rdsr commented on a change in pull request #1255: URL: https://github.com/apache/iceberg/pull/1255#discussion_r465481812
########## File path: flink/src/main/java/org/apache/iceberg/flink/data/FlinkOrcReaders.java ########## @@ -0,0 +1,260 @@ +/* + * 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.iceberg.flink.data; + +import java.math.BigDecimal; +import java.time.Instant; +import java.time.LocalDateTime; +import java.time.ZoneOffset; +import java.util.List; +import java.util.Map; +import org.apache.flink.table.data.ArrayData; +import org.apache.flink.table.data.DecimalData; +import org.apache.flink.table.data.GenericArrayData; +import org.apache.flink.table.data.GenericMapData; +import org.apache.flink.table.data.GenericRowData; +import org.apache.flink.table.data.MapData; +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.data.StringData; +import org.apache.flink.table.data.TimestampData; +import org.apache.iceberg.orc.OrcValueReader; +import org.apache.iceberg.orc.OrcValueReaders; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Types; +import org.apache.orc.storage.ql.exec.vector.BytesColumnVector; +import org.apache.orc.storage.ql.exec.vector.ColumnVector; +import org.apache.orc.storage.ql.exec.vector.DecimalColumnVector; +import org.apache.orc.storage.ql.exec.vector.ListColumnVector; +import org.apache.orc.storage.ql.exec.vector.LongColumnVector; +import org.apache.orc.storage.ql.exec.vector.MapColumnVector; +import org.apache.orc.storage.ql.exec.vector.TimestampColumnVector; +import org.apache.orc.storage.serde2.io.HiveDecimalWritable; + +class FlinkOrcReaders { + private FlinkOrcReaders() { + } + + static OrcValueReader<StringData> strings() { + return StringReader.INSTANCE; + } + + static OrcValueReader<Integer> dates() { + return DateReader.INSTANCE; + } + + static OrcValueReader<DecimalData> decimals(int precision, int scale) { + if (precision <= 18) { + return new Decimal18Reader(precision, scale); + } else { + return new Decimal38Reader(precision, scale); + } + } + + static OrcValueReader<Integer> times() { + return TimeReader.INSTANCE; + } + + static OrcValueReader<TimestampData> timestamps() { + return TimestampReader.INSTANCE; + } + + static OrcValueReader<TimestampData> timestampTzs() { + return TimestampTzReader.INSTANCE; + } + + static <T> OrcValueReader<ArrayData> array(OrcValueReader<T> elementReader) { + return new ArrayReader<>(elementReader); + } + + public static <K, V> OrcValueReader<MapData> map(OrcValueReader<K> keyReader, OrcValueReader<V> valueReader) { + return new MapReader<>(keyReader, valueReader); + } + + public static OrcValueReader<RowData> struct(List<OrcValueReader<?>> readers, + Types.StructType struct, + Map<Integer, ?> idToConstant) { + return new StructReader(readers, struct, idToConstant); + } + + private static class StringReader implements OrcValueReader<StringData> { + private static final StringReader INSTANCE = new StringReader(); + + @Override + public StringData nonNullRead(ColumnVector vector, int row) { + BytesColumnVector bytesVector = (BytesColumnVector) vector; + return StringData.fromBytes(bytesVector.vector[row], bytesVector.start[row], bytesVector.length[row]); + } + } + + private static class DateReader implements OrcValueReader<Integer> { + private static final DateReader INSTANCE = new DateReader(); + + @Override + public Integer nonNullRead(ColumnVector vector, int row) { + return (int) ((LongColumnVector) vector).vector[row]; + } + } + + private static class Decimal18Reader implements OrcValueReader<DecimalData> { + private final int precision; Review comment: Seems like these are not really used. I wonder if that's a bug. As per the Iceberg spec, for decimals, scale cannot change but precision can widen. In that case, I presume we should be able to make use of the read iceberg schema's precision. We don't have to address it here but I guess a ticket is warranted where we should see if schema evolution for decimals in ORC works correctly ---------------------------------------------------------------- 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: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
