import org.apache.parquet.hadoop.ParquetReader;
import org.apache.parquet.hadoop.ParquetWriter;
public class ParquetExample {
public static void main(String[] args) throws IOException {
ParquetReader<GenericRecord> reader = AvroParquetReader
.<GenericRecord>builder(new Path("input.parquet"))
.withConf(new Configuration())
.build();
GenericRecord record;
while ((record = reader.read()) != null) {
// ...
}
reader.close();
ParquetWriter<GenericRecord> writer = AvroParquetWriter
.<GenericRecord>writer(new Path("output.parquet"))
.withSchema(schema)
.withConf(new Configuration())
.build();
GenericRecord record = new GenericData.Record(schema);
record.put("column1", "data1");
record.put("column2", 123);
writer.write(record);
writer.close();
}
}
