Add Dynamic Schema support to StorageWriteToBigQuery #39236
There are no files selected for viewing
This file contains hidden or 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 |
|---|---|---|
| @@ -1,4 +1,4 @@ | ||
| { | ||
| "comment": "Modify this file in a trivial way to cause this test suite to run", | ||
| "modification": 21 | ||
| } | ||
This file contains hidden or 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 |
|---|---|---|
| @@ -1,4 +1,4 @@ | ||
| { | ||
| "comment": "Modify this file in a trivial way to cause this test suite to run", | ||
| "modification": 7 | ||
| } |
This file contains hidden or 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 hidden or 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 hidden or 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 hidden or 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 hidden or 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 |
|---|---|---|
|
|
@@ -887,7 +887,7 @@ public static Descriptor wrapDescriptorProto(DescriptorProto descriptorProto) | |
| if (unknownFields != null) { | ||
| unknownFields.set(key, entry.getValue()); | ||
| } | ||
| if (ignoreUnknownValues || entry.getValue() == null) { | ||
| continue; | ||
| } else { | ||
| String prefix = schemaInformation.getFullName(); | ||
|
|
@@ -2087,4 +2087,45 @@ private static boolean isProtoFieldTypeInteger(FieldDescriptor.Type type) { | |
| return false; | ||
| } | ||
| } | ||
|
|
||
| static boolean hasExtraFields( | ||
| com.google.api.services.bigquery.model.@Nullable TableSchema clientSchema, | ||
| com.google.api.services.bigquery.model.@Nullable TableSchema bqSchema) { | ||
| if (clientSchema == null || clientSchema.getFields() == null) { | ||
| return false; | ||
| } | ||
| if (bqSchema == null || bqSchema.getFields() == null) { | ||
| return false; | ||
| } | ||
| java.util.Map<String, com.google.api.services.bigquery.model.TableFieldSchema> bqFieldMap = | ||
| bqSchema.getFields().stream() | ||
| .collect( | ||
| java.util.stream.Collectors.toMap( | ||
| com.google.api.services.bigquery.model.TableFieldSchema::getName, | ||
| f -> f, | ||
| (a, b) -> a)); | ||
| for (com.google.api.services.bigquery.model.TableFieldSchema clientField : | ||
| clientSchema.getFields()) { | ||
| com.google.api.services.bigquery.model.TableFieldSchema bqField = | ||
| bqFieldMap.get(clientField.getName()); | ||
| if (bqField == null) { | ||
| return true; | ||
| } | ||
| if ("RECORD".equalsIgnoreCase(clientField.getType()) | ||
| || "STRUCT".equalsIgnoreCase(clientField.getType())) { | ||
| if (clientField.getFields() != null && bqField.getFields() != null) { | ||
| com.google.api.services.bigquery.model.TableSchema nestedClient = | ||
| new com.google.api.services.bigquery.model.TableSchema() | ||
| .setFields(clientField.getFields()); | ||
| com.google.api.services.bigquery.model.TableSchema nestedBq = | ||
| new com.google.api.services.bigquery.model.TableSchema() | ||
| .setFields(bqField.getFields()); | ||
| if (hasExtraFields(nestedClient, nestedBq)) { | ||
| return true; | ||
| } | ||
| } | ||
| } | ||
| } | ||
| return false; | ||
| } | ||
| } | ||
This file contains hidden or 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 |
|---|---|---|
|
|
@@ -53,6 +53,7 @@ | |
| import org.apache.beam.sdk.values.TypeDescriptors; | ||
| import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.annotations.VisibleForTesting; | ||
| import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.base.Strings; | ||
| import org.checkerframework.checker.nullness.qual.Nullable; | ||
| import org.joda.time.Duration; | ||
|
|
||
| /** | ||
|
|
@@ -241,20 +242,35 @@ public PCollectionRowTuple expand(PCollectionRowTuple input) { | |
| Schema.of( | ||
| Field.of("failed_row", FieldType.row(inputSchema)), | ||
| Field.of("error_message", FieldType.STRING)); | ||
| boolean isDynamicDestinations = configuration.getTable().equals(DYNAMIC_DESTINATIONS); | ||
| @Nullable Schema recordSchema = | ||
| isDynamicDestinations ? inputSchema.getField(RECORD).getType().getRowSchema() : null; | ||
| PCollection<Row> failedRowsWithErrors = | ||
| result | ||
| .getFailedStorageApiInserts() | ||
| .apply( | ||
| "Construct failed rows and errors", | ||
| MapElements.into(TypeDescriptors.rows()) | ||
| .via( | ||
| (storageError) -> { | ||
| Row failedRow; | ||
| if (isDynamicDestinations && recordSchema != null) { | ||
| Row recordRow = | ||
| BigQueryUtils.toBeamRow(recordSchema, storageError.getRow()); | ||
| failedRow = | ||
| Row.withSchema(inputSchema) | ||
| .withFieldValue(DESTINATION, "") | ||
| .withFieldValue(RECORD, recordRow) | ||
| .build(); | ||
| } else { | ||
| failedRow = | ||
| BigQueryUtils.toBeamRow(inputSchema, storageError.getRow()); | ||
| } | ||
| return Row.withSchema(errorSchema) | ||
| .withFieldValue("error_message", storageError.getErrorMessage()) | ||
| .withFieldValue("failed_row", failedRow) | ||
| .build(); | ||
| })) | ||
| .setRowSchema(errorSchema); | ||
| return PCollectionRowTuple.of("post_write", postWrite) | ||
| .and(configuration.getErrorHandling().getOutput(), failedRowsWithErrors); | ||
|
|
||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think you can also trigger .github/trigger_files/beam_PostCommit_Python_Xlang_Gcp_Direct.json for faster validation