ahmedabu98 commented on code in PR #23827:
URL: https://github.com/apache/beam/pull/23827#discussion_r1008160736


##########
sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/providers/BigQueryDirectReadSchemaTransformProvider.java:
##########
@@ -0,0 +1,206 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.beam.sdk.io.gcp.bigquery.providers;
+
+import static 
org.apache.beam.vendor.guava.v26_0_jre.com.google.common.base.Preconditions.checkArgument;
+
+import com.google.api.services.bigquery.model.TableRow;
+import com.google.auto.service.AutoService;
+import com.google.auto.value.AutoValue;
+import java.util.Collections;
+import java.util.List;
+import javax.annotation.Nullable;
+import org.apache.beam.sdk.annotations.Experimental;
+import org.apache.beam.sdk.annotations.Experimental.Kind;
+import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO;
+import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO.TypedRead;
+import org.apache.beam.sdk.io.gcp.bigquery.BigQueryServices;
+import org.apache.beam.sdk.io.gcp.bigquery.BigQueryUtils;
+import 
org.apache.beam.sdk.io.gcp.bigquery.providers.BigQueryDirectReadSchemaTransformProvider.BigQueryDirectReadSchemaTransformConfiguration;
+import org.apache.beam.sdk.schemas.AutoValueSchema;
+import org.apache.beam.sdk.schemas.Schema;
+import org.apache.beam.sdk.schemas.annotations.DefaultSchema;
+import org.apache.beam.sdk.schemas.transforms.SchemaTransform;
+import org.apache.beam.sdk.schemas.transforms.SchemaTransformProvider;
+import org.apache.beam.sdk.schemas.transforms.TypedSchemaTransformProvider;
+import org.apache.beam.sdk.transforms.MapElements;
+import org.apache.beam.sdk.transforms.PTransform;
+import org.apache.beam.sdk.values.PCollection;
+import org.apache.beam.sdk.values.PCollectionRowTuple;
+import org.apache.beam.sdk.values.Row;
+import org.apache.beam.sdk.values.TypeDescriptor;
+import org.apache.beam.vendor.guava.v26_0_jre.com.google.common.base.Strings;
+
+/**
+ * An implementation of {@link TypedSchemaTransformProvider} for BigQuery 
Storage Read API jobs
+ * configured via {@link BigQueryDirectReadSchemaTransformConfiguration}.
+ *
+ * <p><b>Internal only:</b> This class is actively being worked on, and it 
will likely change. We
+ * provide no backwards compatibility guarantees, and it should not be 
implemented outside the Beam
+ * repository.
+ */
+@SuppressWarnings({
+  "nullness" // TODO(https://github.com/apache/beam/issues/20497)
+})
+@Experimental(Kind.SCHEMAS)
+@AutoService(SchemaTransformProvider.class)
+public class BigQueryDirectReadSchemaTransformProvider
+    extends 
TypedSchemaTransformProvider<BigQueryDirectReadSchemaTransformConfiguration> {
+
+  private static final String OUTPUT_TAG = "OUTPUT_ROWS";
+
+  @Override
+  protected Class<BigQueryDirectReadSchemaTransformConfiguration> 
configurationClass() {
+    return BigQueryDirectReadSchemaTransformConfiguration.class;
+  }
+
+  @Override
+  protected SchemaTransform 
from(BigQueryDirectReadSchemaTransformConfiguration configuration) {
+    return new BigQueryDirectReadSchemaTransform(configuration);
+  }
+
+  @Override
+  public String identifier() {
+    return String.format("bigquery:direct-read");
+  }
+
+  @Override
+  public List<String> inputCollectionNames() {
+    return Collections.emptyList();
+  }
+
+  @Override
+  public List<String> outputCollectionNames() {
+    return Collections.singletonList(OUTPUT_TAG);
+  }
+
+  /** Configuration for reading from BigQuery with Storage Read API. */
+  @DefaultSchema(AutoValueSchema.class)
+  @AutoValue
+  public abstract static class BigQueryDirectReadSchemaTransformConfiguration {
+
+    /** Instantiates a {@link 
BigQueryDirectReadSchemaTransformConfiguration.Builder} instance. */
+    public static Builder builder() {
+      return new 
AutoValue_BigQueryDirectReadSchemaTransformProvider_BigQueryDirectReadSchemaTransformConfiguration
+          .Builder();
+    }
+
+    @Nullable
+    public abstract String getQuery();
+
+    @Nullable
+    public abstract String getTableSpec();
+
+    @Nullable
+    public abstract String getRowRestriction();
+
+    @Nullable
+    public abstract List<String> getSelectedFields();
+
+    @Nullable
+    public abstract BigQueryServices getBigQueryServices();
+
+    /** Builder for the {@link 
BigQueryDirectReadSchemaTransformConfiguration}. */
+    @AutoValue.Builder
+    public abstract static class Builder {
+      public abstract Builder setQuery(String query);
+
+      public abstract Builder setTableSpec(String tableSpec);
+
+      public abstract Builder setRowRestriction(String rowRestriction);
+
+      public abstract Builder setSelectedFields(List<String> selectedFields);
+
+      public abstract Builder setBigQueryServices(BigQueryServices 
bigQueryServices);
+
+      /** Builds a {@link BigQueryDirectReadSchemaTransformConfiguration} 
instance. */
+      public abstract BigQueryDirectReadSchemaTransformConfiguration build();
+    }
+  }
+
+  /**
+   * A {@link SchemaTransform} for BigQuery Storage Read API, configured with 
{@link
+   * BigQueryDirectReadSchemaTransformConfiguration} and instantiated by {@link
+   * BigQueryDirectReadSchemaTransformProvider}.
+   */
+  private static class BigQueryDirectReadSchemaTransform implements 
SchemaTransform {
+    private final BigQueryDirectReadSchemaTransformConfiguration configuration;
+
+    BigQueryDirectReadSchemaTransform(
+        BigQueryDirectReadSchemaTransformConfiguration configuration) {
+      this.configuration = configuration;
+    }
+
+    @Override
+    public PTransform<PCollectionRowTuple, PCollectionRowTuple> 
buildTransform() {
+      return new BigQueryDirectReadPCollectionRowTupleTransform(configuration);
+    }
+  }
+
+  static class BigQueryDirectReadPCollectionRowTupleTransform
+      extends PTransform<PCollectionRowTuple, PCollectionRowTuple> {
+    private final BigQueryDirectReadSchemaTransformConfiguration configuration;
+
+    BigQueryDirectReadPCollectionRowTupleTransform(
+        BigQueryDirectReadSchemaTransformConfiguration configuration) {
+      this.configuration = configuration;
+    }
+
+    @Override
+    public PCollectionRowTuple expand(PCollectionRowTuple input) {
+      checkArgument(
+          input.getAll().isEmpty(),
+          String.format(
+              "Input to %s is expected to be empty, but is not.", 
getClass().getSimpleName()));
+
+      BigQueryIO.TypedRead<TableRow> read = createDirectReadTransform();
+
+      PCollection<TableRow> tableRows = input.getPipeline().apply(read);
+      Schema schema = tableRows.getSchema();
+      PCollection<Row> rows =
+          tableRows.apply(
+              MapElements.into(TypeDescriptor.of(Row.class))
+                  .via((tableRow) -> BigQueryUtils.toBeamRow(schema, 
tableRow)));
+
+      return PCollectionRowTuple.of(OUTPUT_TAG, rows.setRowSchema(schema));
+    }
+
+    BigQueryIO.TypedRead<TableRow> createDirectReadTransform() {
+      BigQueryIO.TypedRead<TableRow> read =
+          
BigQueryIO.readTableRowsWithSchema().withMethod(TypedRead.Method.DIRECT_READ);
+
+      if (!Strings.isNullOrEmpty(configuration.getQuery())) {

Review Comment:
   Validation is already done in BigQueryIO, should there be one here too? 
   
   Bigger question: to what extent should a configuration class validation be 
similar to that of the actual connector? e.g. should we validate that the 
tablespec is in the right `<project>:<dataset>.<table>` format, then should we 
verify the table exists?



-- 
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.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to