feat: add new sample - Load: Column Based Time Partitioning

samples/src/main/java/com/example/bigquery/AddColumnLoadAppend.java

@@ -30,7 +30,6 @@
 import com.google.cloud.bigquery.LegacySQLTypeName;
 import com.google.cloud.bigquery.LoadJobConfiguration;
 import com.google.cloud.bigquery.Schema;
-import com.google.cloud.bigquery.Table;
 import com.google.cloud.bigquery.TableId;
 import com.google.common.collect.ImmutableList;
 import java.util.UUID;
@@ -53,7 +52,6 @@ public static void addColumnLoadAppend(String datasetName, String tableName, Str
  BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();
 
  TableId tableId = TableId.of(datasetName, tableName);
- Table table = bigquery.getTable(tableId);
 
  // Add a new column to a BigQuery table while appending rows via a load job.
  // 'REQUIRED' fields cannot be added to an existing schema, so the additional column must be
@@ -79,7 +77,6 @@ public static void addColumnLoadAppend(String datasetName, String tableName, Str
  // Create a job ID so that we can safely retry.
  JobId jobId = JobId.of(UUID.randomUUID().toString());
  Job loadJob = bigquery.create(JobInfo.newBuilder(loadJobConfig).setJobId(jobId).build());
- System.out.println(loadJob.getJobId());
 
  // Load data from a GCS parquet file into the table
  // Blocks until this load table job completes its execution, either failing or succeeding.

samples/src/main/java/com/example/bigquery/CreatePartitionedTable.java

@@ -50,8 +50,8 @@ public static void createPartitionedTable(String datasetName, String tableName)
  Schema schema =
  Schema.of(
  Field.of("stringField", StandardSQLTypeName.STRING),
- Field.of("booleanField", StandardSQLTypeName.BOOL));
- Field.of("dateField", StandardSQLTypeName.DATE);
+ Field.of("booleanField", StandardSQLTypeName.BOOL),
+  Field.of("dateField", StandardSQLTypeName.DATE));
 
  StandardTableDefinition tableDefinition =
  StandardTableDefinition.newBuilder()

samples/src/main/java/com/example/bigquery/LoadPartitionedTable.java

@@ -0,0 +1,102 @@
+/*
+ * Copyright 2020 Google LLC
+ *
+ * Licensed 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 com.example.bigquery;
+
+// [START bigquery_load_table_partitioned]
+import com.google.cloud.bigquery.BigQuery;
+import com.google.cloud.bigquery.BigQueryException;
+import com.google.cloud.bigquery.BigQueryOptions;
+import com.google.cloud.bigquery.Field;
+import com.google.cloud.bigquery.FormatOptions;
+import com.google.cloud.bigquery.Job;
+import com.google.cloud.bigquery.JobId;
+import com.google.cloud.bigquery.JobInfo;
+import com.google.cloud.bigquery.LoadJobConfiguration;
+import com.google.cloud.bigquery.Schema;
+import com.google.cloud.bigquery.StandardSQLTypeName;
+import com.google.cloud.bigquery.TableId;
+import com.google.cloud.bigquery.TimePartitioning;
+import java.time.Duration;
+import java.time.temporal.ChronoUnit;
+import java.util.UUID;
+
+public class LoadPartitionedTable {
+
+ public static void runLoadPartitionedTable() throws Exception {
+ // TODO(developer): Replace these variables before running the sample.
+ String datasetName = "MY_DATASET_NAME";
+ String tableName = "MY_TABLE_NAME";
+ String sourceUri = "/path/to/file.csv";
+ loadPartitionedTable(datasetName, tableName, sourceUri);
+ }
+
+ public static void loadPartitionedTable(String datasetName, String tableName, String sourceUri)
+ throws Exception {
+ try {
+ // Initialize client that will be used to send requests. This client only needs to be created
+ // once, and can be reused for multiple requests.
+ BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();
+
+ TableId tableId = TableId.of(datasetName, tableName);
+
+ Schema schema =
+ Schema.of(
+ Field.of("name", StandardSQLTypeName.STRING),
+ Field.of("post_abbr", StandardSQLTypeName.STRING),
+ Field.of("date", StandardSQLTypeName.DATE));
+
+ // Configure time partitioning. For full list of options, see:
+ // https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#TimePartitioning
+ TimePartitioning partitioning =
+ TimePartitioning.newBuilder(TimePartitioning.Type.DAY)
+ .setField("date")
+ .setExpirationMs(Duration.of(90, ChronoUnit.DAYS).toMillis())
+ .build();
+
+ LoadJobConfiguration loadJobConfig =
+ LoadJobConfiguration.builder(tableId, sourceUri)
+ .setFormatOptions(FormatOptions.csv())
+ .setSchema(schema)
+ .setTimePartitioning(partitioning)
+ .build();
+
+ // Create a job ID so that we can safely retry.
+ JobId jobId = JobId.of(UUID.randomUUID().toString());
+ Job loadJob = bigquery.create(JobInfo.newBuilder(loadJobConfig).setJobId(jobId).build());
+
+ // Load data from a GCS parquet file into the table
+ // Blocks until this load table job completes its execution, either failing or succeeding.
+ Job completedJob = loadJob.waitFor();
+
+ // Check for errors
+ if (completedJob == null) {
+ throw new Exception("Job not executed since it no longer exists.");
+ } else if (completedJob.getStatus().getError() != null) {
+ // You can also look at queryJob.getStatus().getExecutionErrors() for all
+ // errors, not just the latest one.
+ throw new Exception(
+ "BigQuery was unable to load into the table due to an error: \n"
+ + loadJob.getStatus().getError());
+ }
+ System.out.println("Data successfully loaded into time partitioned table during load job");
+ } catch (BigQueryException | InterruptedException e) {
+ System.out.println(
+ "Data not loaded into time partitioned table during load job \n" + e.toString());
+ }
+ }
+}
+// [END bigquery_load_table_partitioned]

samples/src/test/java/com/example/bigquery/AddColumnLoadAppendIT.java

@@ -16,6 +16,7 @@
 
 package com.example.bigquery;
 
+import static com.google.common.truth.Truth.assertThat;
 import static junit.framework.TestCase.assertNotNull;
 
 import com.google.cloud.bigquery.Field;
@@ -72,6 +73,8 @@ public void testAddColumnLoadAppend() throws Exception {
 
  AddColumnLoadAppend.addColumnLoadAppend(BIGQUERY_DATASET_NAME, tableName, sourceUri);
 
+ assertThat(bout.toString()).contains("Column successfully added during load append job");
+
  // Clean up
  DeleteTable.deleteTable(BIGQUERY_DATASET_NAME, tableName);
  }

samples/src/test/java/com/example/bigquery/LoadPartitionedTableIT.java

@@ -0,0 +1,72 @@
+/*
+ * Copyright 2020 Google LLC
+ *
+ * Licensed 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 com.example.bigquery;
+
+import static com.google.common.truth.Truth.assertThat;
+import static junit.framework.TestCase.assertNotNull;
+
+import java.io.ByteArrayOutputStream;
+import java.io.PrintStream;
+import org.junit.After;
+import org.junit.Before;
+import org.junit.BeforeClass;
+import org.junit.Test;
+
+public class LoadPartitionedTableIT {
+ private ByteArrayOutputStream bout;
+ private PrintStream out;
+
+ private static final String BIGQUERY_DATASET_NAME = System.getenv("BIGQUERY_DATASET_NAME");
+
+ private static void requireEnvVar(String varName) {
+ assertNotNull(
+ "Environment variable " + varName + " is required to perform these tests.",
+ System.getenv(varName));
+ }
+
+ @BeforeClass
+ public static void checkRequirements() {
+ requireEnvVar("BIGQUERY_DATASET_NAME");
+ }
+
+ @Before
+ public void setUp() {
+ bout = new ByteArrayOutputStream();
+ out = new PrintStream(bout);
+ System.setOut(out);
+ }
+
+ @After
+ public void tearDown() {
+ System.setOut(null);
+ }
+
+ @Test
+ public void loadPartitionedTable() throws Exception {
+ String sourceUri = "gs://cloud-samples-data/bigquery/us-states/us-states-by-date.csv";
+
+ String tableName = "PARTITIONED_TABLE_TEST";
+
+ LoadPartitionedTable.loadPartitionedTable(BIGQUERY_DATASET_NAME, tableName, sourceUri);
+
+ assertThat(bout.toString())
+ .contains("Data successfully loaded into time partitioned table during load job");
+
+ // Clean up
+ DeleteTable.deleteTable(BIGQUERY_DATASET_NAME, tableName);
+ }
+}