paul-rogers commented on a change in pull request #1778: Drill-7233: Format Plugin for HDF5 URL: https://github.com/apache/drill/pull/1778#discussion_r342890687
########## File path: contrib/format-hdf5/src/main/java/org/apache/drill/exec/store/hdf5/writers/HDF5MapDataWriter.java ########## @@ -0,0 +1,136 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.drill.exec.store.hdf5.writers; + +import ch.systemsx.cisd.hdf5.HDF5CompoundMemberInformation; +import ch.systemsx.cisd.hdf5.IHDF5Reader; +import org.apache.drill.common.exceptions.UserException; +import org.apache.drill.exec.physical.resultSet.RowSetLoader; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.util.ArrayList; + +public class HDF5MapDataWriter extends HDF5DataWriter { + private static final Logger logger = LoggerFactory.getLogger(HDF5MapDataWriter.class); + + private final String UNSAFE_SPACE_SEPARATOR = " "; + + private final String SAFE_SPACE_SEPARATOR = "_"; + + private ArrayList<HDF5DataWriter> dataWriters; + + private ArrayList<String> fieldNames; + + + public HDF5MapDataWriter(IHDF5Reader reader, RowSetLoader columnWriter, String datapath) { + super(reader, columnWriter, datapath); + fieldNames = new ArrayList<>(); + + compoundData = reader.compounds().readArray(datapath, Object[].class); + dataWriters = new ArrayList<>(); + fieldNames = getFieldNames(); + try { + getDataWriters(); + } catch (Exception e) { + throw UserException.dataReadError().addContext("Error writing Compound Field: ").addContext(e.getMessage()).build(logger); + } + } + + public boolean write() { + if (!hasNext()) { + return false; + } else { + // Loop through the columns and write the columns + columnWriter.start(); + for (int i = 0; i < dataWriters.size(); i++) { + dataWriters.get(i).write(); + } + columnWriter.save(); + counter++; + return true; + } + } + + public boolean hasNext() { + return counter < dataWriters.get(0).getDatasize(); + } + + private ArrayList<String> getFieldNames() { + ArrayList<String> names = new ArrayList<>(); + + HDF5CompoundMemberInformation[] infos = reader.compounds().getDataSetInfo(datapath); + for (HDF5CompoundMemberInformation info : infos) { + names.add(info.getName().replace(UNSAFE_SPACE_SEPARATOR, SAFE_SPACE_SEPARATOR)); + } + return names; + } + + /** + * This function will populate the ArrayList of DataWriters. Since HDF5 Maps contain homogeneous columns, + * it is fine to get the first row, and iterate through the columns to get the data types and build the schema accordingly. + */ Review comment: Do we handle the case where there is no first row? ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
