pgaref commented on a change in pull request #998: URL: https://github.com/apache/hive/pull/998#discussion_r417303568
########## File path: ql/src/test/org/apache/hadoop/hive/ql/io/TestSkippingTextInputFormat.java ########## @@ -0,0 +1,205 @@ +/* + * 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.hadoop.hive.ql.io; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.ql.exec.Utilities; +import org.apache.hadoop.hive.ql.plan.MapredWork; +import org.apache.hadoop.hive.ql.plan.PartitionDesc; +import org.apache.hadoop.hive.ql.plan.TableDesc; +import org.apache.hadoop.io.LongWritable; +import org.apache.hadoop.io.Text; +import org.apache.hadoop.io.compress.CompressionCodec; +import org.apache.hadoop.io.compress.CompressionCodecFactory; +import org.apache.hadoop.mapred.FileInputFormat; +import org.apache.hadoop.mapred.FileSplit; +import org.apache.hadoop.mapred.InputSplit; +import org.apache.hadoop.mapred.JobConf; +import org.apache.hadoop.mapred.RecordReader; +import org.apache.hadoop.mapred.Reporter; +import org.junit.After; +import org.junit.Before; +import org.junit.Test; + +import java.io.File; +import java.io.IOException; +import java.io.OutputStreamWriter; +import java.util.ArrayList; +import java.util.LinkedHashMap; +import java.util.List; + +import static org.junit.Assert.assertTrue; + +/** + * Unittest for SkippingTextInputFormat with Skip Header/Footer. + */ +public class TestSkippingTextInputFormat { + + private Configuration conf; + private JobConf job; + private FileSystem fileSystem; + private Path testDir; + Reporter reporter; + + private Path dataDir; + + private CompressionCodecFactory compressionCodecs = null; + private CompressionCodec codec; + + @Before + public void setUp() throws IOException { + conf = new Configuration(); + job = new JobConf(conf); + + TableDesc tblDesc = Utilities.defaultTd; + PartitionDesc partDesc = new PartitionDesc(tblDesc, null); + LinkedHashMap<Path, PartitionDesc> pt = new LinkedHashMap<>(); + pt.put(new Path("/tmp/testfolder"), partDesc); + MapredWork mrwork = new MapredWork(); + mrwork.getMapWork().setPathToPartitionInfo(pt); + Utilities.setMapRedWork(job, mrwork,new Path("/tmp/" + System.getProperty("user.name"), "hive")); + + fileSystem = FileSystem.getLocal(conf); + testDir = new Path(System.getProperty("test.tmp.dir", System.getProperty( + "user.dir", new File(".").getAbsolutePath())) + + "/TestSkippingTextInputFormat"); + reporter = Reporter.NULL; + fileSystem.delete(testDir, true); + + dataDir = new Path(testDir, "datadir"); + fileSystem.mkdirs(dataDir); + } + + @After + public void tearDown() throws IOException { + fileSystem.delete(testDir, true); + } + + /** + * Test CSV input file with header/footer skip. + */ + @Test + public void testSkipFileSplits() throws Exception { + FileSystem fs = dataDir.getFileSystem(job); + FileInputFormat.setInputPaths(job, dataDir); + + // First Dir with 1 File + Path dir1_file1 = new Path(dataDir, "skipfile1.csv"); + writeTextFile(dir1_file1, Review comment: Just wanted to avoid creating even more files for this simple test. Moreover, I find it easier to have both data and test in one place where possible ---------------------------------------------------------------- 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]
