Google BigQuery Storage: Node.js Client

const {adapt, managedwriter} = require('@google-cloud/bigquery-storage');
const {WriterClient, JSONWriter} = managedwriter;

async function appendJSONRowsDefaultStream() {      
  const projectId = 'my_project';
  const datasetId = 'my_dataset';
  const tableId = 'my_table';

  const destinationTable = `projects/${projectId}/datasets/${datasetId}/tables/${tableId}`;
  const writeClient = new WriterClient({projectId});

  try {
    const writeStream = await writeClient.getWriteStream({
      streamId: `${destinationTable}/streams/_default`,
      view: 'FULL'
    });
    const protoDescriptor = adapt.convertStorageSchemaToProto2Descriptor(
      writeStream.tableSchema,
      'root'
    );

    const connection = await writeClient.createStreamConnection({
      streamId: managedwriter.DefaultStream,
      destinationTable,
    });
    const streamId = connection.getStreamId();

    const writer = new JSONWriter({
      streamId,
      connection,
      protoDescriptor,
    });

    let rows = [];
    const pendingWrites = [];

    // Row 1
    let row = {
      row_num: 1,
      customer_name: 'Octavia',
    };
    rows.push(row);

    // Row 2
    row = {
      row_num: 2,
      customer_name: 'Turing',
    };
    rows.push(row);

    // Send batch.
    let pw = writer.appendRows(rows);
    pendingWrites.push(pw);

    rows = [];

    // Row 3
    row = {
      row_num: 3,
      customer_name: 'Bell',
    };
    rows.push(row);

    // Send batch.
    pw = writer.appendRows(rows);
    pendingWrites.push(pw);

    const results = await Promise.all(
      pendingWrites.map(pw => pw.getResult())
    );
    console.log('Write results:', results);
  } catch (err) {
    console.log(err);
  } finally {
    writeClient.close();
  }
}

// The read stream contains blocks of Avro-encoded bytes. We use the
// 'avsc' library to decode these blocks. Install avsc with the following
// command: npm install avsc
const avro = require('avsc');

// See reference documentation at
// https://cloud.google.com/bigquery/docs/reference/storage
const {BigQueryReadClient} = require('@google-cloud/bigquery-storage');

const client = new BigQueryReadClient();

async function bigqueryStorageQuickstart() {
  // Get current project ID. The read session is created in this project.
  // This project can be different from that which contains the table.
  const myProjectId = await client.getProjectId();

  // This example reads baby name data from the public datasets.
  const projectId = 'bigquery-public-data';
  const datasetId = 'usa_names';
  const tableId = 'usa_1910_current';

  const tableReference = `projects/${projectId}/datasets/${datasetId}/tables/${tableId}`;

  const parent = `projects/${myProjectId}`;

  /* We limit the output columns to a subset of those allowed in the table,
   * and set a simple filter to only report names from the state of
   * Washington (WA).
   */
  const readOptions = {
    selectedFields: ['name', 'number', 'state'],
    rowRestriction: 'state = "WA"',
  };

  let tableModifiers = null;
  const snapshotSeconds = 0;

  // Set a snapshot time if it's been specified.
  if (snapshotSeconds > 0) {
    tableModifiers = {snapshotTime: {seconds: snapshotSeconds}};
  }

  // API request.
  const request = {
    parent,
    readSession: {
      table: tableReference,
      // This API can also deliver data serialized in Apache Arrow format.
      // This example leverages Apache Avro.
      dataFormat: 'AVRO',
      readOptions,
      tableModifiers,
    },
  };

  const [session] = await client.createReadSession(request);

  const schema = JSON.parse(session.avroSchema.schema);

  const avroType = avro.Type.forSchema(schema);

  /* The offset requested must be less than the last
   * row read from ReadRows. Requesting a larger offset is
   * undefined.
   */
  let offset = 0;

  const readRowsRequest = {
    // Required stream name and optional offset. Offset requested must be less than
    // the last row read from readRows(). Requesting a larger offset is undefined.
    readStream: session.streams[0].name,
    offset,
  };

  const names = new Set();
  const states = [];

  /* We'll use only a single stream for reading data from the table. Because
   * of dynamic sharding, this will yield all the rows in the table. However,
   * if you wanted to fan out multiple readers you could do so by having a
   * reader process each individual stream.
   */
  client
    .readRows(readRowsRequest)
    .on('error', console.error)
    .on('data', data => {
      offset = data.avroRows.serializedBinaryRows.offset;

      try {
        // Decode all rows in buffer
        let pos;
        do {
          const decodedData = avroType.decode(
            data.avroRows.serializedBinaryRows,
            pos
          );

          if (decodedData.value) {
            names.add(decodedData.value.name);

            if (!states.includes(decodedData.value.state)) {
              states.push(decodedData.value.state);
            }
          }

          pos = decodedData.offset;
        } while (pos > 0);
      } catch (error) {
        console.log(error);
      }
    })
    .on('end', () => {
      console.log(`Got ${names.size} unique names in states: ${states}`);
      console.log(`Last offset: ${offset}`);
    });
}