[
https://issues.apache.org/jira/browse/BEAM-4461?focusedWorklogId=381943&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-381943
]
ASF GitHub Bot logged work on BEAM-4461:
----------------------------------------
Author: ASF GitHub Bot
Created on: 04/Feb/20 23:06
Start Date: 04/Feb/20 23:06
Worklog Time Spent: 10m
Work Description: TheNeuralBit commented on pull request #10766:
[BEAM-4461] Add Selected.flattenedSchema
URL: https://github.com/apache/beam/pull/10766#discussion_r374969408
##########
File path:
sdks/java/core/src/main/java/org/apache/beam/sdk/schemas/transforms/Select.java
##########
@@ -69,55 +75,117 @@
* }</pre>
*/
@Experimental(Kind.SCHEMAS)
-public class Select<T> extends PTransform<PCollection<T>, PCollection<Row>> {
- private final FieldAccessDescriptor fieldAccessDescriptor;
-
- private Select(FieldAccessDescriptor fieldAccessDescriptor) {
- this.fieldAccessDescriptor = fieldAccessDescriptor;
+public class Select {
+ public static <T> Select.Fields<T> create() {
+ return new Fields<>(FieldAccessDescriptor.create());
}
/** Select a set of top-level field ids from the row. */
- public static <T> Select<T> fieldIds(Integer... ids) {
- return new Select<>(FieldAccessDescriptor.withFieldIds(ids));
+ public static <T> Fields<T> fieldIds(Integer... ids) {
+ return new Fields<>(FieldAccessDescriptor.withFieldIds(ids));
}
/** Select a set of top-level field names from the row. */
- public static <T> Select<T> fieldNames(String... names) {
- return new Select<>(FieldAccessDescriptor.withFieldNames(names));
+ public static <T> Fields<T> fieldNames(String... names) {
+ return new Fields<>(FieldAccessDescriptor.withFieldNames(names));
}
/**
* Select a set of fields described in a {@link FieldAccessDescriptor}.
*
* <p>This allows for nested fields to be selected as well.
*/
- public static <T> Select<T> fieldAccess(FieldAccessDescriptor
fieldAccessDescriptor) {
- return new Select<>(fieldAccessDescriptor);
+ public static <T> Fields<T> fieldAccess(FieldAccessDescriptor
fieldAccessDescriptor) {
+ return new Fields<>(fieldAccessDescriptor);
+ }
+
+ /**
+ * Selects every leaf-level field. This results in a a nested schema being
flattened into a single
+ * top-level schema.
+ */
Review comment:
This should probably indicate it will concat field names with underscores
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
Issue Time Tracking
-------------------
Worklog Id: (was: 381943)
Time Spent: 29h 10m (was: 29h)
> Create a library of useful transforms that use schemas
> ------------------------------------------------------
>
> Key: BEAM-4461
> URL: https://issues.apache.org/jira/browse/BEAM-4461
> Project: Beam
> Issue Type: Sub-task
> Components: sdk-java-core
> Reporter: Reuven Lax
> Assignee: Reuven Lax
> Priority: Major
> Time Spent: 29h 10m
> Remaining Estimate: 0h
>
> e.g. JoinBy(fields). Project, Filter, etc.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
