@Test
public void testReadingDirectory() throws Exception {
Path index =
directoryTreeFactory.addIndex(directoryTreeFactory.getIndexerPaths().get(0), "Index1");
Path bucket = directoryTreeFactory.addBucket(index, "db_0_1_idx");
String[] header = {"header", "_raw"};
String file1Content =
"header,_raw\n"
+ "\"ImCESTvlhu\",\"LOjZxHYGZy\"\n"
+ "\"kqYkcFhbSB\",\"RRLjuHCHze\"\n"
+ "\"kmeEaOcKTx\",\"mvIPrMSOSS\"\n"
+ "\"lzzPLYFGFU\",\"sGHTPVsYlF\"\n"
+ "\"zpUxVlTaAq\",\"ysoUYuyZKO\"";
String file2Content =
"header,_raw\n"
+ "\"fkBkKfCkuT\",\"BRlSkqHmHe\"\n"
+ "\"dWDJViEuot\",\"LcdkTQBLmu\"\n"
+ "\"ovQoDFATdn\",\"YewByxPXqN\"\n"
+ "\"tKBxjsSZmV\",\"luuOivALWj\"\n"
+ "\"mssAbiUnub\",\"NeYnIlDMdW\"";
int[] offsets = new int[] {12, 38, 64, 90, 116};
Path file1 = HadoopFileTestUtils.createPath(bucket.toString(), "file1.csv");
Path file2 = HadoopFileTestUtils.createPath(bucket.toString(), "file2.csv");
HadoopFileTestUtils.createFileWithContent(fs, file1, file1Content);
HadoopFileTestUtils.createFileWithContent(fs, file2, file2Content);
Path outputPath = new Path(FileTestUtils.getRandomTestFilepath());
assertTrue(
runJob(
new Configuration(),
new String[] {directoryTreeFactory.getRoot().toString(), outputPath.toString()}));
String expectedContent =
"0\theader,_raw\n"
+ "12\tImCESTvlhu,LOjZxHYGZy\n"
+ "38\tkqYkcFhbSB,RRLjuHCHze\n"
+ "64\tkmeEaOcKTx,mvIPrMSOSS\n"
+ "90\tlzzPLYFGFU,sGHTPVsYlF\n"
+ "116\tzpUxVlTaAq,ysoUYuyZKO\n"
+ "153\tfkBkKfCkuT,BRlSkqHmHe\n"
+ "179\tdWDJViEuot,LcdkTQBLmu\n"
+ "205\tovQoDFATdn,YewByxPXqN\n"
+ "231\ttKBxjsSZmV,luuOivALWj\n"
+ "257\tmssAbiUnub,NeYnIlDMdW\n";
String actualResults = HadoopFileTestUtils.readMapReduceOutputFile(fs, outputPath);
assertEquals(expectedContent, actualResults);
}
private void runTestOnContent(String content, int[] offsets) throws Exception {
Path index =
directoryTreeFactory.addIndex(directoryTreeFactory.getIndexerPaths().get(0), "Index1");
Path bucket = directoryTreeFactory.addBucket(index, "db_0_1_idx");
Path inputPath =
HadoopFileTestUtils.createPath(bucket.toString(), FileTestUtils.getRandomFilename("csv"));
HadoopFileTestUtils.createFileWithContent(fs, inputPath, content);
Path outputPath = new Path(FileTestUtils.getRandomTestFilepath());
assertTrue(
runJob(
new Configuration(),
new String[] {directoryTreeFactory.getRoot().toString(), outputPath.toString()}));
String result = HadoopFileTestUtils.readMapReduceOutputFile(fs, outputPath);
String expected = getExpectedResult(content, offsets);
assertEquals(expected, result);
}
