shimamoto commented on a change in pull request #1627: DRILL-7014: Format plugin for LTSV files URL: https://github.com/apache/drill/pull/1627#discussion_r253770219
########## File path: contrib/format-ltsv/src/main/java/org/apache/drill/exec/store/ltsv/LTSVRecordReader.java ########## @@ -0,0 +1,127 @@ +/* + * 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.ltsv; + +import io.netty.buffer.DrillBuf; +import org.apache.drill.common.exceptions.ExecutionSetupException; +import org.apache.drill.common.exceptions.UserException; +import org.apache.drill.common.expression.SchemaPath; +import org.apache.drill.exec.exception.OutOfMemoryException; +import org.apache.drill.exec.ops.FragmentContext; +import org.apache.drill.exec.ops.OperatorContext; +import org.apache.drill.exec.physical.impl.OutputMutator; +import org.apache.drill.exec.store.AbstractRecordReader; +import org.apache.drill.exec.store.dfs.DrillFileSystem; +import org.apache.drill.exec.vector.complex.impl.VectorContainerWriter; +import org.apache.drill.exec.vector.complex.writer.BaseWriter; +import org.apache.hadoop.fs.FSDataInputStream; +import org.apache.hadoop.fs.Path; + +import java.io.BufferedReader; +import java.io.IOException; +import java.io.InputStreamReader; +import java.text.ParseException; +import java.util.List; + +public class LTSVRecordReader extends AbstractRecordReader { + + private static final org.slf4j.Logger logger = org.slf4j.LoggerFactory.getLogger(LTSVRecordReader.class); + private static final int MAX_RECORDS_PER_BATCH = 8096; + + private String inputPath; + private BufferedReader reader; + private DrillBuf buffer; + private VectorContainerWriter writer; + private LTSVFormatPluginConfig config; + private int lineCount; + + public LTSVRecordReader(FragmentContext fragmentContext, String inputPath, DrillFileSystem fileSystem, + List<SchemaPath> columns, LTSVFormatPluginConfig config) throws OutOfMemoryException { + try { + FSDataInputStream fsStream = fileSystem.open(new Path(inputPath)); + this.inputPath = inputPath; + this.lineCount = 0; + this.reader = new BufferedReader(new InputStreamReader(fsStream.getWrappedStream(), "UTF-8")); + this.config = config; + this.buffer = fragmentContext.getManagedBuffer(); + setColumns(columns); + + } catch(IOException e){ + logger.debug("LTSV Plugin: " + e.getMessage()); + } + } + + public void setup(final OperatorContext context, final OutputMutator output) throws ExecutionSetupException { + this.writer = new VectorContainerWriter(output); + } + + public int next() { + this.writer.allocate(); + this.writer.reset(); + + int recordCount = 0; + + try { + BaseWriter.MapWriter map = this.writer.rootAsMap(); + String line = null; + + while(recordCount < MAX_RECORDS_PER_BATCH &&(line = this.reader.readLine()) != null){ + lineCount++; + + // Skip empty lines + if(line.trim().length() == 0){ + continue; + } + + this.writer.setPosition(recordCount); + map.start(); + + String[] fields = line.split("\t"); + for(String field: fields){ + int index = field.indexOf(":"); + if(index <= 0) { + throw new ParseException( + "Invalid LTSV format: " + inputPath + "\n" + lineCount + ":" + line, 0 Review comment: This code is enclosed in a try block. When an exception occurs, the exception is caught and wrapped in Drill one. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on 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
