paul-rogers commented on a change in pull request #1951: DRILL-7454: Convert Avro to EVF URL: https://github.com/apache/drill/pull/1951#discussion_r363133984
########## File path: exec/java-exec/src/main/java/org/apache/drill/exec/store/avro/AvroBatchReader.java ########## @@ -0,0 +1,368 @@ +/* + * 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.avro; + +import org.apache.avro.Schema; +import org.apache.avro.file.DataFileReader; +import org.apache.avro.generic.GenericArray; +import org.apache.avro.generic.GenericContainer; +import org.apache.avro.generic.GenericDatumReader; +import org.apache.avro.generic.GenericFixed; +import org.apache.avro.generic.GenericRecord; +import org.apache.avro.mapred.FsInput; +import org.apache.avro.util.Utf8; +import org.apache.drill.common.exceptions.UserException; +import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework; +import org.apache.drill.exec.physical.impl.scan.framework.ManagedReader; +import org.apache.drill.exec.physical.resultSet.ResultSetLoader; +import org.apache.drill.exec.physical.resultSet.RowSetLoader; +import org.apache.drill.exec.record.metadata.ColumnMetadata; +import org.apache.drill.exec.record.metadata.TupleMetadata; +import org.apache.drill.exec.util.ImpersonationUtil; +import org.apache.drill.exec.vector.accessor.ArrayWriter; +import org.apache.drill.exec.vector.accessor.DictWriter; +import org.apache.drill.exec.vector.accessor.ObjectWriter; +import org.apache.drill.exec.vector.accessor.ScalarWriter; +import org.apache.drill.exec.vector.accessor.TupleWriter; +import org.apache.drill.shaded.guava.com.google.common.base.Charsets; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.mapred.FileSplit; +import org.apache.hadoop.security.UserGroupInformation; +import org.joda.time.DateTimeConstants; +import org.joda.time.Period; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.math.BigDecimal; +import java.math.BigInteger; +import java.nio.ByteBuffer; +import java.nio.ByteOrder; +import java.nio.IntBuffer; +import java.security.PrivilegedExceptionAction; +import java.util.List; +import java.util.Map; + +public class AvroBatchReader implements ManagedReader<FileScanFramework.FileSchemaNegotiator> { + + private static final Logger logger = LoggerFactory.getLogger(AvroBatchReader.class); + + // currently config is unused but maybe used later + private final AvroReaderConfig config; + + private Path filePath; + private long endPosition; + private DataFileReader<GenericContainer> reader; + private ResultSetLoader loader; + // re-use container instance + private GenericContainer container = null; + + public AvroBatchReader(AvroReaderConfig config) { + this.config = config; + } + + @Override + public boolean open(FileScanFramework.FileSchemaNegotiator negotiator) { + FileSplit split = negotiator.split(); + filePath = split.getPath(); + + // Avro files are splittable, define reading start / end positions + long startPosition = split.getStart(); + endPosition = startPosition + split.getLength(); + + logger.debug("Processing Avro file: {}, start position: {}, end position: {}", + filePath, startPosition, endPosition); + + reader = prepareReader(split, negotiator.fileSystem(), + negotiator.userName(), negotiator.context().getFragmentContext().getQueryUserName()); + + logger.debug("Avro file schema: {}", reader.getSchema()); + TupleMetadata schema = AvroSchemaUtil.convert(reader.getSchema()); Review comment: Here we are converting the Avro schema to a Drill schema, which makes sense. If we scan a directory with multiple files, they should all have the same schema (or an evolved schema: `(A, B) --> (A,B,C) --> (B,C)`. In the future, it would be handy to infer the schema a plan time, then pass the resulting schema to each reader so we don't have to repeat identical work in each of perhaps hundreds of readers. ---------------------------------------------------------------- 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] With regards, Apache Git Services
