Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[CsvIO] Changed CsvIOParseConfiguration to include DLQ #31852

Merged
merged 5 commits into from
Jul 12, 2024
Merged

[CsvIO] Changed CsvIOParseConfiguration to include DLQ #31852

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
1b59c22
Create CsvIOParseConfiguration class
lahariguduru Jun 28, 2024
ee9291f
Altered CsvIOParseConfiguration class to include Dead Letter Queue me…
lahariguduru Jul 11, 2024
74c9686
Merge branch 'master' into csv-parse-configuration
lahariguduru Jul 11, 2024
6d06453
Altered CsvIOParseConfiguration class to allow for Dead Letter Queue …
lahariguduru Jul 11, 2024
7d01633
removed System.out.println(input)
lahariguduru Jul 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 26 additions & 5 deletions sdks/java/io/csv/src/main/java/org/apache/beam/sdk/io/csv/CsvIOParseConfiguration.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,22 +22,27 @@
import java.util.Map;
import java.util.Optional;
import org.apache.beam.sdk.schemas.Schema;
import org.apache.beam.sdk.transforms.DoFn;
import org.apache.beam.sdk.transforms.PTransform;
import org.apache.beam.sdk.transforms.ParDo;
import org.apache.beam.sdk.transforms.SerializableFunction;
import org.apache.beam.sdk.transforms.errorhandling.BadRecord;
import org.apache.beam.sdk.values.PCollection;
import org.apache.commons.csv.CSVFormat;

/** Stores parameters needed for CSV record parsing. */
@AutoValue
abstract class CsvIOParseConfiguration {

/** A Dead Letter Queue that returns potential errors with {@link BadRecord}. */
final PTransform<PCollection<BadRecord>, PCollection<BadRecord>> errorHandlerTransform =
new BadRecordOutput();

static Builder builder() {
return new AutoValue_CsvIOParseConfiguration.Builder();
}

/**
* The expected <a
* href="https://javadoc.io/doc/org.apache.commons/commons-csv/1.8/org/apache/commons/csv/CSVFormat.html">CSVFormat</a>
* of the parsed CSV record.
*/
/** The expected {@link CSVFormat} of the parsed CSV record. */
abstract CSVFormat getCsvFormat();

/** The expected {@link Schema} of the target type. */
Expand Down Expand Up @@ -66,4 +71,20 @@ final CsvIOParseConfiguration build() {
return autoBuild();
}
}

private static class BadRecordOutput
extends PTransform<PCollection<BadRecord>, PCollection<BadRecord>> {

@Override
public PCollection<BadRecord> expand(PCollection<BadRecord> input) {
return input.apply(ParDo.of(new BadRecordTransformFn()));
}

private static class BadRecordTransformFn extends DoFn<BadRecord, BadRecord> {
@ProcessElement
public void process(@Element BadRecord input, OutputReceiver<BadRecord> receiver) {
receiver.output(input);
}
}
}
}
Loading