Examples with Clustering com.google.api.services.bigquery.model.Clustering used on opensource projects

Example 1 with Clustering

use of com.google.api.services.bigquery.model.Clustering in project beam by apache.

the class BigQueryIOWriteTest method testTimePartitioningClustering.

void testTimePartitioningClustering(BigQueryIO.Write.Method insertMethod, boolean enablePartitioning, boolean enableClustering) throws Exception {
    TableRow row1 = new TableRow().set("date", "2018-01-01").set("number", "1");
    TableRow row2 = new TableRow().set("date", "2018-01-02").set("number", "2");
    TimePartitioning timePartitioning = new TimePartitioning().setType("DAY").setField("date");
    Clustering clustering = new Clustering().setFields(ImmutableList.of("date"));
    TableSchema schema = new TableSchema().setFields(ImmutableList.of(new TableFieldSchema().setName("date").setType("DATE"), new TableFieldSchema().setName("number").setType("INTEGER")));
    Write<TableRow> writeTransform = BigQueryIO.writeTableRows().to("project-id:dataset-id.table-id").withTestServices(fakeBqServices).withMethod(insertMethod).withSchema(schema).withoutValidation();
    if (enablePartitioning) {
        writeTransform = writeTransform.withTimePartitioning(timePartitioning);
    }
    if (enableClustering) {
        writeTransform = writeTransform.withClustering(clustering);
    }
    p.apply(Create.of(row1, row2)).apply(writeTransform);
    p.run();
    Table table = fakeDatasetService.getTable(BigQueryHelpers.parseTableSpec("project-id:dataset-id.table-id"));
    assertEquals(schema, table.getSchema());
    if (enablePartitioning) {
        assertEquals(timePartitioning, table.getTimePartitioning());
    }
    if (enableClustering) {
        assertEquals(clustering, table.getClustering());
    }
}

Example 2 with Clustering

use of com.google.api.services.bigquery.model.Clustering in project beam by apache.

the class BigQueryIOWriteTest method testClusteringTableFunction.

@Test
public void testClusteringTableFunction() throws Exception {
    TableRow row1 = new TableRow().set("date", "2018-01-01").set("number", "1");
    TableRow row2 = new TableRow().set("date", "2018-01-02").set("number", "2");
    TimePartitioning timePartitioning = new TimePartitioning().setType("DAY").setField("date");
    Clustering clustering = new Clustering().setFields(ImmutableList.of("date"));
    TableSchema schema = new TableSchema().setFields(ImmutableList.of(new TableFieldSchema().setName("date").setType("DATE"), new TableFieldSchema().setName("number").setType("INTEGER")));
    // withMethod overrides the pipeline option, so we need to explicitly request
    // STORAGE_API_WRITES.
    BigQueryIO.Write.Method method = useStorageApi ? (useStorageApiApproximate ? Method.STORAGE_API_AT_LEAST_ONCE : Method.STORAGE_WRITE_API) : Method.FILE_LOADS;
    p.apply(Create.of(row1, row2)).apply(BigQueryIO.writeTableRows().to((ValueInSingleWindow<TableRow> vsw) -> {
        String tableSpec = "project-id:dataset-id.table-" + vsw.getValue().get("number");
        return new TableDestination(tableSpec, null, new TimePartitioning().setType("DAY").setField("date"), new Clustering().setFields(ImmutableList.of("date")));
    }).withTestServices(fakeBqServices).withMethod(method).withSchema(schema).withClustering().withoutValidation());
    p.run();
    Table table = fakeDatasetService.getTable(BigQueryHelpers.parseTableSpec("project-id:dataset-id.table-1"));
    assertEquals(schema, table.getSchema());
    assertEquals(timePartitioning, table.getTimePartitioning());
    assertEquals(clustering, table.getClustering());
}

Example 3 with Clustering

use of com.google.api.services.bigquery.model.Clustering in project beam by apache.

the class FakeJobService method runCopyJob.

private JobStatus runCopyJob(JobConfigurationTableCopy copy) throws InterruptedException, IOException {
    List<TableReference> sources = copy.getSourceTables();
    TableReference destination = copy.getDestinationTable();
    WriteDisposition writeDisposition = WriteDisposition.valueOf(copy.getWriteDisposition());
    CreateDisposition createDisposition = CreateDisposition.valueOf(copy.getCreateDisposition());
    Table existingTable = datasetService.getTable(destination);
    if (!validateDispositions(existingTable, createDisposition, writeDisposition)) {
        return new JobStatus().setState("FAILED").setErrorResult(new ErrorProto());
    }
    TimePartitioning partitioning = null;
    Clustering clustering = null;
    TableSchema schema = null;
    boolean first = true;
    List<TableRow> allRows = Lists.newArrayList();
    for (TableReference source : sources) {
        Table table = checkNotNull(datasetService.getTable(source));
        if (!first) {
            if (!Objects.equals(partitioning, table.getTimePartitioning())) {
                return new JobStatus().setState("FAILED").setErrorResult(new ErrorProto());
            }
            if (!Objects.equals(clustering, table.getClustering())) {
                return new JobStatus().setState("FAILED").setErrorResult(new ErrorProto());
            }
            if (!Objects.equals(schema, table.getSchema())) {
                return new JobStatus().setState("FAILED").setErrorResult(new ErrorProto());
            }
        }
        partitioning = table.getTimePartitioning();
        clustering = table.getClustering();
        schema = table.getSchema();
        first = false;
        allRows.addAll(datasetService.getAllRows(source.getProjectId(), source.getDatasetId(), source.getTableId()));
    }
    datasetService.createTable(new Table().setTableReference(destination).setSchema(schema).setTimePartitioning(partitioning).setClustering(clustering).setEncryptionConfiguration(copy.getDestinationEncryptionConfiguration()));
    datasetService.insertAll(destination, allRows, null);
    return new JobStatus().setState("DONE");
}