://[BUCKET_NAME]/dictionary.txt
3858 },
3859 },
3860 "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
3861 },
3862 },
3863 ],
3864 "infoTypes": [ # List of infoTypes this rule set is applied to.
3865 { # Type of information detected by the API.
3866 "name": "A String", # Name of the information type. Either a name of your choosing when
3867 # creating a CustomInfoType, or one of the names listed
3868 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
3869 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3870 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3871 },
3872 ],
3873 },
3874 ],
3875 "contentOptions": [ # List of options defining data content to scan.
3876 # If empty, text, images, and other content will be included.
3877 "A String",
3878 ],
3879 "infoTypes": [ # Restricts what info_types to look for. The values must correspond to
3880 # InfoType values returned by ListInfoTypes or listed at
3881 # https://cloud.google.com/dlp/docs/infotypes-reference.
3882 #
3883 # When no InfoTypes or CustomInfoTypes are specified in a request, the
3884 # system may automatically choose what detectors to run. By default this may
3885 # be all types, but may change over time as detectors are updated.
3886 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3887 # If you need precise control and predictability as to what detectors are
3888 # run you should specify specific InfoTypes listed in the reference,
3889 # otherwise a default list will be used, which may change over time.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3890 { # Type of information detected by the API.
3891 "name": "A String", # Name of the information type. Either a name of your choosing when
3892 # creating a CustomInfoType, or one of the names listed
3893 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
3894 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3895 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3896 },
3897 ],
3898 },
3899 "inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.
3900 # `inspect_config` will be merged into the values persisted as part of the
3901 # template.
3902 "actions": [ # Actions to execute at the completion of the job.
3903 { # A task to execute on the completion of a job.
3904 # See https://cloud.google.com/dlp/docs/concepts-actions to learn more.
3905 "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
3906 # OutputStorageConfig. Only a single instance of this action can be
3907 # specified.
3908 # Compatible with: Inspect, Risk
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3909 "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3910 "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
3911 # dataset. If table_id is not set a new one will be generated
3912 # for you with the following format:
3913 # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for
3914 # generating the date details.
3915 #
3916 # For Inspect, each column in an existing output table must have the same
3917 # name, type, and mode of a field in the `Finding` object.
3918 #
3919 # For Risk, an existing output table should be the output of a previous
3920 # Risk analysis job run on the same source table, with the same privacy
3921 # metric and quasi-identifiers. Risk jobs that analyze the same table but
3922 # compute a different privacy metric, or use different sets of
3923 # quasi-identifiers, cannot store their results in the same table.
3924 # identified by its project_id, dataset_id, and table_name. Within a query
3925 # a table is often referenced with a string in the format of:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3926 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
3927 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3928 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
3929 # If omitted, project ID is inferred from the API call.
3930 "tableId": "A String", # Name of the table.
3931 "datasetId": "A String", # Dataset ID of the table.
3932 },
3933 "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only
3934 # used for Inspect and must be unspecified for Risk jobs. Columns are derived
3935 # from the `Finding` object. If appending to an existing table, any columns
3936 # from the predefined schema that are missing will be added. No columns in
3937 # the existing table will be deleted.
3938 #
3939 # If unspecified, then all available columns will be used for a new table or
3940 # an (existing) table with no schema, and no changes will be made to an
3941 # existing table that has a schema.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3942 # Only for use with external storage.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3943 },
3944 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3945 "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3946 # completion/failure.
3947 # completion/failure.
3948 },
3949 "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
3950 # Command Center (CSCC Alpha).
3951 # This action is only available for projects which are parts of
3952 # an organization and whitelisted for the alpha Cloud Security Command
3953 # Center.
3954 # The action will publish count of finding instances and their info types.
3955 # The summary of findings will be persisted in CSCC and are governed by CSCC
3956 # service-specific policy, see https://cloud.google.com/terms/service-terms
3957 # Only a single instance of this action can be specified.
3958 # Compatible with: Inspect
3959 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3960 "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.
3961 # will publish a metric to stack driver on each infotype requested and
3962 # how many findings were found for it. CustomDetectors will be bucketed
3963 # as 'Custom' under the Stackdriver label 'info_type'.
3964 },
3965 "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.
3966 # results of the DlpJob will be applied to the entry for the resource scanned
3967 # in Cloud Data Catalog. Any labels previously written by another DlpJob will
3968 # be deleted. InfoType naming patterns are strictly enforced when using this
3969 # feature. Note that the findings will be persisted in Cloud Data Catalog
3970 # storage and are governed by Data Catalog service-specific policy, see
3971 # https://cloud.google.com/terms/service-terms
3972 # Only a single instance of this action can be specified and only allowed if
3973 # all resources being scanned are BigQuery tables.
3974 # Compatible with: Inspect
3975 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3976 "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
3977 # message contains a single field, `DlpJobName`, which is equal to the
3978 # finished job's
3979 # [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
3980 # Compatible with: Inspect, Risk
3981 "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given
3982 # publishing access rights to the DLP API service account executing
3983 # the long running DlpJob sending the notifications.
3984 # Format is projects/{project}/topics/{topic}.
3985 },
3986 },
3987 ],
3988 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3989 "lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
3990 "createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3991 "name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the
3992 # triggeredJob is created, for example
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3993 # `projects/dlp-test-project/jobTriggers/53234423`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3994 }</pre>
3995</div>
3996
3997<div class="method">
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]3998 <code class="details" id="list">list(parent, orderBy=None, pageSize=None, pageToken=None, x__xgafv=None, locationId=None, filter=None)</code>
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]3999 <pre>Lists job triggers.
4000See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.
4001
4002Args:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4003 parent: string, Required. The parent resource name, for example `projects/my-project-id`. (required)
4004 orderBy: string, Comma separated list of triggeredJob fields to order by,
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4005followed by `asc` or `desc` postfix. This list is case-insensitive,
4006default sorting order is ascending, redundant space characters are
4007insignificant.
4008
4009Example: `name asc,update_time, create_time desc`
4010
4011Supported fields are:
4012
4013- `create_time`: corresponds to time the JobTrigger was created.
4014- `update_time`: corresponds to time the JobTrigger was last updated.
4015- `last_run_time`: corresponds to the last time the JobTrigger ran.
4016- `name`: corresponds to JobTrigger's name.
4017- `display_name`: corresponds to JobTrigger's display name.
4018- `status`: corresponds to JobTrigger's status.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4019 pageSize: integer, Size of the page, can be limited by a server.
4020 pageToken: string, Page token to continue retrieval. Comes from previous call
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4021to ListJobTriggers. `order_by` field must not
4022change for subsequent calls.
4023 x__xgafv: string, V1 error format.
4024 Allowed values
4025 1 - v1 error format
4026 2 - v2 error format
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4027 locationId: string, The geographic location where job triggers will be retrieved from.
4028Use `-` for all locations. Reserved for future extensions.
4029 filter: string, Allows filtering.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4030
4031Supported syntax:
4032
4033* Filter expressions are made up of one or more restrictions.
4034* Restrictions can be combined by `AND` or `OR` logical operators. A
4035sequence of restrictions implicitly uses `AND`.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4036* A restriction has the form of `{field} {operator} {value}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4037* Supported fields/values for inspect jobs:
4038 - `status` - HEALTHY|PAUSED|CANCELLED
4039 - `inspected_storage` - DATASTORE|CLOUD_STORAGE|BIGQUERY
4040 - 'last_run_time` - RFC 3339 formatted timestamp, surrounded by
4041 quotation marks. Nanoseconds are ignored.
4042 - 'error_count' - Number of errors that have occurred while running.
4043* The operator must be `=` or `!=` for status and inspected_storage.
4044
4045Examples:
4046
4047* inspected_storage = cloud_storage AND status = HEALTHY
4048* inspected_storage = cloud_storage OR inspected_storage = bigquery
4049* inspected_storage = cloud_storage AND (state = PAUSED OR state = HEALTHY)
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4050* last_run_time &gt; \"2017-12-12T00:00:00+00:00\"
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4051
4052The length of this field should be no more than 500 characters.
4053
4054Returns:
4055 An object of the form:
4056
4057 { # Response message for ListJobTriggers.
4058 "nextPageToken": "A String", # If the next page is available then the next page token to be used
4059 # in following ListJobTriggers request.
4060 "jobTriggers": [ # List of triggeredJobs, up to page_size in ListJobTriggersRequest.
4061 { # Contains a configuration to make dlp api calls on a repeating basis.
4062 # See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4063 "status": "A String", # Required. A status for this trigger.
4064 "updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
4065 "errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4066 # errors may result in the JobTrigger automatically being paused.
4067 # Will return the last 100 errors. Whenever the JobTrigger is modified
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4068 # this list will be cleared.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4069 { # Details information about an error encountered during job execution or
4070 # the results of an unsuccessful activation of the JobTrigger.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4071 "timestamps": [ # The times the error occurred.
4072 "A String",
4073 ],
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4074 "details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4075 # different programming environments, including REST APIs and RPC APIs. It is
4076 # used by [gRPC](https://github.com/grpc). Each `Status` message contains
4077 # three pieces of data: error code, error message, and error details.
4078 #
4079 # You can find out more about this error model and how to work with it in the
4080 # [API Design Guide](https://cloud.google.com/apis/design/errors).
4081 "message": "A String", # A developer-facing error message, which should be in English. Any
4082 # user-facing error message should be localized and sent in the
4083 # google.rpc.Status.details field, or localized by the client.
4084 "code": 42, # The status code, which should be an enum value of google.rpc.Code.
4085 "details": [ # A list of messages that carry the error details. There is a common set of
4086 # message types for APIs to use.
4087 {
4088 "a_key": "", # Properties of the object. Contains field @type with type URL.
4089 },
4090 ],
4091 },
4092 },
4093 ],
4094 "displayName": "A String", # Display name (max 100 chars)
4095 "description": "A String", # User provided description (max 256 chars)
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4096 "triggers": [ # A list of triggers which will be OR'ed together. Only one in the list
4097 # needs to trigger for a job to be started. The list may contain only
4098 # a single Schedule trigger and must have at least one object.
4099 { # What event needs to occur for a new job to be started.
4100 "manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.
4101 # Early access feature is in a pre-release state and might change or have
4102 # limited support. For more information, see
4103 # https://cloud.google.com/products#product-launch-stages.
4104 # and finished.
4105 },
4106 "schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.
4107 "recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For
4108 # example: every day (86400 seconds).
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4109 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4110 # A scheduled start time will be skipped if the previous
4111 # execution has not ended when its scheduled time occurs.
4112 #
4113 # This value must be set to a time duration greater than or equal
4114 # to 1 day and can be no longer than 60 days.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4115 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4116 },
4117 ],
4118 "inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
4119 "storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
4120 "cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4121 # bucket.
4122 "bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger
4123 # than this value then the rest of the bytes are omitted. Only one
4124 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
4125 "sampleMethod": "A String",
4126 "fileSet": { # Set of files to scan. # The set of one or more files to scan.
4127 "url": "A String", # The Cloud Storage url of the file(s) to scan, in the format
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4128 # `gs://&lt;bucket&gt;/&lt;path&gt;`. Trailing wildcard in the path is allowed.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4129 #
4130 # If the url ends in a trailing slash, the bucket or directory represented
4131 # by the url will be scanned non-recursively (content in sub-directories
4132 # will not be scanned). This means that `gs://mybucket/` is equivalent to
4133 # `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
4134 # `gs://mybucket/directory/*`.
4135 #
4136 # Exactly one of `url` or `regex_file_set` must be set.
4137 "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
4138 # `regex_file_set` must be set.
4139 # expressions are used to allow fine-grained control over which files in the
4140 # bucket to include.
4141 #
4142 # Included files are those that match at least one item in `include_regex` and
4143 # do not match any items in `exclude_regex`. Note that a file that matches
4144 # items from both lists will _not_ be included. For a match to occur, the
4145 # entire file path (i.e., everything in the url after the bucket name) must
4146 # match the regular expression.
4147 #
4148 # For example, given the input `{bucket_name: "mybucket", include_regex:
4149 # ["directory1/.*"], exclude_regex:
4150 # ["directory1/excluded.*"]}`:
4151 #
4152 # * `gs://mybucket/directory1/myfile` will be included
4153 # * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches
4154 # across `/`)
4155 # * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the
4156 # full path doesn't match any items in `include_regex`)
4157 # * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path
4158 # matches an item in `exclude_regex`)
4159 #
4160 # If `include_regex` is left empty, it will match all files by default
4161 # (this is equivalent to setting `include_regex: [".*"]`).
4162 #
4163 # Some other common use cases:
4164 #
4165 # * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all
4166 # files in `mybucket` except for .pdf files
4167 # * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will
4168 # include all files directly under `gs://mybucket/directory/`, without matching
4169 # across `/`
4170 "excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in
4171 # the bucket that match at least one of these regular expressions will be
4172 # excluded from the scan.
4173 #
4174 # Regular expressions use RE2
4175 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
4176 # under the google/re2 repository on GitHub.
4177 "A String",
4178 ],
4179 "bucketName": "A String", # The name of a Cloud Storage bucket. Required.
4180 "includeRegex": [ # A list of regular expressions matching file paths to include. All files in
4181 # the bucket that match at least one of these regular expressions will be
4182 # included in the set of files, except for those that also match an item in
4183 # `exclude_regex`. Leaving this field empty will match all files by default
4184 # (this is equivalent to including `.*` in the list).
4185 #
4186 # Regular expressions use RE2
4187 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
4188 # under the google/re2 repository on GitHub.
4189 "A String",
4190 ],
4191 },
4192 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4193 "filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.
4194 # Number of files scanned is rounded down. Must be between 0 and 100,
4195 # inclusively. Both 0 and 100 means no limit. Defaults to 0.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4196 "bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The
4197 # number of bytes scanned is rounded down. Must be between 0 and 100,
4198 # inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one
4199 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4200 "fileTypes": [ # List of file type groups to include in the scan.
4201 # If empty, all files are scanned and available data format processors
4202 # are applied. In addition, the binary content of the selected files
4203 # is always scanned as well.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4204 # Images are scanned only as binary if the specified region
4205 # does not support image inspection and no file_types were specified.
4206 # Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4207 "A String",
4208 ],
4209 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4210 "datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
4211 "partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always
4212 # by project and namespace, however the namespace ID may be empty.
4213 # A partition ID identifies a grouping of entities. The grouping is always
4214 # by project and namespace, however the namespace ID may be empty.
4215 #
4216 # A partition ID contains several dimensions:
4217 # project ID and namespace ID.
4218 "projectId": "A String", # The ID of the project to which the entities belong.
4219 "namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
4220 },
4221 "kind": { # A representation of a Datastore kind. # The kind to process.
4222 "name": "A String", # The name of the kind.
4223 },
4224 },
4225 "bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
4226 "excludedFields": [ # References to fields excluded from scanning. This allows you to skip
4227 # inspection of entire columns which you know have no findings.
4228 { # General identifier of a data field in a storage service.
4229 "name": "A String", # Name describing the field.
4230 },
4231 ],
4232 "rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the
4233 # rest of the rows are omitted. If not set, or if set to 0, all rows will be
4234 # scanned. Only one of rows_limit and rows_limit_percent can be specified.
4235 # Cannot be used in conjunction with TimespanConfig.
4236 "sampleMethod": "A String",
4237 "identifyingFields": [ # Table fields that may uniquely identify a row within the table. When
4238 # `actions.saveFindings.outputConfig.table` is specified, the values of
4239 # columns specified here are available in the output table under
4240 # `location.content_locations.record_location.record_key.id_values`. Nested
4241 # fields such as `person.birthdate.year` are allowed.
4242 { # General identifier of a data field in a storage service.
4243 "name": "A String", # Name describing the field.
4244 },
4245 ],
4246 "rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows
4247 # scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and
4248 # 100 means no limit. Defaults to 0. Only one of rows_limit and
4249 # rows_limit_percent can be specified. Cannot be used in conjunction with
4250 # TimespanConfig.
4251 "tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.
4252 # identified by its project_id, dataset_id, and table_name. Within a query
4253 # a table is often referenced with a string in the format of:
4254 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
4255 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
4256 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
4257 # If omitted, project ID is inferred from the API call.
4258 "tableId": "A String", # Name of the table.
4259 "datasetId": "A String", # Dataset ID of the table.
4260 },
4261 },
4262 "timespanConfig": { # Configuration of the timespan of the items to include in scanning.
4263 # Currently only supported when inspecting Google Cloud Storage and BigQuery.
4264 "timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.
4265 # Used for data sources like Datastore and BigQuery.
4266 #
4267 # For BigQuery:
4268 # Required to filter out rows based on the given start and
4269 # end times. If not specified and the table was modified between the given
4270 # start and end times, the entire table will be scanned.
4271 # The valid data types of the timestamp field are: `INTEGER`, `DATE`,
4272 # `TIMESTAMP`, or `DATETIME` BigQuery column.
4273 #
4274 # For Datastore.
4275 # Valid data types of the timestamp field are: `TIMESTAMP`.
4276 # Datastore entity will be scanned if the timestamp property does not
4277 # exist or its value is empty or invalid.
4278 "name": "A String", # Name describing the field.
4279 },
4280 "endTime": "A String", # Exclude files or rows newer than this value.
4281 # If set to zero, no upper time limit is applied.
4282 "startTime": "A String", # Exclude files or rows older than this value.
4283 "enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out
4284 # a valid start_time to avoid scanning files that have not been modified
4285 # since the last time the JobTrigger executed. This will be based on the
4286 # time of the execution of the last run of the JobTrigger.
4287 },
4288 "hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.
4289 # Early access feature is in a pre-release state and might change or have
4290 # limited support. For more information, see
4291 # https://cloud.google.com/products#product-launch-stages.
4292 # of Google Cloud Platform.
4293 "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings
4294 # meaningful such as the columns that are primary keys.
4295 "identifyingFields": [ # The columns that are the primary keys for table objects included in
4296 # ContentItem. A copy of this cell's value will stored alongside alongside
4297 # each finding so that the finding can be traced to the specific row it came
4298 # from. No more than 3 may be provided.
4299 { # General identifier of a data field in a storage service.
4300 "name": "A String", # Name describing the field.
4301 },
4302 ],
4303 },
4304 "labels": { # To organize findings, these labels will be added to each finding.
4305 #
4306 # Label keys must be between 1 and 63 characters long and must conform
4307 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
4308 #
4309 # Label values must be between 0 and 63 characters long and must conform
4310 # to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.
4311 #
4312 # No more than 10 labels can be associated with a given finding.
4313 #
4314 # Examples:
4315 # * `"environment" : "production"`
4316 # * `"pipeline" : "etl"`
4317 "a_key": "A String",
4318 },
4319 "requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their
4320 # 'finding_labels' map. Request may contain others, but any missing one of
4321 # these will be rejected.
4322 #
4323 # Label keys must be between 1 and 63 characters long and must conform
4324 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
4325 #
4326 # No more than 10 keys can be required.
4327 "A String",
4328 ],
4329 "description": "A String", # A short description of where the data is coming from. Will be stored once
4330 # in the job. 256 max length.
4331 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4332 },
4333 "inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.
4334 # When used with redactContent only info_types and min_likelihood are currently
4335 # used.
4336 "excludeInfoTypes": True or False, # When true, excludes type information of the findings.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4337 "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4338 "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
4339 # When set within `InspectContentRequest`, the maximum returned is 2000
4340 # regardless if this is set higher.
4341 "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
4342 { # Max findings configuration per infoType, per content item or long
4343 # running DlpJob.
4344 "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per
4345 # info_type should be provided. If InfoTypeLimit does not have an
4346 # info_type, the DLP API applies the limit against all info_types that
4347 # are found but not specified in another InfoTypeLimit.
4348 "name": "A String", # Name of the information type. Either a name of your choosing when
4349 # creating a CustomInfoType, or one of the names listed
4350 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
4351 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4352 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4353 },
4354 "maxFindings": 42, # Max findings limit for the given infoType.
4355 },
4356 ],
4357 "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4358 # When set within `InspectJobConfig`,
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4359 # the maximum returned is 2000 regardless if this is set higher.
4360 # When set within `InspectContentRequest`, this field is ignored.
4361 },
4362 "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
4363 # POSSIBLE.
4364 # See https://cloud.google.com/dlp/docs/likelihood to learn more.
4365 "customInfoTypes": [ # CustomInfoTypes provided by the user. See
4366 # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.
4367 { # Custom information type provided by the user. Used to find domain-specific
4368 # sensitive information configurable to the data in question.
4369 "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
4370 "pattern": "A String", # Pattern defining the regular expression. Its syntax
4371 # (https://github.com/google/re2/wiki/Syntax) can be found under the
4372 # google/re2 repository on GitHub.
4373 "groupIndexes": [ # The index of the submatch to extract as findings. When not
4374 # specified, the entire match is returned. No more than 3 may be included.
4375 42,
4376 ],
4377 },
4378 "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
4379 # support reversing.
4380 # such as
4381 # [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).
4382 # These types of transformations are
4383 # those that perform pseudonymization, thereby producing a "surrogate" as
4384 # output. This should be used in conjunction with a field on the
4385 # transformation such as `surrogate_info_type`. This CustomInfoType does
4386 # not support the use of `detection_rules`.
4387 },
4388 "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in
4389 # infoType, when the name matches one of existing infoTypes and that infoType
4390 # is specified in `InspectContent.info_types` field. Specifying the latter
4391 # adds findings to the one detected by the system. If built-in info type is
4392 # not specified in `InspectContent.info_types` list then the name is treated
4393 # as a custom info type.
4394 "name": "A String", # Name of the information type. Either a name of your choosing when
4395 # creating a CustomInfoType, or one of the names listed
4396 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
4397 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4398 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4399 },
4400 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
4401 # be used to match sensitive information specific to the data, such as a list
4402 # of employee IDs or job titles.
4403 #
4404 # Dictionary words are case-insensitive and all characters other than letters
4405 # and digits in the unicode [Basic Multilingual
4406 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
4407 # will be replaced with whitespace when scanning for matches, so the
4408 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
4409 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
4410 # surrounding any match must be of a different type than the adjacent
4411 # characters within the word, so letters must be next to non-letters and
4412 # digits next to non-digits. For example, the dictionary word "jen" will
4413 # match the first three letters of the text "jen123" but will return no
4414 # matches for "jennifer".
4415 #
4416 # Dictionary words containing a large number of characters that are not
4417 # letters or digits may result in unexpected findings because such characters
4418 # are treated as whitespace. The
4419 # [limits](https://cloud.google.com/dlp/limits) page contains details about
4420 # the size limits of dictionaries. For dictionaries that do not fit within
4421 # these constraints, consider using `LargeCustomDictionaryConfig` in the
4422 # `StoredInfoType` API.
4423 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
4424 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
4425 # at least one phrase and every phrase must contain at least 2 characters
4426 # that are letters or digits. [required]
4427 "A String",
4428 ],
4429 },
4430 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
4431 # is accepted.
4432 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
4433 # Example: gs://[BUCKET_NAME]/dictionary.txt
4434 },
4435 },
4436 "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
4437 # `InspectDataSource`. Not currently supported in `InspectContent`.
4438 "name": "A String", # Resource name of the requested `StoredInfoType`, for example
4439 # `organizations/433245324/storedInfoTypes/432452342` or
4440 # `projects/project-id/storedInfoTypes/432452342`.
4441 "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
4442 # inspection was created. Output-only field, populated by the system.
4443 },
4444 "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.
4445 # Rules are applied in order that they are specified. Not supported for the
4446 # `surrogate_type` CustomInfoType.
4447 { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a
4448 # `CustomInfoType` to alter behavior under certain circumstances, depending
4449 # on the specific details of the rule. Not supported for the `surrogate_type`
4450 # custom infoType.
4451 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
4452 # proximity of hotwords.
4453 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
4454 # The total length of the window cannot exceed 1000 characters. Note that
4455 # the finding itself will be included in the window, so that hotwords may
4456 # be used to match substrings of the finding itself. For example, the
4457 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
4458 # adjusted upwards if the area code is known to be the local area code of
4459 # a company office using the hotword regex "\(xxx\)", where "xxx"
4460 # is the area code in question.
4461 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4462 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4463 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4464 },
4465 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
4466 "pattern": "A String", # Pattern defining the regular expression. Its syntax
4467 # (https://github.com/google/re2/wiki/Syntax) can be found under the
4468 # google/re2 repository on GitHub.
4469 "groupIndexes": [ # The index of the submatch to extract as findings. When not
4470 # specified, the entire match is returned. No more than 3 may be included.
4471 42,
4472 ],
4473 },
4474 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
4475 # part of a detection rule.
4476 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
4477 # levels. For example, if a finding would be `POSSIBLE` without the
4478 # detection rule and `relative_likelihood` is 1, then it is upgraded to
4479 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
4480 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
4481 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
4482 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
4483 # a final likelihood of `LIKELY`.
4484 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
4485 },
4486 },
4487 },
4488 ],
4489 "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding
4490 # to be returned. It still can be used for rules matching.
4491 "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be
4492 # altered by a detection rule if the finding meets the criteria specified by
4493 # the rule. Defaults to `VERY_LIKELY` if not specified.
4494 },
4495 ],
4496 "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
4497 # included in the response; see Finding.quote.
4498 "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.
4499 # Exclusion rules, contained in the set are executed in the end, other
4500 # rules are executed in the order they are specified for each info type.
4501 { # Rule set for modifying a set of infoTypes to alter behavior under certain
4502 # circumstances, depending on the specific details of the rules within the set.
4503 "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
4504 { # A single inspection rule to be applied to infoTypes, specified in
4505 # `InspectionRuleSet`.
4506 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
4507 # proximity of hotwords.
4508 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
4509 # The total length of the window cannot exceed 1000 characters. Note that
4510 # the finding itself will be included in the window, so that hotwords may
4511 # be used to match substrings of the finding itself. For example, the
4512 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
4513 # adjusted upwards if the area code is known to be the local area code of
4514 # a company office using the hotword regex "\(xxx\)", where "xxx"
4515 # is the area code in question.
4516 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4517 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4518 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4519 },
4520 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
4521 "pattern": "A String", # Pattern defining the regular expression. Its syntax
4522 # (https://github.com/google/re2/wiki/Syntax) can be found under the
4523 # google/re2 repository on GitHub.
4524 "groupIndexes": [ # The index of the submatch to extract as findings. When not
4525 # specified, the entire match is returned. No more than 3 may be included.
4526 42,
4527 ],
4528 },
4529 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
4530 # part of a detection rule.
4531 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
4532 # levels. For example, if a finding would be `POSSIBLE` without the
4533 # detection rule and `relative_likelihood` is 1, then it is upgraded to
4534 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
4535 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
4536 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
4537 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
4538 # a final likelihood of `LIKELY`.
4539 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
4540 },
4541 },
4542 "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
4543 # `InspectionRuleSet` are removed from results.
4544 "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
4545 "pattern": "A String", # Pattern defining the regular expression. Its syntax
4546 # (https://github.com/google/re2/wiki/Syntax) can be found under the
4547 # google/re2 repository on GitHub.
4548 "groupIndexes": [ # The index of the submatch to extract as findings. When not
4549 # specified, the entire match is returned. No more than 3 may be included.
4550 42,
4551 ],
4552 },
4553 "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.
4554 "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or
4555 # contained within with a finding of an infoType from this list. For
4556 # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and
4557 # `exclusion_rule` containing `exclude_info_types.info_types` with
4558 # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap
4559 # with EMAIL_ADDRESS finding.
4560 # That leads to "555-222-2222@example.org" to generate only a single
4561 # finding, namely email address.
4562 { # Type of information detected by the API.
4563 "name": "A String", # Name of the information type. Either a name of your choosing when
4564 # creating a CustomInfoType, or one of the names listed
4565 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
4566 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4567 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4568 },
4569 ],
4570 },
4571 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
4572 # be used to match sensitive information specific to the data, such as a list
4573 # of employee IDs or job titles.
4574 #
4575 # Dictionary words are case-insensitive and all characters other than letters
4576 # and digits in the unicode [Basic Multilingual
4577 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
4578 # will be replaced with whitespace when scanning for matches, so the
4579 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
4580 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
4581 # surrounding any match must be of a different type than the adjacent
4582 # characters within the word, so letters must be next to non-letters and
4583 # digits next to non-digits. For example, the dictionary word "jen" will
4584 # match the first three letters of the text "jen123" but will return no
4585 # matches for "jennifer".
4586 #
4587 # Dictionary words containing a large number of characters that are not
4588 # letters or digits may result in unexpected findings because such characters
4589 # are treated as whitespace. The
4590 # [limits](https://cloud.google.com/dlp/limits) page contains details about
4591 # the size limits of dictionaries. For dictionaries that do not fit within
4592 # these constraints, consider using `LargeCustomDictionaryConfig` in the
4593 # `StoredInfoType` API.
4594 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
4595 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
4596 # at least one phrase and every phrase must contain at least 2 characters
4597 # that are letters or digits. [required]
4598 "A String",
4599 ],
4600 },
4601 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
4602 # is accepted.
4603 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
4604 # Example: gs://[BUCKET_NAME]/dictionary.txt
4605 },
4606 },
4607 "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
4608 },
4609 },
4610 ],
4611 "infoTypes": [ # List of infoTypes this rule set is applied to.
4612 { # Type of information detected by the API.
4613 "name": "A String", # Name of the information type. Either a name of your choosing when
4614 # creating a CustomInfoType, or one of the names listed
4615 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
4616 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4617 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4618 },
4619 ],
4620 },
4621 ],
4622 "contentOptions": [ # List of options defining data content to scan.
4623 # If empty, text, images, and other content will be included.
4624 "A String",
4625 ],
4626 "infoTypes": [ # Restricts what info_types to look for. The values must correspond to
4627 # InfoType values returned by ListInfoTypes or listed at
4628 # https://cloud.google.com/dlp/docs/infotypes-reference.
4629 #
4630 # When no InfoTypes or CustomInfoTypes are specified in a request, the
4631 # system may automatically choose what detectors to run. By default this may
4632 # be all types, but may change over time as detectors are updated.
4633 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4634 # If you need precise control and predictability as to what detectors are
4635 # run you should specify specific InfoTypes listed in the reference,
4636 # otherwise a default list will be used, which may change over time.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4637 { # Type of information detected by the API.
4638 "name": "A String", # Name of the information type. Either a name of your choosing when
4639 # creating a CustomInfoType, or one of the names listed
4640 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
4641 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4642 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4643 },
4644 ],
4645 },
4646 "inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.
4647 # `inspect_config` will be merged into the values persisted as part of the
4648 # template.
4649 "actions": [ # Actions to execute at the completion of the job.
4650 { # A task to execute on the completion of a job.
4651 # See https://cloud.google.com/dlp/docs/concepts-actions to learn more.
4652 "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
4653 # OutputStorageConfig. Only a single instance of this action can be
4654 # specified.
4655 # Compatible with: Inspect, Risk
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4656 "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4657 "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
4658 # dataset. If table_id is not set a new one will be generated
4659 # for you with the following format:
4660 # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for
4661 # generating the date details.
4662 #
4663 # For Inspect, each column in an existing output table must have the same
4664 # name, type, and mode of a field in the `Finding` object.
4665 #
4666 # For Risk, an existing output table should be the output of a previous
4667 # Risk analysis job run on the same source table, with the same privacy
4668 # metric and quasi-identifiers. Risk jobs that analyze the same table but
4669 # compute a different privacy metric, or use different sets of
4670 # quasi-identifiers, cannot store their results in the same table.
4671 # identified by its project_id, dataset_id, and table_name. Within a query
4672 # a table is often referenced with a string in the format of:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4673 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
4674 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4675 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
4676 # If omitted, project ID is inferred from the API call.
4677 "tableId": "A String", # Name of the table.
4678 "datasetId": "A String", # Dataset ID of the table.
4679 },
4680 "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only
4681 # used for Inspect and must be unspecified for Risk jobs. Columns are derived
4682 # from the `Finding` object. If appending to an existing table, any columns
4683 # from the predefined schema that are missing will be added. No columns in
4684 # the existing table will be deleted.
4685 #
4686 # If unspecified, then all available columns will be used for a new table or
4687 # an (existing) table with no schema, and no changes will be made to an
4688 # existing table that has a schema.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4689 # Only for use with external storage.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4690 },
4691 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4692 "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4693 # completion/failure.
4694 # completion/failure.
4695 },
4696 "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
4697 # Command Center (CSCC Alpha).
4698 # This action is only available for projects which are parts of
4699 # an organization and whitelisted for the alpha Cloud Security Command
4700 # Center.
4701 # The action will publish count of finding instances and their info types.
4702 # The summary of findings will be persisted in CSCC and are governed by CSCC
4703 # service-specific policy, see https://cloud.google.com/terms/service-terms
4704 # Only a single instance of this action can be specified.
4705 # Compatible with: Inspect
4706 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4707 "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.
4708 # will publish a metric to stack driver on each infotype requested and
4709 # how many findings were found for it. CustomDetectors will be bucketed
4710 # as 'Custom' under the Stackdriver label 'info_type'.
4711 },
4712 "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.
4713 # results of the DlpJob will be applied to the entry for the resource scanned
4714 # in Cloud Data Catalog. Any labels previously written by another DlpJob will
4715 # be deleted. InfoType naming patterns are strictly enforced when using this
4716 # feature. Note that the findings will be persisted in Cloud Data Catalog
4717 # storage and are governed by Data Catalog service-specific policy, see
4718 # https://cloud.google.com/terms/service-terms
4719 # Only a single instance of this action can be specified and only allowed if
4720 # all resources being scanned are BigQuery tables.
4721 # Compatible with: Inspect
4722 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4723 "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
4724 # message contains a single field, `DlpJobName`, which is equal to the
4725 # finished job's
4726 # [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
4727 # Compatible with: Inspect, Risk
4728 "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given
4729 # publishing access rights to the DLP API service account executing
4730 # the long running DlpJob sending the notifications.
4731 # Format is projects/{project}/topics/{topic}.
4732 },
4733 },
4734 ],
4735 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4736 "lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
4737 "createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4738 "name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the
4739 # triggeredJob is created, for example
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4740 # `projects/dlp-test-project/jobTriggers/53234423`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4741 },
4742 ],
4743 }</pre>
4744</div>
4745
4746<div class="method">
4747 <code class="details" id="list_next">list_next(previous_request, previous_response)</code>
4748 <pre>Retrieves the next page of results.
4749
4750Args:
4751 previous_request: The request for the previous page. (required)
4752 previous_response: The response from the request for the previous page. (required)
4753
4754Returns:
4755 A request object that you can call 'execute()' on to request the next
4756 page. Returns None if there are no more items in the collection.
4757 </pre>
4758</div>
4759
4760<div class="method">
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4761 <code class="details" id="patch">patch(name, body=None, x__xgafv=None)</code>
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4762 <pre>Updates a job trigger.
4763See https://cloud.google.com/dlp/docs/creating-job-triggers to learn more.
4764
4765Args:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4766 name: string, Required. Resource name of the project and the triggeredJob, for example
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4767`projects/dlp-test-project/jobTriggers/53234423`. (required)
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4768 body: object, The request body.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4769 The object takes the form of:
4770
4771{ # Request message for UpdateJobTrigger.
4772 "jobTrigger": { # Contains a configuration to make dlp api calls on a repeating basis. # New JobTrigger value.
4773 # See https://cloud.google.com/dlp/docs/concepts-job-triggers to learn more.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4774 "status": "A String", # Required. A status for this trigger.
4775 "updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
4776 "errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4777 # errors may result in the JobTrigger automatically being paused.
4778 # Will return the last 100 errors. Whenever the JobTrigger is modified
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4779 # this list will be cleared.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4780 { # Details information about an error encountered during job execution or
4781 # the results of an unsuccessful activation of the JobTrigger.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4782 "timestamps": [ # The times the error occurred.
4783 "A String",
4784 ],
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4785 "details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4786 # different programming environments, including REST APIs and RPC APIs. It is
4787 # used by [gRPC](https://github.com/grpc). Each `Status` message contains
4788 # three pieces of data: error code, error message, and error details.
4789 #
4790 # You can find out more about this error model and how to work with it in the
4791 # [API Design Guide](https://cloud.google.com/apis/design/errors).
4792 "message": "A String", # A developer-facing error message, which should be in English. Any
4793 # user-facing error message should be localized and sent in the
4794 # google.rpc.Status.details field, or localized by the client.
4795 "code": 42, # The status code, which should be an enum value of google.rpc.Code.
4796 "details": [ # A list of messages that carry the error details. There is a common set of
4797 # message types for APIs to use.
4798 {
4799 "a_key": "", # Properties of the object. Contains field @type with type URL.
4800 },
4801 ],
4802 },
4803 },
4804 ],
4805 "displayName": "A String", # Display name (max 100 chars)
4806 "description": "A String", # User provided description (max 256 chars)
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4807 "triggers": [ # A list of triggers which will be OR'ed together. Only one in the list
4808 # needs to trigger for a job to be started. The list may contain only
4809 # a single Schedule trigger and must have at least one object.
4810 { # What event needs to occur for a new job to be started.
4811 "manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.
4812 # Early access feature is in a pre-release state and might change or have
4813 # limited support. For more information, see
4814 # https://cloud.google.com/products#product-launch-stages.
4815 # and finished.
4816 },
4817 "schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.
4818 "recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For
4819 # example: every day (86400 seconds).
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4820 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4821 # A scheduled start time will be skipped if the previous
4822 # execution has not ended when its scheduled time occurs.
4823 #
4824 # This value must be set to a time duration greater than or equal
4825 # to 1 day and can be no longer than 60 days.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4826 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4827 },
4828 ],
4829 "inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
4830 "storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
4831 "cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4832 # bucket.
4833 "bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger
4834 # than this value then the rest of the bytes are omitted. Only one
4835 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
4836 "sampleMethod": "A String",
4837 "fileSet": { # Set of files to scan. # The set of one or more files to scan.
4838 "url": "A String", # The Cloud Storage url of the file(s) to scan, in the format
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4839 # `gs://&lt;bucket&gt;/&lt;path&gt;`. Trailing wildcard in the path is allowed.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4840 #
4841 # If the url ends in a trailing slash, the bucket or directory represented
4842 # by the url will be scanned non-recursively (content in sub-directories
4843 # will not be scanned). This means that `gs://mybucket/` is equivalent to
4844 # `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
4845 # `gs://mybucket/directory/*`.
4846 #
4847 # Exactly one of `url` or `regex_file_set` must be set.
4848 "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
4849 # `regex_file_set` must be set.
4850 # expressions are used to allow fine-grained control over which files in the
4851 # bucket to include.
4852 #
4853 # Included files are those that match at least one item in `include_regex` and
4854 # do not match any items in `exclude_regex`. Note that a file that matches
4855 # items from both lists will _not_ be included. For a match to occur, the
4856 # entire file path (i.e., everything in the url after the bucket name) must
4857 # match the regular expression.
4858 #
4859 # For example, given the input `{bucket_name: "mybucket", include_regex:
4860 # ["directory1/.*"], exclude_regex:
4861 # ["directory1/excluded.*"]}`:
4862 #
4863 # * `gs://mybucket/directory1/myfile` will be included
4864 # * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches
4865 # across `/`)
4866 # * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the
4867 # full path doesn't match any items in `include_regex`)
4868 # * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path
4869 # matches an item in `exclude_regex`)
4870 #
4871 # If `include_regex` is left empty, it will match all files by default
4872 # (this is equivalent to setting `include_regex: [".*"]`).
4873 #
4874 # Some other common use cases:
4875 #
4876 # * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all
4877 # files in `mybucket` except for .pdf files
4878 # * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will
4879 # include all files directly under `gs://mybucket/directory/`, without matching
4880 # across `/`
4881 "excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in
4882 # the bucket that match at least one of these regular expressions will be
4883 # excluded from the scan.
4884 #
4885 # Regular expressions use RE2
4886 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
4887 # under the google/re2 repository on GitHub.
4888 "A String",
4889 ],
4890 "bucketName": "A String", # The name of a Cloud Storage bucket. Required.
4891 "includeRegex": [ # A list of regular expressions matching file paths to include. All files in
4892 # the bucket that match at least one of these regular expressions will be
4893 # included in the set of files, except for those that also match an item in
4894 # `exclude_regex`. Leaving this field empty will match all files by default
4895 # (this is equivalent to including `.*` in the list).
4896 #
4897 # Regular expressions use RE2
4898 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
4899 # under the google/re2 repository on GitHub.
4900 "A String",
4901 ],
4902 },
4903 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4904 "filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.
4905 # Number of files scanned is rounded down. Must be between 0 and 100,
4906 # inclusively. Both 0 and 100 means no limit. Defaults to 0.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4907 "bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The
4908 # number of bytes scanned is rounded down. Must be between 0 and 100,
4909 # inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one
4910 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4911 "fileTypes": [ # List of file type groups to include in the scan.
4912 # If empty, all files are scanned and available data format processors
4913 # are applied. In addition, the binary content of the selected files
4914 # is always scanned as well.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4915 # Images are scanned only as binary if the specified region
4916 # does not support image inspection and no file_types were specified.
4917 # Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]4918 "A String",
4919 ],
4920 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]4921 "datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
4922 "partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always
4923 # by project and namespace, however the namespace ID may be empty.
4924 # A partition ID identifies a grouping of entities. The grouping is always
4925 # by project and namespace, however the namespace ID may be empty.
4926 #
4927 # A partition ID contains several dimensions:
4928 # project ID and namespace ID.
4929 "projectId": "A String", # The ID of the project to which the entities belong.
4930 "namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
4931 },
4932 "kind": { # A representation of a Datastore kind. # The kind to process.
4933 "name": "A String", # The name of the kind.
4934 },
4935 },
4936 "bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
4937 "excludedFields": [ # References to fields excluded from scanning. This allows you to skip
4938 # inspection of entire columns which you know have no findings.
4939 { # General identifier of a data field in a storage service.
4940 "name": "A String", # Name describing the field.
4941 },
4942 ],
4943 "rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the
4944 # rest of the rows are omitted. If not set, or if set to 0, all rows will be
4945 # scanned. Only one of rows_limit and rows_limit_percent can be specified.
4946 # Cannot be used in conjunction with TimespanConfig.
4947 "sampleMethod": "A String",
4948 "identifyingFields": [ # Table fields that may uniquely identify a row within the table. When
4949 # `actions.saveFindings.outputConfig.table` is specified, the values of
4950 # columns specified here are available in the output table under
4951 # `location.content_locations.record_location.record_key.id_values`. Nested
4952 # fields such as `person.birthdate.year` are allowed.
4953 { # General identifier of a data field in a storage service.
4954 "name": "A String", # Name describing the field.
4955 },
4956 ],
4957 "rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows
4958 # scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and
4959 # 100 means no limit. Defaults to 0. Only one of rows_limit and
4960 # rows_limit_percent can be specified. Cannot be used in conjunction with
4961 # TimespanConfig.
4962 "tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.
4963 # identified by its project_id, dataset_id, and table_name. Within a query
4964 # a table is often referenced with a string in the format of:
4965 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
4966 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
4967 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
4968 # If omitted, project ID is inferred from the API call.
4969 "tableId": "A String", # Name of the table.
4970 "datasetId": "A String", # Dataset ID of the table.
4971 },
4972 },
4973 "timespanConfig": { # Configuration of the timespan of the items to include in scanning.
4974 # Currently only supported when inspecting Google Cloud Storage and BigQuery.
4975 "timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.
4976 # Used for data sources like Datastore and BigQuery.
4977 #
4978 # For BigQuery:
4979 # Required to filter out rows based on the given start and
4980 # end times. If not specified and the table was modified between the given
4981 # start and end times, the entire table will be scanned.
4982 # The valid data types of the timestamp field are: `INTEGER`, `DATE`,
4983 # `TIMESTAMP`, or `DATETIME` BigQuery column.
4984 #
4985 # For Datastore.
4986 # Valid data types of the timestamp field are: `TIMESTAMP`.
4987 # Datastore entity will be scanned if the timestamp property does not
4988 # exist or its value is empty or invalid.
4989 "name": "A String", # Name describing the field.
4990 },
4991 "endTime": "A String", # Exclude files or rows newer than this value.
4992 # If set to zero, no upper time limit is applied.
4993 "startTime": "A String", # Exclude files or rows older than this value.
4994 "enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out
4995 # a valid start_time to avoid scanning files that have not been modified
4996 # since the last time the JobTrigger executed. This will be based on the
4997 # time of the execution of the last run of the JobTrigger.
4998 },
4999 "hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.
5000 # Early access feature is in a pre-release state and might change or have
5001 # limited support. For more information, see
5002 # https://cloud.google.com/products#product-launch-stages.
5003 # of Google Cloud Platform.
5004 "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings
5005 # meaningful such as the columns that are primary keys.
5006 "identifyingFields": [ # The columns that are the primary keys for table objects included in
5007 # ContentItem. A copy of this cell's value will stored alongside alongside
5008 # each finding so that the finding can be traced to the specific row it came
5009 # from. No more than 3 may be provided.
5010 { # General identifier of a data field in a storage service.
5011 "name": "A String", # Name describing the field.
5012 },
5013 ],
5014 },
5015 "labels": { # To organize findings, these labels will be added to each finding.
5016 #
5017 # Label keys must be between 1 and 63 characters long and must conform
5018 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
5019 #
5020 # Label values must be between 0 and 63 characters long and must conform
5021 # to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.
5022 #
5023 # No more than 10 labels can be associated with a given finding.
5024 #
5025 # Examples:
5026 # * `"environment" : "production"`
5027 # * `"pipeline" : "etl"`
5028 "a_key": "A String",
5029 },
5030 "requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their
5031 # 'finding_labels' map. Request may contain others, but any missing one of
5032 # these will be rejected.
5033 #
5034 # Label keys must be between 1 and 63 characters long and must conform
5035 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
5036 #
5037 # No more than 10 keys can be required.
5038 "A String",
5039 ],
5040 "description": "A String", # A short description of where the data is coming from. Will be stored once
5041 # in the job. 256 max length.
5042 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5043 },
5044 "inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.
5045 # When used with redactContent only info_types and min_likelihood are currently
5046 # used.
5047 "excludeInfoTypes": True or False, # When true, excludes type information of the findings.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5048 "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5049 "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
5050 # When set within `InspectContentRequest`, the maximum returned is 2000
5051 # regardless if this is set higher.
5052 "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
5053 { # Max findings configuration per infoType, per content item or long
5054 # running DlpJob.
5055 "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per
5056 # info_type should be provided. If InfoTypeLimit does not have an
5057 # info_type, the DLP API applies the limit against all info_types that
5058 # are found but not specified in another InfoTypeLimit.
5059 "name": "A String", # Name of the information type. Either a name of your choosing when
5060 # creating a CustomInfoType, or one of the names listed
5061 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
5062 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5063 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5064 },
5065 "maxFindings": 42, # Max findings limit for the given infoType.
5066 },
5067 ],
5068 "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5069 # When set within `InspectJobConfig`,
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5070 # the maximum returned is 2000 regardless if this is set higher.
5071 # When set within `InspectContentRequest`, this field is ignored.
5072 },
5073 "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
5074 # POSSIBLE.
5075 # See https://cloud.google.com/dlp/docs/likelihood to learn more.
5076 "customInfoTypes": [ # CustomInfoTypes provided by the user. See
5077 # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.
5078 { # Custom information type provided by the user. Used to find domain-specific
5079 # sensitive information configurable to the data in question.
5080 "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
5081 "pattern": "A String", # Pattern defining the regular expression. Its syntax
5082 # (https://github.com/google/re2/wiki/Syntax) can be found under the
5083 # google/re2 repository on GitHub.
5084 "groupIndexes": [ # The index of the submatch to extract as findings. When not
5085 # specified, the entire match is returned. No more than 3 may be included.
5086 42,
5087 ],
5088 },
5089 "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
5090 # support reversing.
5091 # such as
5092 # [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).
5093 # These types of transformations are
5094 # those that perform pseudonymization, thereby producing a "surrogate" as
5095 # output. This should be used in conjunction with a field on the
5096 # transformation such as `surrogate_info_type`. This CustomInfoType does
5097 # not support the use of `detection_rules`.
5098 },
5099 "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in
5100 # infoType, when the name matches one of existing infoTypes and that infoType
5101 # is specified in `InspectContent.info_types` field. Specifying the latter
5102 # adds findings to the one detected by the system. If built-in info type is
5103 # not specified in `InspectContent.info_types` list then the name is treated
5104 # as a custom info type.
5105 "name": "A String", # Name of the information type. Either a name of your choosing when
5106 # creating a CustomInfoType, or one of the names listed
5107 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
5108 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5109 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5110 },
5111 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
5112 # be used to match sensitive information specific to the data, such as a list
5113 # of employee IDs or job titles.
5114 #
5115 # Dictionary words are case-insensitive and all characters other than letters
5116 # and digits in the unicode [Basic Multilingual
5117 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
5118 # will be replaced with whitespace when scanning for matches, so the
5119 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
5120 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
5121 # surrounding any match must be of a different type than the adjacent
5122 # characters within the word, so letters must be next to non-letters and
5123 # digits next to non-digits. For example, the dictionary word "jen" will
5124 # match the first three letters of the text "jen123" but will return no
5125 # matches for "jennifer".
5126 #
5127 # Dictionary words containing a large number of characters that are not
5128 # letters or digits may result in unexpected findings because such characters
5129 # are treated as whitespace. The
5130 # [limits](https://cloud.google.com/dlp/limits) page contains details about
5131 # the size limits of dictionaries. For dictionaries that do not fit within
5132 # these constraints, consider using `LargeCustomDictionaryConfig` in the
5133 # `StoredInfoType` API.
5134 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
5135 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
5136 # at least one phrase and every phrase must contain at least 2 characters
5137 # that are letters or digits. [required]
5138 "A String",
5139 ],
5140 },
5141 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
5142 # is accepted.
5143 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
5144 # Example: gs://[BUCKET_NAME]/dictionary.txt
5145 },
5146 },
5147 "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
5148 # `InspectDataSource`. Not currently supported in `InspectContent`.
5149 "name": "A String", # Resource name of the requested `StoredInfoType`, for example
5150 # `organizations/433245324/storedInfoTypes/432452342` or
5151 # `projects/project-id/storedInfoTypes/432452342`.
5152 "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
5153 # inspection was created. Output-only field, populated by the system.
5154 },
5155 "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.
5156 # Rules are applied in order that they are specified. Not supported for the
5157 # `surrogate_type` CustomInfoType.
5158 { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a
5159 # `CustomInfoType` to alter behavior under certain circumstances, depending
5160 # on the specific details of the rule. Not supported for the `surrogate_type`
5161 # custom infoType.
5162 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
5163 # proximity of hotwords.
5164 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
5165 # The total length of the window cannot exceed 1000 characters. Note that
5166 # the finding itself will be included in the window, so that hotwords may
5167 # be used to match substrings of the finding itself. For example, the
5168 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
5169 # adjusted upwards if the area code is known to be the local area code of
5170 # a company office using the hotword regex "\(xxx\)", where "xxx"
5171 # is the area code in question.
5172 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5173 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5174 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5175 },
5176 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
5177 "pattern": "A String", # Pattern defining the regular expression. Its syntax
5178 # (https://github.com/google/re2/wiki/Syntax) can be found under the
5179 # google/re2 repository on GitHub.
5180 "groupIndexes": [ # The index of the submatch to extract as findings. When not
5181 # specified, the entire match is returned. No more than 3 may be included.
5182 42,
5183 ],
5184 },
5185 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
5186 # part of a detection rule.
5187 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
5188 # levels. For example, if a finding would be `POSSIBLE` without the
5189 # detection rule and `relative_likelihood` is 1, then it is upgraded to
5190 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
5191 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
5192 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
5193 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
5194 # a final likelihood of `LIKELY`.
5195 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
5196 },
5197 },
5198 },
5199 ],
5200 "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding
5201 # to be returned. It still can be used for rules matching.
5202 "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be
5203 # altered by a detection rule if the finding meets the criteria specified by
5204 # the rule. Defaults to `VERY_LIKELY` if not specified.
5205 },
5206 ],
5207 "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
5208 # included in the response; see Finding.quote.
5209 "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.
5210 # Exclusion rules, contained in the set are executed in the end, other
5211 # rules are executed in the order they are specified for each info type.
5212 { # Rule set for modifying a set of infoTypes to alter behavior under certain
5213 # circumstances, depending on the specific details of the rules within the set.
5214 "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
5215 { # A single inspection rule to be applied to infoTypes, specified in
5216 # `InspectionRuleSet`.
5217 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
5218 # proximity of hotwords.
5219 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
5220 # The total length of the window cannot exceed 1000 characters. Note that
5221 # the finding itself will be included in the window, so that hotwords may
5222 # be used to match substrings of the finding itself. For example, the
5223 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
5224 # adjusted upwards if the area code is known to be the local area code of
5225 # a company office using the hotword regex "\(xxx\)", where "xxx"
5226 # is the area code in question.
5227 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5228 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5229 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5230 },
5231 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
5232 "pattern": "A String", # Pattern defining the regular expression. Its syntax
5233 # (https://github.com/google/re2/wiki/Syntax) can be found under the
5234 # google/re2 repository on GitHub.
5235 "groupIndexes": [ # The index of the submatch to extract as findings. When not
5236 # specified, the entire match is returned. No more than 3 may be included.
5237 42,
5238 ],
5239 },
5240 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
5241 # part of a detection rule.
5242 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
5243 # levels. For example, if a finding would be `POSSIBLE` without the
5244 # detection rule and `relative_likelihood` is 1, then it is upgraded to
5245 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
5246 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
5247 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
5248 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
5249 # a final likelihood of `LIKELY`.
5250 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
5251 },
5252 },
5253 "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
5254 # `InspectionRuleSet` are removed from results.
5255 "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
5256 "pattern": "A String", # Pattern defining the regular expression. Its syntax
5257 # (https://github.com/google/re2/wiki/Syntax) can be found under the
5258 # google/re2 repository on GitHub.
5259 "groupIndexes": [ # The index of the submatch to extract as findings. When not
5260 # specified, the entire match is returned. No more than 3 may be included.
5261 42,
5262 ],
5263 },
5264 "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.
5265 "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or
5266 # contained within with a finding of an infoType from this list. For
5267 # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and
5268 # `exclusion_rule` containing `exclude_info_types.info_types` with
5269 # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap
5270 # with EMAIL_ADDRESS finding.
5271 # That leads to "555-222-2222@example.org" to generate only a single
5272 # finding, namely email address.
5273 { # Type of information detected by the API.
5274 "name": "A String", # Name of the information type. Either a name of your choosing when
5275 # creating a CustomInfoType, or one of the names listed
5276 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
5277 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5278 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5279 },
5280 ],
5281 },
5282 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
5283 # be used to match sensitive information specific to the data, such as a list
5284 # of employee IDs or job titles.
5285 #
5286 # Dictionary words are case-insensitive and all characters other than letters
5287 # and digits in the unicode [Basic Multilingual
5288 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
5289 # will be replaced with whitespace when scanning for matches, so the
5290 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
5291 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
5292 # surrounding any match must be of a different type than the adjacent
5293 # characters within the word, so letters must be next to non-letters and
5294 # digits next to non-digits. For example, the dictionary word "jen" will
5295 # match the first three letters of the text "jen123" but will return no
5296 # matches for "jennifer".
5297 #
5298 # Dictionary words containing a large number of characters that are not
5299 # letters or digits may result in unexpected findings because such characters
5300 # are treated as whitespace. The
5301 # [limits](https://cloud.google.com/dlp/limits) page contains details about
5302 # the size limits of dictionaries. For dictionaries that do not fit within
5303 # these constraints, consider using `LargeCustomDictionaryConfig` in the
5304 # `StoredInfoType` API.
5305 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
5306 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
5307 # at least one phrase and every phrase must contain at least 2 characters
5308 # that are letters or digits. [required]
5309 "A String",
5310 ],
5311 },
5312 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
5313 # is accepted.
5314 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
5315 # Example: gs://[BUCKET_NAME]/dictionary.txt
5316 },
5317 },
5318 "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
5319 },
5320 },
5321 ],
5322 "infoTypes": [ # List of infoTypes this rule set is applied to.
5323 { # Type of information detected by the API.
5324 "name": "A String", # Name of the information type. Either a name of your choosing when
5325 # creating a CustomInfoType, or one of the names listed
5326 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
5327 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5328 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5329 },
5330 ],
5331 },
5332 ],
5333 "contentOptions": [ # List of options defining data content to scan.
5334 # If empty, text, images, and other content will be included.
5335 "A String",
5336 ],
5337 "infoTypes": [ # Restricts what info_types to look for. The values must correspond to
5338 # InfoType values returned by ListInfoTypes or listed at
5339 # https://cloud.google.com/dlp/docs/infotypes-reference.
5340 #
5341 # When no InfoTypes or CustomInfoTypes are specified in a request, the
5342 # system may automatically choose what detectors to run. By default this may
5343 # be all types, but may change over time as detectors are updated.
5344 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5345 # If you need precise control and predictability as to what detectors are
5346 # run you should specify specific InfoTypes listed in the reference,
5347 # otherwise a default list will be used, which may change over time.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5348 { # Type of information detected by the API.
5349 "name": "A String", # Name of the information type. Either a name of your choosing when
5350 # creating a CustomInfoType, or one of the names listed
5351 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
5352 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5353 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5354 },
5355 ],
5356 },
5357 "inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.
5358 # `inspect_config` will be merged into the values persisted as part of the
5359 # template.
5360 "actions": [ # Actions to execute at the completion of the job.
5361 { # A task to execute on the completion of a job.
5362 # See https://cloud.google.com/dlp/docs/concepts-actions to learn more.
5363 "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
5364 # OutputStorageConfig. Only a single instance of this action can be
5365 # specified.
5366 # Compatible with: Inspect, Risk
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5367 "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5368 "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
5369 # dataset. If table_id is not set a new one will be generated
5370 # for you with the following format:
5371 # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for
5372 # generating the date details.
5373 #
5374 # For Inspect, each column in an existing output table must have the same
5375 # name, type, and mode of a field in the `Finding` object.
5376 #
5377 # For Risk, an existing output table should be the output of a previous
5378 # Risk analysis job run on the same source table, with the same privacy
5379 # metric and quasi-identifiers. Risk jobs that analyze the same table but
5380 # compute a different privacy metric, or use different sets of
5381 # quasi-identifiers, cannot store their results in the same table.
5382 # identified by its project_id, dataset_id, and table_name. Within a query
5383 # a table is often referenced with a string in the format of:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5384 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
5385 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5386 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
5387 # If omitted, project ID is inferred from the API call.
5388 "tableId": "A String", # Name of the table.
5389 "datasetId": "A String", # Dataset ID of the table.
5390 },
5391 "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only
5392 # used for Inspect and must be unspecified for Risk jobs. Columns are derived
5393 # from the `Finding` object. If appending to an existing table, any columns
5394 # from the predefined schema that are missing will be added. No columns in
5395 # the existing table will be deleted.
5396 #
5397 # If unspecified, then all available columns will be used for a new table or
5398 # an (existing) table with no schema, and no changes will be made to an
5399 # existing table that has a schema.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5400 # Only for use with external storage.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5401 },
5402 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5403 "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5404 # completion/failure.
5405 # completion/failure.
5406 },
5407 "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
5408 # Command Center (CSCC Alpha).
5409 # This action is only available for projects which are parts of
5410 # an organization and whitelisted for the alpha Cloud Security Command
5411 # Center.
5412 # The action will publish count of finding instances and their info types.
5413 # The summary of findings will be persisted in CSCC and are governed by CSCC
5414 # service-specific policy, see https://cloud.google.com/terms/service-terms
5415 # Only a single instance of this action can be specified.
5416 # Compatible with: Inspect
5417 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5418 "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.
5419 # will publish a metric to stack driver on each infotype requested and
5420 # how many findings were found for it. CustomDetectors will be bucketed
5421 # as 'Custom' under the Stackdriver label 'info_type'.
5422 },
5423 "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.
5424 # results of the DlpJob will be applied to the entry for the resource scanned
5425 # in Cloud Data Catalog. Any labels previously written by another DlpJob will
5426 # be deleted. InfoType naming patterns are strictly enforced when using this
5427 # feature. Note that the findings will be persisted in Cloud Data Catalog
5428 # storage and are governed by Data Catalog service-specific policy, see
5429 # https://cloud.google.com/terms/service-terms
5430 # Only a single instance of this action can be specified and only allowed if
5431 # all resources being scanned are BigQuery tables.
5432 # Compatible with: Inspect
5433 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5434 "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
5435 # message contains a single field, `DlpJobName`, which is equal to the
5436 # finished job's
5437 # [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
5438 # Compatible with: Inspect, Risk
5439 "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given
5440 # publishing access rights to the DLP API service account executing
5441 # the long running DlpJob sending the notifications.
5442 # Format is projects/{project}/topics/{topic}.
5443 },
5444 },
5445 ],
5446 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5447 "lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
5448 "createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5449 "name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the
5450 # triggeredJob is created, for example
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5451 # `projects/dlp-test-project/jobTriggers/53234423`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5452 },
5453 "updateMask": "A String", # Mask to control which fields get updated.
5454 }
5455
5456 x__xgafv: string, V1 error format.
5457 Allowed values
5458 1 - v1 error format
5459 2 - v2 error format
5460
5461Returns:
5462 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.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5466 "status": "A String", # Required. A status for this trigger.
5467 "updateTime": "A String", # Output only. The last update timestamp of a triggeredJob.
5468 "errors": [ # Output only. A stream of errors encountered when the trigger was activated. Repeated
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5469 # errors may result in the JobTrigger automatically being paused.
5470 # Will return the last 100 errors. Whenever the JobTrigger is modified
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5471 # this list will be cleared.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5472 { # Details information about an error encountered during job execution or
5473 # the results of an unsuccessful activation of the JobTrigger.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5474 "timestamps": [ # The times the error occurred.
5475 "A String",
5476 ],
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5477 "details": { # The `Status` type defines a logical error model that is suitable for # Detailed error codes and messages.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5478 # different programming environments, including REST APIs and RPC APIs. It is
5479 # used by [gRPC](https://github.com/grpc). Each `Status` message contains
5480 # three pieces of data: error code, error message, and error details.
5481 #
5482 # You can find out more about this error model and how to work with it in the
5483 # [API Design Guide](https://cloud.google.com/apis/design/errors).
5484 "message": "A String", # A developer-facing error message, which should be in English. Any
5485 # user-facing error message should be localized and sent in the
5486 # google.rpc.Status.details field, or localized by the client.
5487 "code": 42, # The status code, which should be an enum value of google.rpc.Code.
5488 "details": [ # A list of messages that carry the error details. There is a common set of
5489 # message types for APIs to use.
5490 {
5491 "a_key": "", # Properties of the object. Contains field @type with type URL.
5492 },
5493 ],
5494 },
5495 },
5496 ],
5497 "displayName": "A String", # Display name (max 100 chars)
5498 "description": "A String", # User provided description (max 256 chars)
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5499 "triggers": [ # A list of triggers which will be OR'ed together. Only one in the list
5500 # needs to trigger for a job to be started. The list may contain only
5501 # a single Schedule trigger and must have at least one object.
5502 { # What event needs to occur for a new job to be started.
5503 "manual": { # Job trigger option for hybrid jobs. Jobs must be manually created # For use with hybrid jobs. Jobs must be manually created and finished.
5504 # Early access feature is in a pre-release state and might change or have
5505 # limited support. For more information, see
5506 # https://cloud.google.com/products#product-launch-stages.
5507 # and finished.
5508 },
5509 "schedule": { # Schedule for triggeredJobs. # Create a job on a repeating basis based on the elapse of time.
5510 "recurrencePeriodDuration": "A String", # With this option a job is started a regular periodic basis. For
5511 # example: every day (86400 seconds).
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5512 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5513 # A scheduled start time will be skipped if the previous
5514 # execution has not ended when its scheduled time occurs.
5515 #
5516 # This value must be set to a time duration greater than or equal
5517 # to 1 day and can be no longer than 60 days.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5518 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5519 },
5520 ],
5521 "inspectJob": { # Controls what and how to inspect for findings. # For inspect jobs, a snapshot of the configuration.
5522 "storageConfig": { # Shared message indicating Cloud storage type. # The data to scan.
5523 "cloudStorageOptions": { # Options defining a file or a set of files within a Google Cloud Storage # Google Cloud Storage options.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5524 # bucket.
5525 "bytesLimitPerFile": "A String", # Max number of bytes to scan from a file. If a scanned file's size is bigger
5526 # than this value then the rest of the bytes are omitted. Only one
5527 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
5528 "sampleMethod": "A String",
5529 "fileSet": { # Set of files to scan. # The set of one or more files to scan.
5530 "url": "A String", # The Cloud Storage url of the file(s) to scan, in the format
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5531 # `gs://&lt;bucket&gt;/&lt;path&gt;`. Trailing wildcard in the path is allowed.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5532 #
5533 # If the url ends in a trailing slash, the bucket or directory represented
5534 # by the url will be scanned non-recursively (content in sub-directories
5535 # will not be scanned). This means that `gs://mybucket/` is equivalent to
5536 # `gs://mybucket/*`, and `gs://mybucket/directory/` is equivalent to
5537 # `gs://mybucket/directory/*`.
5538 #
5539 # Exactly one of `url` or `regex_file_set` must be set.
5540 "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
5541 # `regex_file_set` must be set.
5542 # expressions are used to allow fine-grained control over which files in the
5543 # bucket to include.
5544 #
5545 # Included files are those that match at least one item in `include_regex` and
5546 # do not match any items in `exclude_regex`. Note that a file that matches
5547 # items from both lists will _not_ be included. For a match to occur, the
5548 # entire file path (i.e., everything in the url after the bucket name) must
5549 # match the regular expression.
5550 #
5551 # For example, given the input `{bucket_name: "mybucket", include_regex:
5552 # ["directory1/.*"], exclude_regex:
5553 # ["directory1/excluded.*"]}`:
5554 #
5555 # * `gs://mybucket/directory1/myfile` will be included
5556 # * `gs://mybucket/directory1/directory2/myfile` will be included (`.*` matches
5557 # across `/`)
5558 # * `gs://mybucket/directory0/directory1/myfile` will _not_ be included (the
5559 # full path doesn't match any items in `include_regex`)
5560 # * `gs://mybucket/directory1/excludedfile` will _not_ be included (the path
5561 # matches an item in `exclude_regex`)
5562 #
5563 # If `include_regex` is left empty, it will match all files by default
5564 # (this is equivalent to setting `include_regex: [".*"]`).
5565 #
5566 # Some other common use cases:
5567 #
5568 # * `{bucket_name: "mybucket", exclude_regex: [".*\.pdf"]}` will include all
5569 # files in `mybucket` except for .pdf files
5570 # * `{bucket_name: "mybucket", include_regex: ["directory/[^/]+"]}` will
5571 # include all files directly under `gs://mybucket/directory/`, without matching
5572 # across `/`
5573 "excludeRegex": [ # A list of regular expressions matching file paths to exclude. All files in
5574 # the bucket that match at least one of these regular expressions will be
5575 # excluded from the scan.
5576 #
5577 # Regular expressions use RE2
5578 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
5579 # under the google/re2 repository on GitHub.
5580 "A String",
5581 ],
5582 "bucketName": "A String", # The name of a Cloud Storage bucket. Required.
5583 "includeRegex": [ # A list of regular expressions matching file paths to include. All files in
5584 # the bucket that match at least one of these regular expressions will be
5585 # included in the set of files, except for those that also match an item in
5586 # `exclude_regex`. Leaving this field empty will match all files by default
5587 # (this is equivalent to including `.*` in the list).
5588 #
5589 # Regular expressions use RE2
5590 # [syntax](https://github.com/google/re2/wiki/Syntax); a guide can be found
5591 # under the google/re2 repository on GitHub.
5592 "A String",
5593 ],
5594 },
5595 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5596 "filesLimitPercent": 42, # Limits the number of files to scan to this percentage of the input FileSet.
5597 # Number of files scanned is rounded down. Must be between 0 and 100,
5598 # inclusively. Both 0 and 100 means no limit. Defaults to 0.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5599 "bytesLimitPerFilePercent": 42, # Max percentage of bytes to scan from a file. The rest are omitted. The
5600 # number of bytes scanned is rounded down. Must be between 0 and 100,
5601 # inclusively. Both 0 and 100 means no limit. Defaults to 0. Only one
5602 # of bytes_limit_per_file and bytes_limit_per_file_percent can be specified.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5603 "fileTypes": [ # List of file type groups to include in the scan.
5604 # If empty, all files are scanned and available data format processors
5605 # are applied. In addition, the binary content of the selected files
5606 # is always scanned as well.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5607 # Images are scanned only as binary if the specified region
5608 # does not support image inspection and no file_types were specified.
5609 # Image inspection is restricted to 'global', 'us', 'asia', and 'europe'.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5610 "A String",
5611 ],
5612 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5613 "datastoreOptions": { # Options defining a data set within Google Cloud Datastore. # Google Cloud Datastore options.
5614 "partitionId": { # Datastore partition ID. # A partition ID identifies a grouping of entities. The grouping is always
5615 # by project and namespace, however the namespace ID may be empty.
5616 # A partition ID identifies a grouping of entities. The grouping is always
5617 # by project and namespace, however the namespace ID may be empty.
5618 #
5619 # A partition ID contains several dimensions:
5620 # project ID and namespace ID.
5621 "projectId": "A String", # The ID of the project to which the entities belong.
5622 "namespaceId": "A String", # If not empty, the ID of the namespace to which the entities belong.
5623 },
5624 "kind": { # A representation of a Datastore kind. # The kind to process.
5625 "name": "A String", # The name of the kind.
5626 },
5627 },
5628 "bigQueryOptions": { # Options defining BigQuery table and row identifiers. # BigQuery options.
5629 "excludedFields": [ # References to fields excluded from scanning. This allows you to skip
5630 # inspection of entire columns which you know have no findings.
5631 { # General identifier of a data field in a storage service.
5632 "name": "A String", # Name describing the field.
5633 },
5634 ],
5635 "rowsLimit": "A String", # Max number of rows to scan. If the table has more rows than this value, the
5636 # rest of the rows are omitted. If not set, or if set to 0, all rows will be
5637 # scanned. Only one of rows_limit and rows_limit_percent can be specified.
5638 # Cannot be used in conjunction with TimespanConfig.
5639 "sampleMethod": "A String",
5640 "identifyingFields": [ # Table fields that may uniquely identify a row within the table. When
5641 # `actions.saveFindings.outputConfig.table` is specified, the values of
5642 # columns specified here are available in the output table under
5643 # `location.content_locations.record_location.record_key.id_values`. Nested
5644 # fields such as `person.birthdate.year` are allowed.
5645 { # General identifier of a data field in a storage service.
5646 "name": "A String", # Name describing the field.
5647 },
5648 ],
5649 "rowsLimitPercent": 42, # Max percentage of rows to scan. The rest are omitted. The number of rows
5650 # scanned is rounded down. Must be between 0 and 100, inclusively. Both 0 and
5651 # 100 means no limit. Defaults to 0. Only one of rows_limit and
5652 # rows_limit_percent can be specified. Cannot be used in conjunction with
5653 # TimespanConfig.
5654 "tableReference": { # Message defining the location of a BigQuery table. A table is uniquely # Complete BigQuery table reference.
5655 # identified by its project_id, dataset_id, and table_name. Within a query
5656 # a table is often referenced with a string in the format of:
5657 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
5658 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
5659 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
5660 # If omitted, project ID is inferred from the API call.
5661 "tableId": "A String", # Name of the table.
5662 "datasetId": "A String", # Dataset ID of the table.
5663 },
5664 },
5665 "timespanConfig": { # Configuration of the timespan of the items to include in scanning.
5666 # Currently only supported when inspecting Google Cloud Storage and BigQuery.
5667 "timestampField": { # General identifier of a data field in a storage service. # Specification of the field containing the timestamp of scanned items.
5668 # Used for data sources like Datastore and BigQuery.
5669 #
5670 # For BigQuery:
5671 # Required to filter out rows based on the given start and
5672 # end times. If not specified and the table was modified between the given
5673 # start and end times, the entire table will be scanned.
5674 # The valid data types of the timestamp field are: `INTEGER`, `DATE`,
5675 # `TIMESTAMP`, or `DATETIME` BigQuery column.
5676 #
5677 # For Datastore.
5678 # Valid data types of the timestamp field are: `TIMESTAMP`.
5679 # Datastore entity will be scanned if the timestamp property does not
5680 # exist or its value is empty or invalid.
5681 "name": "A String", # Name describing the field.
5682 },
5683 "endTime": "A String", # Exclude files or rows newer than this value.
5684 # If set to zero, no upper time limit is applied.
5685 "startTime": "A String", # Exclude files or rows older than this value.
5686 "enableAutoPopulationOfTimespanConfig": True or False, # When the job is started by a JobTrigger we will automatically figure out
5687 # a valid start_time to avoid scanning files that have not been modified
5688 # since the last time the JobTrigger executed. This will be based on the
5689 # time of the execution of the last run of the JobTrigger.
5690 },
5691 "hybridOptions": { # Configuration to control jobs where the content being inspected is outside # Hybrid inspection options.
5692 # Early access feature is in a pre-release state and might change or have
5693 # limited support. For more information, see
5694 # https://cloud.google.com/products#product-launch-stages.
5695 # of Google Cloud Platform.
5696 "tableOptions": { # Instructions regarding the table content being inspected. # If the container is a table, additional information to make findings
5697 # meaningful such as the columns that are primary keys.
5698 "identifyingFields": [ # The columns that are the primary keys for table objects included in
5699 # ContentItem. A copy of this cell's value will stored alongside alongside
5700 # each finding so that the finding can be traced to the specific row it came
5701 # from. No more than 3 may be provided.
5702 { # General identifier of a data field in a storage service.
5703 "name": "A String", # Name describing the field.
5704 },
5705 ],
5706 },
5707 "labels": { # To organize findings, these labels will be added to each finding.
5708 #
5709 # Label keys must be between 1 and 63 characters long and must conform
5710 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
5711 #
5712 # Label values must be between 0 and 63 characters long and must conform
5713 # to the regular expression `([a-z]([-a-z0-9]*[a-z0-9])?)?`.
5714 #
5715 # No more than 10 labels can be associated with a given finding.
5716 #
5717 # Examples:
5718 # * `"environment" : "production"`
5719 # * `"pipeline" : "etl"`
5720 "a_key": "A String",
5721 },
5722 "requiredFindingLabelKeys": [ # These are labels that each inspection request must include within their
5723 # 'finding_labels' map. Request may contain others, but any missing one of
5724 # these will be rejected.
5725 #
5726 # Label keys must be between 1 and 63 characters long and must conform
5727 # to the following regular expression: `[a-z]([-a-z0-9]*[a-z0-9])?`.
5728 #
5729 # No more than 10 keys can be required.
5730 "A String",
5731 ],
5732 "description": "A String", # A short description of where the data is coming from. Will be stored once
5733 # in the job. 256 max length.
5734 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5735 },
5736 "inspectConfig": { # Configuration description of the scanning process. # How and what to scan for.
5737 # When used with redactContent only info_types and min_likelihood are currently
5738 # used.
5739 "excludeInfoTypes": True or False, # When true, excludes type information of the findings.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5740 "limits": { # Configuration to control the number of findings returned. # Configuration to control the number of findings returned.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5741 "maxFindingsPerRequest": 42, # Max number of findings that will be returned per request/job.
5742 # When set within `InspectContentRequest`, the maximum returned is 2000
5743 # regardless if this is set higher.
5744 "maxFindingsPerInfoType": [ # Configuration of findings limit given for specified infoTypes.
5745 { # Max findings configuration per infoType, per content item or long
5746 # running DlpJob.
5747 "infoType": { # Type of information detected by the API. # Type of information the findings limit applies to. Only one limit per
5748 # info_type should be provided. If InfoTypeLimit does not have an
5749 # info_type, the DLP API applies the limit against all info_types that
5750 # are found but not specified in another InfoTypeLimit.
5751 "name": "A String", # Name of the information type. Either a name of your choosing when
5752 # creating a CustomInfoType, or one of the names listed
5753 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
5754 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5755 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5756 },
5757 "maxFindings": 42, # Max findings limit for the given infoType.
5758 },
5759 ],
5760 "maxFindingsPerItem": 42, # Max number of findings that will be returned for each item scanned.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5761 # When set within `InspectJobConfig`,
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5762 # the maximum returned is 2000 regardless if this is set higher.
5763 # When set within `InspectContentRequest`, this field is ignored.
5764 },
5765 "minLikelihood": "A String", # Only returns findings equal or above this threshold. The default is
5766 # POSSIBLE.
5767 # See https://cloud.google.com/dlp/docs/likelihood to learn more.
5768 "customInfoTypes": [ # CustomInfoTypes provided by the user. See
5769 # https://cloud.google.com/dlp/docs/creating-custom-infotypes to learn more.
5770 { # Custom information type provided by the user. Used to find domain-specific
5771 # sensitive information configurable to the data in question.
5772 "regex": { # Message defining a custom regular expression. # Regular expression based CustomInfoType.
5773 "pattern": "A String", # Pattern defining the regular expression. Its syntax
5774 # (https://github.com/google/re2/wiki/Syntax) can be found under the
5775 # google/re2 repository on GitHub.
5776 "groupIndexes": [ # The index of the submatch to extract as findings. When not
5777 # specified, the entire match is returned. No more than 3 may be included.
5778 42,
5779 ],
5780 },
5781 "surrogateType": { # Message for detecting output from deidentification transformations # Message for detecting output from deidentification transformations that
5782 # support reversing.
5783 # such as
5784 # [`CryptoReplaceFfxFpeConfig`](/dlp/docs/reference/rest/v2/organizations.deidentifyTemplates#cryptoreplaceffxfpeconfig).
5785 # These types of transformations are
5786 # those that perform pseudonymization, thereby producing a "surrogate" as
5787 # output. This should be used in conjunction with a field on the
5788 # transformation such as `surrogate_info_type`. This CustomInfoType does
5789 # not support the use of `detection_rules`.
5790 },
5791 "infoType": { # Type of information detected by the API. # CustomInfoType can either be a new infoType, or an extension of built-in
5792 # infoType, when the name matches one of existing infoTypes and that infoType
5793 # is specified in `InspectContent.info_types` field. Specifying the latter
5794 # adds findings to the one detected by the system. If built-in info type is
5795 # not specified in `InspectContent.info_types` list then the name is treated
5796 # as a custom info type.
5797 "name": "A String", # Name of the information type. Either a name of your choosing when
5798 # creating a CustomInfoType, or one of the names listed
5799 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
5800 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5801 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5802 },
5803 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # A list of phrases to detect as a CustomInfoType.
5804 # be used to match sensitive information specific to the data, such as a list
5805 # of employee IDs or job titles.
5806 #
5807 # Dictionary words are case-insensitive and all characters other than letters
5808 # and digits in the unicode [Basic Multilingual
5809 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
5810 # will be replaced with whitespace when scanning for matches, so the
5811 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
5812 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
5813 # surrounding any match must be of a different type than the adjacent
5814 # characters within the word, so letters must be next to non-letters and
5815 # digits next to non-digits. For example, the dictionary word "jen" will
5816 # match the first three letters of the text "jen123" but will return no
5817 # matches for "jennifer".
5818 #
5819 # Dictionary words containing a large number of characters that are not
5820 # letters or digits may result in unexpected findings because such characters
5821 # are treated as whitespace. The
5822 # [limits](https://cloud.google.com/dlp/limits) page contains details about
5823 # the size limits of dictionaries. For dictionaries that do not fit within
5824 # these constraints, consider using `LargeCustomDictionaryConfig` in the
5825 # `StoredInfoType` API.
5826 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
5827 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
5828 # at least one phrase and every phrase must contain at least 2 characters
5829 # that are letters or digits. [required]
5830 "A String",
5831 ],
5832 },
5833 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
5834 # is accepted.
5835 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
5836 # Example: gs://[BUCKET_NAME]/dictionary.txt
5837 },
5838 },
5839 "storedType": { # A reference to a StoredInfoType to use with scanning. # Load an existing `StoredInfoType` resource for use in
5840 # `InspectDataSource`. Not currently supported in `InspectContent`.
5841 "name": "A String", # Resource name of the requested `StoredInfoType`, for example
5842 # `organizations/433245324/storedInfoTypes/432452342` or
5843 # `projects/project-id/storedInfoTypes/432452342`.
5844 "createTime": "A String", # Timestamp indicating when the version of the `StoredInfoType` used for
5845 # inspection was created. Output-only field, populated by the system.
5846 },
5847 "detectionRules": [ # Set of detection rules to apply to all findings of this CustomInfoType.
5848 # Rules are applied in order that they are specified. Not supported for the
5849 # `surrogate_type` CustomInfoType.
5850 { # Deprecated; use `InspectionRuleSet` instead. Rule for modifying a
5851 # `CustomInfoType` to alter behavior under certain circumstances, depending
5852 # on the specific details of the rule. Not supported for the `surrogate_type`
5853 # custom infoType.
5854 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
5855 # proximity of hotwords.
5856 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
5857 # The total length of the window cannot exceed 1000 characters. Note that
5858 # the finding itself will be included in the window, so that hotwords may
5859 # be used to match substrings of the finding itself. For example, the
5860 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
5861 # adjusted upwards if the area code is known to be the local area code of
5862 # a company office using the hotword regex "\(xxx\)", where "xxx"
5863 # is the area code in question.
5864 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5865 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5866 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5867 },
5868 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
5869 "pattern": "A String", # Pattern defining the regular expression. Its syntax
5870 # (https://github.com/google/re2/wiki/Syntax) can be found under the
5871 # google/re2 repository on GitHub.
5872 "groupIndexes": [ # The index of the submatch to extract as findings. When not
5873 # specified, the entire match is returned. No more than 3 may be included.
5874 42,
5875 ],
5876 },
5877 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
5878 # part of a detection rule.
5879 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
5880 # levels. For example, if a finding would be `POSSIBLE` without the
5881 # detection rule and `relative_likelihood` is 1, then it is upgraded to
5882 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
5883 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
5884 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
5885 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
5886 # a final likelihood of `LIKELY`.
5887 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
5888 },
5889 },
5890 },
5891 ],
5892 "exclusionType": "A String", # If set to EXCLUSION_TYPE_EXCLUDE this infoType will not cause a finding
5893 # to be returned. It still can be used for rules matching.
5894 "likelihood": "A String", # Likelihood to return for this CustomInfoType. This base value can be
5895 # altered by a detection rule if the finding meets the criteria specified by
5896 # the rule. Defaults to `VERY_LIKELY` if not specified.
5897 },
5898 ],
5899 "includeQuote": True or False, # When true, a contextual quote from the data that triggered a finding is
5900 # included in the response; see Finding.quote.
5901 "ruleSet": [ # Set of rules to apply to the findings for this InspectConfig.
5902 # Exclusion rules, contained in the set are executed in the end, other
5903 # rules are executed in the order they are specified for each info type.
5904 { # Rule set for modifying a set of infoTypes to alter behavior under certain
5905 # circumstances, depending on the specific details of the rules within the set.
5906 "rules": [ # Set of rules to be applied to infoTypes. The rules are applied in order.
5907 { # A single inspection rule to be applied to infoTypes, specified in
5908 # `InspectionRuleSet`.
5909 "hotwordRule": { # The rule that adjusts the likelihood of findings within a certain # Hotword-based detection rule.
5910 # proximity of hotwords.
5911 "proximity": { # Message for specifying a window around a finding to apply a detection # Proximity of the finding within which the entire hotword must reside.
5912 # The total length of the window cannot exceed 1000 characters. Note that
5913 # the finding itself will be included in the window, so that hotwords may
5914 # be used to match substrings of the finding itself. For example, the
5915 # certainty of a phone number regex "\(\d{3}\) \d{3}-\d{4}" could be
5916 # adjusted upwards if the area code is known to be the local area code of
5917 # a company office using the hotword regex "\(xxx\)", where "xxx"
5918 # is the area code in question.
5919 # rule.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5920 "windowBefore": 42, # Number of characters before the finding to consider.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5921 "windowAfter": 42, # Number of characters after the finding to consider.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5922 },
5923 "hotwordRegex": { # Message defining a custom regular expression. # Regular expression pattern defining what qualifies as a hotword.
5924 "pattern": "A String", # Pattern defining the regular expression. Its syntax
5925 # (https://github.com/google/re2/wiki/Syntax) can be found under the
5926 # google/re2 repository on GitHub.
5927 "groupIndexes": [ # The index of the submatch to extract as findings. When not
5928 # specified, the entire match is returned. No more than 3 may be included.
5929 42,
5930 ],
5931 },
5932 "likelihoodAdjustment": { # Message for specifying an adjustment to the likelihood of a finding as # Likelihood adjustment to apply to all matching findings.
5933 # part of a detection rule.
5934 "relativeLikelihood": 42, # Increase or decrease the likelihood by the specified number of
5935 # levels. For example, if a finding would be `POSSIBLE` without the
5936 # detection rule and `relative_likelihood` is 1, then it is upgraded to
5937 # `LIKELY`, while a value of -1 would downgrade it to `UNLIKELY`.
5938 # Likelihood may never drop below `VERY_UNLIKELY` or exceed
5939 # `VERY_LIKELY`, so applying an adjustment of 1 followed by an
5940 # adjustment of -1 when base likelihood is `VERY_LIKELY` will result in
5941 # a final likelihood of `LIKELY`.
5942 "fixedLikelihood": "A String", # Set the likelihood of a finding to a fixed value.
5943 },
5944 },
5945 "exclusionRule": { # The rule that specifies conditions when findings of infoTypes specified in # Exclusion rule.
5946 # `InspectionRuleSet` are removed from results.
5947 "regex": { # Message defining a custom regular expression. # Regular expression which defines the rule.
5948 "pattern": "A String", # Pattern defining the regular expression. Its syntax
5949 # (https://github.com/google/re2/wiki/Syntax) can be found under the
5950 # google/re2 repository on GitHub.
5951 "groupIndexes": [ # The index of the submatch to extract as findings. When not
5952 # specified, the entire match is returned. No more than 3 may be included.
5953 42,
5954 ],
5955 },
5956 "excludeInfoTypes": { # List of exclude infoTypes. # Set of infoTypes for which findings would affect this rule.
5957 "infoTypes": [ # InfoType list in ExclusionRule rule drops a finding when it overlaps or
5958 # contained within with a finding of an infoType from this list. For
5959 # example, for `InspectionRuleSet.info_types` containing "PHONE_NUMBER"` and
5960 # `exclusion_rule` containing `exclude_info_types.info_types` with
5961 # "EMAIL_ADDRESS" the phone number findings are dropped if they overlap
5962 # with EMAIL_ADDRESS finding.
5963 # That leads to "555-222-2222@example.org" to generate only a single
5964 # finding, namely email address.
5965 { # Type of information detected by the API.
5966 "name": "A String", # Name of the information type. Either a name of your choosing when
5967 # creating a CustomInfoType, or one of the names listed
5968 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
5969 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]5970 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]5971 },
5972 ],
5973 },
5974 "dictionary": { # Custom information type based on a dictionary of words or phrases. This can # Dictionary which defines the rule.
5975 # be used to match sensitive information specific to the data, such as a list
5976 # of employee IDs or job titles.
5977 #
5978 # Dictionary words are case-insensitive and all characters other than letters
5979 # and digits in the unicode [Basic Multilingual
5980 # Plane](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane)
5981 # will be replaced with whitespace when scanning for matches, so the
5982 # dictionary phrase "Sam Johnson" will match all three phrases "sam johnson",
5983 # "Sam, Johnson", and "Sam (Johnson)". Additionally, the characters
5984 # surrounding any match must be of a different type than the adjacent
5985 # characters within the word, so letters must be next to non-letters and
5986 # digits next to non-digits. For example, the dictionary word "jen" will
5987 # match the first three letters of the text "jen123" but will return no
5988 # matches for "jennifer".
5989 #
5990 # Dictionary words containing a large number of characters that are not
5991 # letters or digits may result in unexpected findings because such characters
5992 # are treated as whitespace. The
5993 # [limits](https://cloud.google.com/dlp/limits) page contains details about
5994 # the size limits of dictionaries. For dictionaries that do not fit within
5995 # these constraints, consider using `LargeCustomDictionaryConfig` in the
5996 # `StoredInfoType` API.
5997 "wordList": { # Message defining a list of words or phrases to search for in the data. # List of words or phrases to search for.
5998 "words": [ # Words or phrases defining the dictionary. The dictionary must contain
5999 # at least one phrase and every phrase must contain at least 2 characters
6000 # that are letters or digits. [required]
6001 "A String",
6002 ],
6003 },
6004 "cloudStoragePath": { # Message representing a single file or path in Cloud Storage. # Newline-delimited file of words in Cloud Storage. Only a single file
6005 # is accepted.
6006 "path": "A String", # A url representing a file or path (no wildcards) in Cloud Storage.
6007 # Example: gs://[BUCKET_NAME]/dictionary.txt
6008 },
6009 },
6010 "matchingType": "A String", # How the rule is applied, see MatchingType documentation for details.
6011 },
6012 },
6013 ],
6014 "infoTypes": [ # List of infoTypes this rule set is applied to.
6015 { # Type of information detected by the API.
6016 "name": "A String", # Name of the information type. Either a name of your choosing when
6017 # creating a CustomInfoType, or one of the names listed
6018 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
6019 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]6020 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]6021 },
6022 ],
6023 },
6024 ],
6025 "contentOptions": [ # List of options defining data content to scan.
6026 # If empty, text, images, and other content will be included.
6027 "A String",
6028 ],
6029 "infoTypes": [ # Restricts what info_types to look for. The values must correspond to
6030 # InfoType values returned by ListInfoTypes or listed at
6031 # https://cloud.google.com/dlp/docs/infotypes-reference.
6032 #
6033 # When no InfoTypes or CustomInfoTypes are specified in a request, the
6034 # system may automatically choose what detectors to run. By default this may
6035 # be all types, but may change over time as detectors are updated.
6036 #
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]6037 # If you need precise control and predictability as to what detectors are
6038 # run you should specify specific InfoTypes listed in the reference,
6039 # otherwise a default list will be used, which may change over time.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]6040 { # Type of information detected by the API.
6041 "name": "A String", # Name of the information type. Either a name of your choosing when
6042 # creating a CustomInfoType, or one of the names listed
6043 # at https://cloud.google.com/dlp/docs/infotypes-reference when specifying
6044 # a built-in type. InfoType names should conform to the pattern
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]6045 # `[a-zA-Z0-9_]{1,64}`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]6046 },
6047 ],
6048 },
6049 "inspectTemplateName": "A String", # If provided, will be used as the default for all values in InspectConfig.
6050 # `inspect_config` will be merged into the values persisted as part of the
6051 # template.
6052 "actions": [ # Actions to execute at the completion of the job.
6053 { # A task to execute on the completion of a job.
6054 # See https://cloud.google.com/dlp/docs/concepts-actions to learn more.
6055 "saveFindings": { # If set, the detailed findings will be persisted to the specified # Save resulting findings in a provided location.
6056 # OutputStorageConfig. Only a single instance of this action can be
6057 # specified.
6058 # Compatible with: Inspect, Risk
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]6059 "outputConfig": { # Cloud repository for storing output. # Location to store findings outside of DLP.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]6060 "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
6061 # dataset. If table_id is not set a new one will be generated
6062 # for you with the following format:
6063 # dlp_googleapis_yyyy_mm_dd_[dlp_job_id]. Pacific timezone will be used for
6064 # generating the date details.
6065 #
6066 # For Inspect, each column in an existing output table must have the same
6067 # name, type, and mode of a field in the `Finding` object.
6068 #
6069 # For Risk, an existing output table should be the output of a previous
6070 # Risk analysis job run on the same source table, with the same privacy
6071 # metric and quasi-identifiers. Risk jobs that analyze the same table but
6072 # compute a different privacy metric, or use different sets of
6073 # quasi-identifiers, cannot store their results in the same table.
6074 # identified by its project_id, dataset_id, and table_name. Within a query
6075 # a table is often referenced with a string in the format of:
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]6076 # `&lt;project_id&gt;:&lt;dataset_id&gt;.&lt;table_id&gt;` or
6077 # `&lt;project_id&gt;.&lt;dataset_id&gt;.&lt;table_id&gt;`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]6078 "projectId": "A String", # The Google Cloud Platform project ID of the project containing the table.
6079 # If omitted, project ID is inferred from the API call.
6080 "tableId": "A String", # Name of the table.
6081 "datasetId": "A String", # Dataset ID of the table.
6082 },
6083 "outputSchema": "A String", # Schema used for writing the findings for Inspect jobs. This field is only
6084 # used for Inspect and must be unspecified for Risk jobs. Columns are derived
6085 # from the `Finding` object. If appending to an existing table, any columns
6086 # from the predefined schema that are missing will be added. No columns in
6087 # the existing table will be deleted.
6088 #
6089 # If unspecified, then all available columns will be used for a new table or
6090 # an (existing) table with no schema, and no changes will be made to an
6091 # existing table that has a schema.
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]6092 # Only for use with external storage.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]6093 },
6094 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]6095 "jobNotificationEmails": { # Enable email notification to project owners and editors on jobs's # Enable email notification for project owners and editors on job's
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]6096 # completion/failure.
6097 # completion/failure.
6098 },
6099 "publishSummaryToCscc": { # Publish the result summary of a DlpJob to the Cloud Security # Publish summary to Cloud Security Command Center (Alpha).
6100 # Command Center (CSCC Alpha).
6101 # This action is only available for projects which are parts of
6102 # an organization and whitelisted for the alpha Cloud Security Command
6103 # Center.
6104 # The action will publish count of finding instances and their info types.
6105 # The summary of findings will be persisted in CSCC and are governed by CSCC
6106 # service-specific policy, see https://cloud.google.com/terms/service-terms
6107 # Only a single instance of this action can be specified.
6108 # Compatible with: Inspect
6109 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]6110 "publishToStackdriver": { # Enable Stackdriver metric dlp.googleapis.com/finding_count. This # Enable Stackdriver metric dlp.googleapis.com/finding_count.
6111 # will publish a metric to stack driver on each infotype requested and
6112 # how many findings were found for it. CustomDetectors will be bucketed
6113 # as 'Custom' under the Stackdriver label 'info_type'.
6114 },
6115 "publishFindingsToCloudDataCatalog": { # Publish findings of a DlpJob to Cloud Data Catalog. Labels summarizing the # Publish findings to Cloud Datahub.
6116 # results of the DlpJob will be applied to the entry for the resource scanned
6117 # in Cloud Data Catalog. Any labels previously written by another DlpJob will
6118 # be deleted. InfoType naming patterns are strictly enforced when using this
6119 # feature. Note that the findings will be persisted in Cloud Data Catalog
6120 # storage and are governed by Data Catalog service-specific policy, see
6121 # https://cloud.google.com/terms/service-terms
6122 # Only a single instance of this action can be specified and only allowed if
6123 # all resources being scanned are BigQuery tables.
6124 # Compatible with: Inspect
6125 },
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]6126 "pubSub": { # Publish a message into given Pub/Sub topic when DlpJob has completed. The # Publish a notification to a pubsub topic.
6127 # message contains a single field, `DlpJobName`, which is equal to the
6128 # finished job's
6129 # [`DlpJob.name`](/dlp/docs/reference/rest/v2/projects.dlpJobs#DlpJob).
6130 # Compatible with: Inspect, Risk
6131 "topic": "A String", # Cloud Pub/Sub topic to send notifications to. The topic must have given
6132 # publishing access rights to the DLP API service account executing
6133 # the long running DlpJob sending the notifications.
6134 # Format is projects/{project}/topics/{topic}.
6135 },
6136 },
6137 ],
6138 },
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]6139 "lastRunTime": "A String", # Output only. The timestamp of the last time this trigger executed.
6140 "createTime": "A String", # Output only. The creation timestamp of a triggeredJob.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]6141 "name": "A String", # Unique resource name for the triggeredJob, assigned by the service when the
6142 # triggeredJob is created, for example
Dan O'Mearadd494642020-05-01 07:42:23 -0700[diff] [blame^]6143 # `projects/dlp-test-project/jobTriggers/53234423`.
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame]6144 }</pre>
6145</div>
6146
6147</body></html>