使用分頁功能透過 BigQuery API 讀取資料

using Google.Api.Gax;
using Google.Apis.Bigquery.v2.Data;
using Google.Cloud.BigQuery.V2;
using System;
using System.Linq;

public class BigQueryBrowseTable
{
    public void BrowseTable(
        string projectId = "your-project-id"
    )
    {
        BigQueryClient client = BigQueryClient.Create(projectId);
        TableReference tableReference = new TableReference()
        {
            TableId = "shakespeare",
            DatasetId = "samples",
            ProjectId = "bigquery-public-data"
        };
        // Load all rows from a table
        PagedEnumerable<TableDataList, BigQueryRow> result = client.ListRows(
            tableReference: tableReference,
            schema: null
        );
        // Print the first 10 rows
        foreach (BigQueryRow row in result.Take(10))
        {
            Console.WriteLine($"{row["corpus"]}: {row["word_count"]}");
        }
    }
}

import com.google.cloud.bigquery.BigQuery;
import com.google.cloud.bigquery.BigQuery.TableDataListOption;
import com.google.cloud.bigquery.BigQueryException;
import com.google.cloud.bigquery.BigQueryOptions;
import com.google.cloud.bigquery.TableId;
import com.google.cloud.bigquery.TableResult;

// Sample to directly browse a table with optional paging
public class BrowseTable {

  public static void runBrowseTable() {
    // TODO(developer): Replace these variables before running the sample.
    String table = "MY_TABLE_NAME";
    String dataset = "MY_DATASET_NAME";
    browseTable(dataset, table);
  }

  public static void browseTable(String dataset, String table) {
    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();

      // Identify the table itself
      TableId tableId = TableId.of(dataset, table);

      // Page over 100 records. If you don't need pagination, remove the pageSize parameter.
      TableResult result = bigquery.listTableData(tableId, TableDataListOption.pageSize(100));

      // Print the records
      result
          .iterateAll()
          .forEach(
              row -> {
                row.forEach(fieldValue -> System.out.print(fieldValue.toString() + ", "));
                System.out.println();
              });

      System.out.println("Query ran successfully");
    } catch (BigQueryException e) {
      System.out.println("Query failed to run \n" + e.toString());
    }
  }
}

import (
	"context"
	"fmt"
	"io"

	"cloud.google.com/go/bigquery"
	"google.golang.org/api/iterator"
)

// browseTable demonstrates reading data from a BigQuery table directly without the use of a query.
// For large tables, we also recommend the BigQuery Storage API.
func browseTable(w io.Writer, projectID, datasetID, tableID string) error {
	// projectID := "my-project-id"
	// datasetID := "mydataset"
	// tableID := "mytable"
	ctx := context.Background()
	client, err := bigquery.NewClient(ctx, projectID)
	if err != nil {
		return fmt.Errorf("bigquery.NewClient: %v", err)
	}
	defer client.Close()

	table := client.Dataset(datasetID).Table(tableID)
	it := table.Read(ctx)
	for {
		var row []bigquery.Value
		err := it.Next(&row)
		if err == iterator.Done {
			break
		}
		if err != nil {
			return err
		}
		fmt.Fprintln(w, row)
	}
	return nil
}

// Import the Google Cloud client library using default credentials
const {BigQuery} = require('@google-cloud/bigquery');
const bigquery = new BigQuery();

async function browseTable() {
  // Retrieve a table's rows using manual pagination.

  /**
   * TODO(developer): Uncomment the following lines before running the sample.
   */
  // const datasetId = 'my_dataset'; // Existing dataset
  // const tableId = 'my_table'; // Table to create

  const query = `SELECT name, SUM(number) as total_people
    FROM \`bigquery-public-data.usa_names.usa_1910_2013\`
    GROUP BY name 
    ORDER BY total_people 
    DESC LIMIT 100`;

  // Create table reference.
  const dataset = bigquery.dataset(datasetId);
  const destinationTable = dataset.table(tableId);

  // For all options, see https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#jobconfigurationquery
  const queryOptions = {
    query: query,
    destination: destinationTable,
  };

  // Run the query as a job
  const [job] = await bigquery.createQueryJob(queryOptions);

  // For all options, see https://cloud.google.com/bigquery/docs/reference/v2/jobs/getQueryResults
  const queryResultsOptions = {
    // Retrieve zero resulting rows.
    maxResults: 0,
  };

  // Wait for the job to finish.
  await job.getQueryResults(queryResultsOptions);

  function manualPaginationCallback(err, rows, nextQuery) {
    rows.forEach(row => {
      console.log(`name: ${row.name}, ${row.total_people} total people`);
    });

    if (nextQuery) {
      // More results exist.
      destinationTable.getRows(nextQuery, manualPaginationCallback);
    }
  }

  // For all options, see https://cloud.google.com/bigquery/docs/reference/v2/tabledata/list
  const getRowsOptions = {
    autoPaginate: false,
    maxResults: 20,
  };

  // Retrieve all rows.
  destinationTable.getRows(getRowsOptions, manualPaginationCallback);
}
browseTable();

use Google\Cloud\BigQuery\BigQueryClient;

/** Uncomment and populate these variables in your code */
// $projectId = 'The Google project ID';
// $datasetId = 'The BigQuery dataset ID';
// $tableId   = 'The BigQuery table ID';
// $maxResults = 10;

$maxResults = 10;
$startIndex = 0;

$options = [
    'maxResults' => $maxResults,
    'startIndex' => $startIndex
];
$bigQuery = new BigQueryClient([
    'projectId' => $projectId,
]);
$dataset = $bigQuery->dataset($datasetId);
$table = $dataset->table($tableId);
$numRows = 0;
foreach ($table->rows($options) as $row) {
    print('---');
    foreach ($row as $column => $value) {
        printf('%s: %s' . PHP_EOL, $column, $value);
    }
    $numRows++;
}

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to browse data rows.
# table_id = "your-project.your_dataset.your_table_name"

# Download all rows from a table.
rows_iter = client.list_rows(table_id)  # Make an API request.

# Iterate over rows to make the API requests to fetch row data.
rows = list(rows_iter)
print("Downloaded {} rows from table {}".format(len(rows), table_id))

# Download at most 10 rows.
rows_iter = client.list_rows(table_id, max_results=10)
rows = list(rows_iter)
print("Downloaded {} rows from table {}".format(len(rows), table_id))

# Specify selected fields to limit the results to certain columns.
table = client.get_table(table_id)  # Make an API request.
fields = table.schema[:2]  # First two columns.
rows_iter = client.list_rows(table_id, selected_fields=fields, max_results=10)
rows = list(rows_iter)
print("Selected {} columns from table {}.".format(len(rows_iter.schema), table_id))
print("Downloaded {} rows from table {}".format(len(rows), table_id))

# Print row data in tabular format.
rows = client.list_rows(table, max_results=10)
format_string = "{!s:<16} " * len(rows.schema)
field_names = [field.name for field in rows.schema]
print(format_string.format(*field_names))  # Prints column headers.
for row in rows:
    print(format_string.format(*row))  # Prints row data.

require "google/cloud/bigquery"

def browse_table
  bigquery = Google::Cloud::Bigquery.new project_id: "bigquery-public-data"
  dataset  = bigquery.dataset "samples"
  table    = dataset.table "shakespeare"

  # Load all rows from a table
  rows = table.data

  # Load the first 10 rows
  rows = table.data max: 10

  # Print row data
  rows.each { |row| puts row }
end