[
https://issues.apache.org/jira/browse/BEAM-14035?focusedWorklogId=751958&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-751958
]
ASF GitHub Bot logged work on BEAM-14035:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 02/Apr/22 17:07
Start Date: 02/Apr/22 17:07
Worklog Time Spent: 10m
Work Description: damondouglas commented on a change in pull request
#17181:
URL: https://github.com/apache/beam/pull/17181#discussion_r841097800
##########
File path:
sdks/java/io/google-cloud-platform/src/test/java/org/apache/beam/sdk/io/gcp/bigquery/BigQuerySchemaTransformReadProviderTest.java
##########
@@ -0,0 +1,159 @@
+/*
+ * 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;
+
+import static org.junit.Assert.assertTrue;
+
+import com.google.api.services.bigquery.model.Table;
+import com.google.api.services.bigquery.model.TableReference;
+import com.google.api.services.bigquery.model.TableRow;
+import com.google.api.services.bigquery.model.TableSchema;
+import java.io.IOException;
+import java.util.Arrays;
+import java.util.List;
+import
org.apache.beam.sdk.io.gcp.bigquery.BigQuerySchemaTransformReadProvider.PCollectionRowTupleTransform;
+import org.apache.beam.sdk.io.gcp.testing.FakeBigQueryServices;
+import org.apache.beam.sdk.io.gcp.testing.FakeDatasetService;
+import org.apache.beam.sdk.io.gcp.testing.FakeJobService;
+import org.apache.beam.sdk.schemas.AutoValueSchema;
+import org.apache.beam.sdk.schemas.Schema;
+import org.apache.beam.sdk.schemas.Schema.Field;
+import org.apache.beam.sdk.schemas.Schema.FieldType;
+import org.apache.beam.sdk.schemas.transforms.SchemaTransform;
+import org.apache.beam.sdk.schemas.transforms.SchemaTransformProvider;
+import org.apache.beam.sdk.testing.PAssert;
+import org.apache.beam.sdk.testing.TestPipeline;
+import org.apache.beam.sdk.transforms.SerializableFunction;
+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.junit.After;
+import org.junit.Before;
+import org.junit.Rule;
+import org.junit.Test;
+import org.junit.rules.TemporaryFolder;
+import org.junit.runner.RunWith;
+import org.junit.runners.JUnit4;
+
+/** Test for {@link BigQuerySchemaTransformReadProvider}. */
+@RunWith(JUnit4.class)
+public class BigQuerySchemaTransformReadProviderTest {
+ private static final AutoValueSchema AUTO_VALUE_SCHEMA = new
AutoValueSchema();
+ private static final
TypeDescriptor<BigQuerySchemaTransformReadConfiguration> TYPE_DESCRIPTOR =
+ TypeDescriptor.of(BigQuerySchemaTransformReadConfiguration.class);
+ private static final
SerializableFunction<BigQuerySchemaTransformReadConfiguration, Row>
+ ROW_SERIALIZABLE_FUNCTION =
AUTO_VALUE_SCHEMA.toRowFunction(TYPE_DESCRIPTOR);
+
+ private static final String FAKE_PROJECT = "fakeproject";
+ private static final String FAKE_DATASET = "fakedataset";
+ private static final String FAKE_TABLE_ID = "faketable";
+ // private static final String FAKE_QUERY = String.format("select * from
`%s.%s.%s`", FAKE_PROJECT,
+ // FAKE_DATASET, FAKE_TABLE_ID);
+
+ private static final TableReference FAKE_TABLE_REFERENCE = new
TableReference()
+ .setProjectId(FAKE_PROJECT)
+ .setDatasetId(FAKE_DATASET)
+ .setTableId(FAKE_TABLE_ID);
+
+ private static final String FAKE_TABLE_SPEC =
BigQueryHelpers.toTableSpec(FAKE_TABLE_REFERENCE);
+
+ private static final Schema FAKE_SCHEMA = Schema.of(
+ Field.of("name", FieldType.STRING),
+ Field.of("number", FieldType.INT64)
+ );
+
+ private static final List<TableRow> FAKE_RECORDS = Arrays.asList(
+ new TableRow().set("name", "a").set("number", 1L),
+ new TableRow().set("name", "b").set("number", 2L),
+ new TableRow().set("name", "c").set("number", 3L)
+ );
+
+ private static final List<Row> FAKE_ROWS = Arrays.asList(
+ Row.withSchema(FAKE_SCHEMA)
+ .withFieldValue("name", "a")
+ .withFieldValue("number", 1L)
+ .build(),
+ Row.withSchema(FAKE_SCHEMA)
+ .withFieldValue("name", "b")
+ .withFieldValue("number", 2L)
+ .build(),
+ Row.withSchema(FAKE_SCHEMA)
+ .withFieldValue("name", "c")
+ .withFieldValue("number", 3L)
+ .build()
+ );
+
+ private static final TableSchema FAKE_TABLE_SCHEMA =
BigQueryUtils.toTableSchema(FAKE_SCHEMA);
+ private static final BigQueryOptions OPTIONS =
+ TestPipeline.testingPipelineOptions().as(BigQueryOptions.class);
+ private final FakeDatasetService fakeDatasetService = new
FakeDatasetService();
+ private final FakeJobService fakeJobService = new FakeJobService();
+ private final Table fakeTable = new Table();
+ private final TemporaryFolder temporaryFolder = new TemporaryFolder();
+ private final FakeBigQueryServices fakeBigQueryServices =
+ new FakeBigQueryServices()
+ .withJobService(fakeJobService)
+ .withDatasetService(fakeDatasetService);
+
+ @Before
+ public void setUp() throws IOException, InterruptedException {
+ FakeDatasetService.setUp();
+ FakeJobService.setUp();
+ BigQueryIO.clearCreatedTables();
+ fakeTable.setSchema(FAKE_TABLE_SCHEMA);
+ fakeTable.setTableReference(FAKE_TABLE_REFERENCE);
+ fakeTable.setNumBytes(1024L * 1024L);
+ fakeDatasetService.createDataset(FAKE_PROJECT, FAKE_DATASET, "", "", null);
+ fakeDatasetService.createTable(fakeTable);
+ fakeDatasetService.insertAll(fakeTable.getTableReference(), FAKE_RECORDS,
null);
+ temporaryFolder.create();
+ OPTIONS.setProject(FAKE_PROJECT);
+ OPTIONS.setTempLocation(temporaryFolder.getRoot().getAbsolutePath());
+ }
+
+ @After
+ public void tearDown() {
+ temporaryFolder.delete();
+ }
+
+ @Rule
+ public transient TestPipeline p = TestPipeline.fromOptions(OPTIONS);
+
+ @Test
+ public void testFromExtractConfiguration() {
Review comment:
I agree. I will make this change.
--
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]
Issue Time Tracking
-------------------
Worklog Id: (was: 751958)
Time Spent: 4.5h (was: 4h 20m)
> Convert BigQuery SchemaIO to SchemaTransform
> --------------------------------------------
>
> Key: BEAM-14035
> URL: https://issues.apache.org/jira/browse/BEAM-14035
> Project: Beam
> Issue Type: Sub-task
> Components: sdk-java-core
> Reporter: Lara Schmidt
> Assignee: Damon Douglas
> Priority: P2
> Time Spent: 4.5h
> Remaining Estimate: 0h
>
> The output of this task is to refactor
> org.apache.beam.sdk.io.gcp.bigquery.BigQuerySchemaIOProvider [1] to implement
> SchemaTransform [2] and SchemaTransformProvider interfaces [3].
> Please see https://issues.apache.org/jira/browse/BEAM-14168 for more
> information on additional work remaining after this task is complete.
> As a result of this task there will be:
> 1. one class deletion and four classes created for the PR reflecting whether
> we are reading from or writing to BigQuery, via BigQueryIO.Read and
> BigQueryIO.Write, respectively.
> * delete:
> sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQuerySchemaIOProvider.java
> * create:
> sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQuerySchemaTransformReadConfiguration.java
> * create:
> sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQuerySchemaTransformReadProvider.java
> * create:
> sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQuerySchemaTransformWriteConfiguration.java
> * create:
> sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQuerySchemaTransformWriteProvider.java
> 2. The testing strategy will leverage the use of the
> org.apache.beam.sdk.transforms.display.DisplayData class instead of using the
> org.apache.beam.sdk.io.gcp.testing.FakeBigQueryServices.
> We will test whether the input of BigQuerySchemaTransformReadConfiguration
> yields a BigQueryIO.Read with correct query, tableSpec, useLegacySQL
> (defaulted to false), and queryLocation values.
> We will test whether the input of BigQuerySchemaTransformWriteConfiguration
> yields a BigQueryIO.Write with correct tableReference, createDisposition, and
> writeDisposition values.
> References:
> 1 -
> [sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQuerySchemaIOProvider.java|https://github.com/apache/beam/blob/fc00b9697a0dfb73a03981f4d6c2c8dd1e316d5e/sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQuerySchemaIOProvider.java]
> 2 -
> [SchemaTransform|https://github.com/apache/beam/blob/a47a725863fc8c37a9b8520cebeef83677fe531d/sdks/java/core/src/main/java/org/apache/beam/sdk/schemas/transforms/SchemaTransform.java]
> 3 -
> [SchemaTransformProvider|https://github.com/apache/beam/blob/a47a725863fc8c37a9b8520cebeef83677fe531d/sdks/java/core/src/main/java/org/apache/beam/sdk/schemas/transforms/SchemaTransformProvider.java]
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
