acryl-datahub 1.2.0.10rc5__py3-none-any.whl → 1.2.0.10rc7__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of acryl-datahub might be problematic. Click here for more details.
- {acryl_datahub-1.2.0.10rc5.dist-info → acryl_datahub-1.2.0.10rc7.dist-info}/METADATA +2515 -2515
- {acryl_datahub-1.2.0.10rc5.dist-info → acryl_datahub-1.2.0.10rc7.dist-info}/RECORD +13 -13
- datahub/_version.py +1 -1
- datahub/ingestion/source/metabase.py +9 -2
- datahub/ingestion/source/redshift/query.py +23 -19
- datahub/metadata/_internal_schema_classes.py +524 -524
- datahub/metadata/_urns/urn_defs.py +1702 -1702
- datahub/metadata/schema.avsc +17583 -17977
- datahub/sdk/entity_client.py +11 -4
- {acryl_datahub-1.2.0.10rc5.dist-info → acryl_datahub-1.2.0.10rc7.dist-info}/WHEEL +0 -0
- {acryl_datahub-1.2.0.10rc5.dist-info → acryl_datahub-1.2.0.10rc7.dist-info}/entry_points.txt +0 -0
- {acryl_datahub-1.2.0.10rc5.dist-info → acryl_datahub-1.2.0.10rc7.dist-info}/licenses/LICENSE +0 -0
- {acryl_datahub-1.2.0.10rc5.dist-info → acryl_datahub-1.2.0.10rc7.dist-info}/top_level.txt +0 -0
|
@@ -1,7 +1,7 @@
|
|
|
1
|
-
acryl_datahub-1.2.0.
|
|
1
|
+
acryl_datahub-1.2.0.10rc7.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
|
|
2
2
|
datahub/__init__.py,sha256=aq_i5lVREmoLfYIqcx_pEQicO855YlhD19tWc1eZZNI,59
|
|
3
3
|
datahub/__main__.py,sha256=pegIvQ9hzK7IhqVeUi1MeADSZ2QlP-D3K0OQdEg55RU,106
|
|
4
|
-
datahub/_version.py,sha256=
|
|
4
|
+
datahub/_version.py,sha256=cd8EZsDwwIMWrvKB56EZ1C9Dzre3O-4gvEXudlmDjfQ,324
|
|
5
5
|
datahub/entrypoints.py,sha256=9Qf-37rNnTzbGlx8S75OCDazIclFp6zWNcCEL1zCZto,9015
|
|
6
6
|
datahub/errors.py,sha256=p5rFAdAGVCk4Lqolol1YvthceadUSwpaCxLXRcyCCFQ,676
|
|
7
7
|
datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
@@ -215,7 +215,7 @@ datahub/ingestion/source/ge_data_profiler.py,sha256=9lEQdLcMBa7znqa6Zz-QWA4Uiv8K
|
|
|
215
215
|
datahub/ingestion/source/ge_profiling_config.py,sha256=FIuZtce0gRncSRKA1V9GLg8H5JyJPieZweFJS36Q_CI,11523
|
|
216
216
|
datahub/ingestion/source/glue_profiling_config.py,sha256=vpMJH4Lf_qgR32BZy58suabri1yV5geaAPjzg2eORDc,2559
|
|
217
217
|
datahub/ingestion/source/ldap.py,sha256=PKoA5pVjuIxFfW1TcbYNIWSm7-C7shK2FDn7Zo5mrVM,18705
|
|
218
|
-
datahub/ingestion/source/metabase.py,sha256=
|
|
218
|
+
datahub/ingestion/source/metabase.py,sha256=txzrTtxD1hla3yspxY6GQRCZUFWOK03d0-wJqDmT9AQ,32695
|
|
219
219
|
datahub/ingestion/source/mlflow.py,sha256=t7heUgivLXU7lxc-ndZxc1LZuoDKZgpSIe-x3ExXfMg,33340
|
|
220
220
|
datahub/ingestion/source/mode.py,sha256=omehI5t10-TucVTgiREb3s-9suFFy9YsNidF9qtnc-M,72191
|
|
221
221
|
datahub/ingestion/source/mongodb.py,sha256=ykUA2Jyn0rxzOO-pCWosOqvFTIRgFmqkCTRHAsxpOYc,21423
|
|
@@ -450,7 +450,7 @@ datahub/ingestion/source/redshift/datashares.py,sha256=7G4YoEigZTl-K1aWDw3Jl8s3-
|
|
|
450
450
|
datahub/ingestion/source/redshift/exception.py,sha256=dxzYUIv5B_FAWhOuzG2u5We7FX-ar4jhOXPXAlEIvgM,2055
|
|
451
451
|
datahub/ingestion/source/redshift/lineage.py,sha256=nqrvWJqaI493i1hIZ_7patrdOb16sZrgSSGapdMcEiU,31710
|
|
452
452
|
datahub/ingestion/source/redshift/profile.py,sha256=H1Xtc2rXScUv4w0b2BbM7POjYEwqIql_rpWvlumY_EM,4309
|
|
453
|
-
datahub/ingestion/source/redshift/query.py,sha256=
|
|
453
|
+
datahub/ingestion/source/redshift/query.py,sha256=HKobQ-0crARgT8Mkfe-WBqVR9ZadYCZ9DGaUoEHHHww,48234
|
|
454
454
|
datahub/ingestion/source/redshift/redshift.py,sha256=zalndYg_LK5aJ8cX_ZuXLcTYajtlavmV-dmQIsjGxjg,41260
|
|
455
455
|
datahub/ingestion/source/redshift/redshift_data_reader.py,sha256=zc69jwXHdF-w8J4Hq-ZQ6BjHQ75Ij2iNDMpoRJlcmlU,1724
|
|
456
456
|
datahub/ingestion/source/redshift/redshift_schema.py,sha256=7F-l_omOuKMuGE_rBWXVPG_GWXFKnCMzC4frNxZB9cs,24800
|
|
@@ -642,12 +642,12 @@ datahub/lite/lite_registry.py,sha256=bpH0kasP-LtwwUFNA2QsOIehfekAYfJtN-AkQLmSWnw
|
|
|
642
642
|
datahub/lite/lite_server.py,sha256=p9Oa2nNs65mqcssSIVOr7VOzWqfVstz6ZQEdT4f82S0,1949
|
|
643
643
|
datahub/lite/lite_util.py,sha256=G0LQHKkyEb1pc_q183g6hflShclGx7kikgMaOxtVVcs,4545
|
|
644
644
|
datahub/metadata/__init__.py,sha256=AjhXPjI6cnpdcrBRrE5gOWo15vv2TTl2ctU4UAnUN7A,238
|
|
645
|
-
datahub/metadata/_internal_schema_classes.py,sha256=
|
|
646
|
-
datahub/metadata/schema.avsc,sha256=
|
|
645
|
+
datahub/metadata/_internal_schema_classes.py,sha256=BBxTUOoQF1h-WXtAHGQM-Rh3Mhirx5nJBPserPZKFeY,1069945
|
|
646
|
+
datahub/metadata/schema.avsc,sha256=ykx9zsPrLioYBg84eMi4NGyev4POl6BkyAYFPXAjvMQ,771886
|
|
647
647
|
datahub/metadata/schema_classes.py,sha256=tPT8iHCak4IsZi_oL0nirbPpI8ETTPTZzapqLRpeKU4,1326
|
|
648
648
|
datahub/metadata/urns.py,sha256=nfrCTExR-k2P9w272WVtWSN3xW1VUJngPwP3xnvULjU,1217
|
|
649
649
|
datahub/metadata/_urns/__init__.py,sha256=cOF3GHMDgPhmbLKbN02NPpuLGHSu0qNgQyBRv08eqF0,243
|
|
650
|
-
datahub/metadata/_urns/urn_defs.py,sha256=
|
|
650
|
+
datahub/metadata/_urns/urn_defs.py,sha256=_LgqKLHrmHHxpvrP-93NMJSLEnoFI8q72lkX17mK1XA,143257
|
|
651
651
|
datahub/metadata/com/__init__.py,sha256=gsAIuTxzfJdI7a9ybZlgMIHMAYksM1SxGxXjtySgKSc,202
|
|
652
652
|
datahub/metadata/com/linkedin/__init__.py,sha256=gsAIuTxzfJdI7a9ybZlgMIHMAYksM1SxGxXjtySgKSc,202
|
|
653
653
|
datahub/metadata/com/linkedin/events/__init__.py,sha256=s_dR0plZF-rOxxIbE8ojekJqwiHzl2WYR-Z3kW6kKS0,298
|
|
@@ -973,7 +973,7 @@ datahub/sdk/dataflow.py,sha256=gdAPVVkyKvsKtsa1AwhN_LpzidG_XzV3nhtd1cjnzDA,11128
|
|
|
973
973
|
datahub/sdk/datajob.py,sha256=5kU0txTDcn2ce3AhNry83TazPVhoYZ2rAPPNWM1_FP8,13677
|
|
974
974
|
datahub/sdk/dataset.py,sha256=-C4TCJAs1PFkLAgkUZEU1JOg3orm7AAIkqjw7oo_4PQ,31400
|
|
975
975
|
datahub/sdk/entity.py,sha256=Q29AbpS58L4gD8ETwoNIwG-ouytz4c0MSSFi6-jLl_4,6742
|
|
976
|
-
datahub/sdk/entity_client.py,sha256=
|
|
976
|
+
datahub/sdk/entity_client.py,sha256=LtFu0lYOl5s_B2G7HXoYY6uXaTBld-MC8Z_UeVKYCbc,9770
|
|
977
977
|
datahub/sdk/lineage_client.py,sha256=qSe2TEt4HKRVytAsDokkfzqErZiL46c0TMe6g2C5hAg,33766
|
|
978
978
|
datahub/sdk/main_client.py,sha256=LAymeMOkrjjJjQQ8Nc7G3hvF3P8Y0k0AXrDEGDGt4iU,5706
|
|
979
979
|
datahub/sdk/mlmodel.py,sha256=cO5R8BYVljmQ0w33RIOuZmj4nq8OJCDVAZGTQI6YFS8,12628
|
|
@@ -1121,8 +1121,8 @@ datahub_provider/operators/datahub_assertion_operator.py,sha256=uvTQ-jk2F0sbqqxp
|
|
|
1121
1121
|
datahub_provider/operators/datahub_assertion_sensor.py,sha256=lCBj_3x1cf5GMNpHdfkpHuyHfVxsm6ff5x2Z5iizcAo,140
|
|
1122
1122
|
datahub_provider/operators/datahub_operation_operator.py,sha256=aevDp2FzX7FxGlXrR0khoHNbxbhKR2qPEX5e8O2Jyzw,174
|
|
1123
1123
|
datahub_provider/operators/datahub_operation_sensor.py,sha256=8fcdVBCEPgqy1etTXgLoiHoJrRt_nzFZQMdSzHqSG7M,168
|
|
1124
|
-
acryl_datahub-1.2.0.
|
|
1125
|
-
acryl_datahub-1.2.0.
|
|
1126
|
-
acryl_datahub-1.2.0.
|
|
1127
|
-
acryl_datahub-1.2.0.
|
|
1128
|
-
acryl_datahub-1.2.0.
|
|
1124
|
+
acryl_datahub-1.2.0.10rc7.dist-info/METADATA,sha256=kx-48Qes8ImK7vKjHellg40w5JwltF8xYZmAnuIy_JU,184162
|
|
1125
|
+
acryl_datahub-1.2.0.10rc7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
|
1126
|
+
acryl_datahub-1.2.0.10rc7.dist-info/entry_points.txt,sha256=pzsBoTx-D-iTcmpX8oCGCyzlHP2112EygUMzZWz56M8,10105
|
|
1127
|
+
acryl_datahub-1.2.0.10rc7.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
|
|
1128
|
+
acryl_datahub-1.2.0.10rc7.dist-info/RECORD,,
|
datahub/_version.py
CHANGED
|
@@ -13,7 +13,10 @@ from pydantic import Field, root_validator, validator
|
|
|
13
13
|
from requests.models import HTTPError
|
|
14
14
|
|
|
15
15
|
import datahub.emitter.mce_builder as builder
|
|
16
|
-
from datahub.configuration.source_common import
|
|
16
|
+
from datahub.configuration.source_common import (
|
|
17
|
+
DatasetLineageProviderConfigBase,
|
|
18
|
+
LowerCaseDatasetUrnConfigMixin,
|
|
19
|
+
)
|
|
17
20
|
from datahub.ingestion.api.common import PipelineContext
|
|
18
21
|
from datahub.ingestion.api.decorators import (
|
|
19
22
|
SourceCapability,
|
|
@@ -61,7 +64,11 @@ logger = logging.getLogger(__name__)
|
|
|
61
64
|
DATASOURCE_URN_RECURSION_LIMIT = 5
|
|
62
65
|
|
|
63
66
|
|
|
64
|
-
class MetabaseConfig(
|
|
67
|
+
class MetabaseConfig(
|
|
68
|
+
DatasetLineageProviderConfigBase,
|
|
69
|
+
StatefulIngestionConfigBase,
|
|
70
|
+
LowerCaseDatasetUrnConfigMixin,
|
|
71
|
+
):
|
|
65
72
|
# See the Metabase /api/session endpoint for details
|
|
66
73
|
# https://www.metabase.com/docs/latest/api-documentation.html#post-apisession
|
|
67
74
|
connect_uri: str = Field(default="localhost:3000", description="Metabase host URL.")
|
|
@@ -89,7 +89,7 @@ class RedshiftCommonQuery:
|
|
|
89
89
|
) -> str:
|
|
90
90
|
# NOTE: it looks like description is available only in pg_description
|
|
91
91
|
# So this remains preferrred way
|
|
92
|
-
tables_query = """
|
|
92
|
+
tables_query = f"""
|
|
93
93
|
SELECT CASE c.relkind
|
|
94
94
|
WHEN 'r' THEN 'TABLE'
|
|
95
95
|
WHEN 'v' THEN 'VIEW'
|
|
@@ -120,6 +120,7 @@ class RedshiftCommonQuery:
|
|
|
120
120
|
LEFT JOIN pg_catalog.pg_namespace n ON n.oid = c.relnamespace
|
|
121
121
|
LEFT JOIN pg_class_info as ci on c.oid = ci.reloid
|
|
122
122
|
LEFT JOIN pg_catalog.pg_description pgd ON pgd.objsubid = 0 AND pgd.objoid = c.oid
|
|
123
|
+
JOIN svv_redshift_schemas rs ON rs.schema_name = n.nspname AND rs.database_name = '{database}'
|
|
123
124
|
WHERE c.relkind IN ('r','v','m','S','f')
|
|
124
125
|
AND n.nspname !~ '^pg_'
|
|
125
126
|
AND n.nspname != 'information_schema'
|
|
@@ -128,23 +129,24 @@ class RedshiftCommonQuery:
|
|
|
128
129
|
external_tables_query = f"""
|
|
129
130
|
SELECT 'EXTERNAL_TABLE' as tabletype,
|
|
130
131
|
NULL AS "schema_oid",
|
|
131
|
-
schemaname AS "schema",
|
|
132
|
+
t.schemaname AS "schema",
|
|
132
133
|
NULL AS "rel_oid",
|
|
133
|
-
tablename AS "relname",
|
|
134
|
+
t.tablename AS "relname",
|
|
134
135
|
NULL as "creation_time",
|
|
135
136
|
NULL AS "diststyle",
|
|
136
137
|
NULL AS "owner_id",
|
|
137
138
|
NULL AS "owner_name",
|
|
138
139
|
NULL AS "view_definition",
|
|
139
140
|
NULL AS "privileges",
|
|
140
|
-
"location",
|
|
141
|
-
parameters,
|
|
142
|
-
input_format,
|
|
143
|
-
output_format,
|
|
144
|
-
serde_parameters,
|
|
141
|
+
t."location",
|
|
142
|
+
t.parameters,
|
|
143
|
+
t.input_format,
|
|
144
|
+
t.output_format,
|
|
145
|
+
t.serde_parameters,
|
|
145
146
|
NULL as table_description
|
|
146
|
-
FROM pg_catalog.svv_external_tables
|
|
147
|
-
|
|
147
|
+
FROM pg_catalog.svv_external_tables t
|
|
148
|
+
JOIN SVV_EXTERNAL_SCHEMAS s ON t.schemaname = s.schemaname
|
|
149
|
+
WHERE t.redshift_database_name='{database}'
|
|
148
150
|
ORDER BY "schema",
|
|
149
151
|
"relname"
|
|
150
152
|
"""
|
|
@@ -232,11 +234,12 @@ class RedshiftCommonQuery:
|
|
|
232
234
|
ON att.attrelid = c.oid
|
|
233
235
|
LEFT JOIN pg_catalog.pg_attrdef ad
|
|
234
236
|
ON (att.attrelid, att.attnum) = (ad.adrelid, ad.adnum)
|
|
237
|
+
JOIN svv_redshift_schemas rs ON rs.schema_name = n.nspname AND rs.database_name = '{database_name}'
|
|
235
238
|
WHERE n.nspname !~ '^pg_'
|
|
236
239
|
AND n.nspname != 'information_schema'
|
|
237
240
|
AND att.attnum > 0
|
|
238
241
|
AND NOT att.attisdropped
|
|
239
|
-
and
|
|
242
|
+
and n.nspname = '{schema_name}'
|
|
240
243
|
UNION
|
|
241
244
|
SELECT
|
|
242
245
|
view_schema as "schema",
|
|
@@ -263,26 +266,27 @@ class RedshiftCommonQuery:
|
|
|
263
266
|
WHERE 1 and schema = '{schema_name}'
|
|
264
267
|
UNION
|
|
265
268
|
SELECT
|
|
266
|
-
schemaname as "schema",
|
|
267
|
-
tablename as "table_name",
|
|
268
|
-
columnname as "name",
|
|
269
|
+
c.schemaname as "schema",
|
|
270
|
+
c.tablename as "table_name",
|
|
271
|
+
c.columnname as "name",
|
|
269
272
|
null as "encode",
|
|
270
273
|
-- Spectrum represents data types differently.
|
|
271
274
|
-- Standardize, so we can infer types.
|
|
272
|
-
external_type AS "type",
|
|
275
|
+
c.external_type AS "type",
|
|
273
276
|
null as "distkey",
|
|
274
277
|
0 as "sortkey",
|
|
275
278
|
null as "notnull",
|
|
276
279
|
null as "comment",
|
|
277
280
|
null as "adsrc",
|
|
278
281
|
null as "attnum",
|
|
279
|
-
external_type AS "format_type",
|
|
282
|
+
c.external_type AS "format_type",
|
|
280
283
|
null as "default",
|
|
281
284
|
null as "schema_oid",
|
|
282
285
|
null as "table_oid"
|
|
283
|
-
FROM SVV_EXTERNAL_COLUMNS
|
|
284
|
-
|
|
285
|
-
|
|
286
|
+
FROM SVV_EXTERNAL_COLUMNS c
|
|
287
|
+
JOIN SVV_EXTERNAL_SCHEMAS s ON c.schemaname = s.schemaname
|
|
288
|
+
WHERE c.schemaname = '{schema_name}'
|
|
289
|
+
AND c.redshift_database_name = '{database_name}'
|
|
286
290
|
ORDER BY "schema", "table_name", "attnum"
|
|
287
291
|
"""
|
|
288
292
|
|