Add support for PARQUET format in BigQuery load jobs. by tswast · Pull Request #3357 · googleapis/google-cloud-java · GitHub
Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -438,10 +438,10 @@ public Long writeRemoteFileToTable(String datasetName, String tableName)
.setSchema(schema)
.build();
// Load the table
Job remoteLoadJob = bigquery.create(JobInfo.of(configuration));
remoteLoadJob = remoteLoadJob.waitFor();
Job loadJob = bigquery.create(JobInfo.of(configuration));
loadJob = loadJob.waitFor();
// Check the table
System.out.println("State: " + remoteLoadJob.getStatus().getState());
System.out.println("State: " + loadJob.getStatus().getState());
return ((StandardTableDefinition) bigquery.getTable(tableId).getDefinition()).getNumRows();
// [END bigquery_load_table_gcs_json]
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -14,13 +14,18 @@
* limitations under the License.
*/

package com.google.cloud.examples.bigquery.cloudsnippets;
package com.google.cloud.examples.bigquery.snippets;

import com.google.cloud.bigquery.BigQuery;
import com.google.cloud.bigquery.FieldValue;
import com.google.cloud.bigquery.FieldValueList;
import com.google.cloud.bigquery.FormatOptions;
import com.google.cloud.bigquery.Job;
import com.google.cloud.bigquery.JobInfo;
import com.google.cloud.bigquery.LoadJobConfiguration;
import com.google.cloud.bigquery.QueryJobConfiguration;
import com.google.cloud.bigquery.QueryParameterValue;
import com.google.cloud.bigquery.StandardTableDefinition;
import com.google.cloud.bigquery.TableId;
import java.util.concurrent.TimeoutException;
import org.joda.time.DateTime;
Expand Down Expand Up @@ -283,4 +288,25 @@ public void runQueryWithTimestampParameters() throws InterruptedException {
}
// [END bigquery_query_params_timestamps]
}

/**
* Example of loading a parquet file from GCS to a table.
*/
public void loadTableGcsParquet(String datasetName) throws InterruptedException {
// [START bigquery_load_table_gcs_parquet]
String sourceUri = "gs://cloud-samples-data/bigquery/us-states/us-states.parquet";
TableId tableId = TableId.of(datasetName, "us_states");
LoadJobConfiguration configuration =
LoadJobConfiguration.builder(tableId, sourceUri)
.setFormatOptions(FormatOptions.parquet())
.build();
// Load the table
Job loadJob = bigquery.create(JobInfo.of(configuration));
loadJob = loadJob.waitFor();
// Check the table
StandardTableDefinition destinationTable = bigquery.getTable(tableId).getDefinition();
System.out.println("State: " + loadJob.getStatus().getState());
System.out.printf("Loaded %d rows.\n", destinationTable.getNumRows());
// [END bigquery_load_table_gcs_parquet]
}
}