Skip to content

Prevent field duplications on schema merge in BigQuery sink #945

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

Merged
feast-ci-bot merged 1 commit into from
Aug 12, 2020
Merged

Prevent field duplications on schema merge in BigQuery sink #945

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
36 changes: 12 additions & 24 deletions ...y/src/main/java/feast/storage/connectors/bigquery/writer/FeatureSetSpecToTableSchema.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,9 +28,7 @@
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.*;
import java.util.stream.Collectors;
import org.apache.beam.repackaged.core.org.apache.commons.lang3.tuple.Pair;
import org.apache.beam.sdk.coders.Coder;
Expand Down Expand Up @@ -146,8 +144,11 @@ private void createTable(String specKey, Schema schema) {
*/
private Schema createSchemaFromSpec(
FeatureSetProto.FeatureSetSpec spec, String specKey, Table existingTable) {
List<Field> fields = new ArrayList<>();
log.info("Table {} will have the following fields:", specKey);
Map<String, Field> fields = new LinkedHashMap<>();
if (existingTable != null) {
Schema existingSchema = existingTable.getDefinition().getSchema();
existingSchema.getFields().forEach(f -> fields.put(f.getName(), f));
}

for (FeatureSetProto.EntitySpec entitySpec : spec.getEntitiesList()) {
Field.Builder builder =
Expand All @@ -157,8 +158,7 @@ private Schema createSchemaFromSpec(
builder.setMode(Field.Mode.REPEATED);
}
Field field = builder.build();
log.info("- {}", field.toString());
fields.add(field);
fields.put(field.getName(), field);
}
for (FeatureSetProto.FeatureSpec featureSpec : spec.getFeaturesList()) {
Field.Builder builder =
Expand All @@ -169,8 +169,7 @@ private Schema createSchemaFromSpec(
}

Field field = builder.build();
log.info("- {}", field.toString());
fields.add(field);
fields.put(field.getName(), field);
}

// Refer to protos/feast/core/Store.proto for reserved fields in BigQuery.
Expand All @@ -192,24 +191,13 @@ private Schema createSchemaFromSpec(
Field.newBuilder(entry.getKey(), entry.getValue().getLeft())
.setDescription(entry.getValue().getRight())
.build();
log.info("- {}", field.toString());
fields.add(field);
fields.put(field.getName(), field);
}

List<Field> fieldsList = new ArrayList<>();
if (existingTable != null) {
Schema existingSchema = existingTable.getDefinition().getSchema();
fieldsList.addAll(existingSchema.getFields());
}

for (Field field : fields) {
if (!fieldsList.contains(field)) {
fieldsList.add(field);
log.info("- {}", field.toString());
}
}
log.info("Table {} will have the following fields:", specKey);
fields.values().forEach(f -> log.info("- {}", f.toString()));

return Schema.of(FieldList.of(fieldsList));
return Schema.of(FieldList.of(fields.values()));
}

/**
Expand Down
9 changes: 8 additions & 1 deletion ...ors/bigquery/src/test/java/feast/storage/connectors/bigquery/writer/BigQuerySinkTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -315,7 +315,9 @@ public void updateSchemaWithExistingTable() {
TableId.of("test-project", "test_dataset", "myproject_fs_2"),
StandardTableDefinition.of(
Schema.of(
Field.of("old_feature_1", LegacySQLTypeName.FLOAT),
Field.newBuilder("old_feature_1", LegacySQLTypeName.FLOAT)
.setDescription("Some old description")
.build(),
Field.of("old_feature_2", LegacySQLTypeName.INTEGER)))));

FeatureSetSpec spec_fs_2 =
Expand All @@ -332,6 +334,11 @@ public void updateSchemaWithExistingTable() {
.setName("feature")
.setValueType(ValueProto.ValueType.Enum.STRING)
.build())
.addFeatures(
FeatureSpec.newBuilder()
.setName("old_feature_1")
.setValueType(ValueProto.ValueType.Enum.FLOAT)
.build())
.build();

FeatureSink sink =
Expand Down