Examples with TextInputFormat org.apache.flink.api.java.io.TextInputFormat used on opensource projects

Example 11 with TextInputFormat

use of org.apache.flink.api.java.io.TextInputFormat in project flink by apache.

the class StreamExecutionEnvironment method readTextFile.

/**
 * Reads the given file line-by-line and creates a data stream that contains a string with the
 * contents of each such line. The {@link java.nio.charset.Charset} with the given name will be
 * used to read the files.
 *
 * <p><b>NOTES ON CHECKPOINTING: </b> The source monitors the path, creates the {@link
 * org.apache.flink.core.fs.FileInputSplit FileInputSplits} to be processed, forwards them to
 * the downstream readers to read the actual data, and exits, without waiting for the readers to
 * finish reading. This implies that no more checkpoint barriers are going to be forwarded after
 * the source exits, thus having no checkpoints after that point.
 *
 * @param filePath The path of the file, as a URI (e.g., "file:///some/local/file" or
 *     "hdfs://host:port/file/path")
 * @param charsetName The name of the character set used to read the file
 * @return The data stream that represents the data read from the given file as text lines
 */
public DataStreamSource<String> readTextFile(String filePath, String charsetName) {
    Preconditions.checkArgument(!StringUtils.isNullOrWhitespaceOnly(filePath), "The file path must not be null or blank.");
    TextInputFormat format = new TextInputFormat(new Path(filePath));
    format.setFilesFilter(FilePathFilter.createDefaultFilter());
    TypeInformation<String> typeInfo = BasicTypeInfo.STRING_TYPE_INFO;
    format.setCharsetName(charsetName);
    return readFile(format, filePath, FileProcessingMode.PROCESS_ONCE, -1, typeInfo);
}

Example 12 with TextInputFormat

use of org.apache.flink.api.java.io.TextInputFormat in project flink by apache.

the class ContinuousFileProcessingCheckpointITCase method testProgram.

@Override
public void testProgram(StreamExecutionEnvironment env) {
    env.enableCheckpointing(10);
    // create and start the file creating thread.
    fc = new FileCreator();
    fc.start();
    // create the monitoring source along with the necessary readers.
    TextInputFormat format = new TextInputFormat(new org.apache.flink.core.fs.Path(localFsURI));
    format.setFilesFilter(FilePathFilter.createDefaultFilter());
    DataStream<String> inputStream = env.readFile(format, localFsURI, FileProcessingMode.PROCESS_CONTINUOUSLY, INTERVAL);
    TestingSinkFunction sink = new TestingSinkFunction();
    inputStream.flatMap(new FlatMapFunction<String, String>() {

        @Override
        public void flatMap(String value, Collector<String> out) throws Exception {
            out.collect(value);
        }
    }).addSink(sink).setParallelism(1);
}

Example 13 with TextInputFormat

use of org.apache.flink.api.java.io.TextInputFormat in project flink by apache.

the class ContinuousFileProcessingTest method testInvalidPathSpecification.

@Test
public void testInvalidPathSpecification() throws Exception {
    String invalidPath = "hdfs://" + hdfsCluster.getURI().getHost() + ":" + hdfsCluster.getNameNodePort() + "/invalid/";
    TextInputFormat format = new TextInputFormat(new Path(invalidPath));
    ContinuousFileMonitoringFunction<String> monitoringFunction = new ContinuousFileMonitoringFunction<>(format, FileProcessingMode.PROCESS_ONCE, 1, INTERVAL);
    try {
        monitoringFunction.run(new DummySourceContext() {

            @Override
            public void collect(TimestampedFileInputSplit element) {
                // we should never arrive here with an invalid path
                Assert.fail("Test passes with an invalid path.");
            }
        });
        // we should never arrive here with an invalid path
        Assert.fail("Test passed with an invalid path.");
    } catch (FileNotFoundException e) {
        Assert.assertEquals("The provided file path " + format.getFilePath() + " does not exist.", e.getMessage());
    }
}

Example 14 with TextInputFormat

use of org.apache.flink.api.java.io.TextInputFormat in project flink by apache.

the class ContinuousFileProcessingTest method testFileReadingOperatorWithIngestionTime.

@Test
public void testFileReadingOperatorWithIngestionTime() throws Exception {
    String testBasePath = hdfsURI + "/" + UUID.randomUUID() + "/";
    Set<org.apache.hadoop.fs.Path> filesCreated = new HashSet<>();
    Map<Integer, String> expectedFileContents = new HashMap<>();
    Map<String, Long> modTimes = new HashMap<>();
    for (int i = 0; i < NO_OF_FILES; i++) {
        Tuple2<org.apache.hadoop.fs.Path, String> file = createFileAndFillWithData(testBasePath, "file", i, "This is test line.");
        filesCreated.add(file.f0);
        modTimes.put(file.f0.getName(), hdfs.getFileStatus(file.f0).getModificationTime());
        expectedFileContents.put(i, file.f1);
    }
    TextInputFormat format = new TextInputFormat(new Path(testBasePath));
    final long watermarkInterval = 10;
    final OneInputStreamOperatorTestHarness<TimestampedFileInputSplit, String> tester = createHarness(format);
    SteppingMailboxProcessor localMailbox = createLocalMailbox(tester);
    tester.getExecutionConfig().setAutoWatermarkInterval(watermarkInterval);
    tester.setTimeCharacteristic(TimeCharacteristic.IngestionTime);
    tester.open();
    Assert.assertEquals(TimeCharacteristic.IngestionTime, tester.getTimeCharacteristic());
    tester.setProcessingTime(201);
    // test that watermarks are correctly emitted
    ConcurrentLinkedQueue<Object> output = tester.getOutput();
    while (output.isEmpty()) {
        localMailbox.runMailboxStep();
    }
    Assert.assertTrue(output.toString(), output.peek() instanceof Watermark);
    Assert.assertEquals(200, ((Watermark) output.poll()).getTimestamp());
    tester.setProcessingTime(301);
    Assert.assertTrue(output.peek() instanceof Watermark);
    Assert.assertEquals(300, ((Watermark) output.poll()).getTimestamp());
    tester.setProcessingTime(401);
    Assert.assertTrue(output.peek() instanceof Watermark);
    Assert.assertEquals(400, ((Watermark) output.poll()).getTimestamp());
    tester.setProcessingTime(501);
    Assert.assertTrue(output.peek() instanceof Watermark);
    Assert.assertEquals(500, ((Watermark) output.poll()).getTimestamp());
    Assert.assertTrue(output.isEmpty());
    // create the necessary splits for the test
    FileInputSplit[] splits = format.createInputSplits(tester.getExecutionConfig().getParallelism());
    // and feed them to the operator
    Map<Integer, List<String>> actualFileContents = new HashMap<>();
    long lastSeenWatermark = Long.MIN_VALUE;
    // counter for the lines read from the splits
    int lineCounter = 0;
    int watermarkCounter = 0;
    for (FileInputSplit split : splits) {
        // set the next "current processing time".
        long nextTimestamp = tester.getProcessingTime() + watermarkInterval;
        tester.setProcessingTime(nextTimestamp);
        // send the next split to be read and wait until it is fully read, the +1 is for the
        // watermark.
        RunnableWithException runnableWithException = () -> tester.processElement(new StreamRecord<>(new TimestampedFileInputSplit(modTimes.get(split.getPath().getName()), split.getSplitNumber(), split.getPath(), split.getStart(), split.getLength(), split.getHostnames())));
        runnableWithException.run();
        // BUT THIS IS JUST FOR THIS TEST
        while (tester.getOutput().isEmpty() || tester.getOutput().size() != (LINES_PER_FILE + 1)) {
            localMailbox.runMailboxStep();
        }
        // verify that the results are the expected
        for (Object line : tester.getOutput()) {
            if (line instanceof StreamRecord) {
                @SuppressWarnings("unchecked") StreamRecord<String> element = (StreamRecord<String>) line;
                lineCounter++;
                Assert.assertEquals(nextTimestamp, element.getTimestamp());
                int fileIdx = Character.getNumericValue(element.getValue().charAt(0));
                List<String> content = actualFileContents.get(fileIdx);
                if (content == null) {
                    content = new ArrayList<>();
                    actualFileContents.put(fileIdx, content);
                }
                content.add(element.getValue() + "\n");
            } else if (line instanceof Watermark) {
                long watermark = ((Watermark) line).getTimestamp();
                Assert.assertEquals(nextTimestamp - (nextTimestamp % watermarkInterval), watermark);
                Assert.assertTrue(watermark > lastSeenWatermark);
                watermarkCounter++;
                lastSeenWatermark = watermark;
            } else {
                Assert.fail("Unknown element in the list.");
            }
        }
        // clean the output to be ready for the next split
        tester.getOutput().clear();
    }
    // now we are processing one split after the other,
    // so all the elements must be here by now.
    Assert.assertEquals(NO_OF_FILES * LINES_PER_FILE, lineCounter);
    // because we expect one watermark per split.
    Assert.assertEquals(splits.length, watermarkCounter);
    // then close the reader gracefully so that the Long.MAX watermark is emitted
    synchronized (tester.getCheckpointLock()) {
        tester.close();
    }
    for (org.apache.hadoop.fs.Path file : filesCreated) {
        hdfs.delete(file, false);
    }
    // check if the last element is the LongMax watermark (by now this must be the only element)
    Assert.assertEquals(1, tester.getOutput().size());
    Assert.assertTrue(tester.getOutput().peek() instanceof Watermark);
    Assert.assertEquals(Long.MAX_VALUE, ((Watermark) tester.getOutput().poll()).getTimestamp());
    // check if the elements are the expected ones.
    Assert.assertEquals(expectedFileContents.size(), actualFileContents.size());
    for (Integer fileIdx : expectedFileContents.keySet()) {
        Assert.assertTrue("file" + fileIdx + " not found", actualFileContents.keySet().contains(fileIdx));
        List<String> cntnt = actualFileContents.get(fileIdx);
        Collections.sort(cntnt, new Comparator<String>() {

            @Override
            public int compare(String o1, String o2) {
                return getLineNo(o1) - getLineNo(o2);
            }
        });
        StringBuilder cntntStr = new StringBuilder();
        for (String line : cntnt) {
            cntntStr.append(line);
        }
        Assert.assertEquals(expectedFileContents.get(fileIdx), cntntStr.toString());
    }
}

Example 15 with TextInputFormat

use of org.apache.flink.api.java.io.TextInputFormat in project flink by apache.

the class ContinuousFileProcessingTest method testProcessContinuously.

@Test
public void testProcessContinuously() throws Exception {
    String testBasePath = hdfsURI + "/" + UUID.randomUUID() + "/";
    final OneShotLatch latch = new OneShotLatch();
    // create a single file in the directory
    Tuple2<org.apache.hadoop.fs.Path, String> bootstrap = createFileAndFillWithData(testBasePath, "file", NO_OF_FILES + 1, "This is test line.");
    Assert.assertTrue(hdfs.exists(bootstrap.f0));
    final Set<String> filesToBeRead = new TreeSet<>();
    filesToBeRead.add(bootstrap.f0.getName());
    TextInputFormat format = new TextInputFormat(new Path(testBasePath));
    format.setFilesFilter(FilePathFilter.createDefaultFilter());
    final ContinuousFileMonitoringFunction<String> monitoringFunction = createTestContinuousFileMonitoringFunction(format, FileProcessingMode.PROCESS_CONTINUOUSLY);
    // 1 for the bootstrap + NO_OF_FILES
    final int totalNoOfFilesToBeRead = NO_OF_FILES + 1;
    final FileVerifyingSourceContext context = new FileVerifyingSourceContext(latch, monitoringFunction, 1, totalNoOfFilesToBeRead);
    final Thread t = new Thread() {

        @Override
        public void run() {
            try {
                monitoringFunction.open(new Configuration());
                monitoringFunction.run(context);
            } catch (Exception e) {
                Assert.fail(e.getMessage());
            }
        }
    };
    t.start();
    if (!latch.isTriggered()) {
        latch.await();
    }
    // create some additional files that will be processed in the case of PROCESS_CONTINUOUSLY
    final org.apache.hadoop.fs.Path[] filesCreated = new org.apache.hadoop.fs.Path[NO_OF_FILES];
    for (int i = 0; i < NO_OF_FILES; i++) {
        Tuple2<org.apache.hadoop.fs.Path, String> file = createFileAndFillWithData(testBasePath, "file", i, "This is test line.");
        filesCreated[i] = file.f0;
        filesToBeRead.add(file.f0.getName());
    }
    // wait until the monitoring thread exits
    t.join();
    Assert.assertArrayEquals(filesToBeRead.toArray(), context.getSeenFiles().toArray());
    // finally delete the files created for the test.
    hdfs.delete(bootstrap.f0, false);
    for (org.apache.hadoop.fs.Path path : filesCreated) {
        hdfs.delete(path, false);
    }
}