Blogpost: How to update row keys in Google Big Table (main function)

avro_transform.py

def run():
    pipeline_options = PipelineOptions()
    pipeline = beam.Pipeline(options=pipeline_options)
    options = pipeline_options.view_as(AvroTransformOptions)

    steps = (
            pipeline
            | 'ReadData' >> beam.io.ReadFromAvro(options.input, use_fastavro=True)
            | 'Transaform rowkey' >> beam.ParDo(CellTransformDoFn())
            | 'WriteData' >> beam.io.WriteToAvro(options.output, BIG_TABLE_SCHEMA, use_fastavro=True))

    result = pipeline.run()
    result.wait_until_finish()