org.apache.flink.api.common.io.FileInputFormat.FileBaseStatistics Java Examples

@Test
public void testGetStatistics() throws IOException {
	final String myString = "my mocked line 1\nmy mocked line 2\n";
	final long size = myString.length();
	final Path filePath = createTempFilePath(myString);

	final String myString2 = "my mocked line 1\nmy mocked line 2\nanother mocked line3\n";
	final long size2 = myString2.length();
	final Path filePath2 = createTempFilePath(myString2);

	final long totalSize = size + size2;

	DelimitedInputFormat<String> format = new MyTextInputFormat();
	format.setFilePaths(filePath.toUri().toString(), filePath2.toUri().toString());

	FileInputFormat.FileBaseStatistics stats = format.getStatistics(null);
	assertNotNull(stats);
	assertEquals("The file size from the statistics is wrong.", totalSize, stats.getTotalInputSize());
}
 

@Test
public void testGetStatistics() throws IOException {
	final String myString = "my mocked line 1\nmy mocked line 2\n";
	final long size = myString.length();
	final Path filePath = createTempFilePath(myString);

	final String myString2 = "my mocked line 1\nmy mocked line 2\nanother mocked line3\n";
	final long size2 = myString2.length();
	final Path filePath2 = createTempFilePath(myString2);

	final long totalSize = size + size2;

	DelimitedInputFormat<String> format = new MyTextInputFormat();
	format.setFilePaths(filePath.toUri().toString(), filePath2.toUri().toString());

	FileInputFormat.FileBaseStatistics stats = format.getStatistics(null);
	assertNotNull(stats);
	assertEquals("The file size from the statistics is wrong.", totalSize, stats.getTotalInputSize());
}
 

@Test
public void testGetStatistics() throws IOException {
	final String myString = "my mocked line 1\nmy mocked line 2\n";
	final long size = myString.length();
	final Path filePath = createTempFilePath(myString);

	final String myString2 = "my mocked line 1\nmy mocked line 2\nanother mocked line3\n";
	final long size2 = myString2.length();
	final Path filePath2 = createTempFilePath(myString2);

	final long totalSize = size + size2;

	DelimitedInputFormat<String> format = new MyTextInputFormat();
	format.setFilePaths(filePath.toUri().toString(), filePath2.toUri().toString());

	FileInputFormat.FileBaseStatistics stats = format.getStatistics(null);
	assertNotNull(stats);
	assertEquals("The file size from the statistics is wrong.", totalSize, stats.getTotalInputSize());
}
 

@Override
public BaseStatistics getStatistics(BaseStatistics cachedStats) throws IOException {
	// only gather base statistics for FileInputFormats
	if (!(mapreduceInputFormat instanceof FileInputFormat)) {
		return null;
	}

	JobContext jobContext = new JobContextImpl(configuration, null);

	final FileBaseStatistics cachedFileStats = (cachedStats instanceof FileBaseStatistics) ?
			(FileBaseStatistics) cachedStats : null;

	try {
		final org.apache.hadoop.fs.Path[] paths = FileInputFormat.getInputPaths(jobContext);
		return getFileStats(cachedFileStats, paths, new ArrayList<FileStatus>(1));
	} catch (IOException ioex) {
		if (LOG.isWarnEnabled()) {
			LOG.warn("Could not determine statistics due to an io error: "
					+ ioex.getMessage());
		}
	} catch (Throwable t) {
		if (LOG.isErrorEnabled()) {
			LOG.error("Unexpected problem while getting the file statistics: "
					+ t.getMessage(), t);
		}
	}

	// no statistics available
	return null;
}
 

@Test
public void testGetStatisticsSingleFileWithCachedVersion() throws IOException {
	final String myString = "my mocked line 1\nmy mocked line 2\n";
	final Path tempFile = createTempFilePath(myString);
	final long size = myString.length();
	final long fakeSize = 10065;

	DelimitedInputFormat<String> format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());

	FileBaseStatistics stats = format.getStatistics(null);
	assertNotNull(stats);
	assertEquals("The file size from the statistics is wrong.", size, stats.getTotalInputSize());
	
	format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());
	
	FileBaseStatistics newStats = format.getStatistics(stats);
	assertEquals("Statistics object was changed.", newStats, stats);
	
	// insert fake stats with the correct modification time. the call should return the fake stats
	format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());
	
	FileBaseStatistics fakeStats = new FileBaseStatistics(stats.getLastModificationTime(), fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics latest = format.getStatistics(fakeStats);
	assertEquals("The file size from the statistics is wrong.", fakeSize, latest.getTotalInputSize());
	
	// insert fake stats with the expired modification time. the call should return new accurate stats
	format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());
	
	FileBaseStatistics outDatedFakeStats = new FileBaseStatistics(stats.getLastModificationTime() - 1, fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics reGathered = format.getStatistics(outDatedFakeStats);
	assertEquals("The file size from the statistics is wrong.", size, reGathered.getTotalInputSize());
}
 

@Test
public void testGetStatisticsFileDoesNotExist() throws IOException {
	DelimitedInputFormat<String> format = new MyTextInputFormat();
	format.setFilePaths("file:///path/does/not/really/exist", "file:///another/path/that/does/not/exist");

	FileBaseStatistics stats = format.getStatistics(null);
	assertNull("The file statistics should be null.", stats);
}
 

@Override
public BaseStatistics getStatistics(BaseStatistics cachedStats) throws IOException {
	// only gather base statistics for FileInputFormats
	if (!(mapreduceInputFormat instanceof FileInputFormat)) {
		return null;
	}

	JobContext jobContext = new JobContextImpl(configuration, null);

	final FileBaseStatistics cachedFileStats = (cachedStats instanceof FileBaseStatistics) ?
			(FileBaseStatistics) cachedStats : null;

	try {
		final org.apache.hadoop.fs.Path[] paths = FileInputFormat.getInputPaths(jobContext);
		return getFileStats(cachedFileStats, paths, new ArrayList<FileStatus>(1));
	} catch (IOException ioex) {
		if (LOG.isWarnEnabled()) {
			LOG.warn("Could not determine statistics due to an io error: "
					+ ioex.getMessage());
		}
	} catch (Throwable t) {
		if (LOG.isErrorEnabled()) {
			LOG.error("Unexpected problem while getting the file statistics: "
					+ t.getMessage(), t);
		}
	}

	// no statistics available
	return null;
}
 

@Override
public BaseStatistics getStatistics(BaseStatistics cachedStats) throws IOException {
	// only gather base statistics for FileInputFormats
	if (!(mapredInputFormat instanceof FileInputFormat)) {
		return null;
	}

	final FileBaseStatistics cachedFileStats = (cachedStats instanceof FileBaseStatistics) ?
			(FileBaseStatistics) cachedStats : null;

	try {
		final org.apache.hadoop.fs.Path[] paths = FileInputFormat.getInputPaths(this.jobConf);

		return getFileStats(cachedFileStats, paths, new ArrayList<FileStatus>(1));
	} catch (IOException ioex) {
		if (LOG.isWarnEnabled()) {
			LOG.warn("Could not determine statistics due to an io error: "
					+ ioex.getMessage());
		}
	} catch (Throwable t) {
		if (LOG.isErrorEnabled()) {
			LOG.error("Unexpected problem while getting the file statistics: "
					+ t.getMessage(), t);
		}
	}

	// no statistics available
	return null;
}
 

@Override
public BaseStatistics getStatistics(BaseStatistics cachedStats) throws IOException {
	// only gather base statistics for FileInputFormats
	if (!(mapredInputFormat instanceof FileInputFormat)) {
		return null;
	}

	final FileBaseStatistics cachedFileStats = (cachedStats != null && cachedStats instanceof FileBaseStatistics) ?
			(FileBaseStatistics) cachedStats : null;

	try {
		final org.apache.hadoop.fs.Path[] paths = FileInputFormat.getInputPaths(this.jobConf);

		return getFileStats(cachedFileStats, paths, new ArrayList<FileStatus>(1));
	} catch (IOException ioex) {
		if (LOG.isWarnEnabled()) {
			LOG.warn("Could not determine statistics due to an io error: "
					+ ioex.getMessage());
		}
	} catch (Throwable t) {
		if (LOG.isErrorEnabled()) {
			LOG.error("Unexpected problem while getting the file statistics: "
					+ t.getMessage(), t);
		}
	}

	// no statistics available
	return null;
}
 

@Test
public void testGetStatisticsSingleFileWithCachedVersion() throws IOException {
	final String myString = "my mocked line 1\nmy mocked line 2\n";
	final Path tempFile = createTempFilePath(myString);
	final long size = myString.length();
	final long fakeSize = 10065;

	DelimitedInputFormat<String> format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());

	FileBaseStatistics stats = format.getStatistics(null);
	assertNotNull(stats);
	assertEquals("The file size from the statistics is wrong.", size, stats.getTotalInputSize());
	
	format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());
	
	FileBaseStatistics newStats = format.getStatistics(stats);
	assertEquals("Statistics object was changed.", newStats, stats);
	
	// insert fake stats with the correct modification time. the call should return the fake stats
	format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());
	
	FileBaseStatistics fakeStats = new FileBaseStatistics(stats.getLastModificationTime(), fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics latest = format.getStatistics(fakeStats);
	assertEquals("The file size from the statistics is wrong.", fakeSize, latest.getTotalInputSize());
	
	// insert fake stats with the expired modification time. the call should return new accurate stats
	format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());
	
	FileBaseStatistics outDatedFakeStats = new FileBaseStatistics(stats.getLastModificationTime() - 1, fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics reGathered = format.getStatistics(outDatedFakeStats);
	assertEquals("The file size from the statistics is wrong.", size, reGathered.getTotalInputSize());
}
 

@Test
public void testGetStatisticsFileDoesNotExist() throws IOException {
	DelimitedInputFormat<String> format = new MyTextInputFormat();
	format.setFilePaths("file:///path/does/not/really/exist", "file:///another/path/that/does/not/exist");

	FileBaseStatistics stats = format.getStatistics(null);
	assertNull("The file statistics should be null.", stats);
}
 

@Override
public BaseStatistics getStatistics(BaseStatistics cachedStats) throws IOException {
	// only gather base statistics for FileInputFormats
	if (!(mapreduceInputFormat instanceof FileInputFormat)) {
		return null;
	}

	JobContext jobContext = new JobContextImpl(configuration, null);

	final FileBaseStatistics cachedFileStats = (cachedStats instanceof FileBaseStatistics) ?
			(FileBaseStatistics) cachedStats : null;

	try {
		final org.apache.hadoop.fs.Path[] paths = FileInputFormat.getInputPaths(jobContext);
		return getFileStats(cachedFileStats, paths, new ArrayList<FileStatus>(1));
	} catch (IOException ioex) {
		if (LOG.isWarnEnabled()) {
			LOG.warn("Could not determine statistics due to an io error: "
					+ ioex.getMessage());
		}
	} catch (Throwable t) {
		if (LOG.isErrorEnabled()) {
			LOG.error("Unexpected problem while getting the file statistics: "
					+ t.getMessage(), t);
		}
	}

	// no statistics available
	return null;
}
 

@Override
public BaseStatistics getStatistics(BaseStatistics cachedStats) throws IOException {
	// only gather base statistics for FileInputFormats
	if (!(mapredInputFormat instanceof FileInputFormat)) {
		return null;
	}

	final FileBaseStatistics cachedFileStats = (cachedStats instanceof FileBaseStatistics) ?
			(FileBaseStatistics) cachedStats : null;

	try {
		final org.apache.hadoop.fs.Path[] paths = FileInputFormat.getInputPaths(this.jobConf);

		return getFileStats(cachedFileStats, paths, new ArrayList<FileStatus>(1));
	} catch (IOException ioex) {
		if (LOG.isWarnEnabled()) {
			LOG.warn("Could not determine statistics due to an io error: "
					+ ioex.getMessage());
		}
	} catch (Throwable t) {
		if (LOG.isErrorEnabled()) {
			LOG.error("Unexpected problem while getting the file statistics: "
					+ t.getMessage(), t);
		}
	}

	// no statistics available
	return null;
}
 

@Override
public BaseStatistics getStatistics(BaseStatistics cachedStats) throws IOException {
	// only gather base statistics for FileInputFormats
	if (!(mapredInputFormat instanceof FileInputFormat)) {
		return null;
	}

	final FileBaseStatistics cachedFileStats = (cachedStats instanceof FileBaseStatistics) ?
			(FileBaseStatistics) cachedStats : null;

	try {
		final org.apache.hadoop.fs.Path[] paths = FileInputFormat.getInputPaths(this.jobConf);

		return getFileStats(cachedFileStats, paths, new ArrayList<FileStatus>(1));
	} catch (IOException ioex) {
		if (LOG.isWarnEnabled()) {
			LOG.warn("Could not determine statistics due to an io error: "
					+ ioex.getMessage());
		}
	} catch (Throwable t) {
		if (LOG.isErrorEnabled()) {
			LOG.error("Unexpected problem while getting the file statistics: "
					+ t.getMessage(), t);
		}
	}

	// no statistics available
	return null;
}
 

@Test
public void testGetStatisticsSingleFileWithCachedVersion() throws IOException {
	final String myString = "my mocked line 1\nmy mocked line 2\n";
	final Path tempFile = createTempFilePath(myString);
	final long size = myString.length();
	final long fakeSize = 10065;

	DelimitedInputFormat<String> format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());

	FileBaseStatistics stats = format.getStatistics(null);
	assertNotNull(stats);
	assertEquals("The file size from the statistics is wrong.", size, stats.getTotalInputSize());
	
	format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());
	
	FileBaseStatistics newStats = format.getStatistics(stats);
	assertEquals("Statistics object was changed.", newStats, stats);
	
	// insert fake stats with the correct modification time. the call should return the fake stats
	format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());
	
	FileBaseStatistics fakeStats = new FileBaseStatistics(stats.getLastModificationTime(), fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics latest = format.getStatistics(fakeStats);
	assertEquals("The file size from the statistics is wrong.", fakeSize, latest.getTotalInputSize());
	
	// insert fake stats with the expired modification time. the call should return new accurate stats
	format = new MyTextInputFormat();
	format.setFilePath(tempFile);
	format.configure(new Configuration());
	
	FileBaseStatistics outDatedFakeStats = new FileBaseStatistics(stats.getLastModificationTime() - 1, fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics reGathered = format.getStatistics(outDatedFakeStats);
	assertEquals("The file size from the statistics is wrong.", size, reGathered.getTotalInputSize());
}
 

@Test
public void testGetStatisticsFileDoesNotExist() throws IOException {
	DelimitedInputFormat<String> format = new MyTextInputFormat();
	format.setFilePaths("file:///path/does/not/really/exist", "file:///another/path/that/does/not/exist");

	FileBaseStatistics stats = format.getStatistics(null);
	assertNull("The file statistics should be null.", stats);
}
 

public void setSourceStatistics(GenericDataSourceBase<?, ?> source, FileBaseStatistics stats) {
	final String key = CACHE_KEY + this.statCounter++;
	this.dataStats.cacheBaseStatistics(stats, key);
	source.setStatisticsKey(key);
}
 

public void setSourceStatistics(GenericDataSourceBase<?, ?> source, long size, float recordWidth) {
	setSourceStatistics(source, new FileBaseStatistics(Long.MAX_VALUE, size, recordWidth));
}
 

@Test
public void testGetStatisticsOneFileWithCachedVersion() {
	try {
		final long SIZE = 50873;
		final long FAKE_SIZE = 10065;
		
		String tempFile = TestFileUtils.createTempFile(SIZE);
		
		DummyFileInputFormat format = new DummyFileInputFormat();
		format.setFilePath(tempFile);
		format.configure(new Configuration());
		
		
		FileBaseStatistics stats = format.getStatistics(null);
		Assert.assertEquals("The file size from the statistics is wrong.", SIZE, stats.getTotalInputSize());
		
		format = new DummyFileInputFormat();
		format.setFilePath(tempFile);
		format.configure(new Configuration());
		
		FileBaseStatistics newStats = format.getStatistics(stats);
		Assert.assertTrue("Statistics object was changed", newStats == stats);

		// insert fake stats with the correct modification time. the call should return the fake stats
		format = new DummyFileInputFormat();
		format.setFilePath(tempFile);
		format.configure(new Configuration());
		
		FileBaseStatistics fakeStats = new FileBaseStatistics(stats.getLastModificationTime(), FAKE_SIZE, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
		BaseStatistics latest = format.getStatistics(fakeStats);
		Assert.assertEquals("The file size from the statistics is wrong.", FAKE_SIZE, latest.getTotalInputSize());
		
		// insert fake stats with the expired modification time. the call should return new accurate stats
		format = new DummyFileInputFormat();
		format.setFilePath(tempFile);
		format.configure(new Configuration());
		
		FileBaseStatistics outDatedFakeStats = new FileBaseStatistics(stats.getLastModificationTime() - 1, FAKE_SIZE, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
		BaseStatistics reGathered = format.getStatistics(outDatedFakeStats);
		Assert.assertEquals("The file size from the statistics is wrong.", SIZE, reGathered.getTotalInputSize());
		
	} catch (Exception ex) {
		ex.printStackTrace();
		Assert.fail(ex.getMessage());
	}
}
 

@Test
public void testGetStatisticsMultipleFilesWithCachedVersion() {
	try {
		FileSystem fs = FileSystem.getLocalFileSystem();

		final long SIZE1 = 2077;
		final long SIZE2 = 31909;
		final long SIZE3 = 10;
		final long TOTAL = SIZE1 + SIZE2 + SIZE3;
		final long FAKE_SIZE = 10065;
		
		File tempDirFile = temporaryFolder.newFolder();
		String tempDir = tempDirFile.getAbsolutePath();
		String f1 = TestFileUtils.createTempFileInDirectory(tempDir, SIZE1);
		long modTime1 = fs.getFileStatus(new Path(f1)).getModificationTime();
		String f2 = TestFileUtils.createTempFileInDirectory(tempDir, SIZE2);
		long modTime2 = fs.getFileStatus(new Path(f2)).getModificationTime();
		String f3 = TestFileUtils.createTempFileInDirectory(tempDir, SIZE3);
		long modTime3 = fs.getFileStatus(new Path(f3)).getModificationTime();
		
		DummyFileInputFormat format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics stats = format.getStatistics(null);
		Assert.assertEquals("The file size from the statistics is wrong.", TOTAL, stats.getTotalInputSize());
		
		format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics newStats = format.getStatistics(stats);
		Assert.assertTrue("Statistics object was changed", newStats == stats);

		// insert fake stats with the correct modification time. the call should return the fake stats
		format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics fakeStats = new FileBaseStatistics(stats.getLastModificationTime(), FAKE_SIZE, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
		BaseStatistics latest = format.getStatistics(fakeStats);
		Assert.assertEquals("The file size from the statistics is wrong.", FAKE_SIZE, latest.getTotalInputSize());
		
		// insert fake stats with the correct modification time. the call should return the fake stats
		format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics outDatedFakeStats = new FileBaseStatistics(Math.min(Math.min(modTime1, modTime2), modTime3) - 1, FAKE_SIZE, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
		BaseStatistics reGathered = format.getStatistics(outDatedFakeStats);
		Assert.assertEquals("The file size from the statistics is wrong.", TOTAL, reGathered.getTotalInputSize());
		
	} catch (Exception ex) {
		ex.printStackTrace();
		Assert.fail(ex.getMessage());
	}
}
 

@Test
public void testGetStatisticsMultipleOneFileWithCachedVersion() throws IOException {
	FileSystem fs = FileSystem.getLocalFileSystem();

	final long size1 = 50873;
	final long fakeSize = 10065;
	String tempFile1 = TestFileUtils.createTempFile(size1);
	final long lastModTime1 = fs.getFileStatus(new Path(tempFile1)).getModificationTime();

	final long size2 = 52573;
	String tempFile2 = TestFileUtils.createTempFile(size2);
	final long lastModTime2 = fs.getFileStatus(new Path(tempFile2)).getModificationTime();

	final long sizeTotal = size1 + size2;
	
	MultiDummyFileInputFormat format = new MultiDummyFileInputFormat();
	format.setFilePaths(tempFile1, tempFile2);
	format.configure(new Configuration());
	
	FileBaseStatistics stats = format.getStatistics(null);
	Assert.assertEquals("The file size from the statistics is wrong.", sizeTotal, stats.getTotalInputSize());
	
	format = new MultiDummyFileInputFormat();
	format.setFilePath(tempFile1);
	format.configure(new Configuration());
	
	FileBaseStatistics newStats = format.getStatistics(stats);
	Assert.assertTrue("Statistics object was changed", newStats == stats);

	// insert fake stats with the correct modification time. the call should return the fake stats
	format = new MultiDummyFileInputFormat();
	format.setFilePath(tempFile1);
	format.configure(new Configuration());
	
	FileBaseStatistics fakeStats = new FileBaseStatistics(stats.getLastModificationTime(), fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics latest = format.getStatistics(fakeStats);
	Assert.assertEquals("The file size from the statistics is wrong.", fakeSize, latest.getTotalInputSize());
	
	// insert fake stats with the expired modification time. the call should return new accurate stats
	format = new MultiDummyFileInputFormat();
	format.setFilePaths(tempFile1, tempFile2);
	format.configure(new Configuration());
	
	FileBaseStatistics outDatedFakeStats = new FileBaseStatistics(Math.min(lastModTime1, lastModTime2) - 1, fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics reGathered = format.getStatistics(outDatedFakeStats);
	Assert.assertEquals("The file size from the statistics is wrong.", sizeTotal, reGathered.getTotalInputSize());
}
 

@Test
public void testGetStatisticsMultipleFilesWithCachedVersion() {
	try {
		FileSystem fs = FileSystem.getLocalFileSystem();

		final long SIZE1 = 2077;
		final long SIZE2 = 31909;
		final long SIZE3 = 10;
		final long TOTAL = SIZE1 + SIZE2 + SIZE3;
		final long FAKE_SIZE = 10065;
		
		File tempDirFile = temporaryFolder.newFolder();
		String tempDir = tempDirFile.getAbsolutePath();
		String f1 = TestFileUtils.createTempFileInDirectory(tempDir, SIZE1);
		long modTime1 = fs.getFileStatus(new Path(f1)).getModificationTime();
		String f2 = TestFileUtils.createTempFileInDirectory(tempDir, SIZE2);
		long modTime2 = fs.getFileStatus(new Path(f2)).getModificationTime();
		String f3 = TestFileUtils.createTempFileInDirectory(tempDir, SIZE3);
		long modTime3 = fs.getFileStatus(new Path(f3)).getModificationTime();
		
		DummyFileInputFormat format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics stats = format.getStatistics(null);
		Assert.assertEquals("The file size from the statistics is wrong.", TOTAL, stats.getTotalInputSize());
		
		format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics newStats = format.getStatistics(stats);
		Assert.assertTrue("Statistics object was changed", newStats == stats);

		// insert fake stats with the correct modification time. the call should return the fake stats
		format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics fakeStats = new FileBaseStatistics(stats.getLastModificationTime(), FAKE_SIZE, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
		BaseStatistics latest = format.getStatistics(fakeStats);
		Assert.assertEquals("The file size from the statistics is wrong.", FAKE_SIZE, latest.getTotalInputSize());
		
		// insert fake stats with the correct modification time. the call should return the fake stats
		format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics outDatedFakeStats = new FileBaseStatistics(Math.min(Math.min(modTime1, modTime2), modTime3) - 1, FAKE_SIZE, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
		BaseStatistics reGathered = format.getStatistics(outDatedFakeStats);
		Assert.assertEquals("The file size from the statistics is wrong.", TOTAL, reGathered.getTotalInputSize());
		
	} catch (Exception ex) {
		ex.printStackTrace();
		Assert.fail(ex.getMessage());
	}
}
 

@Test
public void testGetStatisticsOneFileWithCachedVersion() {
	try {
		final long SIZE = 50873;
		final long FAKE_SIZE = 10065;
		
		String tempFile = TestFileUtils.createTempFile(SIZE);
		
		DummyFileInputFormat format = new DummyFileInputFormat();
		format.setFilePath(tempFile);
		format.configure(new Configuration());
		
		
		FileBaseStatistics stats = format.getStatistics(null);
		Assert.assertEquals("The file size from the statistics is wrong.", SIZE, stats.getTotalInputSize());
		
		format = new DummyFileInputFormat();
		format.setFilePath(tempFile);
		format.configure(new Configuration());
		
		FileBaseStatistics newStats = format.getStatistics(stats);
		Assert.assertTrue("Statistics object was changed", newStats == stats);

		// insert fake stats with the correct modification time. the call should return the fake stats
		format = new DummyFileInputFormat();
		format.setFilePath(tempFile);
		format.configure(new Configuration());
		
		FileBaseStatistics fakeStats = new FileBaseStatistics(stats.getLastModificationTime(), FAKE_SIZE, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
		BaseStatistics latest = format.getStatistics(fakeStats);
		Assert.assertEquals("The file size from the statistics is wrong.", FAKE_SIZE, latest.getTotalInputSize());
		
		// insert fake stats with the expired modification time. the call should return new accurate stats
		format = new DummyFileInputFormat();
		format.setFilePath(tempFile);
		format.configure(new Configuration());
		
		FileBaseStatistics outDatedFakeStats = new FileBaseStatistics(stats.getLastModificationTime() - 1, FAKE_SIZE, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
		BaseStatistics reGathered = format.getStatistics(outDatedFakeStats);
		Assert.assertEquals("The file size from the statistics is wrong.", SIZE, reGathered.getTotalInputSize());
		
	} catch (Exception ex) {
		ex.printStackTrace();
		Assert.fail(ex.getMessage());
	}
}
 

@Test
public void testGetStatisticsMultipleOneFileWithCachedVersion() throws IOException {
	FileSystem fs = FileSystem.getLocalFileSystem();

	final long size1 = 50873;
	final long fakeSize = 10065;
	String tempFile1 = TestFileUtils.createTempFile(size1);
	final long lastModTime1 = fs.getFileStatus(new Path(tempFile1)).getModificationTime();

	final long size2 = 52573;
	String tempFile2 = TestFileUtils.createTempFile(size2);
	final long lastModTime2 = fs.getFileStatus(new Path(tempFile2)).getModificationTime();

	final long sizeTotal = size1 + size2;
	
	MultiDummyFileInputFormat format = new MultiDummyFileInputFormat();
	format.setFilePaths(tempFile1, tempFile2);
	format.configure(new Configuration());
	
	FileBaseStatistics stats = format.getStatistics(null);
	Assert.assertEquals("The file size from the statistics is wrong.", sizeTotal, stats.getTotalInputSize());
	
	format = new MultiDummyFileInputFormat();
	format.setFilePath(tempFile1);
	format.configure(new Configuration());
	
	FileBaseStatistics newStats = format.getStatistics(stats);
	Assert.assertTrue("Statistics object was changed", newStats == stats);

	// insert fake stats with the correct modification time. the call should return the fake stats
	format = new MultiDummyFileInputFormat();
	format.setFilePath(tempFile1);
	format.configure(new Configuration());
	
	FileBaseStatistics fakeStats = new FileBaseStatistics(stats.getLastModificationTime(), fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics latest = format.getStatistics(fakeStats);
	Assert.assertEquals("The file size from the statistics is wrong.", fakeSize, latest.getTotalInputSize());
	
	// insert fake stats with the expired modification time. the call should return new accurate stats
	format = new MultiDummyFileInputFormat();
	format.setFilePaths(tempFile1, tempFile2);
	format.configure(new Configuration());
	
	FileBaseStatistics outDatedFakeStats = new FileBaseStatistics(Math.min(lastModTime1, lastModTime2) - 1, fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics reGathered = format.getStatistics(outDatedFakeStats);
	Assert.assertEquals("The file size from the statistics is wrong.", sizeTotal, reGathered.getTotalInputSize());
}
 

public void setSourceStatistics(GenericDataSourceBase<?, ?> source, FileBaseStatistics stats) {
	final String key = CACHE_KEY + this.statCounter++;
	this.dataStats.cacheBaseStatistics(stats, key);
	source.setStatisticsKey(key);
}
 

public void setSourceStatistics(GenericDataSourceBase<?, ?> source, long size, float recordWidth) {
	setSourceStatistics(source, new FileBaseStatistics(Long.MAX_VALUE, size, recordWidth));
}
 

public void setSourceStatistics(GenericDataSourceBase<?, ?> source, long size, float recordWidth) {
	setSourceStatistics(source, new FileBaseStatistics(Long.MAX_VALUE, size, recordWidth));
}
 

public void setSourceStatistics(GenericDataSourceBase<?, ?> source, FileBaseStatistics stats) {
	final String key = CACHE_KEY + this.statCounter++;
	this.dataStats.cacheBaseStatistics(stats, key);
	source.setStatisticsKey(key);
}
 

@Test
public void testGetStatisticsMultipleOneFileWithCachedVersion() throws IOException {
	FileSystem fs = FileSystem.getLocalFileSystem();

	final long size1 = 50873;
	final long fakeSize = 10065;
	String tempFile1 = TestFileUtils.createTempFile(size1);
	final long lastModTime1 = fs.getFileStatus(new Path(tempFile1)).getModificationTime();

	final long size2 = 52573;
	String tempFile2 = TestFileUtils.createTempFile(size2);
	final long lastModTime2 = fs.getFileStatus(new Path(tempFile2)).getModificationTime();

	final long sizeTotal = size1 + size2;
	
	MultiDummyFileInputFormat format = new MultiDummyFileInputFormat();
	format.setFilePaths(tempFile1, tempFile2);
	format.configure(new Configuration());
	
	FileBaseStatistics stats = format.getStatistics(null);
	Assert.assertEquals("The file size from the statistics is wrong.", sizeTotal, stats.getTotalInputSize());
	
	format = new MultiDummyFileInputFormat();
	format.setFilePath(tempFile1);
	format.configure(new Configuration());
	
	FileBaseStatistics newStats = format.getStatistics(stats);
	Assert.assertTrue("Statistics object was changed", newStats == stats);

	// insert fake stats with the correct modification time. the call should return the fake stats
	format = new MultiDummyFileInputFormat();
	format.setFilePath(tempFile1);
	format.configure(new Configuration());
	
	FileBaseStatistics fakeStats = new FileBaseStatistics(stats.getLastModificationTime(), fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics latest = format.getStatistics(fakeStats);
	Assert.assertEquals("The file size from the statistics is wrong.", fakeSize, latest.getTotalInputSize());
	
	// insert fake stats with the expired modification time. the call should return new accurate stats
	format = new MultiDummyFileInputFormat();
	format.setFilePaths(tempFile1, tempFile2);
	format.configure(new Configuration());
	
	FileBaseStatistics outDatedFakeStats = new FileBaseStatistics(Math.min(lastModTime1, lastModTime2) - 1, fakeSize, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
	BaseStatistics reGathered = format.getStatistics(outDatedFakeStats);
	Assert.assertEquals("The file size from the statistics is wrong.", sizeTotal, reGathered.getTotalInputSize());
}
 

@Test
public void testGetStatisticsMultipleFilesWithCachedVersion() {
	try {
		FileSystem fs = FileSystem.getLocalFileSystem();

		final long SIZE1 = 2077;
		final long SIZE2 = 31909;
		final long SIZE3 = 10;
		final long TOTAL = SIZE1 + SIZE2 + SIZE3;
		final long FAKE_SIZE = 10065;
		
		File tempDirFile = temporaryFolder.newFolder();
		String tempDir = tempDirFile.getAbsolutePath();
		String f1 = TestFileUtils.createTempFileInDirectory(tempDir, SIZE1);
		long modTime1 = fs.getFileStatus(new Path(f1)).getModificationTime();
		String f2 = TestFileUtils.createTempFileInDirectory(tempDir, SIZE2);
		long modTime2 = fs.getFileStatus(new Path(f2)).getModificationTime();
		String f3 = TestFileUtils.createTempFileInDirectory(tempDir, SIZE3);
		long modTime3 = fs.getFileStatus(new Path(f3)).getModificationTime();
		
		DummyFileInputFormat format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics stats = format.getStatistics(null);
		Assert.assertEquals("The file size from the statistics is wrong.", TOTAL, stats.getTotalInputSize());
		
		format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics newStats = format.getStatistics(stats);
		Assert.assertTrue("Statistics object was changed", newStats == stats);

		// insert fake stats with the correct modification time. the call should return the fake stats
		format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics fakeStats = new FileBaseStatistics(stats.getLastModificationTime(), FAKE_SIZE, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
		BaseStatistics latest = format.getStatistics(fakeStats);
		Assert.assertEquals("The file size from the statistics is wrong.", FAKE_SIZE, latest.getTotalInputSize());
		
		// insert fake stats with the correct modification time. the call should return the fake stats
		format = new DummyFileInputFormat();
		format.setFilePath(tempDir);
		format.configure(new Configuration());
		
		FileBaseStatistics outDatedFakeStats = new FileBaseStatistics(Math.min(Math.min(modTime1, modTime2), modTime3) - 1, FAKE_SIZE, BaseStatistics.AVG_RECORD_BYTES_UNKNOWN);
		BaseStatistics reGathered = format.getStatistics(outDatedFakeStats);
		Assert.assertEquals("The file size from the statistics is wrong.", TOTAL, reGathered.getTotalInputSize());
		
	} catch (Exception ex) {
		ex.printStackTrace();
		Assert.fail(ex.getMessage());
	}
}