/
datacatalog_v1.projects.locations.entryGroups.entries.html
1817 lines (1731 loc) 路 200 KB
/
datacatalog_v1.projects.locations.entryGroups.entries.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
<html><body>
<style>
body, h1, h2, h3, div, span, p, pre, a {
margin: 0;
padding: 0;
border: 0;
font-weight: inherit;
font-style: inherit;
font-size: 100%;
font-family: inherit;
vertical-align: baseline;
}
body {
font-size: 13px;
padding: 1em;
}
h1 {
font-size: 26px;
margin-bottom: 1em;
}
h2 {
font-size: 24px;
margin-bottom: 1em;
}
h3 {
font-size: 20px;
margin-bottom: 1em;
margin-top: 1em;
}
pre, code {
line-height: 1.5;
font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
}
pre {
margin-top: 0.5em;
}
h1, h2, h3, p {
font-family: Arial, sans serif;
}
h1, h2, h3 {
border-bottom: solid #CCC 1px;
}
.toc_element {
margin-top: 0.5em;
}
.firstline {
margin-left: 2 em;
}
.method {
margin-top: 1em;
border: solid 1px #CCC;
padding: 1em;
background: #EEE;
}
.details {
font-weight: bold;
font-size: 14px;
}
</style>
<h1><a href="datacatalog_v1.html">Google Cloud Data Catalog API</a> . <a href="datacatalog_v1.projects.html">projects</a> . <a href="datacatalog_v1.projects.locations.html">locations</a> . <a href="datacatalog_v1.projects.locations.entryGroups.html">entryGroups</a> . <a href="datacatalog_v1.projects.locations.entryGroups.entries.html">entries</a></h1>
<h2>Instance Methods</h2>
<p class="toc_element">
<code><a href="datacatalog_v1.projects.locations.entryGroups.entries.tags.html">tags()</a></code>
</p>
<p class="firstline">Returns the tags Resource.</p>
<p class="toc_element">
<code><a href="#close">close()</a></code></p>
<p class="firstline">Close httplib2 connections.</p>
<p class="toc_element">
<code><a href="#create">create(parent, body=None, entryId=None, x__xgafv=None)</a></code></p>
<p class="firstline">Creates an entry. You can create entries only with 'FILESET', 'CLUSTER', 'DATA_STREAM', or custom types. Data Catalog automatically creates entries with other types during metadata ingestion from integrated systems. You must enable the Data Catalog API in the project identified by the `parent` parameter. For more information, see [Data Catalog resource project](https://cloud.google.com/data-catalog/docs/concepts/resource-project). An entry group can have a maximum of 100,000 entries.</p>
<p class="toc_element">
<code><a href="#delete">delete(name, x__xgafv=None)</a></code></p>
<p class="firstline">Deletes an existing entry. You can delete only the entries created by the CreateEntry method. You must enable the Data Catalog API in the project identified by the `name` parameter. For more information, see [Data Catalog resource project](https://cloud.google.com/data-catalog/docs/concepts/resource-project).</p>
<p class="toc_element">
<code><a href="#get">get(name, x__xgafv=None)</a></code></p>
<p class="firstline">Gets an entry.</p>
<p class="toc_element">
<code><a href="#getIamPolicy">getIamPolicy(resource, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Gets the access control policy for a resource. May return: * A`NOT_FOUND` error if the resource doesn't exist or you don't have the permission to view it. * An empty policy if the resource exists but doesn't have a set policy. Supported resources are: - Tag templates - Entry groups Note: This method doesn't get policies from Google Cloud Platform resources ingested into Data Catalog. To call this method, you must have the following Google IAM permissions: - `datacatalog.tagTemplates.getIamPolicy` to get policies on tag templates. - `datacatalog.entryGroups.getIamPolicy` to get policies on entry groups.</p>
<p class="toc_element">
<code><a href="#import_">import_(parent, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Imports entries from some source (e.g. dump in a Cloud Storage bucket) to the Data Catalog. Dump here is a snapshot of the third-party system state, that needs to be ingested in the Data Catalog. Import of entries is a sync operation that reconciles state of the third-party system and Data Catalog. ImportEntries is a long-running operation done in the background, so this method returns long-running operation resource. The resource can be queried with Operations.GetOperation which contains metadata and response.</p>
<p class="toc_element">
<code><a href="#list">list(parent, pageSize=None, pageToken=None, readMask=None, x__xgafv=None)</a></code></p>
<p class="firstline">Lists entries. Note: Currently, this method can list only custom entries. To get a list of both custom and automatically created entries, use SearchCatalog.</p>
<p class="toc_element">
<code><a href="#list_next">list_next()</a></code></p>
<p class="firstline">Retrieves the next page of results.</p>
<p class="toc_element">
<code><a href="#modifyEntryContacts">modifyEntryContacts(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Modifies contacts, part of the business context of an Entry. To call this method, you must have the `datacatalog.entries.updateContacts` IAM permission on the corresponding project.</p>
<p class="toc_element">
<code><a href="#modifyEntryOverview">modifyEntryOverview(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Modifies entry overview, part of the business context of an Entry. To call this method, you must have the `datacatalog.entries.updateOverview` IAM permission on the corresponding project.</p>
<p class="toc_element">
<code><a href="#patch">patch(name, body=None, updateMask=None, x__xgafv=None)</a></code></p>
<p class="firstline">Updates an existing entry. You must enable the Data Catalog API in the project identified by the `entry.name` parameter. For more information, see [Data Catalog resource project](https://cloud.google.com/data-catalog/docs/concepts/resource-project).</p>
<p class="toc_element">
<code><a href="#star">star(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Marks an Entry as starred by the current user. Starring information is private to each user.</p>
<p class="toc_element">
<code><a href="#testIamPermissions">testIamPermissions(resource, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Gets your permissions on a resource. Returns an empty set of permissions if the resource doesn't exist. Supported resources are: - Tag templates - Entry groups Note: This method gets policies only within Data Catalog and can't be used to get policies from BigQuery, Pub/Sub, Dataproc Metastore, and any external Google Cloud Platform resources ingested into Data Catalog. No Google IAM permissions are required to call this method.</p>
<p class="toc_element">
<code><a href="#unstar">unstar(name, body=None, x__xgafv=None)</a></code></p>
<p class="firstline">Marks an Entry as NOT starred by the current user. Starring information is private to each user.</p>
<h3>Method Details</h3>
<div class="method">
<code class="details" id="close">close()</code>
<pre>Close httplib2 connections.</pre>
</div>
<div class="method">
<code class="details" id="create">create(parent, body=None, entryId=None, x__xgafv=None)</code>
<pre>Creates an entry. You can create entries only with 'FILESET', 'CLUSTER', 'DATA_STREAM', or custom types. Data Catalog automatically creates entries with other types during metadata ingestion from integrated systems. You must enable the Data Catalog API in the project identified by the `parent` parameter. For more information, see [Data Catalog resource project](https://cloud.google.com/data-catalog/docs/concepts/resource-project). An entry group can have a maximum of 100,000 entries.
Args:
parent: string, Required. The name of the entry group this entry belongs to. Note: The entry itself and its child resources might not be stored in the location specified in its name. (required)
body: object, The request body.
The object takes the form of:
{ # Entry metadata. A Data Catalog entry represents another resource in Google Cloud Platform (such as a BigQuery dataset or a Pub/Sub topic) or outside of it. You can use the `linked_resource` field in the entry resource to refer to the original resource ID of the source system. An entry resource contains resource details, for example, its schema. Additionally, you can attach flexible metadata to an entry in the form of a Tag.
"bigqueryDateShardedSpec": { # Specification for a group of BigQuery tables with the `[prefix]YYYYMMDD` name pattern. For more information, see [Introduction to partitioned tables] (https://cloud.google.com/bigquery/docs/partitioned-tables#partitioning_versus_sharding). # Output only. Specification for a group of BigQuery tables with the `[prefix]YYYYMMDD` name pattern. For more information, see [Introduction to partitioned tables] (https://cloud.google.com/bigquery/docs/partitioned-tables#partitioning_versus_sharding).
"dataset": "A String", # Output only. The Data Catalog resource name of the dataset entry the current table belongs to. For example: `projects/{PROJECT_ID}/locations/{LOCATION}/entrygroups/{ENTRY_GROUP_ID}/entries/{ENTRY_ID}`.
"latestShardResource": "A String", # Output only. BigQuery resource name of the latest shard.
"shardCount": "A String", # Output only. Total number of shards.
"tablePrefix": "A String", # Output only. The table name prefix of the shards. The name of any given shard is `[table_prefix]YYYYMMDD`. For example, for the `MyTable20180101` shard, the `table_prefix` is `MyTable`.
},
"bigqueryTableSpec": { # Describes a BigQuery table. # Output only. Specification that applies to a BigQuery table. Valid only for entries with the `TABLE` type.
"tableSourceType": "A String", # Output only. The table source type.
"tableSpec": { # Normal BigQuery table specification. # Specification of a BigQuery table. Populated only if the `table_source_type` is `BIGQUERY_TABLE`.
"groupedEntry": "A String", # Output only. If the table is date-sharded, that is, it matches the `[prefix]YYYYMMDD` name pattern, this field is the Data Catalog resource name of the date-sharded grouped entry. For example: `projects/{PROJECT_ID}/locations/{LOCATION}/entrygroups/{ENTRY_GROUP_ID}/entries/{ENTRY_ID}`. Otherwise, `grouped_entry` is empty.
},
"viewSpec": { # Table view specification. # Table view specification. Populated only if the `table_source_type` is `BIGQUERY_VIEW`.
"viewQuery": "A String", # Output only. The query that defines the table view.
},
},
"businessContext": { # Business Context of the entry. # Business Context of the entry. Not supported for BigQuery datasets
"contacts": { # Contact people for the entry. # Contact people for the entry.
"people": [ # The list of contact people for the entry.
{ # A contact person for the entry.
"designation": "A String", # Designation of the person, for example, Data Steward.
"email": "A String", # Email of the person in the format of `john.doe@xyz`, ``, or `John Doe`.
},
],
},
"entryOverview": { # Entry overview fields for rich text descriptions of entries. # Entry overview fields for rich text descriptions of entries.
"overview": "A String", # Entry overview with support for rich text. The overview must only contain Unicode characters, and should be formatted using HTML. The maximum length is 10 MiB as this value holds HTML descriptions including encoded images. The maximum length of the text without images is 100 KiB.
},
},
"dataSource": { # Physical location of an entry. # Output only. Physical location of the entry.
"resource": "A String", # Full name of a resource as defined by the service. For example: `//bigquery.googleapis.com/projects/{PROJECT_ID}/locations/{LOCATION}/datasets/{DATASET_ID}/tables/{TABLE_ID}`
"service": "A String", # Service that physically stores the data.
"sourceEntry": "A String", # Output only. Data Catalog entry name, if applicable.
"storageProperties": { # Details the properties of the underlying storage. # Detailed properties of the underlying storage.
"filePattern": [ # Patterns to identify a set of files for this fileset. Examples of a valid `file_pattern`: * `gs://bucket_name/dir/*`: matches all files in the `bucket_name/dir` directory * `gs://bucket_name/dir/**`: matches all files in the `bucket_name/dir` and all subdirectories recursively * `gs://bucket_name/file*`: matches files prefixed by `file` in `bucket_name` * `gs://bucket_name/??.txt`: matches files with two characters followed by `.txt` in `bucket_name` * `gs://bucket_name/[aeiou].txt`: matches files that contain a single vowel character followed by `.txt` in `bucket_name` * `gs://bucket_name/[a-m].txt`: matches files that contain `a`, `b`, ... or `m` followed by `.txt` in `bucket_name` * `gs://bucket_name/a/*/b`: matches all files in `bucket_name` that match the `a/*/b` pattern, such as `a/c/b`, `a/d/b` * `gs://another_bucket/a.txt`: matches `gs://another_bucket/a.txt`
"A String",
],
"fileType": "A String", # File type in MIME format, for example, `text/plain`.
},
},
"dataSourceConnectionSpec": { # Specification that applies to a data source connection. Valid only for entries with the `DATA_SOURCE_CONNECTION` type. Only one of internal specs can be set at the time, and cannot be changed later. # Specification that applies to a data source connection. Valid only for entries with the `DATA_SOURCE_CONNECTION` type.
"bigqueryConnectionSpec": { # Specification for the BigQuery connection. # Output only. Fields specific to BigQuery connections.
"cloudSql": { # Specification for the BigQuery connection to a Cloud SQL instance. # Specification for the BigQuery connection to a Cloud SQL instance.
"database": "A String", # Database name.
"instanceId": "A String", # Cloud SQL instance ID in the format of `project:location:instance`.
"type": "A String", # Type of the Cloud SQL database.
},
"connectionType": "A String", # The type of the BigQuery connection.
"hasCredential": True or False, # True if there are credentials attached to the BigQuery connection; false otherwise.
},
},
"databaseTableSpec": { # Specification that applies to a table resource. Valid only for entries with the `TABLE` type. # Specification that applies to a table resource. Valid only for entries with the `TABLE` or `EXPLORE` type.
"databaseViewSpec": { # Specification that applies to database view. # Spec what aplies to tables that are actually views. Not set for "real" tables.
"baseTable": "A String", # Name of a singular table this view reflects one to one.
"sqlQuery": "A String", # SQL query used to generate this view.
"viewType": "A String", # Type of this view.
},
"dataplexTable": { # Entry specification for a Dataplex table. # Output only. Fields specific to a Dataplex table and present only in the Dataplex table entries.
"dataplexSpec": { # Common Dataplex fields. # Common Dataplex fields.
"asset": "A String", # Fully qualified resource name of an asset in Dataplex, to which the underlying data source (Cloud Storage bucket or BigQuery dataset) of the entity is attached.
"compressionFormat": "A String", # Compression format of the data, e.g., zip, gzip etc.
"dataFormat": { # Native schema used by a resource represented as an entry. Used by query engines for deserializing and parsing source data. # Format of the data.
"avro": { # Schema in Avro JSON format. # Schema in Avro JSON format.
"text": "A String", # JSON source of the Avro schema.
},
"csv": { # Marks a CSV-encoded data source. # Marks a CSV-encoded data source.
},
"orc": { # Marks an ORC-encoded data source. # Marks an ORC-encoded data source.
},
"parquet": { # Marks a Parquet-encoded data source. # Marks a Parquet-encoded data source.
},
"protobuf": { # Schema in protocol buffer format. # Schema in protocol buffer format.
"text": "A String", # Protocol buffer source of the schema.
},
"thrift": { # Schema in Thrift format. # Schema in Thrift format.
"text": "A String", # Thrift IDL source of the schema.
},
},
"projectId": "A String", # Project ID of the underlying Cloud Storage or BigQuery data. Note that this may not be the same project as the correspondingly Dataplex lake / zone / asset.
},
"externalTables": [ # List of external tables registered by Dataplex in other systems based on the same underlying data. External tables allow to query this data in those systems.
{ # External table registered by Dataplex. Dataplex publishes data discovered from an asset into multiple other systems (BigQuery, DPMS) in form of tables. We call them "external tables". External tables are also synced into the Data Catalog. This message contains pointers to those external tables (fully qualified name, resource name et cetera) within the Data Catalog.
"dataCatalogEntry": "A String", # Name of the Data Catalog entry representing the external table.
"fullyQualifiedName": "A String", # Fully qualified name (FQN) of the external table.
"googleCloudResource": "A String", # Google Cloud resource name of the external table.
"system": "A String", # Service in which the external table is registered.
},
],
"userManaged": True or False, # Indicates if the table schema is managed by the user or not.
},
"type": "A String", # Type of this table.
},
"description": "A String", # Entry description that can consist of several sentences or paragraphs that describe entry contents. The description must not contain Unicode non-characters as well as C0 and C1 control codes except tabs (HT), new lines (LF), carriage returns (CR), and page breaks (FF). The maximum size is 2000 bytes when encoded in UTF-8. Default value is an empty string.
"displayName": "A String", # Display name of an entry. The maximum size is 500 bytes when encoded in UTF-8. Default value is an empty string.
"filesetSpec": { # Specification that applies to a fileset. Valid only for entries with the 'FILESET' type. # Specification that applies to a fileset resource. Valid only for entries with the `FILESET` type.
"dataplexFileset": { # Entry specyfication for a Dataplex fileset. # Fields specific to a Dataplex fileset and present only in the Dataplex fileset entries.
"dataplexSpec": { # Common Dataplex fields. # Common Dataplex fields.
"asset": "A String", # Fully qualified resource name of an asset in Dataplex, to which the underlying data source (Cloud Storage bucket or BigQuery dataset) of the entity is attached.
"compressionFormat": "A String", # Compression format of the data, e.g., zip, gzip etc.
"dataFormat": { # Native schema used by a resource represented as an entry. Used by query engines for deserializing and parsing source data. # Format of the data.
"avro": { # Schema in Avro JSON format. # Schema in Avro JSON format.
"text": "A String", # JSON source of the Avro schema.
},
"csv": { # Marks a CSV-encoded data source. # Marks a CSV-encoded data source.
},
"orc": { # Marks an ORC-encoded data source. # Marks an ORC-encoded data source.
},
"parquet": { # Marks a Parquet-encoded data source. # Marks a Parquet-encoded data source.
},
"protobuf": { # Schema in protocol buffer format. # Schema in protocol buffer format.
"text": "A String", # Protocol buffer source of the schema.
},
"thrift": { # Schema in Thrift format. # Schema in Thrift format.
"text": "A String", # Thrift IDL source of the schema.
},
},
"projectId": "A String", # Project ID of the underlying Cloud Storage or BigQuery data. Note that this may not be the same project as the correspondingly Dataplex lake / zone / asset.
},
},
},
"fullyQualifiedName": "A String", # Fully qualified name (FQN) of the resource. Set automatically for entries representing resources from synced systems. Settable only during creation and read-only afterwards. Can be used for search and lookup of the entries. FQNs take two forms: * For non-regionalized resources: `{SYSTEM}:{PROJECT}.{PATH_TO_RESOURCE_SEPARATED_WITH_DOTS}` * For regionalized resources: `{SYSTEM}:{PROJECT}.{LOCATION_ID}.{PATH_TO_RESOURCE_SEPARATED_WITH_DOTS}` Example for a DPMS table: `dataproc_metastore:{PROJECT_ID}.{LOCATION_ID}.{INSTANCE_ID}.{DATABASE_ID}.{TABLE_ID}`
"gcsFilesetSpec": { # Describes a Cloud Storage fileset entry. # Specification that applies to a Cloud Storage fileset. Valid only for entries with the `FILESET` type.
"filePatterns": [ # Required. Patterns to identify a set of files in Google Cloud Storage. For more information, see [Wildcard Names] (https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames). Note: Currently, bucket wildcards are not supported. Examples of valid `file_patterns`: * `gs://bucket_name/dir/*`: matches all files in `bucket_name/dir` directory * `gs://bucket_name/dir/**`: matches all files in `bucket_name/dir` and all subdirectories * `gs://bucket_name/file*`: matches files prefixed by `file` in `bucket_name` * `gs://bucket_name/??.txt`: matches files with two characters followed by `.txt` in `bucket_name` * `gs://bucket_name/[aeiou].txt`: matches files that contain a single vowel character followed by `.txt` in `bucket_name` * `gs://bucket_name/[a-m].txt`: matches files that contain `a`, `b`, ... or `m` followed by `.txt` in `bucket_name` * `gs://bucket_name/a/*/b`: matches all files in `bucket_name` that match the `a/*/b` pattern, such as `a/c/b`, `a/d/b` * `gs://another_bucket/a.txt`: matches `gs://another_bucket/a.txt` You can combine wildcards to match complex sets of files, for example: `gs://bucket_name/[a-m]??.j*g`
"A String",
],
"sampleGcsFileSpecs": [ # Output only. Sample files contained in this fileset, not all files contained in this fileset are represented here.
{ # Specification of a single file in Cloud Storage.
"filePath": "A String", # Required. Full file path. Example: `gs://bucket_name/a/b.txt`.
"gcsTimestamps": { # Timestamps associated with this resource in a particular system. # Output only. Creation, modification, and expiration timestamps of a Cloud Storage file.
"createTime": "A String", # Creation timestamp of the resource within the given system.
"expireTime": "A String", # Output only. Expiration timestamp of the resource within the given system. Currently only applicable to BigQuery resources.
"updateTime": "A String", # Timestamp of the last modification of the resource or its metadata within a given system. Note: Depending on the source system, not every modification updates this timestamp. For example, BigQuery timestamps every metadata modification but not data or permission changes.
},
"sizeBytes": "A String", # Output only. File size in bytes.
},
],
},
"integratedSystem": "A String", # Output only. Indicates the entry's source system that Data Catalog integrates with, such as BigQuery, Pub/Sub, or Dataproc Metastore.
"labels": { # Cloud labels attached to the entry. In Data Catalog, you can create and modify labels attached only to custom entries. Synced entries have unmodifiable labels that come from the source system.
"a_key": "A String",
},
"linkedResource": "A String", # The resource this metadata entry refers to. For Google Cloud Platform resources, `linked_resource` is the [Full Resource Name] (https://cloud.google.com/apis/design/resource_names#full_resource_name). For example, the `linked_resource` for a table resource from BigQuery is: `//bigquery.googleapis.com/projects/{PROJECT_ID}/datasets/{DATASET_ID}/tables/{TABLE_ID}` Output only when the entry is one of the types in the `EntryType` enum. For entries with a `user_specified_type`, this field is optional and defaults to an empty string. The resource string must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), periods (.), colons (:), slashes (/), dashes (-), and hashes (#). The maximum size is 200 bytes when encoded in UTF-8.
"lookerSystemSpec": { # Specification that applies to entries that are part `LOOKER` system (user_specified_type) # Specification that applies to Looker sysstem. Only settable when `user_specified_system` is equal to `LOOKER`
"parentInstanceDisplayName": "A String", # Name of the parent Looker Instance. Empty if it does not exist.
"parentInstanceId": "A String", # ID of the parent Looker Instance. Empty if it does not exist. Example value: `someinstance.looker.com`
"parentModelDisplayName": "A String", # Name of the parent Model. Empty if it does not exist.
"parentModelId": "A String", # ID of the parent Model. Empty if it does not exist.
"parentViewDisplayName": "A String", # Name of the parent View. Empty if it does not exist.
"parentViewId": "A String", # ID of the parent View. Empty if it does not exist.
},
"name": "A String", # Output only. The resource name of an entry in URL format. Note: The entry itself and its child resources might not be stored in the location specified in its name.
"personalDetails": { # Entry metadata relevant only to the user and private to them. # Output only. Additional information related to the entry. Private to the current user.
"starTime": "A String", # Set if the entry is starred; unset otherwise.
"starred": True or False, # True if the entry is starred by the user; false otherwise.
},
"routineSpec": { # Specification that applies to a routine. Valid only for entries with the `ROUTINE` type. # Specification that applies to a user-defined function or procedure. Valid only for entries with the `ROUTINE` type.
"bigqueryRoutineSpec": { # Fields specific for BigQuery routines. # Fields specific for BigQuery routines.
"importedLibraries": [ # Paths of the imported libraries.
"A String",
],
},
"definitionBody": "A String", # The body of the routine.
"language": "A String", # The language the routine is written in. The exact value depends on the source system. For BigQuery routines, possible values are: * `SQL` * `JAVASCRIPT`
"returnType": "A String", # Return type of the argument. The exact value depends on the source system and the language.
"routineArguments": [ # Arguments of the routine.
{ # Input or output argument of a function or stored procedure.
"mode": "A String", # Specifies whether the argument is input or output.
"name": "A String", # The name of the argument. A return argument of a function might not have a name.
"type": "A String", # Type of the argument. The exact value depends on the source system and the language.
},
],
"routineType": "A String", # The type of the routine.
},
"schema": { # Represents a schema, for example, a BigQuery, GoogleSQL, or Avro schema. # Schema of the entry. An entry might not have any schema attached to it.
"columns": [ # The unified GoogleSQL-like schema of columns. The overall maximum number of columns and nested columns is 10,000. The maximum nested depth is 15 levels.
{ # A column within a schema. Columns can be nested inside other columns.
"column": "A String", # Required. Name of the column. Must be a UTF-8 string without dots (.). The maximum size is 64 bytes.
"defaultValue": "A String", # Optional. Default value for the column.
"description": "A String", # Optional. Description of the column. Default value is an empty string. The description must be a UTF-8 string with the maximum size of 2000 bytes.
"gcRule": "A String", # Optional. Garbage collection policy for the column or column family. Applies to systems like Cloud Bigtable.
"highestIndexingType": "A String", # Optional. Most important inclusion of this column.
"lookerColumnSpec": { # Column info specific to Looker System. # Looker specific column info of this column.
"type": "A String", # Looker specific column type of this column.
},
"mode": "A String", # Optional. A column's mode indicates whether values in this column are required, nullable, or repeated. Only `NULLABLE`, `REQUIRED`, and `REPEATED` values are supported. Default mode is `NULLABLE`.
"ordinalPosition": 42, # Optional. Ordinal position
"subcolumns": [ # Optional. Schema of sub-columns. A column can have zero or more sub-columns.
# Object with schema name: GoogleCloudDatacatalogV1ColumnSchema
],
"type": "A String", # Required. Type of the column. Must be a UTF-8 string with the maximum size of 128 bytes.
},
],
},
"sourceSystemTimestamps": { # Timestamps associated with this resource in a particular system. # Timestamps from the underlying resource, not from the Data Catalog entry. Output only when the entry has a system listed in the `IntegratedSystem` enum. For entries with `user_specified_system`, this field is optional and defaults to an empty timestamp.
"createTime": "A String", # Creation timestamp of the resource within the given system.
"expireTime": "A String", # Output only. Expiration timestamp of the resource within the given system. Currently only applicable to BigQuery resources.
"updateTime": "A String", # Timestamp of the last modification of the resource or its metadata within a given system. Note: Depending on the source system, not every modification updates this timestamp. For example, BigQuery timestamps every metadata modification but not data or permission changes.
},
"sqlDatabaseSystemSpec": { # Specification that applies to entries that are part `SQL_DATABASE` system (user_specified_type) # Specification that applies to a relational database system. Only settable when `user_specified_system` is equal to `SQL_DATABASE`
"databaseVersion": "A String", # Version of the database engine.
"instanceHost": "A String", # Host of the SQL database enum InstanceHost { UNDEFINED = 0; SELF_HOSTED = 1; CLOUD_SQL = 2; AMAZON_RDS = 3; AZURE_SQL = 4; } Host of the enclousing database instance.
"sqlEngine": "A String", # SQL Database Engine. enum SqlEngine { UNDEFINED = 0; MY_SQL = 1; POSTGRE_SQL = 2; SQL_SERVER = 3; } Engine of the enclosing database instance.
},
"type": "A String", # The type of the entry. Only used for entries with types listed in the `EntryType` enum. Currently, only `FILESET` enum value is allowed. All other entries created in Data Catalog must use the `user_specified_type`.
"usageSignal": { # The set of all usage signals that Data Catalog stores. Note: Usually, these signals are updated daily. In rare cases, an update may fail but will be performed again on the next day. # Resource usage statistics.
"commonUsageWithinTimeRange": { # Common usage statistics over each of the predefined time ranges. Supported time ranges are `{"24H", "7D", "30D", "Lifetime"}`.
"a_key": { # Common statistics on the entry's usage. They can be set on any system.
"viewCount": "A String", # View count in source system.
},
},
"favoriteCount": "A String", # Favorite count in the source system.
"updateTime": "A String", # The end timestamp of the duration of usage statistics.
"usageWithinTimeRange": { # Output only. BigQuery usage statistics over each of the predefined time ranges. Supported time ranges are `{"24H", "7D", "30D"}`.
"a_key": { # Detailed statistics on the entry's usage. Usage statistics have the following limitations: - Only BigQuery tables have them. - They only include BigQuery query jobs. - They might be underestimated because wildcard table references are not yet counted. For more information, see [Querying multiple tables using a wildcard table] (https://cloud.google.com/bigquery/docs/querying-wildcard-tables)
"totalCancellations": 3.14, # The number of cancelled attempts to use the underlying entry.
"totalCompletions": 3.14, # The number of successful uses of the underlying entry.
"totalExecutionTimeForCompletionsMillis": 3.14, # Total time spent only on successful uses, in milliseconds.
"totalFailures": 3.14, # The number of failed attempts to use the underlying entry.
},
},
},
"userSpecifiedSystem": "A String", # Indicates the entry's source system that Data Catalog doesn't automatically integrate with. The `user_specified_system` string has the following limitations: * Is case insensitive. * Must begin with a letter or underscore. * Can only contain letters, numbers, and underscores. * Must be at least 1 character and at most 64 characters long.
"userSpecifiedType": "A String", # Custom entry type that doesn't match any of the values allowed for input and listed in the `EntryType` enum. When creating an entry, first check the type values in the enum. If there are no appropriate types for the new entry, provide a custom value, for example, `my_special_type`. The `user_specified_type` string has the following limitations: * Is case insensitive. * Must begin with a letter or underscore. * Can only contain letters, numbers, and underscores. * Must be at least 1 character and at most 64 characters long.
}
entryId: string, Required. The ID of the entry to create. The ID must contain only letters (a-z, A-Z), numbers (0-9), and underscores (_). The maximum size is 64 bytes when encoded in UTF-8.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Entry metadata. A Data Catalog entry represents another resource in Google Cloud Platform (such as a BigQuery dataset or a Pub/Sub topic) or outside of it. You can use the `linked_resource` field in the entry resource to refer to the original resource ID of the source system. An entry resource contains resource details, for example, its schema. Additionally, you can attach flexible metadata to an entry in the form of a Tag.
"bigqueryDateShardedSpec": { # Specification for a group of BigQuery tables with the `[prefix]YYYYMMDD` name pattern. For more information, see [Introduction to partitioned tables] (https://cloud.google.com/bigquery/docs/partitioned-tables#partitioning_versus_sharding). # Output only. Specification for a group of BigQuery tables with the `[prefix]YYYYMMDD` name pattern. For more information, see [Introduction to partitioned tables] (https://cloud.google.com/bigquery/docs/partitioned-tables#partitioning_versus_sharding).
"dataset": "A String", # Output only. The Data Catalog resource name of the dataset entry the current table belongs to. For example: `projects/{PROJECT_ID}/locations/{LOCATION}/entrygroups/{ENTRY_GROUP_ID}/entries/{ENTRY_ID}`.
"latestShardResource": "A String", # Output only. BigQuery resource name of the latest shard.
"shardCount": "A String", # Output only. Total number of shards.
"tablePrefix": "A String", # Output only. The table name prefix of the shards. The name of any given shard is `[table_prefix]YYYYMMDD`. For example, for the `MyTable20180101` shard, the `table_prefix` is `MyTable`.
},
"bigqueryTableSpec": { # Describes a BigQuery table. # Output only. Specification that applies to a BigQuery table. Valid only for entries with the `TABLE` type.
"tableSourceType": "A String", # Output only. The table source type.
"tableSpec": { # Normal BigQuery table specification. # Specification of a BigQuery table. Populated only if the `table_source_type` is `BIGQUERY_TABLE`.
"groupedEntry": "A String", # Output only. If the table is date-sharded, that is, it matches the `[prefix]YYYYMMDD` name pattern, this field is the Data Catalog resource name of the date-sharded grouped entry. For example: `projects/{PROJECT_ID}/locations/{LOCATION}/entrygroups/{ENTRY_GROUP_ID}/entries/{ENTRY_ID}`. Otherwise, `grouped_entry` is empty.
},
"viewSpec": { # Table view specification. # Table view specification. Populated only if the `table_source_type` is `BIGQUERY_VIEW`.
"viewQuery": "A String", # Output only. The query that defines the table view.
},
},
"businessContext": { # Business Context of the entry. # Business Context of the entry. Not supported for BigQuery datasets
"contacts": { # Contact people for the entry. # Contact people for the entry.
"people": [ # The list of contact people for the entry.
{ # A contact person for the entry.
"designation": "A String", # Designation of the person, for example, Data Steward.
"email": "A String", # Email of the person in the format of `john.doe@xyz`, ``, or `John Doe`.
},
],
},
"entryOverview": { # Entry overview fields for rich text descriptions of entries. # Entry overview fields for rich text descriptions of entries.
"overview": "A String", # Entry overview with support for rich text. The overview must only contain Unicode characters, and should be formatted using HTML. The maximum length is 10 MiB as this value holds HTML descriptions including encoded images. The maximum length of the text without images is 100 KiB.
},
},
"dataSource": { # Physical location of an entry. # Output only. Physical location of the entry.
"resource": "A String", # Full name of a resource as defined by the service. For example: `//bigquery.googleapis.com/projects/{PROJECT_ID}/locations/{LOCATION}/datasets/{DATASET_ID}/tables/{TABLE_ID}`
"service": "A String", # Service that physically stores the data.
"sourceEntry": "A String", # Output only. Data Catalog entry name, if applicable.
"storageProperties": { # Details the properties of the underlying storage. # Detailed properties of the underlying storage.
"filePattern": [ # Patterns to identify a set of files for this fileset. Examples of a valid `file_pattern`: * `gs://bucket_name/dir/*`: matches all files in the `bucket_name/dir` directory * `gs://bucket_name/dir/**`: matches all files in the `bucket_name/dir` and all subdirectories recursively * `gs://bucket_name/file*`: matches files prefixed by `file` in `bucket_name` * `gs://bucket_name/??.txt`: matches files with two characters followed by `.txt` in `bucket_name` * `gs://bucket_name/[aeiou].txt`: matches files that contain a single vowel character followed by `.txt` in `bucket_name` * `gs://bucket_name/[a-m].txt`: matches files that contain `a`, `b`, ... or `m` followed by `.txt` in `bucket_name` * `gs://bucket_name/a/*/b`: matches all files in `bucket_name` that match the `a/*/b` pattern, such as `a/c/b`, `a/d/b` * `gs://another_bucket/a.txt`: matches `gs://another_bucket/a.txt`
"A String",
],
"fileType": "A String", # File type in MIME format, for example, `text/plain`.
},
},
"dataSourceConnectionSpec": { # Specification that applies to a data source connection. Valid only for entries with the `DATA_SOURCE_CONNECTION` type. Only one of internal specs can be set at the time, and cannot be changed later. # Specification that applies to a data source connection. Valid only for entries with the `DATA_SOURCE_CONNECTION` type.
"bigqueryConnectionSpec": { # Specification for the BigQuery connection. # Output only. Fields specific to BigQuery connections.
"cloudSql": { # Specification for the BigQuery connection to a Cloud SQL instance. # Specification for the BigQuery connection to a Cloud SQL instance.
"database": "A String", # Database name.
"instanceId": "A String", # Cloud SQL instance ID in the format of `project:location:instance`.
"type": "A String", # Type of the Cloud SQL database.
},
"connectionType": "A String", # The type of the BigQuery connection.
"hasCredential": True or False, # True if there are credentials attached to the BigQuery connection; false otherwise.
},
},
"databaseTableSpec": { # Specification that applies to a table resource. Valid only for entries with the `TABLE` type. # Specification that applies to a table resource. Valid only for entries with the `TABLE` or `EXPLORE` type.
"databaseViewSpec": { # Specification that applies to database view. # Spec what aplies to tables that are actually views. Not set for "real" tables.
"baseTable": "A String", # Name of a singular table this view reflects one to one.
"sqlQuery": "A String", # SQL query used to generate this view.
"viewType": "A String", # Type of this view.
},
"dataplexTable": { # Entry specification for a Dataplex table. # Output only. Fields specific to a Dataplex table and present only in the Dataplex table entries.
"dataplexSpec": { # Common Dataplex fields. # Common Dataplex fields.
"asset": "A String", # Fully qualified resource name of an asset in Dataplex, to which the underlying data source (Cloud Storage bucket or BigQuery dataset) of the entity is attached.
"compressionFormat": "A String", # Compression format of the data, e.g., zip, gzip etc.
"dataFormat": { # Native schema used by a resource represented as an entry. Used by query engines for deserializing and parsing source data. # Format of the data.
"avro": { # Schema in Avro JSON format. # Schema in Avro JSON format.
"text": "A String", # JSON source of the Avro schema.
},
"csv": { # Marks a CSV-encoded data source. # Marks a CSV-encoded data source.
},
"orc": { # Marks an ORC-encoded data source. # Marks an ORC-encoded data source.
},
"parquet": { # Marks a Parquet-encoded data source. # Marks a Parquet-encoded data source.
},
"protobuf": { # Schema in protocol buffer format. # Schema in protocol buffer format.
"text": "A String", # Protocol buffer source of the schema.
},
"thrift": { # Schema in Thrift format. # Schema in Thrift format.
"text": "A String", # Thrift IDL source of the schema.
},
},
"projectId": "A String", # Project ID of the underlying Cloud Storage or BigQuery data. Note that this may not be the same project as the correspondingly Dataplex lake / zone / asset.
},
"externalTables": [ # List of external tables registered by Dataplex in other systems based on the same underlying data. External tables allow to query this data in those systems.
{ # External table registered by Dataplex. Dataplex publishes data discovered from an asset into multiple other systems (BigQuery, DPMS) in form of tables. We call them "external tables". External tables are also synced into the Data Catalog. This message contains pointers to those external tables (fully qualified name, resource name et cetera) within the Data Catalog.
"dataCatalogEntry": "A String", # Name of the Data Catalog entry representing the external table.
"fullyQualifiedName": "A String", # Fully qualified name (FQN) of the external table.
"googleCloudResource": "A String", # Google Cloud resource name of the external table.
"system": "A String", # Service in which the external table is registered.
},
],
"userManaged": True or False, # Indicates if the table schema is managed by the user or not.
},
"type": "A String", # Type of this table.
},
"description": "A String", # Entry description that can consist of several sentences or paragraphs that describe entry contents. The description must not contain Unicode non-characters as well as C0 and C1 control codes except tabs (HT), new lines (LF), carriage returns (CR), and page breaks (FF). The maximum size is 2000 bytes when encoded in UTF-8. Default value is an empty string.
"displayName": "A String", # Display name of an entry. The maximum size is 500 bytes when encoded in UTF-8. Default value is an empty string.
"filesetSpec": { # Specification that applies to a fileset. Valid only for entries with the 'FILESET' type. # Specification that applies to a fileset resource. Valid only for entries with the `FILESET` type.
"dataplexFileset": { # Entry specyfication for a Dataplex fileset. # Fields specific to a Dataplex fileset and present only in the Dataplex fileset entries.
"dataplexSpec": { # Common Dataplex fields. # Common Dataplex fields.
"asset": "A String", # Fully qualified resource name of an asset in Dataplex, to which the underlying data source (Cloud Storage bucket or BigQuery dataset) of the entity is attached.
"compressionFormat": "A String", # Compression format of the data, e.g., zip, gzip etc.
"dataFormat": { # Native schema used by a resource represented as an entry. Used by query engines for deserializing and parsing source data. # Format of the data.
"avro": { # Schema in Avro JSON format. # Schema in Avro JSON format.
"text": "A String", # JSON source of the Avro schema.
},
"csv": { # Marks a CSV-encoded data source. # Marks a CSV-encoded data source.
},
"orc": { # Marks an ORC-encoded data source. # Marks an ORC-encoded data source.
},
"parquet": { # Marks a Parquet-encoded data source. # Marks a Parquet-encoded data source.
},
"protobuf": { # Schema in protocol buffer format. # Schema in protocol buffer format.
"text": "A String", # Protocol buffer source of the schema.
},
"thrift": { # Schema in Thrift format. # Schema in Thrift format.
"text": "A String", # Thrift IDL source of the schema.
},
},
"projectId": "A String", # Project ID of the underlying Cloud Storage or BigQuery data. Note that this may not be the same project as the correspondingly Dataplex lake / zone / asset.
},
},
},
"fullyQualifiedName": "A String", # Fully qualified name (FQN) of the resource. Set automatically for entries representing resources from synced systems. Settable only during creation and read-only afterwards. Can be used for search and lookup of the entries. FQNs take two forms: * For non-regionalized resources: `{SYSTEM}:{PROJECT}.{PATH_TO_RESOURCE_SEPARATED_WITH_DOTS}` * For regionalized resources: `{SYSTEM}:{PROJECT}.{LOCATION_ID}.{PATH_TO_RESOURCE_SEPARATED_WITH_DOTS}` Example for a DPMS table: `dataproc_metastore:{PROJECT_ID}.{LOCATION_ID}.{INSTANCE_ID}.{DATABASE_ID}.{TABLE_ID}`
"gcsFilesetSpec": { # Describes a Cloud Storage fileset entry. # Specification that applies to a Cloud Storage fileset. Valid only for entries with the `FILESET` type.
"filePatterns": [ # Required. Patterns to identify a set of files in Google Cloud Storage. For more information, see [Wildcard Names] (https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames). Note: Currently, bucket wildcards are not supported. Examples of valid `file_patterns`: * `gs://bucket_name/dir/*`: matches all files in `bucket_name/dir` directory * `gs://bucket_name/dir/**`: matches all files in `bucket_name/dir` and all subdirectories * `gs://bucket_name/file*`: matches files prefixed by `file` in `bucket_name` * `gs://bucket_name/??.txt`: matches files with two characters followed by `.txt` in `bucket_name` * `gs://bucket_name/[aeiou].txt`: matches files that contain a single vowel character followed by `.txt` in `bucket_name` * `gs://bucket_name/[a-m].txt`: matches files that contain `a`, `b`, ... or `m` followed by `.txt` in `bucket_name` * `gs://bucket_name/a/*/b`: matches all files in `bucket_name` that match the `a/*/b` pattern, such as `a/c/b`, `a/d/b` * `gs://another_bucket/a.txt`: matches `gs://another_bucket/a.txt` You can combine wildcards to match complex sets of files, for example: `gs://bucket_name/[a-m]??.j*g`
"A String",
],
"sampleGcsFileSpecs": [ # Output only. Sample files contained in this fileset, not all files contained in this fileset are represented here.
{ # Specification of a single file in Cloud Storage.
"filePath": "A String", # Required. Full file path. Example: `gs://bucket_name/a/b.txt`.
"gcsTimestamps": { # Timestamps associated with this resource in a particular system. # Output only. Creation, modification, and expiration timestamps of a Cloud Storage file.
"createTime": "A String", # Creation timestamp of the resource within the given system.
"expireTime": "A String", # Output only. Expiration timestamp of the resource within the given system. Currently only applicable to BigQuery resources.
"updateTime": "A String", # Timestamp of the last modification of the resource or its metadata within a given system. Note: Depending on the source system, not every modification updates this timestamp. For example, BigQuery timestamps every metadata modification but not data or permission changes.
},
"sizeBytes": "A String", # Output only. File size in bytes.
},
],
},
"integratedSystem": "A String", # Output only. Indicates the entry's source system that Data Catalog integrates with, such as BigQuery, Pub/Sub, or Dataproc Metastore.
"labels": { # Cloud labels attached to the entry. In Data Catalog, you can create and modify labels attached only to custom entries. Synced entries have unmodifiable labels that come from the source system.
"a_key": "A String",
},
"linkedResource": "A String", # The resource this metadata entry refers to. For Google Cloud Platform resources, `linked_resource` is the [Full Resource Name] (https://cloud.google.com/apis/design/resource_names#full_resource_name). For example, the `linked_resource` for a table resource from BigQuery is: `//bigquery.googleapis.com/projects/{PROJECT_ID}/datasets/{DATASET_ID}/tables/{TABLE_ID}` Output only when the entry is one of the types in the `EntryType` enum. For entries with a `user_specified_type`, this field is optional and defaults to an empty string. The resource string must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), periods (.), colons (:), slashes (/), dashes (-), and hashes (#). The maximum size is 200 bytes when encoded in UTF-8.
"lookerSystemSpec": { # Specification that applies to entries that are part `LOOKER` system (user_specified_type) # Specification that applies to Looker sysstem. Only settable when `user_specified_system` is equal to `LOOKER`
"parentInstanceDisplayName": "A String", # Name of the parent Looker Instance. Empty if it does not exist.
"parentInstanceId": "A String", # ID of the parent Looker Instance. Empty if it does not exist. Example value: `someinstance.looker.com`
"parentModelDisplayName": "A String", # Name of the parent Model. Empty if it does not exist.
"parentModelId": "A String", # ID of the parent Model. Empty if it does not exist.
"parentViewDisplayName": "A String", # Name of the parent View. Empty if it does not exist.
"parentViewId": "A String", # ID of the parent View. Empty if it does not exist.
},
"name": "A String", # Output only. The resource name of an entry in URL format. Note: The entry itself and its child resources might not be stored in the location specified in its name.
"personalDetails": { # Entry metadata relevant only to the user and private to them. # Output only. Additional information related to the entry. Private to the current user.
"starTime": "A String", # Set if the entry is starred; unset otherwise.
"starred": True or False, # True if the entry is starred by the user; false otherwise.
},
"routineSpec": { # Specification that applies to a routine. Valid only for entries with the `ROUTINE` type. # Specification that applies to a user-defined function or procedure. Valid only for entries with the `ROUTINE` type.
"bigqueryRoutineSpec": { # Fields specific for BigQuery routines. # Fields specific for BigQuery routines.
"importedLibraries": [ # Paths of the imported libraries.
"A String",
],
},
"definitionBody": "A String", # The body of the routine.
"language": "A String", # The language the routine is written in. The exact value depends on the source system. For BigQuery routines, possible values are: * `SQL` * `JAVASCRIPT`
"returnType": "A String", # Return type of the argument. The exact value depends on the source system and the language.
"routineArguments": [ # Arguments of the routine.
{ # Input or output argument of a function or stored procedure.
"mode": "A String", # Specifies whether the argument is input or output.
"name": "A String", # The name of the argument. A return argument of a function might not have a name.
"type": "A String", # Type of the argument. The exact value depends on the source system and the language.
},
],
"routineType": "A String", # The type of the routine.
},
"schema": { # Represents a schema, for example, a BigQuery, GoogleSQL, or Avro schema. # Schema of the entry. An entry might not have any schema attached to it.
"columns": [ # The unified GoogleSQL-like schema of columns. The overall maximum number of columns and nested columns is 10,000. The maximum nested depth is 15 levels.
{ # A column within a schema. Columns can be nested inside other columns.
"column": "A String", # Required. Name of the column. Must be a UTF-8 string without dots (.). The maximum size is 64 bytes.
"defaultValue": "A String", # Optional. Default value for the column.
"description": "A String", # Optional. Description of the column. Default value is an empty string. The description must be a UTF-8 string with the maximum size of 2000 bytes.
"gcRule": "A String", # Optional. Garbage collection policy for the column or column family. Applies to systems like Cloud Bigtable.
"highestIndexingType": "A String", # Optional. Most important inclusion of this column.
"lookerColumnSpec": { # Column info specific to Looker System. # Looker specific column info of this column.
"type": "A String", # Looker specific column type of this column.
},
"mode": "A String", # Optional. A column's mode indicates whether values in this column are required, nullable, or repeated. Only `NULLABLE`, `REQUIRED`, and `REPEATED` values are supported. Default mode is `NULLABLE`.
"ordinalPosition": 42, # Optional. Ordinal position
"subcolumns": [ # Optional. Schema of sub-columns. A column can have zero or more sub-columns.
# Object with schema name: GoogleCloudDatacatalogV1ColumnSchema
],
"type": "A String", # Required. Type of the column. Must be a UTF-8 string with the maximum size of 128 bytes.
},
],
},
"sourceSystemTimestamps": { # Timestamps associated with this resource in a particular system. # Timestamps from the underlying resource, not from the Data Catalog entry. Output only when the entry has a system listed in the `IntegratedSystem` enum. For entries with `user_specified_system`, this field is optional and defaults to an empty timestamp.
"createTime": "A String", # Creation timestamp of the resource within the given system.
"expireTime": "A String", # Output only. Expiration timestamp of the resource within the given system. Currently only applicable to BigQuery resources.
"updateTime": "A String", # Timestamp of the last modification of the resource or its metadata within a given system. Note: Depending on the source system, not every modification updates this timestamp. For example, BigQuery timestamps every metadata modification but not data or permission changes.
},
"sqlDatabaseSystemSpec": { # Specification that applies to entries that are part `SQL_DATABASE` system (user_specified_type) # Specification that applies to a relational database system. Only settable when `user_specified_system` is equal to `SQL_DATABASE`
"databaseVersion": "A String", # Version of the database engine.
"instanceHost": "A String", # Host of the SQL database enum InstanceHost { UNDEFINED = 0; SELF_HOSTED = 1; CLOUD_SQL = 2; AMAZON_RDS = 3; AZURE_SQL = 4; } Host of the enclousing database instance.
"sqlEngine": "A String", # SQL Database Engine. enum SqlEngine { UNDEFINED = 0; MY_SQL = 1; POSTGRE_SQL = 2; SQL_SERVER = 3; } Engine of the enclosing database instance.
},
"type": "A String", # The type of the entry. Only used for entries with types listed in the `EntryType` enum. Currently, only `FILESET` enum value is allowed. All other entries created in Data Catalog must use the `user_specified_type`.
"usageSignal": { # The set of all usage signals that Data Catalog stores. Note: Usually, these signals are updated daily. In rare cases, an update may fail but will be performed again on the next day. # Resource usage statistics.
"commonUsageWithinTimeRange": { # Common usage statistics over each of the predefined time ranges. Supported time ranges are `{"24H", "7D", "30D", "Lifetime"}`.
"a_key": { # Common statistics on the entry's usage. They can be set on any system.
"viewCount": "A String", # View count in source system.
},
},
"favoriteCount": "A String", # Favorite count in the source system.
"updateTime": "A String", # The end timestamp of the duration of usage statistics.
"usageWithinTimeRange": { # Output only. BigQuery usage statistics over each of the predefined time ranges. Supported time ranges are `{"24H", "7D", "30D"}`.
"a_key": { # Detailed statistics on the entry's usage. Usage statistics have the following limitations: - Only BigQuery tables have them. - They only include BigQuery query jobs. - They might be underestimated because wildcard table references are not yet counted. For more information, see [Querying multiple tables using a wildcard table] (https://cloud.google.com/bigquery/docs/querying-wildcard-tables)
"totalCancellations": 3.14, # The number of cancelled attempts to use the underlying entry.
"totalCompletions": 3.14, # The number of successful uses of the underlying entry.
"totalExecutionTimeForCompletionsMillis": 3.14, # Total time spent only on successful uses, in milliseconds.
"totalFailures": 3.14, # The number of failed attempts to use the underlying entry.
},
},
},
"userSpecifiedSystem": "A String", # Indicates the entry's source system that Data Catalog doesn't automatically integrate with. The `user_specified_system` string has the following limitations: * Is case insensitive. * Must begin with a letter or underscore. * Can only contain letters, numbers, and underscores. * Must be at least 1 character and at most 64 characters long.
"userSpecifiedType": "A String", # Custom entry type that doesn't match any of the values allowed for input and listed in the `EntryType` enum. When creating an entry, first check the type values in the enum. If there are no appropriate types for the new entry, provide a custom value, for example, `my_special_type`. The `user_specified_type` string has the following limitations: * Is case insensitive. * Must begin with a letter or underscore. * Can only contain letters, numbers, and underscores. * Must be at least 1 character and at most 64 characters long.
}</pre>
</div>
<div class="method">
<code class="details" id="delete">delete(name, x__xgafv=None)</code>
<pre>Deletes an existing entry. You can delete only the entries created by the CreateEntry method. You must enable the Data Catalog API in the project identified by the `name` parameter. For more information, see [Data Catalog resource project](https://cloud.google.com/data-catalog/docs/concepts/resource-project).
Args:
name: string, Required. The name of the entry to delete. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }
}</pre>
</div>
<div class="method">
<code class="details" id="get">get(name, x__xgafv=None)</code>
<pre>Gets an entry.
Args:
name: string, Required. The name of the entry to get. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Entry metadata. A Data Catalog entry represents another resource in Google Cloud Platform (such as a BigQuery dataset or a Pub/Sub topic) or outside of it. You can use the `linked_resource` field in the entry resource to refer to the original resource ID of the source system. An entry resource contains resource details, for example, its schema. Additionally, you can attach flexible metadata to an entry in the form of a Tag.
"bigqueryDateShardedSpec": { # Specification for a group of BigQuery tables with the `[prefix]YYYYMMDD` name pattern. For more information, see [Introduction to partitioned tables] (https://cloud.google.com/bigquery/docs/partitioned-tables#partitioning_versus_sharding). # Output only. Specification for a group of BigQuery tables with the `[prefix]YYYYMMDD` name pattern. For more information, see [Introduction to partitioned tables] (https://cloud.google.com/bigquery/docs/partitioned-tables#partitioning_versus_sharding).
"dataset": "A String", # Output only. The Data Catalog resource name of the dataset entry the current table belongs to. For example: `projects/{PROJECT_ID}/locations/{LOCATION}/entrygroups/{ENTRY_GROUP_ID}/entries/{ENTRY_ID}`.
"latestShardResource": "A String", # Output only. BigQuery resource name of the latest shard.
"shardCount": "A String", # Output only. Total number of shards.
"tablePrefix": "A String", # Output only. The table name prefix of the shards. The name of any given shard is `[table_prefix]YYYYMMDD`. For example, for the `MyTable20180101` shard, the `table_prefix` is `MyTable`.
},
"bigqueryTableSpec": { # Describes a BigQuery table. # Output only. Specification that applies to a BigQuery table. Valid only for entries with the `TABLE` type.
"tableSourceType": "A String", # Output only. The table source type.
"tableSpec": { # Normal BigQuery table specification. # Specification of a BigQuery table. Populated only if the `table_source_type` is `BIGQUERY_TABLE`.
"groupedEntry": "A String", # Output only. If the table is date-sharded, that is, it matches the `[prefix]YYYYMMDD` name pattern, this field is the Data Catalog resource name of the date-sharded grouped entry. For example: `projects/{PROJECT_ID}/locations/{LOCATION}/entrygroups/{ENTRY_GROUP_ID}/entries/{ENTRY_ID}`. Otherwise, `grouped_entry` is empty.
},
"viewSpec": { # Table view specification. # Table view specification. Populated only if the `table_source_type` is `BIGQUERY_VIEW`.
"viewQuery": "A String", # Output only. The query that defines the table view.
},
},
"businessContext": { # Business Context of the entry. # Business Context of the entry. Not supported for BigQuery datasets
"contacts": { # Contact people for the entry. # Contact people for the entry.
"people": [ # The list of contact people for the entry.
{ # A contact person for the entry.
"designation": "A String", # Designation of the person, for example, Data Steward.
"email": "A String", # Email of the person in the format of `john.doe@xyz`, ``, or `John Doe`.
},
],
},
"entryOverview": { # Entry overview fields for rich text descriptions of entries. # Entry overview fields for rich text descriptions of entries.
"overview": "A String", # Entry overview with support for rich text. The overview must only contain Unicode characters, and should be formatted using HTML. The maximum length is 10 MiB as this value holds HTML descriptions including encoded images. The maximum length of the text without images is 100 KiB.
},
},
"dataSource": { # Physical location of an entry. # Output only. Physical location of the entry.
"resource": "A String", # Full name of a resource as defined by the service. For example: `//bigquery.googleapis.com/projects/{PROJECT_ID}/locations/{LOCATION}/datasets/{DATASET_ID}/tables/{TABLE_ID}`
"service": "A String", # Service that physically stores the data.
"sourceEntry": "A String", # Output only. Data Catalog entry name, if applicable.
"storageProperties": { # Details the properties of the underlying storage. # Detailed properties of the underlying storage.
"filePattern": [ # Patterns to identify a set of files for this fileset. Examples of a valid `file_pattern`: * `gs://bucket_name/dir/*`: matches all files in the `bucket_name/dir` directory * `gs://bucket_name/dir/**`: matches all files in the `bucket_name/dir` and all subdirectories recursively * `gs://bucket_name/file*`: matches files prefixed by `file` in `bucket_name` * `gs://bucket_name/??.txt`: matches files with two characters followed by `.txt` in `bucket_name` * `gs://bucket_name/[aeiou].txt`: matches files that contain a single vowel character followed by `.txt` in `bucket_name` * `gs://bucket_name/[a-m].txt`: matches files that contain `a`, `b`, ... or `m` followed by `.txt` in `bucket_name` * `gs://bucket_name/a/*/b`: matches all files in `bucket_name` that match the `a/*/b` pattern, such as `a/c/b`, `a/d/b` * `gs://another_bucket/a.txt`: matches `gs://another_bucket/a.txt`
"A String",
],
"fileType": "A String", # File type in MIME format, for example, `text/plain`.
},
},
"dataSourceConnectionSpec": { # Specification that applies to a data source connection. Valid only for entries with the `DATA_SOURCE_CONNECTION` type. Only one of internal specs can be set at the time, and cannot be changed later. # Specification that applies to a data source connection. Valid only for entries with the `DATA_SOURCE_CONNECTION` type.
"bigqueryConnectionSpec": { # Specification for the BigQuery connection. # Output only. Fields specific to BigQuery connections.
"cloudSql": { # Specification for the BigQuery connection to a Cloud SQL instance. # Specification for the BigQuery connection to a Cloud SQL instance.
"database": "A String", # Database name.
"instanceId": "A String", # Cloud SQL instance ID in the format of `project:location:instance`.
"type": "A String", # Type of the Cloud SQL database.
},
"connectionType": "A String", # The type of the BigQuery connection.
"hasCredential": True or False, # True if there are credentials attached to the BigQuery connection; false otherwise.
},
},
"databaseTableSpec": { # Specification that applies to a table resource. Valid only for entries with the `TABLE` type. # Specification that applies to a table resource. Valid only for entries with the `TABLE` or `EXPLORE` type.
"databaseViewSpec": { # Specification that applies to database view. # Spec what aplies to tables that are actually views. Not set for "real" tables.
"baseTable": "A String", # Name of a singular table this view reflects one to one.
"sqlQuery": "A String", # SQL query used to generate this view.
"viewType": "A String", # Type of this view.
},
"dataplexTable": { # Entry specification for a Dataplex table. # Output only. Fields specific to a Dataplex table and present only in the Dataplex table entries.
"dataplexSpec": { # Common Dataplex fields. # Common Dataplex fields.
"asset": "A String", # Fully qualified resource name of an asset in Dataplex, to which the underlying data source (Cloud Storage bucket or BigQuery dataset) of the entity is attached.
"compressionFormat": "A String", # Compression format of the data, e.g., zip, gzip etc.
"dataFormat": { # Native schema used by a resource represented as an entry. Used by query engines for deserializing and parsing source data. # Format of the data.
"avro": { # Schema in Avro JSON format. # Schema in Avro JSON format.
"text": "A String", # JSON source of the Avro schema.
},
"csv": { # Marks a CSV-encoded data source. # Marks a CSV-encoded data source.
},
"orc": { # Marks an ORC-encoded data source. # Marks an ORC-encoded data source.
},
"parquet": { # Marks a Parquet-encoded data source. # Marks a Parquet-encoded data source.
},
"protobuf": { # Schema in protocol buffer format. # Schema in protocol buffer format.
"text": "A String", # Protocol buffer source of the schema.
},
"thrift": { # Schema in Thrift format. # Schema in Thrift format.
"text": "A String", # Thrift IDL source of the schema.
},
},
"projectId": "A String", # Project ID of the underlying Cloud Storage or BigQuery data. Note that this may not be the same project as the correspondingly Dataplex lake / zone / asset.
},
"externalTables": [ # List of external tables registered by Dataplex in other systems based on the same underlying data. External tables allow to query this data in those systems.
{ # External table registered by Dataplex. Dataplex publishes data discovered from an asset into multiple other systems (BigQuery, DPMS) in form of tables. We call them "external tables". External tables are also synced into the Data Catalog. This message contains pointers to those external tables (fully qualified name, resource name et cetera) within the Data Catalog.
"dataCatalogEntry": "A String", # Name of the Data Catalog entry representing the external table.
"fullyQualifiedName": "A String", # Fully qualified name (FQN) of the external table.
"googleCloudResource": "A String", # Google Cloud resource name of the external table.
"system": "A String", # Service in which the external table is registered.
},
],
"userManaged": True or False, # Indicates if the table schema is managed by the user or not.
},
"type": "A String", # Type of this table.
},
"description": "A String", # Entry description that can consist of several sentences or paragraphs that describe entry contents. The description must not contain Unicode non-characters as well as C0 and C1 control codes except tabs (HT), new lines (LF), carriage returns (CR), and page breaks (FF). The maximum size is 2000 bytes when encoded in UTF-8. Default value is an empty string.
"displayName": "A String", # Display name of an entry. The maximum size is 500 bytes when encoded in UTF-8. Default value is an empty string.
"filesetSpec": { # Specification that applies to a fileset. Valid only for entries with the 'FILESET' type. # Specification that applies to a fileset resource. Valid only for entries with the `FILESET` type.
"dataplexFileset": { # Entry specyfication for a Dataplex fileset. # Fields specific to a Dataplex fileset and present only in the Dataplex fileset entries.
"dataplexSpec": { # Common Dataplex fields. # Common Dataplex fields.
"asset": "A String", # Fully qualified resource name of an asset in Dataplex, to which the underlying data source (Cloud Storage bucket or BigQuery dataset) of the entity is attached.
"compressionFormat": "A String", # Compression format of the data, e.g., zip, gzip etc.
"dataFormat": { # Native schema used by a resource represented as an entry. Used by query engines for deserializing and parsing source data. # Format of the data.
"avro": { # Schema in Avro JSON format. # Schema in Avro JSON format.
"text": "A String", # JSON source of the Avro schema.
},
"csv": { # Marks a CSV-encoded data source. # Marks a CSV-encoded data source.
},
"orc": { # Marks an ORC-encoded data source. # Marks an ORC-encoded data source.
},
"parquet": { # Marks a Parquet-encoded data source. # Marks a Parquet-encoded data source.
},
"protobuf": { # Schema in protocol buffer format. # Schema in protocol buffer format.
"text": "A String", # Protocol buffer source of the schema.
},
"thrift": { # Schema in Thrift format. # Schema in Thrift format.
"text": "A String", # Thrift IDL source of the schema.
},
},
"projectId": "A String", # Project ID of the underlying Cloud Storage or BigQuery data. Note that this may not be the same project as the correspondingly Dataplex lake / zone / asset.
},
},
},
"fullyQualifiedName": "A String", # Fully qualified name (FQN) of the resource. Set automatically for entries representing resources from synced systems. Settable only during creation and read-only afterwards. Can be used for search and lookup of the entries. FQNs take two forms: * For non-regionalized resources: `{SYSTEM}:{PROJECT}.{PATH_TO_RESOURCE_SEPARATED_WITH_DOTS}` * For regionalized resources: `{SYSTEM}:{PROJECT}.{LOCATION_ID}.{PATH_TO_RESOURCE_SEPARATED_WITH_DOTS}` Example for a DPMS table: `dataproc_metastore:{PROJECT_ID}.{LOCATION_ID}.{INSTANCE_ID}.{DATABASE_ID}.{TABLE_ID}`
"gcsFilesetSpec": { # Describes a Cloud Storage fileset entry. # Specification that applies to a Cloud Storage fileset. Valid only for entries with the `FILESET` type.
"filePatterns": [ # Required. Patterns to identify a set of files in Google Cloud Storage. For more information, see [Wildcard Names] (https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames). Note: Currently, bucket wildcards are not supported. Examples of valid `file_patterns`: * `gs://bucket_name/dir/*`: matches all files in `bucket_name/dir` directory * `gs://bucket_name/dir/**`: matches all files in `bucket_name/dir` and all subdirectories * `gs://bucket_name/file*`: matches files prefixed by `file` in `bucket_name` * `gs://bucket_name/??.txt`: matches files with two characters followed by `.txt` in `bucket_name` * `gs://bucket_name/[aeiou].txt`: matches files that contain a single vowel character followed by `.txt` in `bucket_name` * `gs://bucket_name/[a-m].txt`: matches files that contain `a`, `b`, ... or `m` followed by `.txt` in `bucket_name` * `gs://bucket_name/a/*/b`: matches all files in `bucket_name` that match the `a/*/b` pattern, such as `a/c/b`, `a/d/b` * `gs://another_bucket/a.txt`: matches `gs://another_bucket/a.txt` You can combine wildcards to match complex sets of files, for example: `gs://bucket_name/[a-m]??.j*g`
"A String",
],
"sampleGcsFileSpecs": [ # Output only. Sample files contained in this fileset, not all files contained in this fileset are represented here.
{ # Specification of a single file in Cloud Storage.
"filePath": "A String", # Required. Full file path. Example: `gs://bucket_name/a/b.txt`.
"gcsTimestamps": { # Timestamps associated with this resource in a particular system. # Output only. Creation, modification, and expiration timestamps of a Cloud Storage file.
"createTime": "A String", # Creation timestamp of the resource within the given system.
"expireTime": "A String", # Output only. Expiration timestamp of the resource within the given system. Currently only applicable to BigQuery resources.
"updateTime": "A String", # Timestamp of the last modification of the resource or its metadata within a given system. Note: Depending on the source system, not every modification updates this timestamp. For example, BigQuery timestamps every metadata modification but not data or permission changes.
},
"sizeBytes": "A String", # Output only. File size in bytes.
},
],
},
"integratedSystem": "A String", # Output only. Indicates the entry's source system that Data Catalog integrates with, such as BigQuery, Pub/Sub, or Dataproc Metastore.
"labels": { # Cloud labels attached to the entry. In Data Catalog, you can create and modify labels attached only to custom entries. Synced entries have unmodifiable labels that come from the source system.
"a_key": "A String",
},
"linkedResource": "A String", # The resource this metadata entry refers to. For Google Cloud Platform resources, `linked_resource` is the [Full Resource Name] (https://cloud.google.com/apis/design/resource_names#full_resource_name). For example, the `linked_resource` for a table resource from BigQuery is: `//bigquery.googleapis.com/projects/{PROJECT_ID}/datasets/{DATASET_ID}/tables/{TABLE_ID}` Output only when the entry is one of the types in the `EntryType` enum. For entries with a `user_specified_type`, this field is optional and defaults to an empty string. The resource string must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), periods (.), colons (:), slashes (/), dashes (-), and hashes (#). The maximum size is 200 bytes when encoded in UTF-8.
"lookerSystemSpec": { # Specification that applies to entries that are part `LOOKER` system (user_specified_type) # Specification that applies to Looker sysstem. Only settable when `user_specified_system` is equal to `LOOKER`
"parentInstanceDisplayName": "A String", # Name of the parent Looker Instance. Empty if it does not exist.
"parentInstanceId": "A String", # ID of the parent Looker Instance. Empty if it does not exist. Example value: `someinstance.looker.com`
"parentModelDisplayName": "A String", # Name of the parent Model. Empty if it does not exist.
"parentModelId": "A String", # ID of the parent Model. Empty if it does not exist.
"parentViewDisplayName": "A String", # Name of the parent View. Empty if it does not exist.
"parentViewId": "A String", # ID of the parent View. Empty if it does not exist.
},
"name": "A String", # Output only. The resource name of an entry in URL format. Note: The entry itself and its child resources might not be stored in the location specified in its name.
"personalDetails": { # Entry metadata relevant only to the user and private to them. # Output only. Additional information related to the entry. Private to the current user.
"starTime": "A String", # Set if the entry is starred; unset otherwise.
"starred": True or False, # True if the entry is starred by the user; false otherwise.
},
"routineSpec": { # Specification that applies to a routine. Valid only for entries with the `ROUTINE` type. # Specification that applies to a user-defined function or procedure. Valid only for entries with the `ROUTINE` type.
"bigqueryRoutineSpec": { # Fields specific for BigQuery routines. # Fields specific for BigQuery routines.
"importedLibraries": [ # Paths of the imported libraries.
"A String",
],
},
"definitionBody": "A String", # The body of the routine.
"language": "A String", # The language the routine is written in. The exact value depends on the source system. For BigQuery routines, possible values are: * `SQL` * `JAVASCRIPT`
"returnType": "A String", # Return type of the argument. The exact value depends on the source system and the language.
"routineArguments": [ # Arguments of the routine.
{ # Input or output argument of a function or stored procedure.
"mode": "A String", # Specifies whether the argument is input or output.
"name": "A String", # The name of the argument. A return argument of a function might not have a name.
"type": "A String", # Type of the argument. The exact value depends on the source system and the language.
},
],
"routineType": "A String", # The type of the routine.
},
"schema": { # Represents a schema, for example, a BigQuery, GoogleSQL, or Avro schema. # Schema of the entry. An entry might not have any schema attached to it.
"columns": [ # The unified GoogleSQL-like schema of columns. The overall maximum number of columns and nested columns is 10,000. The maximum nested depth is 15 levels.
{ # A column within a schema. Columns can be nested inside other columns.
"column": "A String", # Required. Name of the column. Must be a UTF-8 string without dots (.). The maximum size is 64 bytes.
"defaultValue": "A String", # Optional. Default value for the column.
"description": "A String", # Optional. Description of the column. Default value is an empty string. The description must be a UTF-8 string with the maximum size of 2000 bytes.
"gcRule": "A String", # Optional. Garbage collection policy for the column or column family. Applies to systems like Cloud Bigtable.
"highestIndexingType": "A String", # Optional. Most important inclusion of this column.
"lookerColumnSpec": { # Column info specific to Looker System. # Looker specific column info of this column.
"type": "A String", # Looker specific column type of this column.
},
"mode": "A String", # Optional. A column's mode indicates whether values in this column are required, nullable, or repeated. Only `NULLABLE`, `REQUIRED`, and `REPEATED` values are supported. Default mode is `NULLABLE`.
"ordinalPosition": 42, # Optional. Ordinal position
"subcolumns": [ # Optional. Schema of sub-columns. A column can have zero or more sub-columns.
# Object with schema name: GoogleCloudDatacatalogV1ColumnSchema
],
"type": "A String", # Required. Type of the column. Must be a UTF-8 string with the maximum size of 128 bytes.
},
],
},
"sourceSystemTimestamps": { # Timestamps associated with this resource in a particular system. # Timestamps from the underlying resource, not from the Data Catalog entry. Output only when the entry has a system listed in the `IntegratedSystem` enum. For entries with `user_specified_system`, this field is optional and defaults to an empty timestamp.
"createTime": "A String", # Creation timestamp of the resource within the given system.
"expireTime": "A String", # Output only. Expiration timestamp of the resource within the given system. Currently only applicable to BigQuery resources.
"updateTime": "A String", # Timestamp of the last modification of the resource or its metadata within a given system. Note: Depending on the source system, not every modification updates this timestamp. For example, BigQuery timestamps every metadata modification but not data or permission changes.
},
"sqlDatabaseSystemSpec": { # Specification that applies to entries that are part `SQL_DATABASE` system (user_specified_type) # Specification that applies to a relational database system. Only settable when `user_specified_system` is equal to `SQL_DATABASE`
"databaseVersion": "A String", # Version of the database engine.
"instanceHost": "A String", # Host of the SQL database enum InstanceHost { UNDEFINED = 0; SELF_HOSTED = 1; CLOUD_SQL = 2; AMAZON_RDS = 3; AZURE_SQL = 4; } Host of the enclousing database instance.
"sqlEngine": "A String", # SQL Database Engine. enum SqlEngine { UNDEFINED = 0; MY_SQL = 1; POSTGRE_SQL = 2; SQL_SERVER = 3; } Engine of the enclosing database instance.
},
"type": "A String", # The type of the entry. Only used for entries with types listed in the `EntryType` enum. Currently, only `FILESET` enum value is allowed. All other entries created in Data Catalog must use the `user_specified_type`.
"usageSignal": { # The set of all usage signals that Data Catalog stores. Note: Usually, these signals are updated daily. In rare cases, an update may fail but will be performed again on the next day. # Resource usage statistics.
"commonUsageWithinTimeRange": { # Common usage statistics over each of the predefined time ranges. Supported time ranges are `{"24H", "7D", "30D", "Lifetime"}`.
"a_key": { # Common statistics on the entry's usage. They can be set on any system.
"viewCount": "A String", # View count in source system.
},
},
"favoriteCount": "A String", # Favorite count in the source system.
"updateTime": "A String", # The end timestamp of the duration of usage statistics.
"usageWithinTimeRange": { # Output only. BigQuery usage statistics over each of the predefined time ranges. Supported time ranges are `{"24H", "7D", "30D"}`.
"a_key": { # Detailed statistics on the entry's usage. Usage statistics have the following limitations: - Only BigQuery tables have them. - They only include BigQuery query jobs. - They might be underestimated because wildcard table references are not yet counted. For more information, see [Querying multiple tables using a wildcard table] (https://cloud.google.com/bigquery/docs/querying-wildcard-tables)
"totalCancellations": 3.14, # The number of cancelled attempts to use the underlying entry.
"totalCompletions": 3.14, # The number of successful uses of the underlying entry.
"totalExecutionTimeForCompletionsMillis": 3.14, # Total time spent only on successful uses, in milliseconds.
"totalFailures": 3.14, # The number of failed attempts to use the underlying entry.
},
},
},
"userSpecifiedSystem": "A String", # Indicates the entry's source system that Data Catalog doesn't automatically integrate with. The `user_specified_system` string has the following limitations: * Is case insensitive. * Must begin with a letter or underscore. * Can only contain letters, numbers, and underscores. * Must be at least 1 character and at most 64 characters long.
"userSpecifiedType": "A String", # Custom entry type that doesn't match any of the values allowed for input and listed in the `EntryType` enum. When creating an entry, first check the type values in the enum. If there are no appropriate types for the new entry, provide a custom value, for example, `my_special_type`. The `user_specified_type` string has the following limitations: * Is case insensitive. * Must begin with a letter or underscore. * Can only contain letters, numbers, and underscores. * Must be at least 1 character and at most 64 characters long.
}</pre>
</div>
<div class="method">
<code class="details" id="getIamPolicy">getIamPolicy(resource, body=None, x__xgafv=None)</code>
<pre>Gets the access control policy for a resource. May return: * A`NOT_FOUND` error if the resource doesn't exist or you don't have the permission to view it. * An empty policy if the resource exists but doesn't have a set policy. Supported resources are: - Tag templates - Entry groups Note: This method doesn't get policies from Google Cloud Platform resources ingested into Data Catalog. To call this method, you must have the following Google IAM permissions: - `datacatalog.tagTemplates.getIamPolicy` to get policies on tag templates. - `datacatalog.entryGroups.getIamPolicy` to get policies on entry groups.
Args:
resource: string, REQUIRED: The resource for which the policy is being requested. See [Resource names](https://cloud.google.com/apis/design/resource_names) for the appropriate value for this field. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for `GetIamPolicy` method.
"options": { # Encapsulates settings provided to GetIamPolicy. # OPTIONAL: A `GetPolicyOptions` object for specifying options to `GetIamPolicy`.
"requestedPolicyVersion": 42, # Optional. The maximum policy version that will be used to format the policy. Valid values are 0, 1, and 3. Requests specifying an invalid value will be rejected. Requests for policies with any conditional role bindings must specify version 3. Policies with no conditional role bindings may specify any valid value or leave the field unset. The policy in the response might use the policy version that you specified, or it might use a lower policy version. For example, if you specify version 3, but the policy has no conditional role bindings, the response uses version 1. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies).
},
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # An Identity and Access Management (IAM) policy, which specifies access controls for Google Cloud resources. A `Policy` is a collection of `bindings`. A `binding` binds one or more `members`, or principals, to a single `role`. Principals can be user accounts, service accounts, Google groups, and domains (such as G Suite). A `role` is a named list of permissions; each `role` can be an IAM predefined role or a user-created custom role. For some types of Google Cloud resources, a `binding` can also specify a `condition`, which is a logical expression that allows access to a resource only if the expression evaluates to `true`. A condition can add constraints based on attributes of the request, the resource, or both. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies). **JSON example:** { "bindings": [ { "role": "roles/resourcemanager.organizationAdmin", "members": [ "user:mike@example.com", "group:admins@example.com", "domain:google.com", "serviceAccount:my-project-id@appspot.gserviceaccount.com" ] }, { "role": "roles/resourcemanager.organizationViewer", "members": [ "user:eve@example.com" ], "condition": { "title": "expirable access", "description": "Does not grant access after Sep 2020", "expression": "request.time < timestamp('2020-10-01T00:00:00.000Z')", } } ], "etag": "BwWWja0YfJA=", "version": 3 } **YAML example:** bindings: - members: - user:mike@example.com - group:admins@example.com - domain:google.com - serviceAccount:my-project-id@appspot.gserviceaccount.com role: roles/resourcemanager.organizationAdmin - members: - user:eve@example.com role: roles/resourcemanager.organizationViewer condition: title: expirable access description: Does not grant access after Sep 2020 expression: request.time < timestamp('2020-10-01T00:00:00.000Z') etag: BwWWja0YfJA= version: 3 For a description of IAM and its features, see the [IAM documentation](https://cloud.google.com/iam/docs/).
"bindings": [ # Associates a list of `members`, or principals, with a `role`. Optionally, may specify a `condition` that determines how and when the `bindings` are applied. Each of the `bindings` must contain at least one principal. The `bindings` in a `Policy` can refer to up to 1,500 principals; up to 250 of these principals can be Google groups. Each occurrence of a principal counts towards these limits. For example, if the `bindings` grant 50 different roles to `user:alice@example.com`, and not to any other principal, then you can add another 1,450 principals to the `bindings` in the `Policy`.
{ # Associates `members`, or principals, with a `role`.
"condition": { # Represents a textual expression in the Common Expression Language (CEL) syntax. CEL is a C-like expression language. The syntax and semantics of CEL are documented at https://github.com/google/cel-spec. Example (Comparison): title: "Summary size limit" description: "Determines if a summary is less than 100 chars" expression: "document.summary.size() < 100" Example (Equality): title: "Requestor is owner" description: "Determines if requestor is the document owner" expression: "document.owner == request.auth.claims.email" Example (Logic): title: "Public documents" description: "Determine whether the document should be publicly visible" expression: "document.type != 'private' && document.type != 'internal'" Example (Data Manipulation): title: "Notification string" description: "Create a notification string with a timestamp." expression: "'New message received at ' + string(document.create_time)" The exact variables and functions that may be referenced within an expression are determined by the service that evaluates it. See the service documentation for additional information. # The condition that is associated with this binding. If the condition evaluates to `true`, then this binding applies to the current request. If the condition evaluates to `false`, then this binding does not apply to the current request. However, a different role binding might grant the same role to one or more of the principals in this binding. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies).
"description": "A String", # Optional. Description of the expression. This is a longer text which describes the expression, e.g. when hovered over it in a UI.
"expression": "A String", # Textual representation of an expression in Common Expression Language syntax.
"location": "A String", # Optional. String indicating the location of the expression for error reporting, e.g. a file name and a position in the file.
"title": "A String", # Optional. Title for the expression, i.e. a short string describing its purpose. This can be used e.g. in UIs which allow to enter the expression.
},
"members": [ # Specifies the principals requesting access for a Google Cloud resource. `members` can have the following values: * `allUsers`: A special identifier that represents anyone who is on the internet; with or without a Google account. * `allAuthenticatedUsers`: A special identifier that represents anyone who is authenticated with a Google account or a service account. Does not include identities that come from external identity providers (IdPs) through identity federation. * `user:{emailid}`: An email address that represents a specific Google account. For example, `alice@example.com` . * `serviceAccount:{emailid}`: An email address that represents a Google service account. For example, `my-other-app@appspot.gserviceaccount.com`. * `serviceAccount:{projectid}.svc.id.goog[{namespace}/{kubernetes-sa}]`: An identifier for a [Kubernetes service account](https://cloud.google.com/kubernetes-engine/docs/how-to/kubernetes-service-accounts). For example, `my-project.svc.id.goog[my-namespace/my-kubernetes-sa]`. * `group:{emailid}`: An email address that represents a Google group. For example, `admins@example.com`. * `domain:{domain}`: The G Suite domain (primary) that represents all the users of that domain. For example, `google.com` or `example.com`. * `deleted:user:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a user that has been recently deleted. For example, `alice@example.com?uid=123456789012345678901`. If the user is recovered, this value reverts to `user:{emailid}` and the recovered user retains the role in the binding. * `deleted:serviceAccount:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a service account that has been recently deleted. For example, `my-other-app@appspot.gserviceaccount.com?uid=123456789012345678901`. If the service account is undeleted, this value reverts to `serviceAccount:{emailid}` and the undeleted service account retains the role in the binding. * `deleted:group:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a Google group that has been recently deleted. For example, `admins@example.com?uid=123456789012345678901`. If the group is recovered, this value reverts to `group:{emailid}` and the recovered group retains the role in the binding.
"A String",
],
"role": "A String", # Role that is assigned to the list of `members`, or principals. For example, `roles/viewer`, `roles/editor`, or `roles/owner`.
},
],
"etag": "A String", # `etag` is used for optimistic concurrency control as a way to help prevent simultaneous updates of a policy from overwriting each other. It is strongly suggested that systems make use of the `etag` in the read-modify-write cycle to perform policy updates in order to avoid race conditions: An `etag` is returned in the response to `getIamPolicy`, and systems are expected to put that etag in the request to `setIamPolicy` to ensure that their change will be applied to the same version of the policy. **Important:** If you use IAM Conditions, you must include the `etag` field whenever you call `setIamPolicy`. If you omit this field, then IAM allows you to overwrite a version `3` policy with a version `1` policy, and all of the conditions in the version `3` policy are lost.
"version": 42, # Specifies the format of the policy. Valid values are `0`, `1`, and `3`. Requests that specify an invalid value are rejected. Any operation that affects conditional role bindings must specify version `3`. This requirement applies to the following operations: * Getting a policy that includes a conditional role binding * Adding a conditional role binding to a policy * Changing a conditional role binding in a policy * Removing any role binding, with or without a condition, from a policy that includes conditions **Important:** If you use IAM Conditions, you must include the `etag` field whenever you call `setIamPolicy`. If you omit this field, then IAM allows you to overwrite a version `3` policy with a version `1` policy, and all of the conditions in the version `3` policy are lost. If a policy does not include any conditions, operations on that policy may specify any valid version or leave the field unset. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies).
}</pre>
</div>
<div class="method">
<code class="details" id="import_">import_(parent, body=None, x__xgafv=None)</code>
<pre>Imports entries from some source (e.g. dump in a Cloud Storage bucket) to the Data Catalog. Dump here is a snapshot of the third-party system state, that needs to be ingested in the Data Catalog. Import of entries is a sync operation that reconciles state of the third-party system and Data Catalog. ImportEntries is a long-running operation done in the background, so this method returns long-running operation resource. The resource can be queried with Operations.GetOperation which contains metadata and response.
Args:
parent: string, Required. Target entry group for ingested entries. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for ImportEntries method.
"gcsBucketPath": "A String", # Path to a Cloud Storage bucket that contains a dump ready for ingestion.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal response of the operation in case of success. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}</pre>
</div>
<div class="method">
<code class="details" id="list">list(parent, pageSize=None, pageToken=None, readMask=None, x__xgafv=None)</code>
<pre>Lists entries. Note: Currently, this method can list only custom entries. To get a list of both custom and automatically created entries, use SearchCatalog.
Args:
parent: string, Required. The name of the entry group that contains the entries to list. Can be provided in URL format. (required)
pageSize: integer, The maximum number of items to return. Default is 10. Maximum limit is 1000. Throws an invalid argument if `page_size` is more than 1000.
pageToken: string, Pagination token that specifies the next page to return. If empty, the first page is returned.
readMask: string, The fields to return for each entry. If empty or omitted, all fields are returned. For example, to return a list of entries with only the `name` field, set `read_mask` to only one path with the `name` value.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response message for ListEntries.
"entries": [ # Entry details.
{ # Entry metadata. A Data Catalog entry represents another resource in Google Cloud Platform (such as a BigQuery dataset or a Pub/Sub topic) or outside of it. You can use the `linked_resource` field in the entry resource to refer to the original resource ID of the source system. An entry resource contains resource details, for example, its schema. Additionally, you can attach flexible metadata to an entry in the form of a Tag.
"bigqueryDateShardedSpec": { # Specification for a group of BigQuery tables with the `[prefix]YYYYMMDD` name pattern. For more information, see [Introduction to partitioned tables] (https://cloud.google.com/bigquery/docs/partitioned-tables#partitioning_versus_sharding). # Output only. Specification for a group of BigQuery tables with the `[prefix]YYYYMMDD` name pattern. For more information, see [Introduction to partitioned tables] (https://cloud.google.com/bigquery/docs/partitioned-tables#partitioning_versus_sharding).
"dataset": "A String", # Output only. The Data Catalog resource name of the dataset entry the current table belongs to. For example: `projects/{PROJECT_ID}/locations/{LOCATION}/entrygroups/{ENTRY_GROUP_ID}/entries/{ENTRY_ID}`.
"latestShardResource": "A String", # Output only. BigQuery resource name of the latest shard.
"shardCount": "A String", # Output only. Total number of shards.
"tablePrefix": "A String", # Output only. The table name prefix of the shards. The name of any given shard is `[table_prefix]YYYYMMDD`. For example, for the `MyTable20180101` shard, the `table_prefix` is `MyTable`.
},
"bigqueryTableSpec": { # Describes a BigQuery table. # Output only. Specification that applies to a BigQuery table. Valid only for entries with the `TABLE` type.
"tableSourceType": "A String", # Output only. The table source type.
"tableSpec": { # Normal BigQuery table specification. # Specification of a BigQuery table. Populated only if the `table_source_type` is `BIGQUERY_TABLE`.
"groupedEntry": "A String", # Output only. If the table is date-sharded, that is, it matches the `[prefix]YYYYMMDD` name pattern, this field is the Data Catalog resource name of the date-sharded grouped entry. For example: `projects/{PROJECT_ID}/locations/{LOCATION}/entrygroups/{ENTRY_GROUP_ID}/entries/{ENTRY_ID}`. Otherwise, `grouped_entry` is empty.
},
"viewSpec": { # Table view specification. # Table view specification. Populated only if the `table_source_type` is `BIGQUERY_VIEW`.
"viewQuery": "A String", # Output only. The query that defines the table view.
},
},
"businessContext": { # Business Context of the entry. # Business Context of the entry. Not supported for BigQuery datasets
"contacts": { # Contact people for the entry. # Contact people for the entry.
"people": [ # The list of contact people for the entry.
{ # A contact person for the entry.
"designation": "A String", # Designation of the person, for example, Data Steward.
"email": "A String", # Email of the person in the format of `john.doe@xyz`, ``, or `John Doe`.
},
],
},
"entryOverview": { # Entry overview fields for rich text descriptions of entries. # Entry overview fields for rich text descriptions of entries.
"overview": "A String", # Entry overview with support for rich text. The overview must only contain Unicode characters, and should be formatted using HTML. The maximum length is 10 MiB as this value holds HTML descriptions including encoded images. The maximum length of the text without images is 100 KiB.
},
},
"dataSource": { # Physical location of an entry. # Output only. Physical location of the entry.
"resource": "A String", # Full name of a resource as defined by the service. For example: `//bigquery.googleapis.com/projects/{PROJECT_ID}/locations/{LOCATION}/datasets/{DATASET_ID}/tables/{TABLE_ID}`
"service": "A String", # Service that physically stores the data.
"sourceEntry": "A String", # Output only. Data Catalog entry name, if applicable.
"storageProperties": { # Details the properties of the underlying storage. # Detailed properties of the underlying storage.
"filePattern": [ # Patterns to identify a set of files for this fileset. Examples of a valid `file_pattern`: * `gs://bucket_name/dir/*`: matches all files in the `bucket_name/dir` directory * `gs://bucket_name/dir/**`: matches all files in the `bucket_name/dir` and all subdirectories recursively * `gs://bucket_name/file*`: matches files prefixed by `file` in `bucket_name` * `gs://bucket_name/??.txt`: matches files with two characters followed by `.txt` in `bucket_name` * `gs://bucket_name/[aeiou].txt`: matches files that contain a single vowel character followed by `.txt` in `bucket_name` * `gs://bucket_name/[a-m].txt`: matches files that contain `a`, `b`, ... or `m` followed by `.txt` in `bucket_name` * `gs://bucket_name/a/*/b`: matches all files in `bucket_name` that match the `a/*/b` pattern, such as `a/c/b`, `a/d/b` * `gs://another_bucket/a.txt`: matches `gs://another_bucket/a.txt`
"A String",
],
"fileType": "A String", # File type in MIME format, for example, `text/plain`.
},
},