chore: import upstream snapshot with attribution
Integration Tests - MySQL + Elasticsearch / Detect Changes (push) Has been cancelled
Integration Tests - MySQL + Elasticsearch / integration-tests-mysql-elasticsearch (push) Has been cancelled
Integration Tests - PostgreSQL + Elasticsearch + Redis / Detect Changes (push) Has been cancelled
Integration Tests - PostgreSQL + Elasticsearch + Redis / integration-tests-postgres-elasticsearch-redis (push) Has been cancelled
Integration Tests - PostgreSQL + OpenSearch / Detect Changes (push) Has been cancelled
Integration Tests - PostgreSQL + OpenSearch / integration-tests-postgres-opensearch (push) Has been cancelled
Java Checkstyle / java-checkstyle (push) Has been cancelled
Maven Collate Tests / maven-collate-ci (push) Has been cancelled
OpenMetadata Service Unit Tests / openmetadata-service-unit-tests-status (push) Has been cancelled
Publish Package to Maven Central Repository / publish-maven-packages (push) Has been cancelled
OpenMetadata Service Unit Tests / Detect Changes (push) Has been cancelled
OpenMetadata Service Unit Tests / openmetadata-service-unit-tests (push) Has been cancelled
OpenMetadata Service Unit Tests / k8s_operator-unit-tests (push) Has been cancelled
Integration Tests - MySQL + Elasticsearch / Detect Changes (push) Has been cancelled
Integration Tests - MySQL + Elasticsearch / integration-tests-mysql-elasticsearch (push) Has been cancelled
Integration Tests - PostgreSQL + Elasticsearch + Redis / Detect Changes (push) Has been cancelled
Integration Tests - PostgreSQL + Elasticsearch + Redis / integration-tests-postgres-elasticsearch-redis (push) Has been cancelled
Integration Tests - PostgreSQL + OpenSearch / Detect Changes (push) Has been cancelled
Integration Tests - PostgreSQL + OpenSearch / integration-tests-postgres-opensearch (push) Has been cancelled
Java Checkstyle / java-checkstyle (push) Has been cancelled
Maven Collate Tests / maven-collate-ci (push) Has been cancelled
OpenMetadata Service Unit Tests / openmetadata-service-unit-tests-status (push) Has been cancelled
Publish Package to Maven Central Repository / publish-maven-packages (push) Has been cancelled
OpenMetadata Service Unit Tests / Detect Changes (push) Has been cancelled
OpenMetadata Service Unit Tests / openmetadata-service-unit-tests (push) Has been cancelled
OpenMetadata Service Unit Tests / k8s_operator-unit-tests (push) Has been cancelled
This commit is contained in:
@@ -0,0 +1,50 @@
|
||||
START TRANSACTION;
|
||||
-- We'll rank all the runs (timestamps) for every day, and delete all the data but the most recent one.
|
||||
DELETE FROM report_data_time_series WHERE JSON_EXTRACT(json, '$.id') IN (
|
||||
select ids FROM (
|
||||
SELECT
|
||||
(json ->> '$.id') AS ids,
|
||||
DENSE_RANK() OVER(PARTITION BY `date` ORDER BY `timestamp` DESC) as denseRank
|
||||
FROM (
|
||||
SELECT
|
||||
*
|
||||
FROM report_data_time_series rdts
|
||||
WHERE json ->> '$.reportDataType' = 'WebAnalyticEntityViewReportData'
|
||||
) duplicates
|
||||
ORDER BY `date` DESC, `timestamp` DESC
|
||||
) as dense_ranked
|
||||
WHERE denseRank != 1
|
||||
);
|
||||
|
||||
DELETE FROM report_data_time_series WHERE JSON_EXTRACT(json, '$.id') IN (
|
||||
select ids FROM (
|
||||
SELECT
|
||||
(json ->> '$.id') AS ids,
|
||||
DENSE_RANK() OVER(PARTITION BY `date` ORDER BY `timestamp` DESC) as denseRank
|
||||
FROM (
|
||||
SELECT
|
||||
*
|
||||
FROM report_data_time_series rdts
|
||||
WHERE json ->> '$.reportDataType' = 'EntityReportData'
|
||||
) duplicates
|
||||
ORDER BY `date` DESC, `timestamp` DESC
|
||||
) as dense_ranked
|
||||
WHERE denseRank != 1
|
||||
);
|
||||
|
||||
DELETE FROM report_data_time_series WHERE JSON_EXTRACT(json, '$.id') IN (
|
||||
select ids FROM (
|
||||
SELECT
|
||||
(json ->> '$.id') AS ids,
|
||||
DENSE_RANK() OVER(PARTITION BY `date` ORDER BY `timestamp` DESC) as denseRank
|
||||
FROM (
|
||||
SELECT
|
||||
*
|
||||
FROM report_data_time_series rdts
|
||||
WHERE json ->> '$.reportDataType' = 'WebAnalyticUserActivityReportData'
|
||||
) duplicates
|
||||
ORDER BY `date` DESC, `timestamp` DESC
|
||||
) as dense_ranked
|
||||
WHERE denseRank != 1
|
||||
);
|
||||
COMMIT;
|
||||
@@ -0,0 +1,120 @@
|
||||
-- Update table and column profile timestamps to be in milliseconds
|
||||
UPDATE entity_extension_time_series
|
||||
SET json = JSON_INSERT(
|
||||
JSON_REMOVE(json, '$.timestamp'),
|
||||
'$.timestamp',
|
||||
JSON_EXTRACT(json, '$.timestamp') * 1000
|
||||
)
|
||||
WHERE
|
||||
extension in ('table.tableProfile', 'table.columnProfile', 'testCase.testCaseResult');
|
||||
;
|
||||
|
||||
START TRANSACTION;
|
||||
-- Create report data time series table and move data from entity_extension_time_series
|
||||
CREATE TABLE IF NOT EXISTS report_data_time_series (
|
||||
entityFQNHash VARCHAR(768) CHARACTER SET ascii COLLATE ascii_bin NOT NULL,
|
||||
extension VARCHAR(256) NOT NULL,
|
||||
jsonSchema VARCHAR(256) NOT NULL,
|
||||
json JSON NOT NULL,
|
||||
timestamp BIGINT UNSIGNED GENERATED ALWAYS AS (json ->> '$.timestamp') NOT NULL,
|
||||
date DATE GENERATED ALWAYS AS (FROM_UNIXTIME((json ->> '$.timestamp') DIV 1000)) NOT NULL,
|
||||
INDEX report_data_time_series_point_ts (timestamp),
|
||||
INDEX report_data_time_series_date (date)
|
||||
);
|
||||
|
||||
INSERT INTO report_data_time_series (entityFQNHash,extension,jsonSchema,json)
|
||||
SELECT entityFQNHash, extension, jsonSchema, json
|
||||
FROM entity_extension_time_series WHERE extension = 'reportData.reportDataResult';
|
||||
|
||||
DELETE FROM entity_extension_time_series
|
||||
WHERE extension = 'reportData.reportDataResult';
|
||||
COMMIT;
|
||||
|
||||
START TRANSACTION;
|
||||
-- Create profiler data time series table and move data from entity_extension_time_series
|
||||
CREATE TABLE IF NOT EXISTS profiler_data_time_series (
|
||||
entityFQNHash VARCHAR(768) CHARACTER SET ascii COLLATE ascii_bin NOT NULL,
|
||||
extension VARCHAR(256) NOT NULL,
|
||||
jsonSchema VARCHAR(256) NOT NULL,
|
||||
json JSON NOT NULL,
|
||||
operation VARCHAR(256) GENERATED ALWAYS AS (json ->> '$.operation') NULL,
|
||||
timestamp BIGINT UNSIGNED GENERATED ALWAYS AS (json ->> '$.timestamp') NOT NULL,
|
||||
UNIQUE profiler_data_time_series_unique_hash_extension_ts (entityFQNHash, extension, operation, timestamp),
|
||||
INDEX profiler_data_time_series_combined_id_ts (extension, timestamp)
|
||||
);
|
||||
|
||||
INSERT INTO profiler_data_time_series (entityFQNHash,extension,jsonSchema,json)
|
||||
SELECT entityFQNHash, extension, jsonSchema, json
|
||||
FROM entity_extension_time_series
|
||||
WHERE extension IN ('table.columnProfile', 'table.tableProfile', 'table.systemProfile');
|
||||
|
||||
DELETE FROM entity_extension_time_series
|
||||
WHERE extension IN ('table.columnProfile', 'table.tableProfile', 'table.systemProfile');
|
||||
COMMIT;
|
||||
|
||||
START TRANSACTION;
|
||||
-- Create data quality data time series table and move data from entity_extension_time_series
|
||||
CREATE TABLE IF NOT EXISTS data_quality_data_time_series (
|
||||
entityFQNHash VARCHAR(768) CHARACTER SET ascii COLLATE ascii_bin NOT NULL,
|
||||
extension VARCHAR(256) NOT NULL,
|
||||
jsonSchema VARCHAR(256) NOT NULL,
|
||||
json JSON NOT NULL,
|
||||
timestamp BIGINT UNSIGNED GENERATED ALWAYS AS (json ->> '$.timestamp') NOT NULL,
|
||||
UNIQUE data_quality_data_time_series_unique_hash_extension_ts (entityFQNHash, extension, timestamp),
|
||||
INDEX data_quality_data_time_series_combined_id_ts (extension, timestamp)
|
||||
);
|
||||
|
||||
INSERT INTO data_quality_data_time_series (entityFQNHash,extension,jsonSchema,json)
|
||||
SELECT entityFQNHash, extension, jsonSchema, json
|
||||
FROM entity_extension_time_series
|
||||
WHERE extension = 'testCase.testCaseResult';
|
||||
|
||||
DELETE FROM entity_extension_time_series
|
||||
WHERE extension = 'testCase.testCaseResult';
|
||||
COMMIT;
|
||||
|
||||
ALTER TABLE automations_workflow MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin,MODIFY COLUMN workflowType VARCHAR(256) COLLATE ascii_bin, MODIFY COLUMN status VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE entity_extension_time_series MODIFY COLUMN entityFQNHash VARCHAR(768) COLLATE ascii_bin, MODIFY COLUMN jsonSchema VARCHAR(50) COLLATE ascii_bin, MODIFY COLUMN extension VARCHAR(100) COLLATE ascii_bin,
|
||||
ADD CONSTRAINT entity_extension_time_series_constraint UNIQUE (entityFQNHash, extension, timestamp);
|
||||
ALTER TABLE field_relationship MODIFY COLUMN fromFQNHash VARCHAR(768) COLLATE ascii_bin, MODIFY COLUMN toFQNHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE thread_entity MODIFY COLUMN entityLink VARCHAR(3072) GENERATED ALWAYS AS (json ->> '$.about') NOT NULL;
|
||||
ALTER TABLE event_subscription_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE ingestion_pipeline_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE bot_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE user_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE team_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE role_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE policy_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE classification MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE tag MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE tag_usage MODIFY COLUMN tagFQNHash VARCHAR(768) COLLATE ascii_bin, MODIFY COLUMN targetFQNHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE glossary_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE glossary_term_entity MODIFY fqnHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE type_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE web_analytic_event MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE data_insight_chart MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE kpi_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE test_definition MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE test_connection_definition MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE test_suite MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE test_case MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE dbservice_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE messaging_service_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE metadata_service_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE pipeline_service_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE dashboard_service_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE mlmodel_service_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE storage_service_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE database_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE database_schema_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE table_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE dashboard_data_model_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE dashboard_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE chart_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE pipeline_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE ml_model_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE metric_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE query_entity MODIFY COLUMN nameHash VARCHAR(256) COLLATE ascii_bin;
|
||||
ALTER TABLE report_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE storage_container_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
ALTER TABLE topic_entity MODIFY COLUMN fqnHash VARCHAR(768) COLLATE ascii_bin;
|
||||
@@ -0,0 +1,53 @@
|
||||
BEGIN;
|
||||
-- We'll rank all the runs (timestamps) for every day, and delete all the data but the most recent one.
|
||||
DELETE FROM report_data_time_series WHERE (json ->> 'id') IN (
|
||||
select ids FROM (
|
||||
SELECT
|
||||
(json ->> 'id') AS ids,
|
||||
DENSE_RANK() OVER(PARTITION BY date ORDER BY timestamp DESC) as denseRank
|
||||
FROM (
|
||||
SELECT
|
||||
*,
|
||||
DATE(TO_TIMESTAMP((json ->> 'timestamp')::bigint/1000)) as date
|
||||
FROM report_data_time_series rdts
|
||||
WHERE json ->> 'reportDataType' = 'WebAnalyticEntityViewReportData'
|
||||
) duplicates
|
||||
ORDER BY date DESC, timestamp DESC
|
||||
) as dense_ranked
|
||||
WHERE denseRank != 1
|
||||
);
|
||||
|
||||
DELETE FROM report_data_time_series WHERE (json ->> 'id') IN (
|
||||
select ids FROM (
|
||||
SELECT
|
||||
(json ->> 'id') AS ids,
|
||||
DENSE_RANK() OVER(PARTITION BY date ORDER BY timestamp DESC) as denseRank
|
||||
FROM (
|
||||
SELECT
|
||||
*,
|
||||
DATE(TO_TIMESTAMP((json ->> 'timestamp')::bigint/1000)) as date
|
||||
FROM report_data_time_series rdts
|
||||
WHERE json ->> 'reportDataType' = 'EntityReportData'
|
||||
) duplicates
|
||||
ORDER BY date DESC, timestamp DESC
|
||||
) as dense_ranked
|
||||
WHERE denseRank != 1
|
||||
);
|
||||
|
||||
DELETE FROM report_data_time_series WHERE (json ->> 'id') IN (
|
||||
select ids FROM (
|
||||
SELECT
|
||||
(json ->> 'id') AS ids,
|
||||
DENSE_RANK() OVER(PARTITION BY date ORDER BY timestamp DESC) as denseRank
|
||||
FROM (
|
||||
SELECT
|
||||
*,
|
||||
DATE(TO_TIMESTAMP((json ->> 'timestamp')::bigint/1000)) as date
|
||||
FROM report_data_time_series rdts
|
||||
WHERE json ->> 'reportDataType' = 'WebAnalyticUserActivityReportData'
|
||||
) duplicates
|
||||
ORDER BY date DESC, timestamp DESC
|
||||
) as dense_ranked
|
||||
WHERE denseRank != 1
|
||||
);
|
||||
COMMIT;
|
||||
@@ -0,0 +1,83 @@
|
||||
-- Update table and column profile timestamps to be in milliseconds
|
||||
UPDATE entity_extension_time_series
|
||||
SET json = jsonb_set(
|
||||
json,
|
||||
'{timestamp}',
|
||||
to_jsonb(cast(json#>'{timestamp}' as int8) *1000)
|
||||
)
|
||||
WHERE
|
||||
extension in ('table.tableProfile', 'table.columnProfile', 'testCase.testCaseResult');
|
||||
;
|
||||
|
||||
BEGIN;
|
||||
-- Run the following SQL to update the schema in a transaction
|
||||
-- Create report data time series table and move data from entity_extension_time_series
|
||||
CREATE TABLE IF NOT EXISTS report_data_time_series (
|
||||
entityFQNHash VARCHAR(768),
|
||||
extension VARCHAR(256) NOT NULL,
|
||||
jsonSchema VARCHAR(256) NOT NULL,
|
||||
json JSONB NOT NULL,
|
||||
timestamp BIGINT CHECK (timestamp > 0) GENERATED ALWAYS AS ((json ->> 'timestamp')::bigint) STORED NOT NULL
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS report_data_time_series_point_ts ON report_data_time_series (timestamp);
|
||||
|
||||
INSERT INTO report_data_time_series (entityFQNHash,extension,jsonSchema,json)
|
||||
|
||||
SELECT entityFQNHash, extension, jsonSchema, json
|
||||
FROM entity_extension_time_series WHERE extension = 'reportData.reportDataResult';
|
||||
|
||||
DELETE FROM entity_extension_time_series
|
||||
WHERE extension = 'reportData.reportDataResult';
|
||||
COMMIT;
|
||||
|
||||
BEGIN;
|
||||
-- Create profiler data time series table and move data from entity_extension_time_series
|
||||
CREATE TABLE IF NOT EXISTS profiler_data_time_series (
|
||||
entityFQNHash VARCHAR(768),
|
||||
extension VARCHAR(256) NOT NULL,
|
||||
jsonSchema VARCHAR(256) NOT NULL,
|
||||
json JSON NOT NULL,
|
||||
operation VARCHAR(256) GENERATED ALWAYS AS ((json ->> 'operation')::text) STORED NULL,
|
||||
timestamp BIGINT CHECK (timestamp > 0) GENERATED ALWAYS AS ((json ->> 'timestamp')::bigint) STORED NOT NULL,
|
||||
CONSTRAINT profiler_data_time_series_unique_hash_extension_ts UNIQUE(entityFQNHash, extension, operation, timestamp)
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS profiler_data_time_series_combined_id_ts ON profiler_data_time_series (extension, timestamp);
|
||||
|
||||
INSERT INTO profiler_data_time_series (entityFQNHash,extension,jsonSchema,json)
|
||||
SELECT entityFQNHash, extension, jsonSchema, json
|
||||
FROM entity_extension_time_series
|
||||
WHERE extension IN ('table.columnProfile', 'table.tableProfile', 'table.systemProfile');
|
||||
|
||||
DELETE FROM entity_extension_time_series
|
||||
WHERE extension IN ('table.columnProfile', 'table.tableProfile', 'table.systemProfile');
|
||||
COMMIT;
|
||||
|
||||
BEGIN;
|
||||
-- Create profiler data time series table and move data from entity_extension_time_series
|
||||
CREATE TABLE IF NOT EXISTS data_quality_data_time_series (
|
||||
entityFQNHash VARCHAR(768),
|
||||
extension VARCHAR(256) NOT NULL,
|
||||
jsonSchema VARCHAR(256) NOT NULL,
|
||||
json JSON NOT NULL,
|
||||
timestamp BIGINT CHECK (timestamp > 0) GENERATED ALWAYS AS ((json ->> 'timestamp')::bigint) STORED NOT NULL,
|
||||
CONSTRAINT data_quality_data_time_series_unique_hash_extension_ts UNIQUE(entityFQNHash, extension, timestamp)
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS data_quality_data_time_series_combined_id_ts ON data_quality_data_time_series (extension, timestamp);
|
||||
|
||||
INSERT INTO data_quality_data_time_series (entityFQNHash,extension,jsonSchema,json)
|
||||
SELECT entityFQNHash, extension, jsonSchema, json
|
||||
FROM entity_extension_time_series
|
||||
WHERE extension = 'testCase.testCaseResult';
|
||||
|
||||
DELETE FROM entity_extension_time_series
|
||||
WHERE extension = 'testCase.testCaseResult';
|
||||
COMMIT;
|
||||
|
||||
ALTER TABLE entity_extension_time_series ALTER COLUMN entityFQNHash TYPE VARCHAR(768), ALTER COLUMN jsonSchema TYPE VARCHAR(50) , ALTER COLUMN extension TYPE VARCHAR(100) ,
|
||||
ADD CONSTRAINT entity_extension_time_series_constraint UNIQUE (entityFQNHash, extension, timestamp);
|
||||
ALTER TABLE field_relationship ALTER COLUMN fromFQNHash TYPE VARCHAR(768), ALTER COLUMN toFQNHash TYPE VARCHAR(768);
|
||||
ALTER TABLE thread_entity ALTER COLUMN entityLink TYPE VARCHAR(3072);
|
||||
ALTER TABLE tag_usage ALTER COLUMN tagFQNHash TYPE VARCHAR(768), ALTER COLUMN targetFQNHash TYPE VARCHAR(768);
|
||||
ALTER TABLE test_suite ALTER COLUMN fqnHash TYPE VARCHAR(768);
|
||||
Reference in New Issue
Block a user