Polepoint opened a new pull request, #59:
URL: https://github.com/apache/parquet-testing/pull/59

   This is the data to reproduce https://github.com/apache/arrow/issues/43745.
   
   The parquet file is generated with this script
   
   ```
   import org.apache.hadoop.fs.Path;
   import org.apache.parquet.example.data.Group;
   import org.apache.parquet.example.data.GroupFactory;
   import org.apache.parquet.example.data.simple.SimpleGroupFactory;
   import org.apache.parquet.hadoop.ParquetFileWriter;
   import org.apache.parquet.hadoop.ParquetReader;
   import org.apache.parquet.hadoop.ParquetWriter;
   import org.apache.parquet.hadoop.example.ExampleParquetWriter;
   import org.apache.parquet.hadoop.example.GroupReadSupport;
   import org.apache.parquet.hadoop.metadata.CompressionCodecName;
   import org.apache.parquet.schema.MessageType;
   import org.apache.parquet.schema.MessageTypeParser;
   
   import java.io.IOException;
   import java.util.UUID;
   
   public class ParquetGenerator {
   
       public static void main(String... args) {
           MessageType schema = MessageTypeParser.parseMessageType(
                   "message example {\n" +
                           "  required binary a (STRING);\n" +
                           "}"
           );
   
           GroupFactory factory = new SimpleGroupFactory(schema);
           ParquetWriter<Group> writer;
           try {
               writer = ExampleParquetWriter.builder(new 
Path("parquet-testing/data/hadoop_lz4_compressed_block_split.parquet"))
                       .withWriteMode(ParquetFileWriter.Mode.CREATE)
                       .withCompressionCodec(CompressionCodecName.LZ4)
                       .config("io.compression.codec.lz4.buffersize", "65536")
                       .withType(schema)
                       .build();
               for (int i = 0; i < 65536; i++) {
                   Group group = factory.newGroup();
                   group.add("a", UUID.randomUUID().toString());
                   writer.write(group);
               }
               writer.close();
           } catch (IOException e) {
               throw new RuntimeException(e);
           }
       }
   }
   ```


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to