forked from pflooky/data-caterer-example
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Update to 0.10.8, add in Delta lake example, update mysql command
- Loading branch information
Showing
4 changed files
with
42 additions
and
3 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,3 +1,3 @@ | ||
FROM datacatering/data-caterer-basic:0.10.6 | ||
FROM datacatering/data-caterer-basic:0.10.8 | ||
|
||
COPY --chown=app:app build/libs/data-caterer-example-0.1.0.jar /opt/spark/jars/data-caterer.jar |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
39 changes: 39 additions & 0 deletions
39
src/main/scala/io/github/datacatering/plan/DeltaLakePlan.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,39 @@ | ||
package io.github.datacatering.plan | ||
|
||
import io.github.datacatering.datacaterer.api.PlanRun | ||
import io.github.datacatering.datacaterer.api.model.{DateType, DecimalType, TimestampType} | ||
|
||
class DeltaLakePlan extends PlanRun { | ||
|
||
val accountTask = delta("customer_accounts", "/opt/app/data/customer/delta") | ||
.schema( | ||
field.name("account_id").regex("ACC[0-9]{8}").unique(true), | ||
field.name("balance").`type`(new DecimalType(5, 2)).min(1).max(1000), | ||
field.name("created_by").sql("CASE WHEN status IN ('open', 'closed') THEN 'eod' ELSE 'event' END"), | ||
field.name("name").expression("#{Name.name}"), | ||
field.name("open_time").`type`(TimestampType).min(java.sql.Date.valueOf("2022-01-01")), | ||
field.name("status").oneOf("open", "closed", "suspended", "pending") | ||
) | ||
.count(count.records(100)) | ||
|
||
val transactionTask = iceberg("customer_transactions", "/opt/app/data/customer/delta") | ||
.schema( | ||
field.name("account_id"), | ||
field.name("full_name"), | ||
field.name("amount").`type`(new DecimalType(4, 2)).min(1).max(100), | ||
field.name("time").`type`(TimestampType).min(java.sql.Date.valueOf("2022-01-01")), | ||
field.name("date").`type`(DateType).sql("DATE(time)") | ||
) | ||
.count(count.recordsPerColumnGenerator(generator.min(1).max(5), "account_id", "full_name")) | ||
|
||
val config = configuration | ||
.generatedReportsFolderPath("/opt/app/data/report") | ||
.enableUniqueCheck(true) | ||
|
||
val myPlan = plan.addForeignKeyRelationship( | ||
accountTask, List("account_id", "name"), | ||
List(transactionTask -> List("account_id", "full_name")) | ||
) | ||
|
||
execute(myPlan, config, accountTask, transactionTask) | ||
} |